HARP: Personalized Hand Reconstruction from a Monocular RGB Video
Korrawe Karunratanakul, Sergey Prokudin, Otmar Hilliges, Siyu Tang
Abstract
sergey.prokudin,otmar.hilliges,siyu.tang@inf.ethz.ch https://korrawe.github.io/harp-project/ Figure 1. Given a short monocular video of a hand and a coarse hand pose and shape estimation for initialization, we reconstruct a photorealistic hand avatar exhibiting faithful personalized appearance and geometry using standard explicit representations and a differentiable renderer without any neural networks. Compared to the baselines, our hand avatar demonstrates better-reconstructed geometry and appearance. The hand avatar can be used to render high-fidelity hand images in novel views and poses in real-time, which serves as a foundation for many AR/VR applications.
Ask about this paper
Your agent reads all of it.
Lune indexed this paper to the last equation, along with the top-tier papers that cite it. Ask a question and the answer quotes them.
Your agent calls
Luneget_paper_fulltext
Free to start. No credit card required.
Terminal
Install the CLIlune papers fulltext 80054d1e-8fa7-415b-a85d-9d4757569c49Cited by top-tier papers13
- MANUS: Markerless Grasp Capture Using Articulated 3D GaussiansChandradeep Pokhariya, Ishaan Nikhil Shah, Angela Xing, Zekun Li et al.CVPR 2024 · 16 citations
- HAVE-FUN: Human Avatar Reconstruction from Few-Shot Unconstrained ImagesXihe Yang, Xingyu Chen, Daiheng Gao, Shaohui Wang et al.CVPR 2024 · 11 citations
- OHTA: One-shot Hand Avatar via Data-driven Implicit PriorsXiaozheng Zheng, Chao Wen, Zhuo Su, Zeran Xu et al.CVPR 2024 · 7 citations
- Learning Interaction-aware 3D Gaussian Splatting for One-shot Hand AvatarsXuan Huang, Hanhui Li, Wanquan Liu, Xiaodan Liang et al.NeurIPS 2024 · 6 citations
- Authentic Hand Avatar from a Phone Scan via Universal Hand ModelGyeongsik Moon, Weipeng Xu, Rohan Joshi, Chenglei Wu et al.CVPR 2024 · 5 citations
Builds on25
- Soft Rasterizer: A Differentiable Renderer for Image-Based 3D ReasoningShichen Liu, Weikai Chen, Tianye Li, Hao LiICCV 2019 · 789 citations
- Learning an animatable detailed 3D face model from in-the-wild imagesYao Feng, Haiwen Feng, Michael J. Black, Timo BolkartSIGGRAPH 2021 · 662 citations
- HumanNeRF: Free-viewpoint Rendering of Moving People from Monocular VideoChung-Yi Weng, Brian Curless, Pratul P. Srinivasan, Jonathan T. Barron et al.CVPR 2022 · 411 citations
- Neural Articulated Radiance FieldAtsuhiro Noguchi, Xiao Sun, Stephen Lin, Tatsuya HaradaICCV 2021 · 242 citations
- Shape, Light, and Material Decomposition from Images using Monte Carlo Rendering and DenoisingJon Hasselgren, Nikolai Hofmann, Jacob MunkbergNeurIPS 2022 · 234 citations
Related papers
- Hand Avatar: Free-Pose Hand Animation and Rendering from Monocular VideoXingyu Chen, Baoyuan Wang, Heung-Yeung ShumCVPR 2023
- High-Fidelity Human Avatars from a Single RGB CameraHao Zhao, Jinsong Zhang, Yu-Kun Lai, Zerong Zheng et al.CVPR 2022 · 38 citations
- FlashAvatar: High-Fidelity Head Avatar with Efficient Gaussian EmbeddingJun Xiang, Xuan Gao, Yudong Guo, Juyong ZhangCVPR 2024 · 51 citations
- Vid2Avatar-Pro: Authentic Avatar from Videos in the Wild via Universal PriorChen Guo, Junxuan Li, Yash Kant, Yaser Sheikh et al.CVPR 2025
- Learning Personalized High Quality Volumetric Head Avatars from Monocular RGB VideosZiqian Bai, Feitong Tan, Zeng Huang, Kripasindhu Sarkar et al.CVPR 2023
