AI Paper Atlas

Research map / 3D vision / Depth and stereo

Deep Material Recognition in Light-Fields via Disentanglement of Spatial and Angular Information

Bichuan Guo, Jiangtao Wen, Yuxing Han

ECCV 2020 · 3D vision › Depth and stereo · approach: Neural light field and illumination imaging · 8 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 sparse directional sub-views (model-4) (ablation)ang-filter · LFMR testaccuracy (%): 77.83 -> 78.91Improved
add angular rotational invariance (weight sharing and directional pooling) (ablation)model-4 · LFMR testaccuracy (%): 78.91 -> 80.74Improved
add angular registration (ablation)model-4 · LFMR testaccuracy (%): 78.91 -> 79.36Improved
add representative selection (ablation)model-4 · LFMR testaccuracy (%): 78.91 -> 79.85Improved
add both registration and selection (ablation)model-4 · LFMR testaccuracy (%): 78.91 -> 80.38Improved
add both registration and selection (ablation)model-S · LFMR testaccuracy (%): 80.74 -> 81.75Improved
select region randomly instead of by depth criterion (ablation)model-S · LFMR testaccuracy (%): 81.75 -> 81.41Hurt
warp pixels with estimated depth instead of selecting a region (ablation)model-S · LFMR testaccuracy (%): 81.45 -> 80.35Hurt
use 1x1 angular kernel instead of 3x3 (ablation)angular-S · LFMR validationaccuracy (%): 81.16 -> 81.92Improved
increase angular filters from 16 to 32 to 64 (ablation)angular-S · LFMR validationaccuracy (%): 81.35 -> 81.92 -> 80.93Mixed
use representative region grid N=3 instead of whole patch (ablation)angular-S with spatial · LFMR validationaccuracy (%): 81.45 -> 81.92Improved
crop angular component into smaller regions (ablation)angular features only · LFMR validationaccuracy (%): 66.34 -> 51.93Hurt

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