AI Paper Atlas

Research map / 3D vision / Depth and stereo

A Differential Volumetric Approach to Multi-View Photometric Stereo

Fotios Logothetis, Roberto Mecca, Roberto Cipolla

ICCV 2019 · 3D vision › Depth and stereo · approach: Photometric stereo · 54 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 proposed volumetric SDF method instead of prior MVPS method from a visual hull initialisationmulti-view photometric stereo · Synthetic ArmadilloRMS Hausdorff distance (mm): 0.370 -> 0.293Improved
use proposed method instead of prior method with 250-triangle initial mesh and 10% noisemulti-view photometric stereo · Synthetic ArmadilloRMS Hausdorff distance (mm): 0.393 -> 0.321Improved
use proposed method instead of prior method with 30K-triangle initial mesh and no noisemulti-view photometric stereo · Synthetic ArmadilloRMS Hausdorff distance (mm): 0.025 -> 0.023Improved
reduce initial mesh from 30K to 250 triangles (no noise), proposed methodproposed method · Synthetic ArmadilloRMS Hausdorff distance (mm): 0.023 -> 0.203Hurt
add 10% vertex noise to initial mesh of 1500 triangles, proposed methodproposed method · Synthetic ArmadilloRMS Hausdorff distance (mm): 0.090 -> 0.131Hurt
add 10% vertex noise to initial mesh of 1500 triangles, prior methodprior MVPS method · Synthetic ArmadilloRMS Hausdorff distance (mm): 0.105 -> 0.153Hurt

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