AI Paper Atlas

Research map / Detection and segmentation / Open-set and few-shot detection

A 4D Light-Field Dataset and CNN Architectures for Material Recognition

Ting-Chun Wang, Jun-Yan Zhu, Ebi Hiroaki, Manmohan Chandraker, Alexei A. Efros, Ravi Ramamoorthi

ECCV 2016 · Detection and segmentation › Open-set and few-shot detection · approach: Object-level representation learning · 179 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 angular filter light-field input instead of single 2D viewMINC VGG-16 · Light-field material dataset (128x128 patches)accuracy (%): 70.2 -> 77.0Improved
add view-pooling of per-view features instead of single 2D viewMINC VGG-16 · Light-field material dataset (128x128 patches)accuracy (%): 70.2 -> 70.0Hurt
average predictions across views instead of one viewMINC VGG-16 · Light-field material dataset (128x128 patches)accuracy (%): 70.2 -> 70.5No clear effect
stack all views across RGB channelsMINC VGG-16 · Light-field material dataset (128x128 patches)accuracy (%): 70.2 -> 72.8Improved
use EPI inputMINC VGG-16 · Light-field material dataset (128x128 patches)accuracy (%): 70.2 -> 72.3Improved
apply angular filter at input rather than after layer 1 (ablation)Angular filter · Light-field material dataset (128x128 patches)accuracy (%): 76.6 -> 77.8Improved
apply angular filter at input rather than after layer 2 (ablation)Angular filter · Light-field material dataset (128x128 patches)accuracy (%): 73.7 -> 77.8Improved
use single-layer angular filter instead of stacked 3x3 filters (ablation)Angular filter · Light-field material dataset (128x128 patches)accuracy (%): 74.8 -> 77.8Improved
use 64 angular output channels instead of 3 (ablation)Angular filter · Light-field material dataset (128x128 patches)accuracy (%): 71.6 -> 77.8Improved
use 64 angular output channels instead of 147 (no compression) (ablation)Angular filter · Light-field material dataset (128x128 patches)accuracy (%): 72.8 -> 77.8Improved
use light-field input at equal pixel count (downsampled) versus 2DLight-field CNN · Light-field patches, downsampled to equal pixel countaccuracy (%): 70.7 -> 75.2Improved
use light-field input with fine-tuning on BTF data versus 2DLight-field CNN · BTF database (fine-tuned)accuracy (%): 67.7 -> 73.0Improved

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