1. Introduction
The vast majority of images used in computer vision and image processing applications are 8-bit standard RGB (sRGB) images, typically saved using the JPEG compression standard. Virtually all image processing application workflows support sRGB and JPEG images. There are many drawbacks, however, when working with sRGB images, e.g. it is well known that sRGB images have a number of non-linear operations applied that makes it difficult to relate the sRGB values back to scene radiance [3], [8], [13], [17], [22], [24].
(a) A resolution high-quality SRGB-JPEG with our metadata embedded (original JPEG size of 9,788 KB, new size of 9,852 KB). (b) Original RAW image is 25,947 KB. (c) Our reconstructed RAW image using the data in the self-contained JPEG. (d) Error map between (b) and (c). Overall reconstruction error is 0.2%.