Self-learning Canonical Space for Multi-view 3D Human Pose Estimation
- URL: http://arxiv.org/abs/2403.12440v2
- Date: Fri, 29 Mar 2024 14:55:50 GMT
- Title: Self-learning Canonical Space for Multi-view 3D Human Pose Estimation
- Authors: Xiaoben Li, Mancheng Meng, Ziyan Wu, Terrence Chen, Fan Yang, Dinggang Shen,
- Abstract summary: Multi-view 3D human pose estimation is naturally superior to single view one.
The accurate annotation of these information is hard to obtain.
We propose a fully self-supervised framework, named cascaded multi-view aggregating network (CMANet)
CMANet is superior to state-of-the-art methods in extensive quantitative and qualitative analysis.
- Score: 57.969696744428475
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Multi-view 3D human pose estimation is naturally superior to single view one, benefiting from more comprehensive information provided by images of multiple views. The information includes camera poses, 2D/3D human poses, and 3D geometry. However, the accurate annotation of these information is hard to obtain, making it challenging to predict accurate 3D human pose from multi-view images. To deal with this issue, we propose a fully self-supervised framework, named cascaded multi-view aggregating network (CMANet), to construct a canonical parameter space to holistically integrate and exploit multi-view information. In our framework, the multi-view information is grouped into two categories: 1) intra-view information , 2) inter-view information. Accordingly, CMANet consists of two components: intra-view module (IRV) and inter-view module (IEV). IRV is used for extracting initial camera pose and 3D human pose of each view; IEV is to fuse complementary pose information and cross-view 3D geometry for a final 3D human pose. To facilitate the aggregation of the intra- and inter-view, we define a canonical parameter space, depicted by per-view camera pose and human pose and shape parameters ($\theta$ and $\beta$) of SMPL model, and propose a two-stage learning procedure. At first stage, IRV learns to estimate camera pose and view-dependent 3D human pose supervised by confident output of an off-the-shelf 2D keypoint detector. At second stage, IRV is frozen and IEV further refines the camera pose and optimizes the 3D human pose by implicitly encoding the cross-view complement and 3D geometry constraint, achieved by jointly fitting predicted multi-view 2D keypoints. The proposed framework, modules, and learning strategy are demonstrated to be effective by comprehensive experiments and CMANet is superior to state-of-the-art methods in extensive quantitative and qualitative analysis.
Related papers
- Unsupervised Learning of Category-Level 3D Pose from Object-Centric Videos [15.532504015622159]
Category-level 3D pose estimation is a fundamentally important problem in computer vision and robotics.
We tackle the problem of learning to estimate the category-level 3D pose only from casually taken object-centric videos.
arXiv Detail & Related papers (2024-07-05T09:43:05Z) - UPose3D: Uncertainty-Aware 3D Human Pose Estimation with Cross-View and Temporal Cues [55.69339788566899]
UPose3D is a novel approach for multi-view 3D human pose estimation.
It improves robustness and flexibility without requiring direct 3D annotations.
arXiv Detail & Related papers (2024-04-23T00:18:00Z) - Multi-person 3D pose estimation from unlabelled data [2.54990557236581]
We present a model based on Graph Neural Networks capable of predicting the cross-view correspondence of the people in the scenario.
We also present a Multilayer Perceptron that takes the 2D points to yield the 3D poses of each person.
arXiv Detail & Related papers (2022-12-16T22:03:37Z) - Self-Supervised 3D Human Pose Estimation with Multiple-View Geometry [2.7541825072548805]
We present a self-supervised learning algorithm for 3D human pose estimation of a single person based on a multiple-view camera system.
We propose a four-loss function learning algorithm, which does not require any 2D or 3D body pose ground-truth.
arXiv Detail & Related papers (2021-08-17T17:31:24Z) - VoxelTrack: Multi-Person 3D Human Pose Estimation and Tracking in the
Wild [98.69191256693703]
We present VoxelTrack for multi-person 3D pose estimation and tracking from a few cameras which are separated by wide baselines.
It employs a multi-branch network to jointly estimate 3D poses and re-identification (Re-ID) features for all people in the environment.
It outperforms the state-of-the-art methods by a large margin on three public datasets including Shelf, Campus and CMU Panoptic.
arXiv Detail & Related papers (2021-08-05T08:35:44Z) - Multi-View Multi-Person 3D Pose Estimation with Plane Sweep Stereo [71.59494156155309]
Existing approaches for multi-view 3D pose estimation explicitly establish cross-view correspondences to group 2D pose detections from multiple camera views.
We present our multi-view 3D pose estimation approach based on plane sweep stereo to jointly address the cross-view fusion and 3D pose reconstruction in a single shot.
arXiv Detail & Related papers (2021-04-06T03:49:35Z) - SMAP: Single-Shot Multi-Person Absolute 3D Pose Estimation [46.85865451812981]
We propose a novel system that first regresses a set of 2.5D representations of body parts and then reconstructs the 3D absolute poses based on these 2.5D representations with a depth-aware part association algorithm.
Such a single-shot bottom-up scheme allows the system to better learn and reason about the inter-person depth relationship, improving both 3D and 2D pose estimation.
arXiv Detail & Related papers (2020-08-26T09:56:07Z) - Self-Supervised 3D Human Pose Estimation via Part Guided Novel Image
Synthesis [72.34794624243281]
We propose a self-supervised learning framework to disentangle variations from unlabeled video frames.
Our differentiable formalization, bridging the representation gap between the 3D pose and spatial part maps, allows us to operate on videos with diverse camera movements.
arXiv Detail & Related papers (2020-04-09T07:55:01Z) - Weakly-Supervised 3D Human Pose Learning via Multi-view Images in the
Wild [101.70320427145388]
We propose a weakly-supervised approach that does not require 3D annotations and learns to estimate 3D poses from unlabeled multi-view data.
We evaluate our proposed approach on two large scale datasets.
arXiv Detail & Related papers (2020-03-17T08:47:16Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.