SIGGRAPH Asia 2024 papers on the web

Page maintained by Ke-Sen Huang. If you have additions or changes, send an e-mail.

Information here is provided with the permission of the ACM.

Note that when possible I link to the page containing the link to the actual PDF or PS of the preprint. I prefer this as it gives some context to the paper and avoids possible copyright problems with direct linking. Thus you may need to search on the page to find the actual document.

Open Access to ACM SIGGRAPH-Sponsored Content: For both SIGGRAPH and SIGGRAPH Asia, conference content is freely accessible in the ACM Digital Library for a one-month period that begins two weeks before each conference, and ends a week after it concludes.

ACM Digital Library:ACM Transactions on Graphics (TOG) Volume 43, Issue 6 (December 2024) Proceedings of ACM SIGGRAPH Asia 2024

ACM DOI ACM Digital Library (DOI) Link for the paper   Paper Abstract Paper Abstract   Author version Author Preprint   Paper Video Paper Video  

Paper Presentation Paper Presentation   Paper Images Paper Images   Paper Data Paper Data   Demo Program or Source Code Demo Program or Source Code Related Links Related Links

Changelog

Geometry Processing Computing

Exact and Efficient Intersection Resolution for Mesh Arrangements Paper Abstract Author Preprint Paper Data Demo Program or Source Code
Jia-Peng Guo, Xiao-Ming Fu (University of Science and Technology of China)
Designing triangle meshes with controlled roughness Paper Abstract Author Preprint
Victor Ceballos Inza (KAUST), Panagiotis Fykouras (BMW Group), Florian Rist (KAUST), Daniel Haseker, Majid Hojjat (BMW Group), Christian Muller (TU Wien), Helmut Pottmann (TU Wien and KAUST)
Stripe Embedding: Efficient Maps with Exact Numeric Computation Author Preprint Demo Program or Source Code
Marco Livesu (CNR IMATI)
Bijective Volumetric Mapping via Star Decomposition Paper Abstract Author Preprint Demo Program or Source Code
Steffen Hinderink, Hendrik Bruckler, Marcel Campen (Osnabruck University)
PCO: Precision-Controllable Offset Surfaces with Sharp Features Paper Abstract Author Preprint Paper Video
Lei Wang, Xudong Wang, Pengfei Wang (Shandong University), Shuangmin Chen (Qingdao University of Science and Technology), Shiqing Xin, Jiong Guo (Shandong University), Wenping Wang (Texas A&M University), Changhe Tu (Shandong University)
A Progressive Embedding Approach to Bijective Tetrahedral Maps driven by Cluster Mesh Topology Paper Abstract Author Preprint
Valentin Zenon Nigolian (University of Bern), Marcel Campen (Osnabruck University), David Bommes (University of Bern)

Going Big in Rendering

InfNeRF: Towards Infinite Scale NeRF Rendering with O(log n) Space Complexity Paper Abstract Author Preprint Demo Program or Source Code
Jiabin Liang, Lanqing Zhang (Sea AI Lab), Zhuoran Zhao (Sea AI Lab and National University of Singapore), Xiangyu Xu (Xi'an Jiaotong University)
Taming 3DGS: High-Quality Radiance Fields with Limited Resources Paper Abstract Author Preprint Paper Video Demo Program or Source Code
Saswat Subhajyoti Mallick* (Carnegie Mellon University), Rahul Goel* (Graz University of Technology and IIIT Hyderabad), Bernhard Kerbl, Francisco Vicente Carrasco (Carnegie Mellon University), Markus Steinberger (Graz University of Technology), Fernando De La Torre (Carnegie Mellon University) * Both authors contributed equally to this research
Representing Long Volumetric Video with Temporal Gaussian Hierarchy Paper Abstract Author Preprint Paper Video Demo Program or Source Code
Zhen Xu (Zhejiang University), Yinghao Xu (Stanford University), Zhiyuan Yu (HKUST), Sida Peng, Jiaming Sun, Hujun Bao, Xiaowei Zhou (Zhejiang University)
LetsGo: Large-Scale Garage Modeling and Rendering via LiDAR-Assisted Gaussian Primitives Paper Abstract Author Preprint Paper Video Demo Program or Source Code
Jiadi Cui* (ShanghaiTech University and Stereye Intelligent Technology Co.,Ltd), Junming Cao* (Shanghai Advanced Research Institute, Chinese Academy of Sciences, China and University of Chinese Academy of Sciences), Fuqiang Zhao* (ShanghaiTech University and NeuDim Digital Technology (Shanghai) Co.,Ltd), Zhipeng He, Yifan Chen (ShanghaiTech University), Yuhui Zhong (DGene Digital Technology Co., Ltd.), Lan Xu, Yujiao Shi (ShanghaiTech University), Yingliang Zhang (DGene Digital Technology Co., Ltd.), Jingyi Yu (ShanghaiTech University) * equal contributions
MVImgNet 2.0: A Larger-scale Dataset of Multi-view Images Paper Abstract Author Preprint
Xiaoguang Han* (SSE, CUHKSZ and FNii, CUHKSZ), Yushuang Wu*, Luyue Shi*, Haolin Liu*, Hongjie Liao, Lingteng Qiu (FNii, CUHKSZ and SSE, CUHKSZ), Weihao Yuan, Xiaodong Gu, Zilong Dong (Alibaba Group), Shuguang Cui (SSE, CUHKSZ and FNii, CUHKSZ) * Equal contribution

Make It Yours - Customizing Image Generation

MoA: Mixture-of-Attention for Subject-Context Disentanglement in Personalized Image Generation Paper Abstract Author Preprint Paper Video Paper Presentation
Kuan-Chieh Wang, Daniil Ostashev, Yuwei Fang, Sergey Tulyakov, Kfir Aberman (Snap Inc.)
ReVersion: Diffusion-Based Relation Inversion from Images Paper Abstract Author Preprint Paper Video Paper Data Demo Program or Source Code
Ziqi Huang*, Tianxing Wu*, Yuming Jiang, Kelvin C.K. Chan, Ziwei Liu (S-Lab, Nanyang Technological University) * Equal contributions
PALP: Prompt Aligned Personalization of Text-to-Image Models Paper Abstract Author Preprint Paper Video
Moab Arar (Google Research and Tel Aviv University), Andrey Voynov, Amir Hertz (Google Research), Omri Avrahami (Google Research and The Hebrew University of Jerusalem), Shlomi Fruchter, Yael Pritch (Google Research), Daniel Cohen-Or (Google Research and Tel Aviv University), Ariel Shamir (Google Research and Reichman University)
Customizing Text-to-Image Models with a Single Image Pair Paper Abstract Author Preprint Paper Video Paper Presentation Demo Program or Source Code
Maxwell Jones, Sheng-Yu Wang, Nupur Kumari (Carnegie Mellon University), David Bau (Northeastern University), Jun-Yan Zhu (Carnegie Mellon University)
Customizing Text-to-Image Diffusion with Object Viewpoint Control Paper Abstract Author Preprint Demo Program or Source Code
Nupur Kumari, Grace Su (Carnegie Mellon University), Richard Zhang, Taesung Park, Eli Shechtman (Adobe Research), Jun-Yan Zhu (Carnegie Mellon University)
Identity-Preserving Face Swapping via Dual Surrogate Generative Models Paper Abstract Author Preprint Paper Video Paper Presentation Demo Program or Source Code
Ziyao Huang, Fan Tang (Institute of Computing Technology, Chinese Academy of Sciences), Yong Zhang (AI Lab, Tencent), Juan Cao, Chengyu Li, Sheng Tang, Jintao Li (Institute of Computing Technology, Chinese Academy of Sciences), Tong-Yee Lee (National Cheng-Kung University)

