Research map / Image generation / Image restoration
Content-Oriented Learned Image Compression
Meng Li, Shangyin Gao, Yihui Feng, Yibo Shi, Jing Wang
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 |
|---|---|---|---|
| add MAE, LPIPS and GAN perceptual losses to an MSE-only model (ablation) | COLIC · Kodak (kodim14, ~0.2 bpp) | visual quality (qualitative) | Mixed |
| add Laplacian loss on structure regions to the perceptual loss (ablation) | COLIC · Kodak (kodim14, ~0.2 bpp) | visual quality (qualitative) | Improved |
| add MSE face loss on small face regions (ablation) | COLIC · Kodak (kodim14, ~0.2 bpp) | visual quality (qualitative) | Improved |
| use asymmetric Gaussian entropy model instead of general Gaussian (ablation) | COLIC · Kodak | BD-rate: about 0.68% BD-rate reduction | Improved |
| add average pooling after each deconvolution layer (ablation) | COLIC · Kodak | checkerboard artifacts (qualitative) | Improved |
| use relativistic average PatchGAN discriminator instead of HiFiC discriminator (ablation) | COLIC · Kodak | detail preservation (qualitative) | Improved |
| use COLIC instead of HiFiC | COLIC · Kodak | PSNR, SSIM, FID | Improved |
Closest papers by meaning
- How To Exploit the Transferability of Learned Image Compression to Conventional Codecs (CVPR 2021 · similarity 0.88)
- GLIC: General Format Learned Image Compression (AAAI 2025 · similarity 0.88)
- Learning End-to-End Lossy Image Compression: A Benchmark (TPAMI 2021 · similarity 0.87)
- Neural Image Compression with Text-guided Encoding for both Pixel-level and Perceptual Fidelity (ICML 2024 · similarity 0.85)
- Learned Image Compression with Dictionary-based Entropy Model (CVPR 2025 · similarity 0.85)
- Good, Cheap, and Fast: Overfitted Image Compression with Wasserstein Distortion (CVPR 2025 · similarity 0.85)
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.
