AI Paper Atlas

Research map / 3D vision / Face and shape

Cyclic Test-Time Adaptation on Monocular Video for 3D Human Mesh Reconstruction

Hyeongjin Nam, Daniel Sungho Jung, Yeonguk Oh, Kyoung Mu Lee

ICCV 2023 · 3D vision › Face and shape · approach: Full-body avatar reconstruction · 22 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add 3D supervision targets from MDNet (L_SMPL) to 2D reprojection loss (ablation)CycleAdapt HMRNet · 3DPW (H36M source)MPJPE: 125.5 -> 96.9Improved
use MDNet outputs as 3D targets for test samples instead of external H36M 3D loss (ablation)CycleAdapt HMRNet · 3DPW (H36M source)MPJPE: 115.2 -> 96.9Improved
add cyclic adaptation (also adapt MDNet iteratively) (ablation)CycleAdapt · 3DPW (H36M source)MPJPE: 96.9 -> 87.7Improved
add self-supervised masked adaptation of MDNet (ablation)MDNet · 3DPW (H36M source)MPJPE: 114.2 -> 96.2Improved
use MDNet instead of Gaussian filter, Motion infiller or SmoothNet for denoising (ablation)CycleAdapt · 3DPW (H36M source)MPJPE: 92.0 -> 87.7Improved
pre-train HMRNet on Human3.6M before adaptation (ablation)CycleAdapt · 3DPWMPJPE after adaptation: 140.6 -> 87.0Improved
pre-train HMRNet on Human3.6M, no adaptation (ablation)HMRNet · 3DPWMPJPE before adaptation: 272.0 -> 230.3No clear effect
CycleAdapt vs prior test-time adaptation with estimated OpenPose keypointsBOA, DynaBOA, DAPA · 3DPW (H36M source)MPJPE: 108.0 -> 87.7 (vs DAPA)Improved
online adaptation setting (MDNet cannot see future frames)CycleAdapt · 3DPW (H36M source)MPJPE: 87.7 -> 90.3Hurt
CycleAdapt vs DAPA running timetest-time adaptation · 3DPWms per image: 431.0 -> 74.1Improved
apply CycleAdapt to PyMAF and Pose2Pose HMRNets instead of SPINCycleAdapt · 3DPWMPJPE: SPIN 87.7, PyMAF 98.5, Pose2Pose 108.1Mixed

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy