AI Paper Atlas

Research map / Image generation / Image restoration

VT-Intrinsic: Physics-Based Decomposition of Reflectance and Shading using a Single Visible-Thermal Image Pair

Zeqing Yuan, Mani Ramanagopal, Aswin C. Sankaranarayanan, Srinivasa G. Narasimhan

CVPR 2026 · Image generation › Image restoration · approach: Image harmonization and color transformation · 1 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 single thermal image ordinalities instead of learned priorsIntrinsic image decomposition · Color chart white LED (albedo)si-MSE: 1.25 -> 0.37Improved
use single thermal image ordinalities instead of learned priorsIntrinsic image decomposition · Color chart sunlight (albedo)si-MSE: 1.98 -> 1.19Improved
use thermal ordinalities instead of learning-based methodsIntrinsic image decomposition · JoLHT-Video Painted Mask (albedo)si-MSE: 2.8 -> 2.7Mixed
replace transient thermal video (JoLHT-Video) with single thermal imageVT-Intrinsic · JoLHT-Video color chart (albedo)si-MSE: 8.4 -> 11Hurt
replace transient thermal video (JoLHT-Video) with single thermal imageVT-Intrinsic · JoLHT-Video color chart (shading)si-MSE: 0.05 -> 0.10Hurt
extend ordinality to infrared-containing illuminationVT-Intrinsic ordinality · USGS spectral reflectance pairsagreementImproved

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