Design It All: Font, Paint, and Colors

HFH-Font: Few-shot Chinese Font Synthesis with Higher Quality, Faster Speed, and Higher Resolution Paper Abstract Author Preprint
Hua Li, Zhouhui Lian (Wangxuan Institute of Computer Technology, Peking University)
SD-ℼXL: Generating Low-Resolution Quantized Imagery via Score Distillation Paper Abstract Author Preprint Paper Video
Alexandre Binninger, Olga Sorkine-Hornung (ETH Zurich)
ProcessPainter: Learning to draw from sequence data Paper Abstract Author Preprint Demo Program or Source Code
Yiren Song*, Shijie Huang*, Chen Yao (National University of Singapore Singapore), Xiaojun Ye (Zhejiang University), Hai Ci (National University of Singapore Singapore), Jiaming Liu (Tiamat), Yuxuan Zhang (Shanghai Jiao Tong University), Mike Zheng Shou (National University of Singapore Singapore) * Both authors contributed equally to this research.
Inverse Painting: Reconstructing The Painting Process Paper Abstract Author Preprint Paper Video
Bowei Chen, Yifan Wang, Brian Curless, Ira Kemelmacher-Shlizerman, Steven M. Seitz (University of Washington)
LVCD: Reference-based Lineart Video Colorization with Diffusion Models Paper Abstract Author Preprint Paper Video Demo Program or Source Code
Zhitong Huang (City University of Hong Kong), Mohan Zhang (WeChat, Tencent Inc.), Jing Liao (City University of Hong Kong)
Colorful Diffuse Intrinsic Image Decomposition in the Wild Paper Abstract Author Preprint Demo Program or Source Code
Chris Careaga, Yagız Aksoy (Simon Fraser University)

Modeling and PDEs

Differential Walk on Spheres Paper Abstract Author Preprint Paper Video Demo Program or Source Code
Bailey Miller (Carnegie Mellon University), Rohan Sawhney (NVIDIA), Keenan Crane, Ioannis Gkioulekas (Carnegie Mellon University)
Projected Walk on Spheres: A Monte Carlo Closest Point Method for Surface PDEs Paper Abstract Author Preprint Paper Video Demo Program or Source Code
Ryusuke Sugimoto, Nathan King, Toshiya Hachisuka, Christopher Batty (University of Waterloo)
Solving Inverse PDE Problems using Grid-Free Monte Carlo Estimators Paper Abstract Author Preprint Paper Video
Ekrem Fatih Yilmazer (EPFL), Delio Vicini (Google Inc.), Wenzel Jakob (EPFL)
DiffCSG: Differentiable CSG via Rasterization Paper Abstract Author Preprint Paper Video
Haocheng Yuan (University of Edinburgh), Adrien Bousseau (Inria, Universite Cote d'Azur), Hao Pan (Microsoft Research Asia), Chengquan Zhang (Nanjing University), Niloy J. Mitra (University College London and Adobe Research), Changjian Li (University of Edinburgh)
Text-guided Controllable Mesh Refinement for Interactive 3D Modeling Paper Abstract Author Preprint
Yun-Chun Chen, Selena Ling (University of Toronto and Adobe Research), Zhiqin Chen, Vladimir G. Kim, Matheus Gadelha (Adobe Research), Alec Jacobson (University of Toronto and Adobe Research)
I❤️MESH: A DSL for Mesh Processing Paper Abstract Author Preprint Demo Program or Source Code
Yong Li (South China University of Technology and George Mason University), Shoaib Kamil (Adobe Research), Keenan Crane (Carnegie Mellon University), Alec Jacobson (University of Toronto and Adobe Research), Yotam Gingold (George Mason University)

Neural Relighting and Reflection

DifFRelight: Diffusion-Based Facial Performance Relighting
Mingming He Pascal Clausen Ahmet Levent Taşel Li Ma Oliver Pilarski Wenqi Xian Laszlo Rikker Xueming Yu Ryan Burgert Ning Yu Paul Debevec
GS³: Efficient Relighting with Triple Gaussian Splatting Paper Abstract Author Preprint Paper Video
Zoubin Bi*, Yixin Zeng*, Chong Zeng, Fan Pei, Xiang Feng, Kun Zhou, Hongzhi Wu (State Key Lab of CAD and CG, Zhejiang University) *contributed equally
OLAT Gaussians for Generic Relightable Appearance Acquisition
Zhiyi Kuang Yanchao Yang Siyan Dong Jiayue Ma Hongbo Fu Youyi Zheng
Reflection-Aware Neural Radiance Fields
Chen Gao Yipeng Wang Changil Kim Jia-Bin Huang Johannes Kopf
NeRF-Casting: Improved View-Dependent Appearance with Consistent Reflections
Dor Verbin Pratul P. Srinivasan Peter Hedman Ben Mildenhall Benjamin Attal Richard Szeliski Jonathan T. Barron
Local Gaussian Density Mixtures for Unstructured Lumigraph Rendering
Xiuchao Wu Jiamin Xu Chi Wang Yifan Peng Qixing Huang James Tompkin Weiwei Xu

Color and Display

COMFI: A Calibrated Observer Metameric Failure Index for Color Critical Tasks
Robert Wanat Michael D. Smith Junwoo Jang Sally Hattori
Large Étendue 3D Holographic Display with Content-adaptive Dynamic Fourier Modulation
Brian Chao Manu Gopakumar Suyeon Choi Jonghyun Kim Liang Shi Gordon Wetzstein
ElaTCSF: A Temporal Contrast Sensitivity Function for Flicker Detection and Modeling Variable Refresh Rate Flicker
Yancheng Cai Ali Bozorgian Maliha Ashraf Robert Wanat Rafal Mantiuk
Perspective-Aligned AR Mirror with Under-Display Camera
Jian Wang Sizhuo Ma Karl Bayer Yi Zhang Peihao Wang Bing Zhou Shree Nayar Gurunandan Krishnan
AR-DAVID: Augmented Reality Display Artifact Video Dataset
Alexandre Chapiro Dongyeon Kim Yuta Asano Rafał K. Mantiuk
V³: Viewing Volumetric Videos on Mobiles via Streamable 2D Dynamic Gaussians Paper Abstract Author Preprint Paper Video
Penghao Wang*, Zhirui Zhang*, Liao Wang*, Kaixin Yao, Siyuan Xie (ShanghaiTech University and NeuDim Digital Technology (Shanghai) Co.,Ltd), Jingyi Yu (ShanghaiTech University), Minye Wu (KU Leuven), Lan Xu (ShanghaiTech University) * Equal contributions.

