AI Paper Atlas

Research map / 3D vision / Human pose estimation

Delving Deep Into Hybrid Annotations for 3D Human Recovery in the Wild

Yu Rong, Ziwei Liu, Cheng Li, Kaidi Cao, Chen Change Loy

ICCV 2019 · 3D vision › Human pose estimation · approach: Human mesh recovery from images · 59 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 dense correspondence supervision to full 3D (ablation)image-only model · UP-3DPVE (mm): 127.4 -> 123.7Improved
replace paired in-the-wild 3D with dense correspondence (both with sparse 2D) (ablation)image-only model · UP-3DPVE (mm): 203.2 -> 137.7Improved
add dense correspondence to 20% 3D (ablation)image-only model · UP-3DPVE (mm): 127.5 vs 127.4 (full 3D)No clear effect
add IUV map as auxiliary input (sparse 2D supervision only) (ablation)image-only model · UP-3DPVE (mm): 203.2 -> 197.3Improved
add body segmentation as auxiliary input (sparse 2D supervision only) (ablation)image-only model · UP-3DPVE (mm): 203.2 -> 201.2Improved
add IUV map as input with 3D & dense & sparse 2D supervision (ablation)image-only model · UP-3DPVE (mm): 123.7 -> 122.4Improved
refine IUV maps by removing noisy predictions (ablation)dense keypoint supervision · UP-3DPVE (mm): 20.1% performance drop without refinementImproved
keep paired in-the-wild 3D annotations (20% vs 0%) (ablation)image-only model · UP-3DPVE (mm): 203.2 -> 136.0Improved
add constrained 3D (Human3.6M) with no in-the-wild 3D (ablation)sparse 2D only model · UP-3DPVE (mm): 230.9 -> 203.2Improved
add constrained 3D with dense & sparse 2D supervision (ablation)image-only model · UP-3DPVE (mm): 173.4 -> 137.3Improved
add constrained 3D when full in-the-wild 3D exists (ablation)image-only model · UP-3DPVE (mm): 128.9 -> 127.4No clear effect
train with dense correspondence instead of HMR on COCOOurs-DC vs HMR · COCO-DensePoseDKD (mm): 102.7 -> 51.8Improved

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