AI Paper Atlas

Research map / 3D vision / Depth and stereo

Transfer Learning for Color Constancy via Statistic Perspective

Yuxiang Tang, Xuejing Kang, Chunxiao Li, Zhaowen Lin, Anlong Ming

AAAI 2022 · 3D vision › Depth and stereo · approach: Snapshot hyperspectral imaging · 21 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 TLCC instead of IGTNColor constancy model · Color Checker (CCD)mean angular error: 1.58 -> 1.51Improved
use TLCC instead of MDLCCColor constancy model · NUS 8mean angular error: 1.78 -> 1.61Improved
apply SE-Scheme without sRGB data (ablation)FC4 · CCDmean angular error: 1.81 -> 1.84Hurt
add sRGB data using SE-Scheme (ablation)FC4 · CCDmean angular error: 1.81 -> 1.73Improved
add Instance Normalization (ablation)FC4 · CCDmean angular error: 1.81 -> 1.83Hurt
add CGIN (ablation)TLCC · CCDmean angular error: 1.65 -> 1.51Improved
add CSTM (ablation)TLCC · CCDmean angular error: 1.58 -> 1.51Improved
add SE-Scheme (ablation)TLCC · CCDmean angular error: 1.81 -> 1.51Improved
add sRGB images to mixed RAW training, increasing from 3,000 to 12,000 (ablation)TLCC · CCDmean angular error: 1.58 -> 1.51Improved

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