Geometry and Fabrication

Approximation by Meshes with Spherical Faces
Anthony S. Cisneros Ramos Alisher Aikyn Martin Kilian Helmut Pottmann Christian Müller
Computational Biomimetics of Winged Seeds
Qiqin Le Jiamu Bu Yanke Qu Bo Zhu Tao Du
Optimized shock-protecting microstructures
Zizhou Huang Daniele Panozzo Denis Zorin
All you need is rotation: Construction of developable strips
Takashi Maekawa Felix Scholz
Alignable Lamella Gridshells Paper Abstract
Davide Pellis (ISTI-CNR)
Layout-Aware Single-Image Document Flattening
Pu Li Jianwei Guo Weize Quan Dongming Yan

Path Guiding, Scattering

MARS: Multi-sample Allocation through Russian roulette and Splitting
Joshua Meyer Alexander Rath Ömercan Yazici Philipp Slusallek
Volume Scattering Probability Guiding Paper Abstract Author Preprint Demo Program or Source Code
Kehan Xu (ETH Zurich), Sebastian Herholz (Intel Corporation), Marco Manzi, Marios Papas (DisneyResearch - Studios), Markus Gross (ETH Zurich and DisneyResearch - Studios)
Efficient Neural Path Guiding with 4D Modeling
Honghao Dong Rui Su Guoping Wang Sheng Li
NeuSmoke: Efficient Smoke Reconstruction and View Synthesis with Neural Transportation Fields
Jiaxiong Qiu Ruihong Cen Zhong Li Han Yan Ming-Ming Cheng Bo Ren
Dynamic Neural Radiosity with Multi-grid Decomposition
Rui Su Honghao Dong Jierui Ren Haojie Jin Yisong Chen Guoping Wang Sheng Li
Neural Global Illumination via Superposed Deformable Feature Fields
Chuankun Zheng, Yuchi Huo, Hongxiang Huang, Hongtao Sheng (Zhejiang University), Junrong Huang (City University of Hong Kong), Rui Tang, Hao Zhu (Manycore Inc.), Rui Wang, Hujun Bao (Zhejiang University)

Look at it Differently: Novel View Synthesis

Quark: Real-time, High-resolution, and General Neural View Synthesis
John Flynn Michael Broxton Lukas Murmann Lucy Chai Matthew DuVall Clément Godard Kathryn Heal Srinivas Kaza Stephen Lombardi Xuan Luo Supreeth Achar Kira Prabhu Tiancheng Sun Lynn Tsai Ryan Overbeck
Pano2Room: Novel View Synthesis from a Single Indoor Panorama
Guo Pu Yiming Zhao Zhouhui Lian
Cafca: High-quality Novel View Synthesis of Expressive Faces from Casual Few-shot Captures Paper Abstract Author Preprint Paper Video Paper Data
Marcel C. Buhler, Gengyan Li (ETH Zurich and Google Inc.), Erroll Wood, Leonhard Helminger, Xu Chen, Tanmay Shah, Daoye Wang, Stephan Garbin, Sergio Orts-Escolano (Google Inc.), Otmar Hilliges (ETH Zurich), Dmitry Lagun, Jeremy Riviere, Paulo Gotardo, Thabo Beeler, Abhimitra Meka, Kripasindhu Sarkar (Google Inc.)
Dynamic Gaussian Marbles for Novel View Synthesis of Casual Monocular Videos Paper Abstract Author Preprint Paper Video Demo Program or Source Code
Colton Stearns, Adam W. Harley, Mikaela Uy (Stanford University), Florian Dubost, Federico Tombari (Google Inc.), Gordon Wetzstein, Leonidas Guibas (Stanford University)
Neural Light Spheres for Implicit Image Stitching and View Synthesis Paper Abstract Author Preprint
Ilya Chugunov, Amogh Joshi (Princeton University), Kiran Murthy, Francois Bleibel (Google Inc.), Felix Heide (Princeton University)
ReN Human: Learning Relightable Neural Implicit Surfaces for Animatable Human Rendering
Rengan Xie Kai Huang In-Young Cho Sen Yang Wei Chen Hujun Bao Wenting Zheng Rong Li Yuchi Huo (), (), (), Hujun Bao (Zhejiang University), (), (), ()

Surface Reconstruction and Modeling

Stochastic Normal Orientation for Point Clouds Paper Abstract Author Preprint Demo Program or Source Code
Guojin Huang, Qing Fang, Zheng Zhang, Ligang Liu, Xiao-Ming Fu (University of Science and Technology of China)
Fast and Globally Consistent Normal Orientation based on the Winding Number Normal Consistency
Siyou Lin Zuoqiang Shi Yebin Liu
Surface Reconstruction Using Rotation Systems Paper Abstract Author Preprint Paper Video Demo Program or Source Code
Ruiqi Cui, Emil Toftegaard Gæde, Eva Rotenberg (Technical University of Denmark), Leif Kobbelt (RWTH Aachen University), J. Andreas Bærentzen (Technical University of Denmark)
PVP-Recon: Progressive View Planning via Warping Consistency for Sparse-View Surface Reconstruction
Sheng Ye Yuze He Matthieu Lin Jenny Sheng Ruoyu Fan Yiheng Han Yubin Hu Ran Yi Yu-Hui Wen Yong-Jin Liu Wenping Wang
3D Reconstruction with Fast Dipole Sums Paper Abstract Author Preprint Paper Video Paper Data Demo Program or Source Code
Hanyu Chen, Bailey Miller, Ioannis Gkioulekas (Carnegie Mellon University)
Architectural Co-LOD Generation
Runze Zhang Shanshan Pan Chenlei Lv Minglun Gong Hui Huang

Your Wish is my Command: Generate, Edit, Rearrange

LLM-enhanced Scene Graph Learning for Household Rearrangement Paper Abstract Author Preprint Paper Video
Wenhao Li, Zhiyuan Yu, Qijin She, Zhinan Yu, Yuqing Lan Chenyang Zhu (National University of Defense Technology), Ruizhen Hu (Shenzhen University), Kai Xu (National University of Defense Technology)
SGEdit: Bridging LLM with Text2Image Generative Model for Scene Graph-based Image Editing
Zhiyuan Zhang DongDong Chen Jing Liao
CPoser: An Optimization-after-Parsing Approach for Text-to-Pose Generation Using Large Language Models.
Yumeng Li Bohong Chen Zhong Ren Yao-Xiang Ding Libin Liu Tianjia Shao Kun Zhou
ParSEL: Parameterized Shape Editing with Language
Aditya Ganeshan Ryan Huang Xianghao Xu R. Kenny Jones Daniel Ritchie
Autonomous Character-Scene Interaction Synthesis from Text Instruction
Nan Jiang Zimo He Zi Wang Hongjie Li Yixin Chen Siyuan Huang Yixin Zhu
Anim-Director: A Large Multimodal Model Powered Agent for Controllable Animation Video Generation
Yunxin Li Haoyuan Shi Baotian Hu Longyue Wang Jiashun Zhu Jinyi Xu Zhen Zhao Min Zhang

