AI Paper Atlas

Research map / 3D vision / Depth and stereo

OpenSubstance: A High-quality Measured Dataset of Multi-View and -Lighting Images and Shapes

Fan Pei, Jinchen Bai, Xiang Feng, Zoubin Bi, Kun Zhou, Hongzhi Wu

ICCV 2025 · 3D vision › Depth and stereo · approach: Photometric stereo · 1 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 uncalibrated photometric stereo instead of calibrated under near-field lightingsingle-view photometric stereo · OpenSubstance single-view photometric stereoMAE (deg): 22.33 -> 12.99Improved
use SuperNormal instead of RNb-NeuS for multi-view shape reconstructionmulti-view photometric stereo · OpenSubstance multi-view photometric stereo (6 objects)Chamfer distance (mm): 0.698 -> 0.475Improved
use GS3 instead of NRHints for OLAT relightingOLAT relighting · OpenSubstance OLAT relighting (5 objects)LPIPS (avg): 0.120 -> 0.088Improved
use GaussianShader instead of TensoIR for non-OLAT relightingnon-OLAT relighting · OpenSubstance non-OLAT relighting (10 objects)PSNR (avg): 27.00 -> 30.94Improved
use GS3 instead of NRHints for OLAT relightingOLAT relighting on APPLE object · OpenSubstance OLAT relighting, APPLEPSNR: 41.08 -> 37.37Hurt

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