让JPEG高效压缩原始图像，还原质量远超直接存JPEG
Raw-JPEG Adapter: Efficient Raw Image Compression with JPEG
- 用轻量可学习的预处理流程，把原始图像转成适配JPEG的形式
- 在多个数据集上重建精度优于直接用JPEG存储，且支持其他编码器
- 参数小到能塞进JPEG注释字段，适合手机等存储受限设备
数码相机将场景光转换为线性原始数据，由图像信号处理器（ISP）生成显示就绪输出。虽然原始数据保留完整传感器信息，对编辑和视觉任务有价值，但如Digital Negative（DNG）等格式占用大量存储，在资源受限场景下不实用。相比之下，JPEG广泛支持、压缩效率高、兼容性好，但不适合原始数据存储。本文提出RawJPEG Adapter，一种轻量、可学习且可逆的预处理流水线，可将原始图像适配标准JPEG压缩。该方法结合空间域与可选频域变换，将紧凑参数存于JPEG注释字段，实现高精度原始数据重建。多数据集实验表明，本方法重建质量优于直接使用JPEG存储，支持多种编码器，并在压缩比与重建精度间取得良好平衡。
原文摘要 · Abstract (English)
Digital cameras digitize scene light into linear raw representations, which the image signal processor (ISP) converts into display-ready outputs. While raw data preserves full sensor information--valuable for editing and vision tasks--formats such as Digital Negative (DNG) require large storage, making them impractical in constrained scenarios. In contrast, JPEG is a widely supported format, offering high compression efficiency and broad compatibility, but it is not well-suited for raw storage. This paper presents RawJPEG Adapter, a lightweight, learnable, and invertible preprocessing pipeline that adapts raw images for standard JPEG compression. Our method applies spatial and optional frequency-domain transforms, with compact parameters stored in the JPEG comment field, enabling accurate raw reconstruction. Experiments across multiple datasets show that our method achieves higher fidelity than direct JPEG storage, supports other codecs, and provides a favorable trade-off between compression ratio and reconstruction accuracy.
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。