Animating Humans

FreeAvatar: Robust 3D Facial Animation Transfer by Learning an Expression Foundation Model
Feng Qiu Wei Zhang Chen Liu Rudong An Lincheng Li Yu Ding Changjie Fan Zhipeng Hu Xin Yu
High-quality Animatable Eyelid Shapes from Lightweight Captures
Junfeng Lyu Feng Xu
Geometry-Aware Retargeting for Two-Skinned Characters Interaction
Inseo Jang Soojin Choi Seokhyeon Hong Chaelin Kim Junyong Noh
Near-realtime facial animation by deep 3d simulation super-resolution Paper Abstract Paper Video Demo Program or Source Code
Hyojoon Park, Sangeetha Grama Srinivasan (University of Wisconsin-Madison), Matthew Cong, Doyub Kim, Byungsoo Kim, Jonathan Swartz, Ken Museth (NVIDIA), Eftychios Sifakis (University of Wisconsin-Madison and NVIDIA)
MotionFix: Text-Driven 3D Human Motion Editing
Nikos Athanasiou Alpár Cseke Markos Diomataris Michael J. Black Gül Varol
Refined Inverse Rigging: A Balanced Approach to High-fidelity Blendshape Animation
Stevo Racković Dušan Jakovetić Cláudia Soares

It's All About Change: Image Editing

DiffUHaul: A Training-Free Method for Object Dragging in Images Paper Abstract Author Preprint Paper Video
Omri Avrahami (NVIDIA Research and The Hebrew University of Jerusalem), Rinon Gal (NVIDIA Research and Tel Aviv University), Gal Chechik (NVIDIA Research), Ohad Fried (Reichman University), Dani Lischinski (The Hebrew University of Jerusalem), Arash Vahdat*, Weili Nie* (NVIDIA Research) *Indicates Equal Advising
InstantDrag: Improving Interactivity in Drag-based Image Editing Paper Abstract Author Preprint Paper Video Demo Program or Source Code
Joonghyuk Shin (Seoul National University), Daehyeon Choi (POSTECH), Jaesik Park (Seoul National University)
Consolidating Attention Features for Multi-view Image Editing Paper Abstract Author Preprint Paper Video
Or Patashnik (Tel Aviv University), Rinon Gal (Tel Aviv University and NVIDIA), Daniel Cohen-Or (Tel Aviv University), Jun-Yan Zhu, Fernando De la Torre (Carnegie Mellon University)
TurboEdit: Text-Based Image Editing Using Few-Step Diffusion Models Paper Abstract Author Preprint Demo Program or Source Code
Gilad Deutch (Tel Aviv University), Rinon Gal (Tel Aviv University and NVIDIA), Daniel Garibi, Or Patashnik, Daniel Cohen-Or (Tel Aviv University)
Generative Portrait Shadow Removal
Jae Shin Yoon Zhixin Shu Mengwei Ren Xuaner Zhang Yannick Hold-Geoffroy Krishna Kumar Singh He Zhang
Content-aware Tile Generation using Exterior Boundary Inpainting
Sam Sartor Pieter Peers

Splats and Blobs: Generate, Deform, Diffuse

EVSplitting: An Efficient and Visually Consistent Splitting Algorithm for 3D Gaussian Splatting Paper Abstract Author Preprint
Qi-Yuan Feng, Geng-Chen Cao, Hao-Xiang Chen, Qun-Ce Xu, Tai-Jiang Mu (Tsinghua University), Ralph Martin (Cardiff University), Shi-Min Hu (Tsinghua University)
3DGSR: Implicit Surface Reconstruction with 3D Gaussian Splatting
Xiaoyang Lyu Yang-Tian Sun Yi-Hua Huang Xiuzhe Wu Ziyi Yang Yilun Chen Jiangmiao Pang Xiaojuan Qi
GaussianObject: High-Quality 3D Object Reconstruction from Four Views with Gaussian Splatting
Chen Yang Sikuang Li Jiemin Fang Ruofan Liang Lingxi Xie Xiaopeng Zhang Wei Shen Qi Tian
Real-time Large-scale Deformation of Gaussian Splatting
Lin Gao Jie Yang Bo-Tao Zhang Jia-Mu Sun Yu-Jie Yuan Hongbo Fu Yu-Kun Lai
BlobGEN-3D: Compositional 3D-Consistent Freeview Image Generation with 3D Blobs
Chao Liu Weili Nie Sifei Liu Abhishek Badki Hang Su Morteza Mardani Benjamin Eckart Arash Vahdat
L3DG: Latent 3D Gaussian Diffusion
Barbara Roessle Norman Müller Lorenzo Porzi Samuel Rota Bulò Peter Kontschieder Angela Dai Matthias Nießner

Beyond RGB

End-to-End Hybrid Refractive-Diffractive Lens Design with Differentiable Ray-Wave Model
Xinge Yang Matheus Souza Kunyi Wang Praneeth Chakravarthula Qiang Fu Wolfgang Heidrich
Plug-and-Play Algorithms for Dynamic Non-line-of-sight Imaging
Coherent Optical Modems for Full-Wavefield Lidar Paper Abstract Author Preprint
Parsa Mirdehghan (University of Toronto and Vector Institute), Brandon Buscaino (Ciena Corporation), Maxx Wu (University of Toronto and Vector Institute), Doug Charlton, Mohammad E. Mousa-Pasandi (Ciena Corporation), Kiriakos N. Kutulakos, David B. Lindell (University of Toronto and Vector Institute)
Learned Multi-aperture Color-coded Optics for Snapshot Hyperspectral Imaging Paper Abstract Author Preprint
Zheng Shi* (Princeton University), Xiong Dun* (Tongji University), Haoyu Wei (The University of Hong Kong), Shiyu Dong, Zhanshan Wang, Xinbin Cheng (Tongji University), Felix Heide (Princeton University), Yifan (Evan) Peng (The University of Hong Kong) * denotes equal contribution
Time-Gated Polarization for Active Non-Line-Of-Sight Imaging

Domo Arigato, Mr. Roboto / Robots and Characters

Robot Motion Diffusion Model: Motion Generation for Robotic Characters
PC-Planner: Physics-Constrained Self-Supervised Learning for Robust Neural Motion Planning with Shape-Aware Distance Function
A Plentoptic 3D Vision System Paper Abstract Author Preprint
Agastya Kalra, Vage Taamazyan (Intrinsic Innovation LLC), Alberto Dall'Olio, Raghav Khanna (Intrinsic Switzerland GmbH), Tomas Gerlich (Intrinsic Innovation LLC), Georgia Giannopoulou (Intrinsic Switzerland GmbH), Guy Stoppi (Intrinsic Canada Corporation), Daniel Baxter, Abhijit Ghosh (Intrinsic Innovation LLC), Rick Szeliski (Google DeepMind), Kartik Venkataraman (Intrinsic Innovation LLC)
Actuators A La Mode: Modal Actuations for Soft Body Locomotion
Decoupling Contact for Fine-Grained Motion Style Transfer
MaskedMimic: Unified Physics-Based Character Control Through Masked Motion Inpainting Paper Abstract Author Preprint Paper Video Demo Program or Source Code
Chen Tessler, Yunrong Guo, Ofir Nabati (NVIDIA), Gal Chechik (NVIDIA and Bar-Ilan University), Xue Bin Peng (NVIDIA and Simon Fraser University)

