AI Paper Atlas

Research map / 3D vision / Face and shape

An Adaptive Screen-Space Meshing Approach for Normal Integration

Moritz Heep, Eduard Zell

ECCV 2024 · 3D vision › Face and shape · approach: Neural implicit surface reconstruction · 5 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 curvature-adaptive meshing instead of uniform meshing with matched vertex count (ablation)screen-space meshing · DiLiGenT-MV (fit to GT depth)RMSE: Bear ortho High 3.74 -> 3.37Improved
integrate on adaptive triangle mesh instead of pixel gridnormal integration · DiLiGenT-MVRMSE: Cow ortho 2.45 -> 2.96 (High)Hurt
meshing-first integration instead of pixel-based integration at high resolutionnormal integration · 8192^2 normal mapruntime: around 3 hours -> 5 minutesImproved
increase mesh resolution from Low to High setting (ablation)adaptive mesh integration · DiLiGenT-MV Bear (ortho)RMSE: 3.95 -> 3.37Improved
increase approximation error parameter epsilonscreen-space meshing · DiLiGenT-MV fitting to GT depthachieved approximation errorHurt
adaptive mesh then integration versus pixel integration followed by remeshingnormal integration pipeline · DiLiGenT-MV Bear (ortho, High)RMSE: 2.98 -> 3.37Hurt

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