Research map / Probabilistic and scientific modeling / Variational and generative sampling
Invertible Rescaling Network and Its Extensions
Mingqing Xiao, Shuxin Zheng, Chang Liu, Zhouchen Lin, Tie‐Yan Liu
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 changed | Where | Measured | Effect |
|---|---|---|---|
| use L2 LR guidance loss instead of L1 (ablation) | IRN · Set5 (4x rescaling) | PSNR (dB): 34.75 -> 36.19 | Improved |
| use L1 HR reconstruction loss instead of L2 (ablation) | IRN · Set5 (4x rescaling) | PSNR (dB): 35.93 -> 36.19 | Improved |
| add partial distribution matching loss (ablation) | IRN · Set5 (4x rescaling) | PSNR (dB): 36.12 -> 36.19 | Improved |
| add partial distribution matching loss (ablation) | IRN · Urban100 (4x rescaling) | PSNR (dB): 30.91 -> 31.41 | Improved |
| set guidance weight lambda2 to 16 instead of 160 (ablation) | IRN · Set5 (4x rescaling) | PSNR (dB): 35.94 -> 36.19 | Improved |
| set guidance weight lambda2 to 16 instead of 1.6 (ablation) | IRN · Set5 (4x rescaling) | PSNR (dB): 35.72 -> 36.19 | Improved |
| raise guidance weight lambda2 from 16 to 160 (ablation) | IRN · Set5 (4x, downscaled LR vs bicubic LR) | PSNR (dB): 44.60 -> 50.14 | Improved |
| replace IRN with IRN+ (full distribution matching and perceptual loss) | IRN · Set5 (4x rescaling) | FID: 33.88 -> 11.15 | Improved |
| replace IRN with IRN+ | IRN · Set5 (4x rescaling) | LPIPS: 0.078 -> 0.031 | Improved |
| replace IRN with IRN+ | IRN · Set5 (4x rescaling) | PSNR (dB): 36.19 -> 33.59 | Hurt |
| use IRN instead of CAR and EDSR | CAR & EDSR · Set5 (4x rescaling) | PSNR (dB): 33.88 -> 36.19 | Improved |
| use IRN instead of CAR and EDSR | CAR & EDSR · Set5 (2x rescaling) | PSNR (dB): 38.94 -> 43.99 | Improved |
Closest papers by meaning
- Invertible Image Rescaling (ECCV 2020 · similarity 0.95)
- Self-Asymmetric Invertible Network for Compression-Aware Image Rescaling (AAAI 2023 · similarity 0.91)
- Plug-and-Play Tri-Branch Invertible Block for Image Rescaling (AAAI 2025 · similarity 0.89)
- Deep Generative Model based Rate-Distortion for Image Downscaling Assessment (CVPR 2024 · similarity 0.85)
- CoDe: An Explicit Content Decoupling Framework for Image Restoration (CVPR 2024 · similarity 0.84)
- Block-Based Multi-Scale Image Rescaling (AAAI 2025 · similarity 0.84)
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.