Threads of Reality: Garments & Knitting

GarVerseLOD: High-Fidelity 3D Garment Reconstruction from a Single In-the-Wild Image using a Dataset with Levels of Details Paper Abstract Author Preprint Paper Video
Zhongjin Luo (SSE, CUHKSZ), Haolin Liu, Chenghong Li (FNii, CUHKSZ and SSE, CUHKSZ), Wanghao Du, Zirong Jin, Wanhu Sun (FNii, CUHKSZ), Yinyu Nie (Huawei Noah’s Ark Lab), Weikai Chen (DCC Algorithm Research Center, Tencent Games), Xiaoguang Han (SSE, CUHKSZ and FNii, CUHKSZ)
FabricDiffusion: High-Fidelity Texture Transfer for 3D Garments Generation from In-The-Wild Images Paper Abstract Author Preprint Paper Video
Cheng Zhang*, Yuanhao Wang*, Francisco Vicente Carrasco (Carnegie Mellon University), Chenglei Wu, Jinlong Yang, Thabo Beeler (Google AR), Fernando De la Torre (Carnegie Mellon University) * Equal contribution
Chebyshev Parameterization for Woven Fabric Modeling Paper Abstract Author Preprint Paper Video Demo Program or Source Code
Annika Oehri*, Aviv Segall*, Jing Ren, Olga Sorkine-Hornung (ETH Zurich) * joint first authors with equal contribution
UFO Instruction Graphs Are Machine Knittable
Volumetric Homogenization for Knitwear Simulation

Computational Design

End-to-end Optimization of Fluidic Lenses Paper Abstract Author Preprint Paper Video
Mulun Na*, Hector A. Jimenez Romero*, Xinge Yang, Jonathan Klein, Dominik L. Michels, Wolfgang Heidrich (KAUST) *Authors contributed equally.
Computational Design of Dense Servers for Immersion Cooling
Tune-It: Optimizing Wire Reconfiguration for Sculpture Manufacturing Paper Abstract Author Preprint Paper Video
Qibing Wu, Zhihao Zhang, Xin Yan, Fanchao Zhong (Shandong University), Yueze Zhu (University College London), Xurong Lu, Runze Xue, Rui Li, Changhe Tu, Haisen Zhao (Shandong University)
Motion-Driven Neural Optimizer for Prophylactic Braces Made by Distributed Microstructures Paper Abstract Author Preprint Paper Video
Xingjian Han*, (Boston University and The University of Manchester), Yu Jiang*, (Dalian University of Technology and The University of Manchester), Weiming Wang (The University of Manchester), Guoxin Fang (The Chinese University of Hong Kong), Simeon Gill (The University of Manchester), Zhiqiang Zhang (University of Leeds), Shengfa Wang (Dalian University of Technology), Jun Saito (Adobe Research), Deepak Kumar (Boston University), Zhongxuan Luo (Dalian University of Technology), Emily Whiting (Boston University), Charlie C.L. Wang (The University of Manchester) * Joint first authors
mpcMech: Multi-Point Conjugation Mechanisms Paper Abstract Author Preprint Paper Video
Ke Chen (USTC), Siqi Li, Peng Song (SUTD), Jianmin Zheng (NTU), Ligang Liu (USTC)
FragmentDiff: A Diffusion Model for Fractured Object Assembly
Qun-Ce Xu, Hao-Xiang Chen, Jiacheng Hua, Xiaohua Zhan (Tsinghua University), Yong-Liang Yang (University of Bath), Tai-Jiang Mu (Tsinghua University)

Text, Texturing, and Stylization

InstanceTex: Instance-level Controllable Texture Synthesis for 3D Scenes via Diffusion Priors
Text-Guided Texturing by Synchronized Multi-View Diffusion
StyleTex: Style Image-Guided Texture Generation for 3D Models
TEXGen: a Generative Diffusion Model for Mesh Textures
Compositional Neural Textures Paper Abstract Author Preprint Paper Video
Peihan Tu (University of Maryland, College Park), Li-Yi Wei (Adobe Research), Matthias Zwicker (University of Maryland, College Park)
Camera Settings as Tokens: Modeling Photography on Latent Diffusion Models

To Bend or not to Bend?

Tencers: Tension-Constrained Elastic Rods
Q3T Prisms: A Linear-Quadratic Solid Shell Element for Elastoplastic Surfaces
A Mesh-based Simulation Framework using Automatic Code Generation
Polar Interpolants for Thin-Shell Microstructure Homogenization
XPBI: Position-Based Dynamics with Smoothing Kernels Handles Continuum Inelasticity
Multi-Resolution Real-Time Deep Pose-Space Deformation

(Don't) Make Some Noise: Denoising

A Statistical Approach to Monte Carlo Denoising
Online Neural Denoising with Cross-Regression for Interactive Rendering Paper Abstract Author Preprint Paper Video
Hajin Choi (Gwangju Institute of Science and Technology), Seokpyo Hong (Samsung Advanced Institute of Technology), Inwoo Ha (Samsung Advanced Institute of Technology and KAIST), Nahyup Kang (Samsung Advanced Institute of Technology), Bochang Moon (Gwangju Institute of Science and Technology)
Filtering-Based Reconstruction for Gradient-Domain Rendering
Spatiotemporal Bilateral Gradient Filtering for Inverse Rendering Paper Abstract Author Preprint
Wesley Chang*, Xuanda Yang*, Yash Belhe*, Ravi Ramamoorthi, Tzu-Mao Li (University of California, San Diego) *The three authors contributed equally to this research
Neural Kernel Regression for Consistent Monte Carlo Denoising

Deform Your Axis: Skeletons and Cages

Dynamic Skeletonization via Variational Medial Axis Sampling
Medial Skeletal Diagram: A Generalized Medial Axis Approach for 3D Shape Representation
MATTopo: Topology-preserving Medial Axis Transform with Restricted Power Diagram Paper Abstract Author Preprint Paper Video Demo Program or Source Code
Ningna Wang (University of Texas at Dallas), Hui Huang (Shenzhen University), Shibo Song Independent Researcher, Bin Wang (Tsinghua University), Wenping Wang (Texas A&M University), Xiaohu Guo (University of Texas at Dallas)
Deformation Recovery: Localized Learning for Detail-Preserving Deformations
Polynomial Cauchy Coordinates for Curved Cages
C^0 Generalized Coons Patches for High-order Cage-based Deformation

Keep in Touch / No Touching

A Time-Dependent Inclusion-Based Method for Continuous Collision Detection between Parametric Surfaces
A Cubic Barrier with Elasticity-Inclusive Dynamic Stiffness Paper Abstract Author Preprint Paper Video Demo Program or Source Code
Ryoichi Ando (ZOZO)
Barrier-Augmented Lagrangian for GPU-based Elastodynamic Contact
Efficient GPU Cloth Simulation with Non-distance Barriers and Subspace Reuse
gDist: Efficient Distance Computation between 3D Meshes on GPU
Trading Spaces: Adaptive Subspace Time Integration for Contacting Elastodynamics

3D Printing, Manufacturing

Inverse Rendering for Tomographic Volumetric Additive Manufacturing
Learning Based Toolpath Planner on Diverse Graphs for 3D Printing Paper Abstract Author Preprint Paper Video
Yuming Huang*, Yuhu Guo*, Renbo Su (The University of Manchester), Xingjian Han (Boston University), Junhao Ding (The Chinese University of Hong Kong), Tianyu Zhang, Tao Liu, Weiming Wang (The University of Manchester), Guoxin Fang, Xu Song (The Chinese University of Hong Kong), Emily Whiting (Boston University), Charlie C. L. Wang (The University of Manchester) * Equal contribution
Differentiable Modeling of Material Spreading in Inkjet Printing for Appearance Prediction
Computational Design of a Kit of Parts for Bending Active Structures
A Flexible Mold for Facade Panel Fabrication
Florian Rist (KAUST) Zhecheng Wang (University of Toronto), Davide Pellis (TU Wien), Marco Palma (), Daoming Liu, Dominik L. Michels (KAUST)

