Human Avatar Animation

Follow this topic Ask about this topic

Momentum

6 papers in the last four weeks, up 100% on the four weeks before. 0.1% of all new papers.

Jul 13Week of Sep 28

Latest papers 47

All topics

GHARP: Real-time Gaussian Head Animation from Large-scale Reconstruction Prior
Oct 7, 2026Ali Benlalah, Sepehr Johari, Patricia Vitoria +14Human Avatar Animation 3D Gaussian Splatting
Apple
emg2face: Expressive Facial Animation with High-Density Surface EMG
Oct 7, 2026Ganidhu Abey, Wendy Greening, Ashika Kamboj +5Human Avatar Animation
University of British Columbia · Google · Imperial College London +1
PixReenact: Pixel-Conditioned Causal Video Diffusion for Streaming Head-Avatar Reenactment
Oct 4, 2026Gavriel Habib, Dvir Samuel, Or Shimshi +1Video Diffusion Models Identity-Preserving Video Generation
OriginAI, Israel · NVIDIA
One Basis to Animate Them All: Gaussian Blendshape Distillation for Real-Time Avatars
Oct 1, 2026Ramazan Fazylov, Stamatis Lefkimmiatis, Ivan LaptevInference Acceleration Human Avatar Animation
Mohamed bin Zayed University of Artificial Intelligence · MWS AI
Learning Semantic Inpainting for Animatable Gaussian Head Avatars
Sep 29, 2026Pilseo Park, Fizza Rubab, Yiying Tong3D Avatar Generation Human Avatar Animation
Michigan State University
WeLike2Party! In-Context Motion Transfer for Multi-Human Image Animation
Sep 29, 2026Sangeyl Lee, Seunghyun Shin, Seungho Park +2Human Avatar Animation
Department of Artificial Intelligence, Yonsei University · AI Graduate School, GIST
Relightable 3D Avatar Reconstruction with Semantic-Adaptive Motion-Illumination Responses
Sep 21, 2026Jiankuo Zhao, Xiangyu Zhu, Jijie Li +33D Gaussian Splatting 3D Avatar Generation
State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing 100190, China · School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing 100049, China · ZKTeco Co., Ltd.
KoUniTalk: A Lightweight Articulation-Centered Korean-English 3D Talking Face Benchmark
Sep 17, 2026Hyunjung Chung, Unsang ParkHuman Avatar Animation Audio-Driven Facial Animation
Sogang University, Seoul, Republic of Korea
Avatar-Forever: Decoupled Parallel Training for High-Quality Real-Time Infinite Avatars
Aug 12, 2026Ruibin Li, Tao Yang, Zhiyuan Ma +3Audio-Video Generation Real-Time Interactive Video Generation
The Hong Kong Polytechnic University · ByteDance · AMD
LiveAnimate: Stable Long-Form Streaming Human Animation in Real-Time
Aug 12, 2026Yuxuan Zhang, Haozhong Xiong, Yubo Huang +6Diffusion Transformer Real-Time Interactive Video Generation
The Chinese University of Hong Kong · Qwen Applications Business Group of Alibaba · Liblib AI
DSAR: Dual-Stream Autoregressive Modeling of Temporal Cloth Dynamics for Photorealistic Animatable Avatars
Aug 11, 2026Haozhong Xiong, Yao Yu, Yu Zhou +13D Avatar Generation Human Avatar Animation
Nanjing University, Nanjing, China
Multi-View Face and Gesture Animation with Dynamic Gaussians
Aug 5, 2026Alireza Javanmardi, Vippin Kumar Jeetmal, Christen Millerdurai +2Multi-View 3D Reconstruction 3D Avatar Generation
1German Research Center for Artificial Intelligence (DFKI) · 2RPTU
Proxy Avatar Meets Low-Rank Caching: Real-Time One-Shot Emotion-Controllable Portrait Animation
Aug 3, 2026Haijie Yang, Jindi Bao, Yixuan Dong +6Video Diffusion Models Identity-Preserving Video Generation
Nanjing University of Science and Technology · Tsientang Institute for Advanced Study · Peking University +1
Forwardrobe: Garment-Aware Gaussian Avatars from a Single Image
Jul 31, 2026Daisheng Jin, Shuyun Wang, Ying He3D Gaussian Splatting 3D Reconstruction
Nanyang Technological University · Singapore · The University of Queensland +1
Split and Drive: Dual-Axis Disentanglement for Real-Time Gaussian Head Avatars
Jul 30, 2026MD Wahiduzzaman Khan, Mingshan Jia, Xiaolin Zhang +23D Gaussian Splatting Disentangled Representation Learning
University of Technology Sydney, Australia · Shandong University of Science and Technology, China
AptAvatar: Fast and Vivid Long-Form Audio-Driven Video Generation for Production-Ready Avatars
Jul 27, 2026Hengyuan Zhang, Jingna Sun, Meiguang Jin +1Video Diffusion Models Long-Horizon Video Generation
Alibaba Group, Taobao and Tmall Group
Head Avatars with Dynamic Explicit Hair
