AdaptPose: Cross-Dataset Adaptation for 3D Human Pose Estimation by Learnable Motion Generation

• URL: http://arxiv.org/abs/2112.11593v1
• Date: Wed, 22 Dec 2021 00:27:52 GMT
• Title: AdaptPose: Cross-Dataset Adaptation for 3D Human Pose Estimation by Learnable Motion Generation
• Authors: Mohsen Gholami, Bastian Wandt, Helge Rhodin, Rabab Ward, and Z. Jane Wang
• Abstract summary: 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%.
• Score: 24.009674750548303
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: This paper addresses the problem of cross-dataset generalization of 3D human pose estimation models. Testing a pre-trained 3D pose estimator on a new dataset results in a major performance drop. Previous methods have mainly addressed this problem by improving the diversity of the training data. We argue that diversity alone is not sufficient and that the characteristics of the training data need to be adapted to those of the new dataset such as camera viewpoint, position, human actions, and body size. To this end, we propose AdaptPose, an end-to-end framework that generates synthetic 3D human motions from a source dataset and uses them to fine-tune a 3D pose estimator. AdaptPose follows an adversarial training scheme. From a source 3D pose the generator generates a sequence of 3D poses and a camera orientation that is used to project the generated poses to a novel view. Without any 3D labels or camera information AdaptPose successfully learns to create synthetic 3D poses from the target dataset while only being trained on 2D poses. In experiments on the Human3.6M, MPI-INF-3DHP, 3DPW, and Ski-Pose datasets our method outperforms previous work in cross-dataset evaluations by 14% and previous semi-supervised learning methods that use partial 3D annotations by 16%.

Related papers

• 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)
• PoseGen: Learning to Generate 3D Human Pose Dataset with NeRF [20.841557239621995]
  This paper proposes an end-to-end framework for generating 3D human pose datasets using Neural Radiance Fields (NeRF) NeRFs are data-driven and do not require 3D scans of humans. Therefore, using NeRF for data generation is a new direction for convenient user-specific data generation.
  arXiv  Detail & Related papers  (2023-12-22T18:50:15Z)
• Decanus to Legatus: Synthetic training for 2D-3D human pose lifting [26.108023246654646]
  We propose an algorithm to generate infinite 3D synthetic human poses (Legatus) from a 3D pose distribution based on 10 initial handcrafted 3D poses (Decanus) Our results show that we can achieve 3D pose estimation performance comparable to methods using real data from specialized datasets but in a zero-shot setup, showing the potential of our framework.
  arXiv  Detail & Related papers  (2022-10-05T13:10:19Z)
• ElePose: Unsupervised 3D Human Pose Estimation by Predicting Camera Elevation and Learning Normalizing Flows on 2D Poses [23.554957518485324]
  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.
  arXiv  Detail & Related papers  (2021-12-14T01:12:45Z)
• 3D Human Pose Regression using Graph Convolutional Network [68.8204255655161]
  We propose a graph convolutional network named PoseGraphNet for 3D human pose regression from 2D poses. Our model's performance is close to the state-of-the-art, but with much fewer parameters.
  arXiv  Detail & Related papers  (2021-05-21T14:41:31Z)
• 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)
• 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)
• Towards Generalization of 3D Human Pose Estimation In The Wild [73.19542580408971]
  3DBodyTex.Pose is a dataset that addresses the task of 3D human pose estimation in-the-wild. 3DBodyTex.Pose offers high quality and rich data containing 405 different real subjects in various clothing and poses, and 81k image samples with ground-truth 2D and 3D pose annotations.
  arXiv  Detail & Related papers  (2020-04-21T13:31:58Z)
• 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)
• Exemplar Fine-Tuning for 3D Human Model Fitting Towards In-the-Wild 3D Human Pose Estimation [107.07047303858664]
  Large-scale human datasets with 3D ground-truth annotations are difficult to obtain in the wild. We address this problem by augmenting existing 2D datasets with high-quality 3D pose fits. The resulting annotations are sufficient to train from scratch 3D pose regressor networks that outperform the current state-of-the-art on in-the-wild benchmarks.
  arXiv  Detail & Related papers  (2020-04-07T20:21:18Z)

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.