AI Paper Atlas

Research map / 3D vision / Depth and stereo

Discontinuity-aware Normal Integration for Generic Central Camera Models

Francesco Milano, Manuel López-Antequera, Naina Dhingra, Roland Siegwart, Robert Thiel

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
add iterative discontinuity (alpha) computation (ablation)Ours · DiLiGenT harvestMADE (mm): 4.83 -> 0.73Improved
add iterative discontinuity (alpha) computation (ablation)Ours · DiLiGenT gobletMADE (mm): 6.56 -> 4.72Improved
add iterative discontinuity (alpha) computation (ablation)Ours · DiLiGenT readingMADE (mm): 0.12 -> 0.17Hurt
add iterative discontinuity (alpha) computation (ablation)Ours · DiLiGenT bearMADE (mm): 0.07 -> 0.03Improved
run more iterations (150 to 1200)Ours · DiLiGenT harvestMADE (mm): 1.35 -> 0.73Improved
use ray-direction local planarity formulation instead of BiNIOurs · DiLiGenT harvestMADE (mm): 1.84 -> 0.73Improved
use ray-direction local planarity formulation instead of BiNIOurs · DiLiGenT bear residualabsolute residual on ground-truth log-depth: 3.72 -> 0.82Improved
provide ground-truth discontinuity valuesOurs · DiLiGenT harvestMADE (mm): 0.73 -> 0.34Improved
include the n^T tau term in the cost function weighting (ablation)Ours w/o alpha · DiLiGenT pot1MADE (mm): 14.40 -> 0.49Improved
include the n^T tau term in the cost function weighting (ablation)Ours w/o alpha · DiLiGenT bearMADE (mm): 0.48 -> 0.07Improved
lower the f multiplier in the bilateral weights from 3000 to 1000 (ablation)Ours w/o alpha · DiLiGenT buddhaMADE (mm): 0.27 -> 1.41Hurt
lower the f multiplier in the bilateral weights from 3000 to 1000 (ablation)Ours w/o alpha · DiLiGenT harvestMADE (mm): 3.89 -> 2.51Mixed

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