Jul 26, 2026Vanessa Sklyarova, Haonan Chen, Berna Kabadayi +84D Reconstruction Dynamic Scene Reconstruction
ETH Zürich, Switzerland · Max Planck Institute for Intelligent Systems, Tübingen, Germany · Tübingen AI Center, University of Tübingen, Germany +5
STEER: Steerable Dyadic Head Avatars
Jul 26, 2026Kartik Teotia, Helge Rhodin, Hyeongwoo Kim +2Human Motion Generation 3D Avatar Generation
Max Planck Institute for Informatics and Saarland Informatics Campus, Germany · Max Planck Institute for Informatics, Germany
FA-LAM: Focus-Aware Large Avatar Model for One-Shot 4D Animatable Gaussian Head
Jul 23, 2026Yingdong Hu, Yisheng He, Yiming Jiang +33D Gaussian Splatting 4D Reconstruction
HKUST Hong Kong SAR, China · Tongyi Lab, Alibaba Group Hangzhou, China · Lingnan University Hong Kong SAR, China
Learn2Chat: Rethinking Dyadic Talking Heads via Interaction-Modulated Monologic Priors
Jul 11, 2026Zikai Huang, Siyue Chen, Xuemiao Xu +4Disentangled Representation Learning Human Motion Generation
School of Computer Science and Engineering, South China University of Technology, Guangdong, China · School of Design, South China University of Technology, Guangdong, China · Guangdong Engineering Center for Large Model and GenAI Technology +2
LUNA: Learning Universal 3D Human Animation Beyond Skinning
Jun 30, 2026Peng Li, Rawal Khirodkar, Junxuan Li +6Human Motion Generation Human Avatar Animation
The Hong Kong University of Science and Technology · Work was done during an internship at Meta. · Codec Avatars Lab, Meta
3D Scene-Adaptive Trajectory-Controllable Human Image Animation with Camera Movement
Jun 29, 2026Deyin Liu, Jicheng Xu, Lin Yuanbo Wu +4Camera-Controlled Video Generation Motion Retargeting
Engineering Research Center of Autonomous Unmanned System Technology, Ministry of Education; Anhui Provincial Key Laboratory of Security Artificial Intelligence; and School of Artificial Intelligence, Anhui University, Hefei, China · University of Surrey, Guildford, United Kingdom · University of Warwick, Coventry, United Kingdom +1
FFAvatar: Feed-Forward 4D Head Avatar Reconstruction from Sparse Portrait Images
Jun 29, 2026Jianjiang Yao, Ke Xian, Renxiang Dai +13D Gaussian Splatting 4D Reconstruction
School of Electronic Information and Communications, Huazhong University of Science and Technology, Wuhan 430074, China
InteractiveAvatar: Real-Time Streaming Video Generation for Consistent and Intent-Aware Avatars
Jun 22, 2026Quanyue Song, Yishan He, Yanfei Zhang +6Real-Time Interactive Video Generation Memory-Augmented Video Generation
State Key Laboratory of Human-Machine Hybrid Augmented Intelligence, Institute of Artificial Intelligence and Robotics, Xi’an Jiaotong University, China · China Telecom Artificial Intelligence Technology (Beijing) Co., Ltd., China · State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, China +1
PIAvatar: Physically Interactive Avatars via Deformation Gradient Decoupling
Jun 19, 2026Sang-Hun Han, Min-Gyu Park, Jisu Shin +3Material Point Method Human Avatar Animation
1GIST · 2KETI · 3Polygom +2
Avatar V: Scaling Video-Reference Avatar Video Generation
Jun 11, 2026Benjamin Liang, Ce Chen, Desmond Lin +20Video-Reference Video Generation Identity-Preserving Video Generation
HeyGen Research
Beyond Skeletons: Learning Animation Directly from Driving Videos with Same2X Training Strategy
Jun 5, 2026Yuan Zeng, Yujia Shi, Yuhao Yang +4Video Diffusion Models Human Motion Generation
1Tsinghua University · 2Harbin Institute of Technology · 3Pengcheng Laboratory
FreeAnimate: Training-Free Human Image Animation with Preview-Guided Denoising
Jun 5, 2026Yuan Zeng, Yujia Shi, Zongqing Lu +1Image-to-Video Generation Human Avatar Animation
Shenzhen International Graduate School, Tsinghua University, China · Harbin Institute of Technology, China · Pengcheng Laboratory, China
Self-Learning Expression Deformations for Data-Efficient Gaussian Avatars
Jun 4, 2026Jiahao Yang, Xiaohang Yang, Qing Wang +33D Gaussian Splatting Self-Supervised Learning
Queen Mary University of London
TokTalk: Expressive Real-time Facial Animation from Audio-LLM Tokens
May 29, 2026Qingcheng Zhao, Yifang Pan, Karan SinghTalking Head Generation Human Avatar Animation
University of Toronto · Toronto, Canada

