RAWIC: Bit-Depth Adaptive Lossless Raw Image Compression

2026-03-30

AI Summary

This work addresses the challenge of lossless compression for high bit-depth Bayer raw images, which is hindered by their large data volume, heterogeneous bit depths, and strong sensor dependency. The authors propose a bit-depth-adaptive lossless compression framework that transforms single-channel Bayer data into four-channel RGGB format and processes it in blocks. By leveraging the actual bit depth of each block as side information, they design a conditional entropy model capable of adapting to diverse cameras and bit depths. This approach achieves, for the first time, a unified model supporting lossless compression across multiple cameras and bit depths, overcoming the limitations of conventional methods that are restricted to 8-bit sRGB or rely on lossy reconstruction. Experiments demonstrate that the proposed method reduces bitrate by 7.7% on average compared to JPEG XL across multiple datasets, significantly outperforming existing lossless codecs.

Abstract

Raw images preserve linear sensor measurements and high bit-depth information crucial for advanced vision tasks and photography applications, yet their storage remains challenging due to large file sizes, varying bit depths, and sensor-dependent characteristics. Existing learned lossless compression methods mainly target 8-bit sRGB images, while raw reconstruction approaches are inherently lossy and rely on camera-specific assumptions. To address these challenges, we introduce RAWIC, a bit-depth-adaptive learned lossless compression framework for Bayer-pattern raw images. We first convert single-channel Bayer data into a four-channel RGGB format and partition it into patches. For each patch, we compute its bit depth and use it as auxiliary input to guide compression. A bit-depth-adaptive entropy model is then designed to estimate patch distributions conditioned on their bit depths. This architecture enables a single model to handle raw images from diverse cameras and bit depths. Experiments show that RAWIC consistently surpasses traditional lossless codecs, achieving an average 7.7% bitrate reduction over JPEG-XL. Our code is available at https://github.com/chunbaobao/RAWIC.

Problem

• raw image compression
• lossless compression
• bit-depth adaptivity
• Bayer-pattern
• entropy modeling

Innovation

• bit-depth-adaptive
• lossless compression
• raw image
• learned entropy model
• Bayer pattern