Research
On the Robustness of Diffusion-Based Image Compression to Bit-Flip Errors
arXiv:2604.05743v2 Announce Type: replace-cross Abstract: Modern image compression methods are typically optimized for the rate--distortion--perception trade-off, whereas their robustness to bit-level
arXiv:2604.05743v2 Announce Type: replace-cross Abstract: Modern image compression methods are typically optimized for the rate--distortion--perception trade-off, whereas their robustness to bit-level corruption is rarely examined. We show that diffusion-based compressors built on the Reverse Channel Coding (RCC) paradigm are substantially more robust to bit flips than classical and learned codecs. We further introduce a more robust variant of Turbo-DDCM that significantly improves robustness while only minimally affecting the rate--distortion--perception trade-off. Our findings suggest that RCC-based compression can yield more resilient compressed representations, potentially reducing reliance on error-correcting codes in highly noisy environments.
Related
- DeCo: Frequency-Decoupled Pixel Diffusion for End-to-End Image Generation
- Generative Phomosaic with Structure-Aligned and Personalized Diffusion
- ChopGrad: Pixel-Wise Losses for Latent Video Diffusion via Truncated Backpropagation
- Improving Robustness In Sparse Autoencoders via Masked Regularization
Source: arXiv cs.AI | 2026-04-10