AI Paper Atlas

Research map / Image generation / Super-resolution

Texture Hallucination for Large-Factor Painting Super-Resolution

Yulun Zhang, Zhifei Zhang, Stephen DiVerdi, Zhaowen Wang, Jose Echevarria, Yun Fu

ECCV 2020 · Image generation › Super-resolution · approach: Efficient lightweight super-resolution · 30 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 wavelet texture, degradation, perceptual and adversarial losses to reconstruction-only training (ablation)Ours · PaintHD 8xPI: 5.253 -> 3.670Improved
add wavelet texture, degradation, perceptual and adversarial losses to reconstruction-only training (ablation)Ours · PaintHD 16xPI: 5.815 -> 4.131Improved
add wavelet texture, degradation, perceptual and adversarial losses to reconstruction-only training (ablation)Ours · CUFED5 8xPI: 4.520 -> 2.339Improved
add wavelet texture, degradation, perceptual and adversarial losses to reconstruction-only training (ablation)Ours · CUFED5 16xPI: 5.298 -> 2.499Improved
add wavelet texture, degradation, perceptual and adversarial losses to reconstruction-only training (ablation)Ours · PaintHD 8xPSNR (dB): 24.02 -> 22.49Hurt
add wavelet texture, degradation, perceptual and adversarial losses to reconstruction-only training (ablation)Ours · CUFED5 8xPSNR (dB): 22.40 -> 20.36Hurt
use simplified pipeline instead of SRNTT with reconstruction loss only (ablation)Ours-Lrec · PaintHD 8xPI: 7.992 -> 5.253Improved
use simplified pipeline instead of SRNTT with reconstruction loss only (ablation)Ours-Lrec · PaintHD 16xPI: 8.464 -> 5.815Improved
use simplified pipeline instead of SRNTT with reconstruction loss only (ablation)Ours-Lrec · PaintHD 8xPSNR (dB): 23.96 -> 24.02Improved
apply texture loss on wavelet high-frequency band instead of raw features (ablation)Ours · PaintHD 8xvisual quality (qualitative)Improved
add degradation loss to reconstruction loss (ablation)Ours · PaintHD 8xvisual quality (qualitative)Improved
use reference-based SR with texture transfer instead of SISR RCANOurs · PaintHD 8xPI: 7.448 -> 3.670Improved

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