RAWIC实现多比特深度原生图像无损压缩，适配不同相机。
RAWIC: Bit-Depth Adaptive Lossless Raw Image Compression
- 将拜耳数据转为四通道格式，按块计算比特深度并引导压缩。
- 在多种相机和比特深度下，平均比JPEG-XL节省7.7%码率。
- 适合需要跨设备兼容的高精度图像存储场景。
原始图像保留线性传感器测量值和高比特深度信息，对高级视觉任务和摄影应用至关重要，但其存储因文件体积大、比特深度多样及传感器特性差异而困难。现有学习型无损压缩方法主要针对8位sRGB图像，而原始图像重建方法本质有损且依赖特定相机假设。为此，我们提出RAWIC，一种适用于拜耳模式原始图像的比特深度自适应学习型无损压缩框架。首先将单通道拜耳数据转换为四通道RGGB格式，并划分为图像块；对每块计算其比特深度，作为辅助输入以指导压缩；设计比特深度自适应熵模型，根据块的比特深度条件估计分布。该架构使单一模型可处理来自不同相机与比特深度的原始图像。实验表明，RAWIC持续优于传统无损编码器，平均比特率较JPEG-XL降低7.7%。代码已开源：https://github.com/chunbaobao/RAWIC。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。