AI Paper Atlas

Research map / 3D vision / Human pose estimation

Cloth2Body: Generating 3D Human Body Mesh from 2D Clothing

Lu Dai, Liqian Ma, Shenhan Qian, Hao Liu, Ziwei Liu, Hui Xiong

ICCV 2023 · 3D vision › Human pose estimation · approach: Human mesh recovery from images · 3 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
use kinematics-aware pose estimation with physics-informed shape instead of HybrIK/HMR/PARE regressionCloth2Body · DeepFashion2-SMPL2D-KPE-C: 27.46 -> 23.53 vs HybrIKImproved
estimate shape from landmarks and joints as proxy instead of direct beta regressionCloth2Body · DeepFashion2-SMPL shapeChest error (mm): 20.0 -> 18.7 vs HMRImproved
add adaptive depth to HybrIK (ablation)HybrIK · DeepFashion2-SMPL2D-KPE-C: 31.58 -> 27.46Improved
add adaptive depth module to Cloth2Body (ablation)Cloth2Body · DeepFashion2-SMPL2D-KPE-C: 23.53 -> 25.72 listed as Ours vs Ours-AdaImproved
add predicted joints image input to shape estimation (ablation)Landmark2Shape · DeepFashion2-SMPLMPJPE-C: 63.67 -> 62.76Improved
add cloth landmark image input to shape estimation (ablation)Landmark2Shape · DeepFashion2-SMPLMPJPE-C: 62.76 -> 62.35Improved
add cloth landmark image input to shape estimation (ablation)Landmark2Shape · DeepFashion2-SMPL2D-KPE-C: 23.56 -> 23.53No clear effect

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