Capture Me If You Can

Millimetric Human Surface Capture in Minutes
RoMo: A Robust Solver for Full-body Unlabeled Optical Motion Capture
FürElise: Capturing and Physically Synthesizing Hand Motion of Piano Performance
Look Ma, no markers: Holistic performance capture without the hassle Paper Abstract Author Preprint Paper Video Paper Data
Charlie Hewitt, Fatemeh Saleh, Sadegh Aliakbarian, Lohit Petikam, Shideh Rezaeifar, Louis Florentin, Zafiirah Hosenie, Thomas J Cashman, Julien Valentin, Darren Cosker, Tadas Baltrusaitis (Microsoft)
EgoHDM: An Online Egocentric-Inertial Human Motion Capture, Localization, and Dense Mapping System
ELMO: Enhanced Real-time LiDAR Motion Capture through Upsampling Paper Abstract Author Preprint
Deok-Kyeong Jang*, Dongseok Yang*, Deokyun Jang*, Byeoli Choi*, Donghoon Shin (MOVIN Inc.), Sung-Hee Lee (KAIST) * Equal contribution.

Going Fast: Accelerated Rendering

AdR-Gaussian: Accelerating Gaussian Splatting with Adaptive Radius
3D Gaussian Ray Tracing: Fast Tracing of Particle Scenes
High-Throughput Batch Rendering for Embodied AI
Efficient Image-Space Shape Splatting for Monte Carlo Rendering Author Preprint Demo Program or Source Code
Xiaochun Tong, Toshiya Hachisuka (University of Waterloo)
DirectL: Efficient Radiance Fields Rendering for 3D Light Field Displays

Characters and Crowds

PDP: Physics-Based Character Animation via Diffusion Policy
Monkey See, Monkey Do: Harnessing Self-attention in Motion Diffusion for Zero-shot Motion Transfer Paper Abstract Author Preprint Paper Video Demo Program or Source Code
Sigal Raab, Inbar Gat, Nathan Sala, Guy Tevet, Rotem Shalev-Arkushin (Tel Aviv University), Ohad Fried (Reichman University), Amit H. Bermano, Daniel Cohen-Or (Tel Aviv University)
CBIL: Collective Behavior Imitation Learning for Fish from Real Videos Paper Abstract
Yifan Wu* (The University of Hong Kong), Zhiyang Dou* (The University of Hong Kong and University of Pennsylvania), Yuko Ishiwaka, Shun Ogawa (SoftBank), Yuke Lou (The University of Hong Kong), Wenping Wang (Texas A&M University), Lingjie Liu (University of Pennsylvania), Taku Komura (The University of Hong Kong) * Equal Contribution
Resolving Collisions in Dense 3D Crowd Animations
Body Gesture Generation for Multimodal Conversational Agents

Neural Shapes

SpaceMesh: A Continuous Representation for Learning Manifold Surface Meshes
NASM: Neural Anisotropic Surface Meshing
Controllable Shape Modeling with Neural Generalized Cylinder
Direct Manipulation of Procedural Implicit Surfaces Paper Abstract Author Preprint Paper Video
Marzia Riso (Sapienza University of Rome and Adobe Research), Elie Michel, Axel Paris, Valentin Deschaintre, Mathieu Gaillard (Adobe Research), Fabio Pellacini (University of Modena and Reggio Emilia)
Neural Laplacian Operator for 3D Point Clouds
SRIF: Semantic Shape Registration Empowered by Diffusion-based Image Morphing and Flow Estimation

Sampling and Light Transport

Hierarchical Light Sampling with Accurate Spherical Gaussian Lighting
BSDF importance sampling using a diffusion model Paper Abstract Author Preprint Paper Video Demo Program or Source Code
Ziyang Fu, Yash Belhe, Haolin Lu, Liwen Wu, Bing Xu, Tzu-Mao Li (University of California, San Diego)
DARTS: Diffusion Approximated Residual Time Sampling for Time-of-flight Rendering in Homogeneous Scattering Media
Neural Product Importance Sampling via Warp Composition Paper Abstract Author Preprint
Joey Litalien (McGill University), Milos Hasan, Fujun Luan, Krishna Mullia, Iliyan Georgiev (Adobe Research)
Manifold Sampling for Differentiable Uncertainty in Radiance Fields
A Generalized Ray Formulation For Wave-Optical Light Transport Paper Abstract Author Preprint Paper Video Paper Data Demo Program or Source Code
Shlomi Steinberg (NVIDIA and University of Waterloo), Ravi Ramamoorthi (NVIDIA and University of California, San Diego), Benedikt Bitterli, Eugene d'Eon (NVIDIA), Ling-Qi Yan (University of California, Santa Barbara), Matt Pharr (NVIDIA)

Diffusing Your Videos

Still-Moving: Customized Video Generation without Customized Video Data
Fashion-VDM: Video Diffusion Model for Virtual Try-On
Lumiere: A Space-Time Diffusion Model for Video Generation
I2VEdit: First-Frame-Guided Video Editing via Image-to-Video Diffusion Models Paper Abstract Author Preprint Paper Video
Wenqi Ouyang (S-Lab, Nanyang Technological University), Yi Dong (Nanyang Technological University), Lei Yang, Jianlou Si (SenseTime Research and Shanghai AI Laboratory), Xingang Pan (S-Lab, Nanyang Technological University)
VidPanos: Generative Panoramic Videos from Casual Panning Videos
TrailBlazer: Trajectory Control for Diffusion-Based Video Generation Paper Abstract Author Preprint Paper Video Demo Program or Source Code
Wan-Duo Kurt Ma (Victoria University of Wellington), J. P. Lewis (NVIDIA Research), W. Bastiaan Kleijn (Victoria University of Wellington)

Fill the Gap: What Happened In-between?

ToonCrafter: Generative Cartoon Interpolation
Skeleton-Driven Inbetweening of Bitmap Character Drawings
SKEL-Betweener: a Neural Motion Rig for Interactive Motion Authoring
DrawingSpinUp: 3D Animation from Single Character Drawings
From Sim-to-Real: Toward General Event-based Low-light Frame Interpolation with Per-scene Optimization
GFFE: G-buffer Free Frame Extrapolation for Low-latency Real-time Rendering

Mesh Processing Unleashed

GauWN: Gaussian-smoothed Winding Number and its Derivatives
Hodge decomposition of vector fields in Cartesian grids
Robust Symmetry Detection via Riemannian Langevin Dynamics
Sharpening and Sparsifying with Surface Hessians
Quad mesh mechanisms

