Papers › Bilevel Online Adaptation for Out-of-Domain Human Mesh Reconstruction

Bilevel Online Adaptation for Out-of-Domain Human Mesh Reconstruction

30 Mar 2021CVPR 2021 1arXiv:2103.16449archive 2025-07-28

Shanyan Guan, Jingwei Xu, Yunbo Wang, Bingbing Ni, Xiaokang Yang

This paper considers a new problem of adapting a pre-trained model of human mesh reconstruction to out-of-domain streaming videos. However, most previous methods based on the parametric SMPL model \cite{loper2015smpl} underperform in new domains with unexpected, domain-specific attributes, such as camera parameters, lengths of bones, backgrounds, and occlusions. Our general idea is to dynamically fine-tune the source model on test video streams with additional temporal constraints, such that it can mitigate the domain gaps without over-fitting the 2D information of individual test frames. A subsequent challenge is how to avoid conflicts between the 2D and temporal constraints. We propose to tackle this problem using a new training algorithm named Bilevel Online Adaptation (BOA), which divides the optimization process of overall multi-objective into two steps of weight probe and weight update in a training iteration. We demonstrate that BOA leads to state-of-the-art results on two human mesh reconstruction benchmarks.

PaperPDFConference PDFCode

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

Code

syguan96/BOA officialmentioned 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 Estimation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
3D Human Pose Estimation 3DPW BOA (w/ 2D GT) MPJPE 77.2 #38 of 119 Archive leaderboard report
3D Human Pose Estimation 3DPW BOA (w/ 2D GT) MPVPE 91.2 #38 of 119 Archive leaderboard report
3D Human Pose Estimation 3DPW BOA (w/ 2D GT) PA-MPJPE 49.5 #38 of 119 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