Papers › Beyond Static Features for Temporally Consistent 3D Human Pose and Shape from a Video

Beyond Static Features for Temporally Consistent 3D Human Pose and Shape from a Video

17 Nov 2020CVPR 2021 1arXiv:2011.08627archive 2025-07-28

Hongsuk Choi, Gyeongsik Moon, Ju Yong Chang, Kyoung Mu Lee

Despite the recent success of single image-based 3D human pose and shape estimation methods, recovering temporally consistent and smooth 3D human motion from a video is still challenging. Several video-based methods have been proposed; however, they fail to resolve the single image-based methods' temporal inconsistency issue due to a strong dependency on a static feature of the current frame. In this regard, we present a temporally consistent mesh recovery system (TCMR). It effectively focuses on the past and future frames' temporal information without being dominated by the current static feature. Our TCMR significantly outperforms previous video-based methods in temporal consistency with better per-frame 3D pose and shape accuracy. We also release the codes. For the demo video, see https://youtu.be/WB3nTnSQDII. For the codes, see https://github.com/hongsukchoi/TCMR_RELEASE.

PaperPDFConference PDFCode

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

Code

hongsukchoi/TCMR_RELEASE officialmentioned in papermentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

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

Tasks

3D Human Pose Estimation3D human pose and shape estimation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
3D Human Pose Estimation 3DPW TCMR (T=16 w/o H3.6M) Acceleration Error 7.1 #54 of 119 Archive leaderboard report
3D Human Pose Estimation 3DPW TCMR (T=16 w/o H3.6M) MPJPE 86.5 #54 of 119 Archive leaderboard report
3D Human Pose Estimation 3DPW TCMR (T=16 w/o H3.6M) MPVPE 102.9 #54 of 119 Archive leaderboard report
3D Human Pose Estimation 3DPW TCMR (T=16 w/o H3.6M) PA-MPJPE 52.7 #54 of 119 Archive leaderboard report
3D Human Pose Estimation 3DPW TCMR (T=16 w/o 3DPW) Acceleration Error 7 #61 of 119 Archive leaderboard report
3D Human Pose Estimation 3DPW TCMR (T=16 w/o 3DPW) MPJPE 95 #61 of 119 Archive leaderboard report
3D Human Pose Estimation 3DPW TCMR (T=16 w/o 3DPW) MPVPE 111.5 #61 of 119 Archive leaderboard report
3D Human Pose Estimation 3DPW TCMR (T=16 w/o 3DPW) PA-MPJPE 55.8 #61 of 119 Archive leaderboard report
3D Human Pose Estimation MPI-INF-3DHP TCMR (T=16 w/o H3.6M) Acceleration Error 8.5 #62 of 108 Archive leaderboard report
3D Human Pose Estimation MPI-INF-3DHP TCMR (T=16 w/o H3.6M) MPJPE 97.3 #62 of 108 Archive leaderboard report
3D Human Pose Estimation MPI-INF-3DHP TCMR (T=16 w/o H3.6M) PA-MPJPE 63.5 #62 of 108 Archive leaderboard report
3D Human Pose Estimation MPI-INF-3DHP TCMR (T=16 w/o 3DPW) Acceleration Error 8 #63 of 108 Archive leaderboard report
3D Human Pose Estimation MPI-INF-3DHP TCMR (T=16 w/o 3DPW) MPJPE 97.4 #63 of 108 Archive leaderboard report
3D Human Pose Estimation MPI-INF-3DHP TCMR (T=16 w/o 3DPW) PA-MPJPE 62.8 #63 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