AI Paper Atlas

Research map / 3D vision / Human pose estimation

A Real World Dataset for Multi-View 3D Reconstruction

Rakesh Shrestha, Siqi Hu, Minghao Gou, Ziyuan Liu, Ping Tan

ECCV 2022 · 3D vision › Human pose estimation · approach: Category-level object pose estimation · 11 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
replace predicted depth with ground-truth depthMeshMVS · real-world multi-view datasetF1@0.3: 58.79 -> 90.85Improved
train on all categories jointly instead of single-category (ablation)MV M-RCNN · real-world dataset meanF1@0.3: 58.15 -> 64.77Improved
train on all categories jointly instead of single-category (ablation)MV M-RCNN · real-world dataset meanChamfer: 10.57 -> 2.24Improved
train on all categories jointly instead of single-category (ablation)MV M-RCNN · Toy FruitF1@0.3: 20.54 -> 59.84Improved
train on all categories jointly instead of single-category (ablation)MV M-RCNN · Toy CarF1@0.3: 65.18 -> 63.90Hurt
use Pixel2Mesh++ instead of MeshMVS (predicted depth)real-world dataset · all categoriesF1@0.3: 58.79 -> 73.30Improved
use IDR instead of DVR per-scene optimizationreal-world dataset · 30 test scenesF1@0.3: 79.56 -> 89.54Improved
use IDR instead of COLMAPreal-world dataset · 30 test scenesF1@0.3: 39.81 -> 89.54Improved

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