AI Paper Atlas

Research map / Image generation / Super-resolution

Hierarchical Image Tokenization for Multi-Scale Image Super Resolution

Isma Hadji, Enrique Sanchez, Adrian Bulat, Brais Martinez, Georgios Tzimiropoulos

ICML 2026 · Image generation › Super-resolution · approach: Perceptual and real-world SR · 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 DPO regularization (ablation)H-VAR · RealSR (128 output scale)PSNR: 20.56 -> 22.09Improved
add DPO regularization (ablation)H-VAR · RealSR (128 output scale)LPIPS: 0.347 -> 0.1996Improved
add DPO regularization (ablation)H-VAR · DRealSR (128 output scale)PSNR: 23.03 -> 25.26Improved
add DPO regularization (ablation)H-VAR · DRealSR (128 output scale)LPIPS: 0.311 -> 0.1871Improved
add DPO regularization (ablation)H-VAR · RealSR (256 output scale)PSNR: 23.09 -> 24.41Improved
add DPO regularization (ablation)H-VAR · RealSR (512 output scale)PSNR: 25.72 -> 25.55No clear effect
add DPO regularization (ablation)H-VAR · DRealSR (512 output scale)PSNR: 28.61 -> 28.73No clear effect
add hierarchical image tokenization (H-VAR vs VARSR-d16 same backbone and data) (ablation)VARSR-d16 · DIV2K-ValLPIPS: 0.495 -> 0.317Improved
add hierarchical image tokenization (H-VAR vs VARSR-d16 same backbone and data) (ablation)VARSR-d16 · RealSRFID: 231.1 -> 130.4Improved
add hierarchical image tokenization (H-VAR vs VARSR-d16 same backbone and data) (ablation)VARSR-d16 · DRealSRPSNR: 27.30 -> 28.73Improved
use 310M H-VAR instead of 1B VARSR trained on large proprietary dataVARSR · RealSRLPIPS: 0.350 -> 0.256Improved
use 310M H-VAR instead of 1B VARSRVARSR · DIV2K-ValMUSIQ: 71.27 -> 69.40Hurt

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