Estimating Ego-Body Pose from Doubly Sparse Egocentric Video Data

• URL: http://arxiv.org/abs/2411.03561v1
• Date: Tue, 05 Nov 2024 23:53:19 GMT
• Title: Estimating Ego-Body Pose from Doubly Sparse Egocentric Video Data
• Authors: Seunggeun Chi, Pin-Hao Huang, Enna Sachdeva, Hengbo Ma, Karthik Ramani, Kwonjoon Lee,
• Abstract summary: Current methods for ego-body pose estimation rely on temporally dense sensor data. We develop a two-stage approach that decomposes the problem into temporal completion and spatial completion.
• Score: 16.431101717478796
• License:
• Abstract: We study the problem of estimating the body movements of a camera wearer from egocentric videos. Current methods for ego-body pose estimation rely on temporally dense sensor data, such as IMU measurements from spatially sparse body parts like the head and hands. However, we propose that even temporally sparse observations, such as hand poses captured intermittently from egocentric videos during natural or periodic hand movements, can effectively constrain overall body motion. Naively applying diffusion models to generate full-body pose from head pose and sparse hand pose leads to suboptimal results. To overcome this, we develop a two-stage approach that decomposes the problem into temporal completion and spatial completion. First, our method employs masked autoencoders to impute hand trajectories by leveraging the spatiotemporal correlations between the head pose sequence and intermittent hand poses, providing uncertainty estimates. Subsequently, we employ conditional diffusion models to generate plausible full-body motions based on these temporally dense trajectories of the head and hands, guided by the uncertainty estimates from the imputation. The effectiveness of our method was rigorously tested and validated through comprehensive experiments conducted on various HMD setup with AMASS and Ego-Exo4D datasets.

Related papers

• Estimating Body and Hand Motion in an Ego-sensed World [64.08911275906544]
  We present EgoAllo, a system for human motion estimation from a head-mounted device. Using only egocentric SLAM poses and images, EgoAllo guides sampling from a conditional diffusion model to estimate 3D body pose, height, and hand parameters.
  arXiv  Detail & Related papers  (2024-10-04T17:59:57Z)
• HMP: Hand Motion Priors for Pose and Shape Estimation from Video [52.39020275278984]
  We develop a generative motion prior specific for hands, trained on the AMASS dataset which features diverse and high-quality hand motions. Our integration of a robust motion prior significantly enhances performance, especially in occluded scenarios. We demonstrate our method's efficacy via qualitative and quantitative evaluations on the HO3D and DexYCB datasets.
  arXiv  Detail & Related papers  (2023-12-27T22:35:33Z)
• STRIDE: Single-video based Temporally Continuous Occlusion Robust 3D Pose Estimation [27.854074900345314]
  We propose STRIDE, a novel Test-Time Training (TTT) approach to fit a human motion prior to each video. Our framework demonstrates flexibility by being model-agnostic, allowing us to use any off-the-shelf 3D pose estimation method for improving robustness and temporal consistency. We validate STRIDE's efficacy through comprehensive experiments on challenging datasets like Occluded Human3.6M, Human3.6M, and OCMotion.
  arXiv  Detail & Related papers  (2023-12-24T11:05:10Z)
• Egocentric Whole-Body Motion Capture with FisheyeViT and Diffusion-Based Motion Refinement [65.08165593201437]
  We explore egocentric whole-body motion capture using a single fisheye camera, which simultaneously estimates human body and hand motion. This task presents significant challenges due to the lack of high-quality datasets, fisheye camera distortion, and human body self-occlusion. We propose a novel approach that leverages FisheyeViT to extract fisheye image features, which are converted into pixel-aligned 3D heatmap representations for 3D human body pose prediction.
  arXiv  Detail & Related papers  (2023-11-28T07:13:47Z)
• EgoPoser: Robust Real-Time Egocentric Pose Estimation from Sparse and Intermittent Observations Everywhere [29.795731025552957]
  EgoPoser robustly models body pose from intermittent hand position and orientation tracking only when inside a headset's field of view. We introduce a novel global motion decomposition method that predicts full-body pose independent of global positions. We experimentally evaluate our method and show that it outperforms state-of-the-art methods both qualitatively and quantitatively.
  arXiv  Detail & Related papers  (2023-08-12T07:46:50Z)
• Ego-Body Pose Estimation via Ego-Head Pose Estimation [22.08240141115053]
  Estimating 3D human motion from an egocentric video sequence plays a critical role in human behavior understanding and has various applications in VR/AR. We propose a new method, Ego-Body Pose Estimation via Ego-Head Pose Estimation (EgoEgo), which decomposes the problem into two stages, connected by the head motion as an intermediate representation. This disentanglement of head and body pose eliminates the need for training datasets with paired egocentric videos and 3D human motion.
  arXiv  Detail & Related papers  (2022-12-09T02:25:20Z)
• Occluded Human Body Capture with Self-Supervised Spatial-Temporal Motion Prior [7.157324258813676]
  We build the first 3D occluded motion dataset(OcMotion), which can be used for both training and testing. A spatial-temporal layer is then designed to learn joint-level correlations. Experimental results show that our method can generate accurate and coherent human motions from occluded videos with good generalization ability and runtime efficiency.
  arXiv  Detail & Related papers  (2022-07-12T08:15:11Z)
• Estimating Egocentric 3D Human Pose in the Wild with External Weak Supervision [72.36132924512299]
  We present a new egocentric pose estimation method, which can be trained on a large-scale in-the-wild egocentric dataset. We propose a novel learning strategy to supervise the egocentric features with the high-quality features extracted by a pretrained external-view pose estimation model. Experiments show that our method predicts accurate 3D poses from a single in-the-wild egocentric image and outperforms the state-of-the-art methods both quantitatively and qualitatively.
  arXiv  Detail & Related papers  (2022-01-20T00:45:13Z)
• Learning Dynamics via Graph Neural Networks for Human Pose Estimation and Tracking [98.91894395941766]
  We propose a novel online approach to learning the pose dynamics, which are independent of pose detections in current fame. Specifically, we derive this prediction of dynamics through a graph neural network(GNN) that explicitly accounts for both spatial-temporal and visual information. Experiments on PoseTrack 2017 and PoseTrack 2018 datasets demonstrate that the proposed method achieves results superior to the state of the art on both human pose estimation and tracking tasks.
  arXiv  Detail & Related papers  (2021-06-07T16:36:50Z)
• Estimating Egocentric 3D Human Pose in Global Space [70.7272154474722]
  We present a new method for egocentric global 3D body pose estimation using a single-mounted fisheye camera. Our approach outperforms state-of-the-art methods both quantitatively and qualitatively.
  arXiv  Detail & Related papers  (2021-04-27T20:01:57Z)

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.