AI Paper Atlas

Research map / Image generation / Image restoration

MatE: Material Extraction from Single-Image via Geometric Prior

Zeyu Zhang, Wei Zhai, Jian Yang, Yang Cao

CVPR 2026 · Image generation › Image restoration · approach: Image harmonization and color transformation · 0 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 rotation alignment and perspective rectification (ablation)MatE · Real-world material extraction (attribute-averaged)LPIPS: 0.464 -> 0.418Improved
add rotation alignment (with rectification) (ablation)MatE · Real-world material extraction (attribute-averaged)LPIPS: 0.428 -> 0.418Improved
add perspective rectification (with rotation alignment) (ablation)MatE · Real-world material extraction (attribute-averaged)LPIPS: 0.435 -> 0.418Improved
add rotation alignment (with rectification) (ablation)MatE · Real-world material extraction (attribute-averaged)SSIM: 0.396 -> 0.377Hurt
add perspective rectification (with rotation alignment) (ablation)MatE · Real-world material extraction (attribute-averaged)SSIM: 0.391 -> 0.377Hurt
add rotation alignment and perspective rectification with the new dataset (ablation)MaterialPicker* · Real-world material extraction (attribute-averaged)LPIPS: 0.526 -> 0.425Improved
use proposed conditioning instead of CLIP feature injection (ablation)MatE · Real-world material extraction (attribute-averaged)LPIPS: 0.674 -> 0.418Improved
use proposed conditioning instead of latent concatenation (ablation)MatE · Real-world material extraction (attribute-averaged)LPIPS: 0.529 -> 0.418Improved
use proposed conditioning instead of ControlNet-style addition (ablation)MatE · Real-world material extraction (attribute-averaged)LPIPS: 0.447 -> 0.418Improved
use proposed conditioning instead of ControlNet-style addition (ablation)MatE · Real-world material extraction (attribute-averaged)CLIP score: 0.723 -> 0.723No clear effect
use MatE instead of MaterialPicker*MatE · Real-world AlbedoLPIPS: 0.554 -> 0.445Improved
use MatE instead of MaterialPicker*MatE · Real-world NormalSSIM: 0.317 -> 0.248Hurt

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