AI Paper Atlas

Research map / Image generation / Image restoration

Self-Asymmetric Invertible Network for Compression-Aware Image Rescaling

Jinhai Yang, Mengxi Guo, Shijie Zhao, Junlin Li, Li Zhang

AAAI 2023 · Image generation › Image restoration · approach: Learned image compression · 10 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 compression-aware asymmetric invertible rescalingImage rescaling · DIV2K validation, JPEG QF=30 and 90, ×2 and ×4PSNR: 31.47 vs 29.38; 35.96 vs 33.44; 27.90 vs 26.27; 30.31 vs 28.98Improved
Use compression-aware asymmetric invertible rescalingImage rescaling · DIV2K, WebP QF=30 and 90, ×2PSNR: 33.15 vs 29.86; 35.83 vs 34.34Improved
Jointly optimize downscaling and upscaling using the asymmetric framework rather than compression-aware fine-tuning (ablation)IRN & EDSR · DIV2K, JPEG QF=75, ×2PSNR: 32.92 -> 34.41Improved
Replace the Dual-IRN framework with SAIN (ablation)Compression-aware asymmetric image rescaling · DIV2K, JPEG QF=75, ×2PSNR: 34.69 -> 35.10Improved
Add a learnable Gaussian mixture instead of using N(0, 1) (ablation)SAIN · DIV2K, JPEG QF=75, ×2PSNR: 35.01 -> 35.10Improved
Add a learnable Gaussian mixture instead of using N(0, 1) (ablation)SAIN · Set5, JPEG QF=75, ×2PSNR: 35.98 -> 36.04Improved
Add the L_rel loss (ablation)SAIN · DIV2K, JPEG QF=75, ×2PSNR: 35.02 -> 35.10Improved
Add the L_fit' loss to guide compression simulation (ablation)SAIN · DIV2K, JPEG QF=75, ×2PSNR: 34.95 -> 35.10Improved
Add the L_reg loss (ablation)SAIN · DIV2K, JPEG QF=75, ×2PSNR: 34.96 -> 35.10Improved
Use five E-InvBlocks in the downscaling module (ablation)SAIN · DIV2K, JPEG QF=75, ×2PSNRImproved
Use five Gaussian mixture components (ablation)SAIN · DIV2K, JPEG QF=75, ×2PSNRImproved
Train at QF=75 rather than QF=25 (ablation)SAIN · DIV2K, JPEG QF=25 evaluation, ×2PSNR: 29.14 -> 30.89Hurt

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