Oct 7, 2026, cs.CVJ/K move · Enter open · S save

GHARP: Real-time Gaussian Head Animation from Large-scale Reconstruction Prior

Ali Benlalah, Sepehr Johari, Patricia Vitoria, Armin Kappeler+13

Apple

Human Avatar Animation 3D Gaussian Splatting 3D Human Reconstruction

Open paper AskPDF arXiv

We present GHARP (Real-time Gaussian Head Animation from Large-scale Reconstruction Prior), a method that animates 3D human heads in real time from a few input images of a subject and a driving expression signal. We decouple the problem into an identity stage that builds a representation of the subject's geometry and appearance offline, and an animation stage that predicts expression-dependent residuals on top of it at runtime. This separation offers a favorable trade-off with respect to fidelity, quality and runtime: the identity stage can be expensive while the animation stage runs a lightweight network, optimized for mobile devices. Our method performs animation in a semantically structured latent space of a pretrained reconstruction model, where expression changes remain spatially contained, making residual prediction efficient. This reconstruction prior provides a consistent spatial layout, allowing fusion of multiple input views into a compact, fixed-size canonical Gaussian representation. While this two-stage design improves the runtime-quality trade-off, it still inherits a problem common to all expression-driven avatar methods: expression codes describe only the face and thus omit body pose and clothing position, making these regions underspecified in the input. The animation network faces an ill-posed mapping and resorts to averaging over conflicting body appearances, producing blur and temporal flicker. We address this with a body alignment network that learns to align the person's body in the target image with the input reference images, removing the ambiguity from the training signal. Our method achieves state-of-the-art quality on the Ava-256 benchmark while running up to 13x faster on an A100 GPU with 8x fewer Gaussians.

Momentum

Related topics

Latest papers 47