Diffuse and Conquer

Portrait Video Editing Empowered by Multimodal Generative Priors Paper Abstract Author Preprint Paper Video Demo Program or Source Code
Xuan Gao, Haiyao Xiao, Chenglai Zhong, Shi-Min Hu (Tsinghua University) Yudong Guo, Juyong Zhang (University of Science and Technology of China)
HyperGAN-CLIP: A Unified Framework for Domain Adaptation, Image Synthesis and Manipulation
StableNormal: Reducing Diffusion Variance for Stable and Sharp Normal Paper Abstract Author Preprint Paper Video Demo Program or Source Code
Chongjie Ye* (FNii, The Chinese University of Hongkong and SSE, The Chinese University of Hongkong), Lingteng Qiu* (FNii, The Chinese University of Hongkong and SSE, The Chinese University of Hongkong and Alibaba Group), Xiaodong Gu, Qi Zuo (Alibaba Group), Yushuang Wu (FNii, The Chinese University of Hongkong and SSE, The Chinese University of Hongkong), Zilong Dong, Liefeng Bo (Alibaba Group), Yuliang Xiu (Max Planck Institute for Intelligent Systems), Xiaoguang Han (SSE, The Chinese University of Hongkong and FNii, The Chinese University of Hongkong) * Equal contribution
StyleCrafter: Taming Stylized Video Diffusion with Reference-Augmented Adapter Learning
Fast High-Resolution Image Synthesis with Latent Adversarial Diffusion Distillation
MV2MV: Multi-View Image Translation via View-Consistent Diffusion Models
Youcheng Cai, Runshi Li, Ligang Liu (University of Science and Technology of China)

Generate It All: Scenes, Humans, LEGOs

Frankenstein: Generating Semantic-Compositional 3D Scenes in One Tri-Plane
DIScene: Object Decoupling and Interaction Modeling for Complex Scene Generation
Xiao-Lei Li, Haodong Li, Hao-Xiang Chen, Tai-Jiang Mu, Shi-Min Hu (Tsinghua University)
TriHuman: A Real-time and Controllable Tri-plane Representation for Detailed Human Geometry and Appearance Synthesis
EgoAvatar: Egocentric View-Driven and Photorealistic Full-body Avatars Paper Abstract Author Preprint Paper Video
Jianchun Chen, Jian Wang (Max Planck Institute for Informatics and VIA Research Center), Yinda Zhang Rohit Pandey Thabo Beeler (Google Inc.), Marc Habermann, Christian Theobalt (Max Planck Institute for Informatics and VIA Research Center)
Learn to Create Simple LEGO Micro Buildings
MagicClay: Sculpting Meshes With Generative Neural Fields Paper Abstract Author Preprint Paper Video Demo Program or Source Code
Amir Barda (Tel Aviv University), Vladimir G. Kim, (Adobe Research), Noam Aigerman (Adobe Research and Universite de Montreal), Amit Haim Bermano (Tel Aviv University), Thibault Groueix (Adobe Research)

Talking Heads and Moving Faces

VOODOO XP: Expressive One-Shot Head Reenactment for VR Telepresence Paper Abstract Author Preprint
Phong Tran (MBZUAI), Egor Zakharov (ETH Zurich), Long-Nhat Ho (MBZUAI), Liwen Hu (Pinscreen), Adilbek Karmanov (MBZUAI), Aviral Agarwal, McLean Goldwhite (Pinscreen), Ariana Bermudez Venegas (MBZUAI), Anh Tuan Tran (VinAI Research), Hao Li (Pinscreen and MBZUAI)
TextToon: Real-Time Text Toonify Head Avatar from Single Video Paper Abstract Author Preprint Paper Video Paper Data
Luchuan Song (University of Rochester), Lele Chen (Sony AI), Celong Liu (Bytedance), Pinxin Liu, Chenliang Xu (University of Rochester)
PersonaTalk: Bring Attention to Your Persona in Visual Dubbing Paper Abstract Author Preprint Paper Video
Longhao Zhang*, Shuang Liang*, Zhipeng Ge*, Tianshu Hu* (Bytedance) *Equal Contribution
TALK-Act: Enhance Textural-Awareness for 2D Speaking Avatar Reenactment with Diffusion Model
Follow-Your-Emoji: Fine-Controllable and Expressive Freestyle Portrait Animation
Fabrig: A Cloth-Simulated Transferable 3D Face Parameterization

Beauty Salon: Hair, Face, Lips, and Teeth

Curly-Cue: Geometric Methods for Highly Coiled Hair Paper Abstract Author Preprint Paper Video Demo Program or Source Code
Haomiao Wu*, Alvin Shi* (Yale University), A.M. Darke (University of California, Santa Cruz), Theodore Kim (Yale University) * Indicates Equal Contribution
SPARK: Self-supervised Personalized Real-time Monocular Face Capture Paper Abstract Author Preprint Paper Video
Kelian Baert (Technicolor Group and University Rennes), Shrisha Bharadwaj (Max Planck Institute for Intelligent Systems), Fabien Castan, Benoit Maujean (Technicolor Group), Marc Christie (University Rennes, IRISA, CNRS, Inria), Victoria Abrevaya (Max Planck Institute for Intelligent Systems), Adnane Boukhayma (Inria, University Rennes, IRISA, CNRS)
GroomCap: High-Fidelity Prior-Free Hair Capture Paper Abstract Author Preprint Paper Video
Yuxiao Zhou (ETH Zurich), Menglei Chai, Daoye Wang, Sebastian Winberg, Erroll Wood, Kripasindhu Sarkar (Google Inc.), Markus Gross (ETH Zurich), Thabo Beeler (Google Inc.)
Towards Unified 3D Hair Reconstruction from Single-View Portraits
The Lips, the Teeth, the tip of the Tongue: LTT Tracking
Hairmony: Fairness-aware hairstyle classification

Differentiable Rendering

Differentiating Variance for Variance-Aware Inverse Rendering Paper Abstract Author Preprint
Kai Yan (University of California, Irvine and Weta Digital), Vincent Pegoraro, Marc Droske, Jirka Vorba (Weta Digital), Shuang Zhao (University of California, Irvine)
Differentiable Owen Scrambling Paper Abstract Author Preprint Demo Program or Source Code
Bastien Doignies (Universite Claude Bernard Lyon 1, CNRS, INSA Lyon, LIRIS), David Coeurjolly, Nicolas Bonneel, Julie Digne (CNRS, Universite Claude Bernard Lyon 1, INSA Lyon, LIRIS), Jean-Claude Iehl, Victor Ostromoukhov (Universite Claude Bernard Lyon 1, CNRS, INSA Lyon, LIRIS)
Neural Differential Appearance Equations
Differentiable Photon Mapping using Generalized Path Gradients
Markov-Chain Monte Carlo Sampling of Visibility Boundaries for Differentiable Rendering Paper Abstract Author Preprint
Peiyu Xu (University of California, Irvine), Sai Bangaru (MIT CSAIL and NVIDIA), Tzu-Mao Li (University of California, San Diego), Shuang Zhao (University of California, Irvine)
A Simple Approach to Differentiable Rendering of SDFs Paper Abstract Author Preprint
Zichen Wang, Xi Deng (Cornell University), Ziyi Zhang, Wenzel Jakob (EPFL), Steve Marschner (Cornell University)

Elastics / Solvers / Neural Physics

MiNNIE: a Mixed Multigrid Method for Real-time Simulation of Nonlinear Near-Incompressible Elastics
Analytic rotation-invariant modelling of anisotropic finite elements
Trust-Region Eigenvalue Filtering for Projected Newton
Accelerate Neural Subspace-Based Reduced-Order Solver of Deformable Simulation by Lipschitz Optimization Paper Abstract Author Preprint Paper Video
Aoran Lyu* (South China University of Technology and The University of Manchester), Shixian Zhao*, Chuhua Xian, Zhihao Cen, Hongmin Cai (South China University of Technology), Guoxin Fang (The Chinese University of Hong Kong) * Equal contribution of the first two authors
Neural Implicit Reduced Fluid Simulation
Neural Garment Dynamic Super-Resolution

