Research map / Image generation / Image restoration
End-to-end Optimized Image Compression
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 the optimized nonlinear transform-coding method instead of JPEG or JPEG 2000 | Image compression · Kodak and other held-out test images | MS-SSIM | Helped |
| Use the optimized nonlinear transform-coding method instead of JPEG or JPEG 2000 | Image compression · Kodak and other held-out test images | PSNR | Mixed |
| Use GDN/IGDN nonlinearities rather than pointwise nonlinearities such as ReLU (ablation) | Nonlinear transform-coding model · Image compression; rate--distortion performance | model parameters needed for comparable performance | Helped |
| Replace GDN/IGDN with other tested activation functions (ablation) | Nonlinear transform-coding model · Image compression; qualitative visual quality | visual quality | No clear effect |
| Use adaptive CABAC entropy coding instead of the non-adaptive probability model (ablation) | Proposed compression method · Kodak test set | bit rate | Helped |
Closest papers by meaning
- Variational image compression with a scale hyperprior (ICLR 2018 · similarity 0.90)
- How To Exploit the Transferability of Learned Image Compression to Conventional Codecs (CVPR 2021 · similarity 0.90)
- Improved Lossy Image Compression With Priming and Spatially Adaptive Bit Rates for Recurrent Networks (CVPR 2018 · similarity 0.90)
- Controllable Distortion-Perception Tradeoff Through Latent Diffusion for Neural Image Compression (AAAI 2025 · similarity 0.89)
- Robustly overfitting latents for flexible neural image compression (NeurIPS 2024 · similarity 0.89)
- Good, Cheap, and Fast: Overfitted Image Compression with Wasserstein Distortion (CVPR 2025 · similarity 0.88)
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.