AI Paper Atlas

Research map / 3D vision / Face and shape

FoV-Net: Rotation-Invariant CAD B-rep Learning via Field-of-View Ray Casting

Matteo Ballegeer, Dries F. Benoit

CVPR 2026 · 3D vision › Face and shape · approach: Single-view 3D reconstruction · 3 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 rotation-invariant FoV-Net instead of UV-Net under random rotationUV-Net · SolidLetters (rotated test)accuracy (%): 8.94 ± 0.46 -> 96.35 ± 0.16Improved
use FoV-Net instead of AAGNet under random rotationAAGNet · MFCAD++ (rotated test)per-face accuracy (%): 80.13 ± 1.71 -> 99.33 ± 0.07Improved
use FoV-Net instead of UV-Net under random rotationUV-Net · Fusion360 (rotated test)per-face accuracy (%): 69.13 ± 2.18 -> 91.72 ± 0.17Improved
add rotation augmentation to UV-NetUV-Net · SolidLetters (rotated test)accuracy (%): 8.94 ± 0.46 -> 94.97 ± 0.10; original 97.10 ± 0.15 -> 95.34 ± 0.12Mixed
add rotation augmentation to AAGNetAAGNet · Fusion360per-face accuracy (%): rotated 79.85 ± 0.92 -> 86.70 ± 0.28; original 90.60 ± 0.25 -> 87.91 ± 0.56Mixed
add global UV grids to FoV-Net (replace LRF UV) (ablation)FoV-Net · SolidLettersaccuracy (%): original 96.35 ± 0.16 -> 97.42 ± 0.17; rotated 96.35 ± 0.16 -> 23.53 ± 0.61Mixed
add global UV grids instead of LRF UV to FoV-Net (ablation)FoV-Net · MFCAD++ (rotated test)per-face accuracy (%): 99.33 ± 0.07 -> 70.45 ± 3.20Hurt
combine LRF UV with FoV grids (ablation)FoV-Net · SolidLettersaccuracy (%): 94.39 -> 96.35Improved
combine OV and IV grids (ablation)FoV-Net · SolidLettersaccuracy (%): 92.92 -> 95.79Improved
add FoV and LRF descriptors over per-face features alone (ablation)FoV-Net · SolidLettersaccuracy (%): 70.68 -> 96.35Improved
add descriptors over topology alone (ablation)FoV-Net · SolidLettersaccuracy (%): 37.72 -> 96.35Improved
increase FoV grid from 1x1 single ray to multi-directional rays (ablation)FoV-Net (FoV only) · SolidLettersaccuracy (%): 75.04 -> 95.79Improved

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