AI Paper Atlas

Research map / 3D vision / Depth and stereo

NormalFusion: Real-Time Acquisition of Surface Normals for High-Resolution RGB-D Scanning

CVPR 2021 · 3D vision › Depth and stereo · approach: Non-line-of-sight imaging · 6 citations (OpenAlex)

Check your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (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 geometry-aware texture warping to align normal texture with baseline geometry (ablation)NormalFusion · scanned geometry and normal texturetexture-to-geometry alignmentHelped
use 8×8 texture tiles and 10 mm voxels instead of 4×4 tiles and 4 mm voxels (ablation)NormalFusion · Liontotal time per frame: 58.5 ms -> 51.3 msHelped
use 8×8 texture tiles and 10 mm voxels instead of 4×4 tiles and 4 mm voxels (ablation)NormalFusion · Fountaintotal time per frame: 75.1 ms -> 56.9 msHelped
use geometry-aware texture warping rather than blending normal texture without warping (ablation)NormalFusion · scanned geometrygeometric detail alignmentHelped
use 4 mm voxels rather than 10 mm voxels (ablation)NormalFusion · Lion and Fountainnormal-map detailMixed
combine high-resolution normals with baseline geometry using NormalFusionsynthetic RGB-D scanning · Synthetic RGB-D datasetaverage distance error: 3.32 mm -> 3.11 mmHelped

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