Fluid Simulation

Particle Laden Fluid on Flow Maps
Solid-Fluid Interaction on Particle Flow Maps
An Eulerian Vortex Method on Flow Maps
An Impulse Ghost Fluid Method for Simulating Two-Phase Flows
A Unified MPM Framework supporting Phase-field Models and Elastic-viscoplastic Phase Transition
Fluid Implicit Particles on Coadjoint Orbits Paper Abstract Author Preprint Paper Video
Mohammad Sina Nabizadeh, Ritoban Roy-Chowdhury, Hang Yin, Ravi Ramamoorthi, Albert Chern (University of California, San Diego)

Modeling and Reconstruction

FacAID: A Transformer Model for Neuro-Symbolic Facade Reconstruction Paper Abstract Author Preprint
Aleksander Plocharski (Warsaw University of Technology and IDEAS NCBR), Jan Swidzinski (IDEAS NCBR), Joanna Porter-Sobieraj (Warsaw University of Technology), Przemyslaw Musialski (New Jersey Institute of Technology and IDEAS NCBR)
Large Scale Farm Scene Modeling from Remote Sensing Imagery Author Preprint Paper Video
Zhiqi Xiao, Hao Jiang (Institute of Computing Technology, Chinese Academy of Sciences and University of Chinese Academy of Sciences), Zhigang Deng (University of Houston), Wenwei Han, Ran Li, Zhaoqi Wang (Institute of Computing Technology, Chinese Academy of Sciences and University of Chinese Academy of Sciences)
Reconstructing translucent thin objects from photos Paper Abstract Author Preprint Paper Video
Xi Deng (Cornell University), Andrea Weidlich, Lifan Wu (Nvidia), Bruce Walter (Cornell University), Ravi Ramamoorthi (NVIDIA and University of California, San Diego), Eugene d'Eon (NVIDIA), Steve Marschner (Cornell University)
DreamUDF: Generating Unsigned Distance Fields from A Single Image
Style-NeRF2NeRF: 3D Style Transfer from Style-Aligned Multi-View Images
NU-NeRF: Neural Reconstruction of Nested Transparent Objects with Uncontrolled Capture Environment

My Name is Carl: Gaussian Humans

Gaussian Surfel Splatting for Live Human Performance Capture Author Preprint Paper Video
Zheng Dong (Zhejiang University), Ke Xu (City University of Hong Kong), Yaoan Gao, Hujun Bao, Weiwei Xu (Zhejiang University), Rynson W.H. Lau (City University of Hong Kong)
GaussianHeads: End-to-End Learning of Drivable Gaussian Head Avatars from Coarse-to-fine Representations
GGHead: Fast and Generalizable 3D Gaussian Heads
Robust Dual Gaussian Splatting for Immersive Human-centric Volumetric Videos Paper Abstract Author Preprint Paper Video
Yuheng Jiang (ShanghaiTech University and NeuDim Digital Technology (Shanghai) Co.,Ltd.), Zhehao Shen, Yu Hong, Chengcheng Guo, Yize Wu (ShanghaiTech University), Yingliang Zhang (DGene Digital Technology Co., Ltd.), Jingyi Yu, Lan Xu (ShanghaiTech University)
NPGA: Neural Parametric Gaussian Avatars Paper Abstract Author Preprint Paper Video
Simon Giebenhain, Tobias Kirschstein (Technical University of Munich), Martin Runz (Synthesia), Lourdes Agapito (University College London), Matthias Niessner (Technical University of Munich)
URAvatar: Universal Relightable Gaussian Codec Avatars

(Do) Make Some Noise

Speed-Aware Audio-Driven Speech Animation using Adaptive Windows
SIGGesture: Generalized Co-Speech Gesture Synthesis via Semantic Injection with Large-Scale Pre-Training Diffusion Models
WaveBlender: Practical Sound-Source Animation in Blended Domains Paper Abstract Author Preprint Paper Video
Kangrui Xue (Stanford University), Jui-Hsien Wang, Timothy R. Langlois (Adobe Research), Doug L. James (Stanford University and NVIDIA)
Dance-to-Music Generation with Encoder-based Textual Inversion
Sketching With Your Voice: "Non-Phonorealistic" Rendering of Sounds via Vocal Imitation

Appearance Modeling

Correlation-aware Encoder-Decoder with Adapters for SVBRDF Acquisition
NFPLight: Deep SVBRDF Estimation via the Combination of Near and Far Field Point Lighting
Polarimetric BSSRDF Acquisition of Dynamic Faces
Hyunho Ha, Inseung Hwang (KAIST), Nestor Monzon (Universidad de Zaragoza), Jaemin Cho, Donggun Kim (KAIST), Seung-Hwan Baek (POSTECH), Adolfo Munoz, Diego Gutierrez (Universidad de Zaragoza), Min H. Kim (KAIST)
ControlMat: A Controlled Generative Approach to Material Capture
Appearance Modeling of Iridescent Feathers with Diverse Nanostructures
A Dynamic By-example BTF Synthesis Scheme

Points, Graphs, Surfaces, and Fields

Occupancy-Based Dual Contouring
Gaussian Opacity Fields: Efficient Adaptive Surface Reconstruction in Unbounded Scenes
A class of new tuned primal subdivision schemes with high-quality limit surface in extraordinary regions
SING: Stability-Incorporated Neighborhood Graph
Multi-level Partition of Unity on Differentiable Moving Particles

Enhancing, Saliency

Boosting 3D Object Generation through PBR Materials
FaceMap: Distortion-Driven Perceptual Facial Saliency Maps
Enhancing the Aesthetics of 3D Shapes via Reference-based Editing
Controlled Spectral Uplifting for Indirect-Light-Metamerism
Procedural Material Generation with Reinforcement Learning
GPU Coroutines for Flexible Splitting and Scheduling of Rendering Tasks

Hand and Human

360-degree Human Video Generation with 4D Diffusion Transformer
Synchronize Dual Hands for Physics-Based Dexterous Guitar Playing
World-Grounded Human Motion Recovery via Gravity-View Coordinates
DiffH2O: Diffusion-Based Synthesis of Hand-Object Interactions from Textual Descriptions
PuzzleAvatar: Assembling 3D Avatars from Personal Albums
Measuring Human Motion Under Clothing

Interactive Methods and VR/AR

Evaluating Visual Perception of Object Motion in Dynamic Environments Paper Abstract Author Preprint Paper Video
Budmonde Duinkharjav (New York University), Jenna Kang (Georgia Institute of Technology and New York University), Gavin S. P. Miller, Chang Xiao (Adobe Research), Qi Sun (New York University)
Casper DPM: Cascaded Perceptual Dynamic Projection Mapping onto Hands
Identifying Behavioral Correlates to Visual Discomfort
ThermOuch: A Wearable Thermo-Haptic Device for Inducing Pain Sensation in Virtual Reality through Thermal Grill Illusion
iSeg: Interactive 3D Segmentation via Interactive Attention
kesen.huang@gmail.com