Learning Analytical Posterior Probability for Human Mesh Recovery
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.
Code (1)
Tasks
Human Mesh RecoverySimilar Papers 제목 키워드 기반
ARTS: Semi-Analytical Regressor using Disentangled Skeletal Representations for Human Mesh Recovery from Videos
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+1Towards Metric-Aware Multi-Person Mesh Recovery by Jointly Optimizing Human Crowd in Camera Space
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 RecoveryHybrIK-X: Hybrid Analytical-Neural Inverse Kinematics for Whole-body Mesh Recovery
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 EstimationSelf-supervised 3D Human Mesh Recovery from Noisy Point Clouds
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 RecoveryMuNet: A Mutualistic Network for Joint 3D Human Mesh Recovery and 3D Clothed Human Reconstruction from Single Images
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