paper-with-me

홈 › Papers

Learning Analytical Posterior Probability for Human Mesh Recovery

2023-01-01 · CVPR 2023 1 · Qi Fang, Kang Chen, Yinghui Fan, Qing Shuai, Jiefeng Li, Weidong Zhang

Despite various probabilistic methods for modeling the uncertainty and ambiguity in human mesh recovery, their overall precision is limited because existing formulations for joint rotations are either not constrained to SO(3) or difficult to learn for neural networks. To address such an issue, we derive a novel analytical formulation for learning posterior probability distributions of human joint rotations conditioned on bone directions in a Bayesian manner, and based on this, we propose a new posterior-guided framework for human mesh recovery. We demonstrate that our framework is not only superior to existing SOTA baselines on multiple benchmarks but also flexible enough to seamlessly incorporate with additional sensors due to its Bayesian nature. The code is available at https://github.com/NetEase-GameAI/ProPose.

📄 PDF Abstract BibTeX

Code (1)

netease-gameai/propose 공식 구현 pytorch

Tasks

Human Mesh Recovery

Similar Papers 제목 키워드 기반

ARTS: Semi-Analytical Regressor using Disentangled Skeletal Representations for Human Mesh Recovery from Videos

2024-10-21 · Tao Tang, Hong Liu, Yingxuan You, Ti Wang 외

Although existing video-based 3D human mesh recovery methods have made significant progress, simultaneously estimating human pose and shape from low-resolution image features limits their performance. These image feature…

3D Human Pose EstimationDisentanglementHuman Mesh RecoveryPose Estimation+1

Towards Metric-Aware Multi-Person Mesh Recovery by Jointly Optimizing Human Crowd in Camera Space

2025-11-17 · Kaiwen Wang, Kaili Zheng, Yiming Shi, Chenyi Guo 외 arxiv

Multi-person human mesh recovery from a single image is a challenging task, hindered by the scarcity of in-the-wild training data. Prevailing in-the-wild human mesh pseudo-ground-truth (pGT) generation pipelines are sing…

Human Mesh Recovery

HybrIK-X: Hybrid Analytical-Neural Inverse Kinematics for Whole-body Mesh Recovery

2023-04-12 · Jiefeng Li, Siyuan Bian, Chao Xu, Zhicun Chen 외

Recovering whole-body mesh by inferring the abstract pose and shape parameters from visual content can obtain 3D bodies with realistic structures. However, the inferring process is highly non-linear and suffers from imag…

3D Human Pose Estimation3D Human ReconstructionKeypoint Estimation

Self-supervised 3D Human Mesh Recovery from Noisy Point Clouds

2021-07-15 · Xinxin Zuo, Sen Wang, Qiang Sun, Minglun Gong 외

This paper presents a novel self-supervised approach to reconstruct human shape and pose from noisy point cloud data. Relying on large amount of dataset with ground-truth annotations, recent learning-based approaches pre…

Human Mesh Recovery

MuNet: A Mutualistic Network for Joint 3D Human Mesh Recovery and 3D Clothed Human Reconstruction from Single Images

2026-05-25 · Yunqi Gao, Leyuan Liu, Yuhan Li, Changxin Gao 외 arxiv

3D human mesh recovery and 3D clothed human reconstruction are inherently related, yet they have long been studied in isolation, thereby overlooking the potential gains of joint optimization. To overcome this limitation,…

Human Mesh Recovery