Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

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

About

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.

Hongsuk Choi, Gyeongsik Moon, Ju Yong Chang, Kyoung Mu Lee• 2020

Related benchmarks

TaskDatasetResultRank
3D Human Pose EstimationMPI-INF-3DHP (test)--
559
3D Human Pose EstimationHuman3.6M (test)--
547
3D Human Pose Estimation3DPW (test)
PA-MPJPE52.4
505
3D Human Mesh Recovery3DPW (test)
PA-MPJPE52.7
264
3D Human Pose and Shape Estimation3DPW (test)
MPJPE-PA52.7
158
Human Mesh Recovery3DPW
PA-MPJPE52.7
123
3D Human Mesh RecoveryHuman3.6M (test)
PA-MPJPE41.1
120
3D Human Pose and Shape EstimationHuman3.6M (test)
PA-MPJPE41.1
119
3D Human Pose and Shape Estimation3DPW
PA-MPJPE52.7
74
Human Mesh ReconstructionHuman3.6M
PA-MPJPE41.1
50
Showing 10 of 41 rows

Other info

Code

Follow for update