Bitflat improves robustness of diffusion image compression against bit errors
BitFlat: Error-Localized Bitstream Design for Robust Diffusion Image Compression
Artificial IntelligenceComputer Vision and Pattern Recognition
Summary
Compressing images with a type of AI called diffusion models can create high-quality pictures at very small file sizes, but even small errors during data transmission can mess up the image a lot. The authors designed BitFlat to help localize these errors so that one flipped bit only affects a small part of the image data, preventing the whole image from getting corrupted. Their method also detects and ignores the corrupted parts during image reconstruction, making the compressed image more reliable without needing to retrain any AI models. Tests showed BitFlat works better than existing methods, even when errors happen frequently or with fewer bits.
What this means in practice
- •For image compression engineers: Build more error-resilient diffusion-based image codecs that maintain quality under noisy bitstream conditions.
- •For communication system designers: Design bitstream encoding schemes that enable quick detection and isolation of bit flips for robust image data transmission.
Authors
Xinfeng Deng, Li Zhou, Haitao Chen, Shengjie Wu, Lingjin Kong, Nan Li, Haitao Zhao, Dongtang Ma
Abstract
Zero-shot diffusion image compression based on reverse channel coding achieves high perceptual quality at low bitrates without retraining, yet its bitstream remains vulnerable to bit flips. Prior work has shown that a joint combinatorial representation can amplify a single bit flip into substitutions of multiple atoms and that indexing each atom independently confines this error propagation. However, independent indexing reduces the number of atoms that fit within the bit budget and gives the decoder no indication of which atoms are corrupted. To address these issues, we propose BitFlat, a training-free error-localizing bitstream framework with two components. Blockwise Locality Alignment (BLA) decomposes the globally coupled atom selection at each diffusion step into independent selection units, each describing one signed atom from a dedicated codebook with a fixed-width field, so that any bit error affects only the unit in which it occurs. Reliability-Aware Diffusion Control (RADC) uses the bits saved by BLA to impose structured valid-codeword constraints within each field and converts the decoding state of each field into a binary reliability gate, which turns detected corrupted atoms into erasures at known positions and excludes them from noise synthesis. BitFlat requires neither target residuals nor additional network forward passes and leaves the diffusion model unchanged. Experiments on Kodak, DIV2K, and CLIC2020 show that BitFlat outperforms conventional, learned, and diffusion-based codecs at bit error rates from $10^{-4}$ to $10^{-2}$ and, even with $26.7\%$ fewer bits, surpasses Robust Turbo-DDCM.