X as Supervision: Contending with Depth Ambiguity in Unsupervised Monocular 3D Pose Estimation

• URL: http://arxiv.org/abs/2411.13026v1
• Date: Wed, 20 Nov 2024 04:18:11 GMT
• Title: X as Supervision: Contending with Depth Ambiguity in Unsupervised Monocular 3D Pose Estimation
• Authors: Yuchen Yang, Xuanyi Liu, Xing Gao, Zhihang Zhong, Xiao Sun,
• Abstract summary: We propose an unsupervised framework featuring a multi-hypothesis detector and multiple tailored pretext tasks. The detector extracts multiple hypotheses from a heatmap within a local window, effectively managing the multi-solution problem. The pretext tasks harness 3D human priors from the SMPL model to regularize the solution space of pose estimation, aligning it with the empirical distribution of 3D human structures.
• Score: 12.765995624408557
• License:
• Abstract: Recent unsupervised methods for monocular 3D pose estimation have endeavored to reduce dependence on limited annotated 3D data, but most are solely formulated in 2D space, overlooking the inherent depth ambiguity issue. Due to the information loss in 3D-to-2D projection, multiple potential depths may exist, yet only some of them are plausible in human structure. To tackle depth ambiguity, we propose a novel unsupervised framework featuring a multi-hypothesis detector and multiple tailored pretext tasks. The detector extracts multiple hypotheses from a heatmap within a local window, effectively managing the multi-solution problem. Furthermore, the pretext tasks harness 3D human priors from the SMPL model to regularize the solution space of pose estimation, aligning it with the empirical distribution of 3D human structures. This regularization is partially achieved through a GCN-based discriminator within the discriminative learning, and is further complemented with synthetic images through rendering, ensuring plausible estimations. Consequently, our approach demonstrates state-of-the-art unsupervised 3D pose estimation performance on various human datasets. Further evaluations on data scale-up and one animal dataset highlight its generalization capabilities. Code will be available at https://github.com/Charrrrrlie/X-as-Supervision.

Related papers

• Utilizing Uncertainty in 2D Pose Detectors for Probabilistic 3D Human Mesh Recovery [23.473909489868454]
  probabilistic approaches learn a distribution over plausible 3D human meshes. We show that this objective function alone is not sufficient to best capture the full distributions. We demonstrate that person segmentation masks can be utilized during training to significantly decrease the number of invalid samples.
  arXiv  Detail & Related papers  (2024-11-25T11:13:12Z)
• DiffuPose: Monocular 3D Human Pose Estimation via Denoising Diffusion Probabilistic Model [25.223801390996435]
  This paper focuses on reconstructing a 3D pose from a single 2D keypoint detection. We build a novel diffusion-based framework to effectively sample diverse 3D poses from an off-the-shelf 2D detector. We evaluate our method on the widely adopted Human3.6M and HumanEva-I datasets.
  arXiv  Detail & Related papers  (2022-12-06T07:22:20Z)
• Homography Loss for Monocular 3D Object Detection [54.04870007473932]
  A differentiable loss function, termed as Homography Loss, is proposed to achieve the goal, which exploits both 2D and 3D information. Our method yields the best performance compared with the other state-of-the-arts by a large margin on KITTI 3D datasets.
  arXiv  Detail & Related papers  (2022-04-02T03:48:03Z)
• On Triangulation as a Form of Self-Supervision for 3D Human Pose Estimation [57.766049538913926]
  Supervised approaches to 3D pose estimation from single images are remarkably effective when labeled data is abundant. Much of the recent attention has shifted towards semi and (or) weakly supervised learning. We propose to impose multi-view geometrical constraints by means of a differentiable triangulation and to use it as form of self-supervision during training when no labels are available.
  arXiv  Detail & Related papers  (2022-03-29T19:11:54Z)
• Uncertainty-Aware Adaptation for Self-Supervised 3D Human Pose Estimation [70.32536356351706]
  We introduce MRP-Net that constitutes a common deep network backbone with two output heads subscribing to two diverse configurations. We derive suitable measures to quantify prediction uncertainty at both pose and joint level. We present a comprehensive evaluation of the proposed approach and demonstrate state-of-the-art performance on benchmark datasets.
  arXiv  Detail & Related papers  (2022-03-29T07:14:58Z)
• Probabilistic Monocular 3D Human Pose Estimation with Normalizing Flows [24.0966076588569]
  We propose a normalizing flow based method that exploits the deterministic 3D-to-2D mapping to solve the ambiguous inverse 2D-to-3D problem. We evaluate our approach on the two benchmark datasets Human3.6M and MPI-INF-3DHP, outperforming all comparable methods in most metrics.
  arXiv  Detail & Related papers  (2021-07-29T07:33:14Z)
• 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)
• Weakly Supervised Generative Network for Multiple 3D Human Pose Hypotheses [74.48263583706712]
  3D human pose estimation from a single image is an inverse problem due to the inherent ambiguity of the missing depth. We propose a weakly supervised deep generative network to address the inverse problem.
  arXiv  Detail & Related papers  (2020-08-13T09:26:01Z)
• Unsupervised Cross-Modal Alignment for Multi-Person 3D Pose Estimation [52.94078950641959]
  We present a deployment friendly, fast bottom-up framework for multi-person 3D human pose estimation. We adopt a novel neural representation of multi-person 3D pose which unifies the position of person instances with their corresponding 3D pose representation. We propose a practical deployment paradigm where paired 2D or 3D pose annotations are unavailable.
  arXiv  Detail & Related papers  (2020-08-04T07:54:25Z)
• Multi-Person Absolute 3D Human Pose Estimation with Weak Depth Supervision [0.0]
  We introduce a network that can be trained with additional RGB-D images in a weakly supervised fashion. Our algorithm is a monocular, multi-person, absolute pose estimator. We evaluate the algorithm on several benchmarks, showing a consistent improvement in error rates.
  arXiv  Detail & Related papers  (2020-04-08T13:29:22Z)

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.