AI Paper Atlas

Research map / 3D vision / Human pose estimation

Learning Single-View 3D Reconstruction with Limited Pose Supervision

Guandao Yang, Yin Cui, Serge Belongie, Bharath Hariharan

ECCV 2018 · 3D vision › Human pose estimation · approach: Monocular 2D-to-3D pose lifting · 63 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 unlabeled images to pose-annotated training (ablation)single-category chair model · ShapeNet chairs (1% pose annotations)IoU: 0.2913 -> 0.3175Improved
add unlabeled images to pose-annotated training (ablation)single-category chair model · ShapeNet chairs (1% pose annotations)AP: 0.3800 -> 0.4162Improved
add pose-annotated images to unlabeled-only training (ablation)single-category chair model · ShapeNet chairs (1% pose annotations)IoU: 0.2065 -> 0.3175Improved
pool multiple categories (category-agnostic) instead of chairs only (ablation)pose+unlabeled chair model · ShapeNet chairs (1% pose annotations)IoU: 0.3175 -> 0.3104Mixed
fine-tune the category-agnostic model on the target category (ablation)category-agnostic model · ShapeNet chairs (1% pose annotations)IoU: 0.3104 -> 0.3250Improved
use category-agnostic pooling at 50% pose supervision instead of category-specific (ablation)Ours · ShapeNet 7 categories meanIoU: 0.54 -> 0.55No clear effect
increase pose annotations from 50% to 100% in category-agnostic model (ablation)Ours · ShapeNet 7 categories meanAP: 0.70 -> 0.71No clear effect
increase pose annotations from 1% to 10% in category-agnostic model (ablation)Ours · ShapeNet 7 categories meanIoU: 0.42 -> 0.51Improved
add unlabeled images when pose supervision is 50% or 100% (ablation)Ours · ShapeNet chairsIoUNo clear effect
add unlabeled images when pose supervision is 10% or less (ablation)Ours · ShapeNet chairsIoUImproved
fine-tune pre-trained category-agnostic model instead of training from scratch on novel category (ablation)Ours · novel categories benches, vessels, cabinets (1% pose)IoU and APImproved
fine-tune instead of applying pre-trained model out-of-category (ablation)Ours · novel categories benches, vessels, cabinets (1% pose)IoU and APImproved

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