ElePose: Unsupervised 3D Human Pose Estimation by Predicting Camera
Elevation and Learning Normalizing Flows on 2D Poses
- URL: http://arxiv.org/abs/2112.07088v1
- Date: Tue, 14 Dec 2021 01:12:45 GMT
- Title: ElePose: Unsupervised 3D Human Pose Estimation by Predicting Camera
Elevation and Learning Normalizing Flows on 2D Poses
- Authors: Bastian Wandt, James J. Little, Helge Rhodin
- Abstract summary: We propose an unsupervised approach that learns to predict a 3D human pose from a single image.
We estimate the 3D pose that is most likely over random projections, with the likelihood estimated using normalizing flows on 2D poses.
We outperform the state-of-the-art unsupervised human pose estimation methods on the benchmark datasets Human3.6M and MPI-INF-3DHP in many metrics.
- Score: 23.554957518485324
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Human pose estimation from single images is a challenging problem that is
typically solved by supervised learning. Unfortunately, labeled training data
does not yet exist for many human activities since 3D annotation requires
dedicated motion capture systems. Therefore, we propose an unsupervised
approach that learns to predict a 3D human pose from a single image while only
being trained with 2D pose data, which can be crowd-sourced and is already
widely available. To this end, we estimate the 3D pose that is most likely over
random projections, with the likelihood estimated using normalizing flows on 2D
poses. While previous work requires strong priors on camera rotations in the
training data set, we learn the distribution of camera angles which
significantly improves the performance. Another part of our contribution is to
stabilize training with normalizing flows on high-dimensional 3D pose data by
first projecting the 2D poses to a linear subspace. We outperform the
state-of-the-art unsupervised human pose estimation methods on the benchmark
datasets Human3.6M and MPI-INF-3DHP in many metrics.
Related papers
- MPL: Lifting 3D Human Pose from Multi-view 2D Poses [75.26416079541723]
We propose combining 2D pose estimation, for which large and rich training datasets exist, and 2D-to-3D pose lifting, using a transformer-based network.
Our experiments demonstrate decreases up to 45% in MPJPE errors compared to the 3D pose obtained by triangulating the 2D poses.
arXiv Detail & Related papers (2024-08-20T12:55:14Z) - Unsupervised Multi-Person 3D Human Pose Estimation From 2D Poses Alone [4.648549457266638]
We present one of the first studies investigating the feasibility of unsupervised multi-person 2D-3D pose estimation.
Our method involves independently lifting each subject's 2D pose to 3D, before combining them in a shared 3D coordinate system.
This by itself enables us to retrieve an accurate 3D reconstruction of their poses.
arXiv Detail & Related papers (2023-09-26T11:42:56Z) - MPM: A Unified 2D-3D Human Pose Representation via Masked Pose Modeling [59.74064212110042]
mpmcan handle multiple tasks including 3D human pose estimation, 3D pose estimation from cluded 2D pose, and 3D pose completion in a textocbfsingle framework.
We conduct extensive experiments and ablation studies on several widely used human pose datasets and achieve state-of-the-art performance on MPI-INF-3DHP.
arXiv Detail & Related papers (2023-06-29T10:30:00Z) - Weakly-supervised Pre-training for 3D Human Pose Estimation via
Perspective Knowledge [36.65402869749077]
We propose a novel method to extract weak 3D information directly from 2D images without 3D pose supervision.
We propose a weakly-supervised pre-training (WSP) strategy to distinguish the depth relationship between two points in an image.
WSP achieves state-of-the-art results on two widely-used benchmarks.
arXiv Detail & Related papers (2022-11-22T03:35:15Z) - VirtualPose: Learning Generalizable 3D Human Pose Models from Virtual
Data [69.64723752430244]
We introduce VirtualPose, a two-stage learning framework to exploit the hidden "free lunch" specific to this task.
The first stage transforms images to abstract geometry representations (AGR), and then the second maps them to 3D poses.
It addresses the generalization issue from two aspects: (1) the first stage can be trained on diverse 2D datasets to reduce the risk of over-fitting to limited appearance; (2) the second stage can be trained on diverse AGR synthesized from a large number of virtual cameras and poses.
arXiv Detail & Related papers (2022-07-20T14:47:28Z) - AdaptPose: Cross-Dataset Adaptation for 3D Human Pose Estimation by
Learnable Motion Generation [24.009674750548303]
Testing a pre-trained 3D pose estimator on a new dataset results in a major performance drop.
We propose AdaptPose, an end-to-end framework that generates synthetic 3D human motions from a source dataset.
Our method outperforms previous work in cross-dataset evaluations by 14% and previous semi-supervised learning methods that use partial 3D annotations by 16%.
arXiv Detail & Related papers (2021-12-22T00:27:52Z) - TriPose: A Weakly-Supervised 3D Human Pose Estimation via Triangulation
from Video [23.00696619207748]
Estimating 3D human poses from video is a challenging problem.
The lack of 3D human pose annotations is a major obstacle for supervised training and for generalization to unseen datasets.
We propose a weakly-supervised training scheme that does not require 3D annotations or calibrated cameras.
arXiv Detail & Related papers (2021-05-14T00:46:48Z) - CanonPose: Self-Supervised Monocular 3D Human Pose Estimation in the
Wild [31.334715988245748]
We propose a self-supervised approach that learns a single image 3D pose estimator from unlabeled multi-view data.
In contrast to most existing methods, we do not require calibrated cameras and can therefore learn from moving cameras.
Key to the success are new, unbiased reconstruction objectives that mix information across views and training samples.
arXiv Detail & Related papers (2020-11-30T10:42:27Z) - Synthetic Training for Monocular Human Mesh Recovery [100.38109761268639]
This paper aims to estimate 3D mesh of multiple body parts with large-scale differences from a single RGB image.
The main challenge is lacking training data that have complete 3D annotations of all body parts in 2D images.
We propose a depth-to-scale (D2S) projection to incorporate the depth difference into the projection function to derive per-joint scale variants.
arXiv Detail & Related papers (2020-10-27T03:31:35Z) - Cascaded deep monocular 3D human pose estimation with evolutionary
training data [76.3478675752847]
Deep representation learning has achieved remarkable accuracy for monocular 3D human pose estimation.
This paper proposes a novel data augmentation method that is scalable for massive amount of training data.
Our method synthesizes unseen 3D human skeletons based on a hierarchical human representation and synthesizings inspired by prior knowledge.
arXiv Detail & Related papers (2020-06-14T03:09:52Z) - 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)
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.