Papers › Deep Two-Stream Video Inference for Human Body Pose and Shape Estimation

Deep Two-Stream Video Inference for Human Body Pose and Shape Estimation

22 Oct 2021arXiv:2110.11680archive 2025-07-28

Ziwen Li, Bo Xu, Han Huang, Cheng Lu, Yandong Guo

Several video-based 3D pose and shape estimation algorithms have been proposed to resolve the temporal inconsistency of single-image-based methods. However it still remains challenging to have stable and accurate reconstruction. In this paper, we propose a new framework Deep Two-Stream Video Inference for Human Body Pose and Shape Estimation (DTS-VIBE), to generate 3D human pose and mesh from RGB videos. We reformulate the task as a multi-modality problem that fuses RGB and optical flow for more reliable estimation. In order to fully utilize both sensory modalities (RGB or optical flow), we train a two-stream temporal network based on transformer to predict SMPL parameters. The supplementary modality, optical flow, helps to maintain temporal consistency by leveraging motion knowledge between two consecutive frames. The proposed algorithm is extensively evaluated on the Human3.6 and 3DPW datasets. The experimental results show that it outperforms other state-of-the-art methods by a significant margin.

PaperPDF

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

3D Human Pose EstimationOptical Flow Estimation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
3D Human Pose Estimation 3DPW DST-VIBE Acceleration Error 11 #40 of 119 Archive leaderboard report
3D Human Pose Estimation 3DPW DST-VIBE MPJPE 76.7 #40 of 119 Archive leaderboard report
3D Human Pose Estimation 3DPW DST-VIBE MPVPE 93.5 #40 of 119 Archive leaderboard report
3D Human Pose Estimation 3DPW DST-VIBE PA-MPJPE 50.3 #40 of 119 Archive leaderboard report
3D Human Pose Estimation MPI-INF-3DHP DST-VIBE Acceleration Error 11.9 #51 of 108 Archive leaderboard report
3D Human Pose Estimation MPI-INF-3DHP DST-VIBE MPJPE 93.4 #51 of 108 Archive leaderboard report
3D Human Pose Estimation MPI-INF-3DHP DST-VIBE PA-MPJPE 62.2 #51 of 108 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections