Snipper: A Spatiotemporal Transformer for Simultaneous Multi-Person 3D Pose Estimation Tracking and Forecasting on a Video Snippet

• URL: http://arxiv.org/abs/2207.04320v3
• Date: Tue, 12 Sep 2023 21:21:35 GMT
• Title: Snipper: A Spatiotemporal Transformer for Simultaneous Multi-Person 3D Pose Estimation Tracking and Forecasting on a Video Snippet
• Authors: Shihao Zou, Yuanlu Xu, Chao Li, Lingni Ma, Li Cheng, Minh Vo
• Abstract summary: Multi-person pose understanding from RGB involves three complex tasks: pose estimation, tracking and motion forecasting. Most existing works either focus on a single task or employ multi-stage approaches to solving multiple tasks separately. We propose Snipper, a unified framework to perform multi-person 3D pose estimation, tracking, and motion forecasting simultaneously in a single stage.
• Score: 24.852728097115744
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Multi-person pose understanding from RGB videos involves three complex tasks: pose estimation, tracking and motion forecasting. Intuitively, accurate multi-person pose estimation facilitates robust tracking, and robust tracking builds crucial history for correct motion forecasting. Most existing works either focus on a single task or employ multi-stage approaches to solving multiple tasks separately, which tends to make sub-optimal decision at each stage and also fail to exploit correlations among the three tasks. In this paper, we propose Snipper, a unified framework to perform multi-person 3D pose estimation, tracking, and motion forecasting simultaneously in a single stage. We propose an efficient yet powerful deformable attention mechanism to aggregate spatiotemporal information from the video snippet. Building upon this deformable attention, a video transformer is learned to encode the spatiotemporal features from the multi-frame snippet and to decode informative pose features for multi-person pose queries. Finally, these pose queries are regressed to predict multi-person pose trajectories and future motions in a single shot. In the experiments, we show the effectiveness of Snipper on three challenging public datasets where our generic model rivals specialized state-of-art baselines for pose estimation, tracking, and forecasting.

Related papers

• StreamMOTP: Streaming and Unified Framework for Joint 3D Multi-Object Tracking and Trajectory Prediction [22.29257945966914]
  We propose a streaming and unified framework for joint 3D Multi-Object Tracking and trajectory Prediction (StreamMOTP) We construct the model in a streaming manner and exploit a memory bank to preserve and leverage the long-term latent features for tracked objects more effectively. We also improve the quality and consistency of predicted trajectories with a dual-stream predictor.
  arXiv  Detail & Related papers  (2024-06-28T11:35:35Z)
• DeTra: A Unified Model for Object Detection and Trajectory Forecasting [68.85128937305697]
  Our approach formulates the union of the two tasks as a trajectory refinement problem. To tackle this unified task, we design a refinement transformer that infers the presence, pose, and multi-modal future behaviors of objects. In our experiments, we observe that ourmodel outperforms the state-of-the-art on Argoverse 2 Sensor and Open dataset.
  arXiv  Detail & Related papers  (2024-06-06T18:12:04Z)
• Deciphering Movement: Unified Trajectory Generation Model for Multi-Agent [53.637837706712794]
  We propose a Unified Trajectory Generation model, UniTraj, that processes arbitrary trajectories as masked inputs. Specifically, we introduce a Ghost Spatial Masking (GSM) module embedded within a Transformer encoder for spatial feature extraction. We benchmark three practical sports game datasets, Basketball-U, Football-U, and Soccer-U, for evaluation.
  arXiv  Detail & Related papers  (2024-05-27T22:15:23Z)
• The MI-Motion Dataset and Benchmark for 3D Multi-Person Motion Prediction [13.177817435234449]
  3D multi-person motion prediction is a challenging task that involves modeling individual behaviors and interactions between people. We introduce the Multi-Person Interaction Motion (MI-Motion) dataset, which includes skeleton sequences of multiple individuals collected by motion capture systems. The dataset contains 167k frames of interacting people's skeleton poses and is categorized into 5 different activity scenes.
  arXiv  Detail & Related papers  (2023-06-23T15:38:22Z)
• Mutual Information-Based Temporal Difference Learning for Human Pose Estimation in Video [16.32910684198013]
  We present a novel multi-frame human pose estimation framework, which employs temporal differences across frames to model dynamic contexts. To be specific, we design a multi-stage entangled learning sequences conditioned on multi-stage differences to derive informative motion representation sequences. These place us to rank No.1 in the Crowd Pose Estimation in Complex Events Challenge on benchmark HiEve.
  arXiv  Detail & Related papers  (2023-03-15T09:29:03Z)
• Modeling Continuous Motion for 3D Point Cloud Object Tracking [54.48716096286417]
  This paper presents a novel approach that views each tracklet as a continuous stream. At each timestamp, only the current frame is fed into the network to interact with multi-frame historical features stored in a memory bank. To enhance the utilization of multi-frame features for robust tracking, a contrastive sequence enhancement strategy is proposed.
  arXiv  Detail & Related papers  (2023-03-14T02:58:27Z)
• Kinematic-aware Hierarchical Attention Network for Human Pose Estimation in Videos [17.831839654593452]
  Previous-based human pose estimation methods have shown promising results by leveraging features of consecutive frames. Most approaches compromise accuracy to jitter and do not comprehend the temporal aspects of human motion. We design an architecture that exploits kinematic keypoint features.
  arXiv  Detail & Related papers  (2022-11-29T01:46:11Z)
• BEVerse: Unified Perception and Prediction in Birds-Eye-View for Vision-Centric Autonomous Driving [92.05963633802979]
  We present BEVerse, a unified framework for 3D perception and prediction based on multi-camera systems. We show that the multi-task BEVerse outperforms single-task methods on 3D object detection, semantic map construction, and motion prediction.
  arXiv  Detail & Related papers  (2022-05-19T17:55:35Z)
• Direct Multi-view Multi-person 3D Pose Estimation [138.48139701871213]
  We present Multi-view Pose transformer (MvP) for estimating multi-person 3D poses from multi-view images. MvP directly regresses the multi-person 3D poses in a clean and efficient way, without relying on intermediate tasks. We show experimentally that our MvP model outperforms the state-of-the-art methods on several benchmarks while being much more efficient.
  arXiv  Detail & Related papers  (2021-11-07T13:09:20Z)
• 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)
• Deep Reinforcement Learning for Active Human Pose Estimation [35.229529080763925]
  We introduce Pose-DRL, a fully trainable deep reinforcement learning-based active pose estimation architecture. We show that our model learns to select viewpoints that yield significantly more accurate pose estimates compared to strong multi-view baselines.
  arXiv  Detail & Related papers  (2020-01-07T13:35:41Z)

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.