AI Paper Atlas

Research map / 3D vision / Depth and stereo

MVPSNet: Fast Generalizable Multi-view Photometric Stereo

Dongxu Zhao, Daniel Lichy, Pierre-Nicolas Perrin, Jan-Michael Frahm, Soumyadip Sengupta

ICCV 2023 · 3D vision › Depth and stereo · approach: Photometric stereo · 25 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
retrain CasMVSNet on synthetic sMVPS data instead of DTU (ablation)CasMVSNet · DiLiGenT-MV (after ICP)L1 Chamfer distance: 1.83 -> 1.24Improved
add multiple lights per view (3 instead of 1) through LAFM (ablation)MVPSNet · DiLiGenT-MV (after ICP)L1 Chamfer distance: 1.09 -> 0.82Improved
use LAFM aggregation versus single-light MVS features (ablation)MVPSNet · DiLiGenT-MV (after ICP)L1 Chamfer distance: 1.24 -> 1.09Improved
add surface normal loss (ablation)MVPSNet · DiLiGenT-MV (after ICP)L1 Chamfer distance: 0.79 -> 0.82No clear effect
add surface normal loss (ablation)MVPSNet · DiLiGenT-MV (after ICP)F-score: 0.985 -> 0.985No clear effect
add multi-light MVPS network versus light-agnostic MVSMVPSNet vs TransMVSNet-RT · DiLiGenT-MV (after ICP)L1 Chamfer distance: 1.09 -> 0.82Improved
use transformer MVS (TransMVSNet) instead of CasMVSNet when retrained on sMVPSMVS baselines · DiLiGenT-MV (after ICP)L1 Chamfer distance: 1.24 -> 1.09Improved
skip ICP registrationMVPSNet · DiLiGenT-MVL1 Chamfer distance: 0.82 -> 0.91Hurt
use PS-NeRF per-scene optimization versus MVPSNetPS-NeRF · DiLiGenT-MV (after ICP)L1 Chamfer distance: 0.81 -> 0.82No clear effect

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 0 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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