Invertible Image Signal Processing

Abstract

Unprocessed RAW data is a highly valuable image format for image editing and computer vision. However, since the file size of RAW data is huge, most users can only get access to processed and compressed sRGB images. To bridge this gap, we design an Invertible Image Signal Processing (InvISP) pipeline, which not only enables rendering visually appealing sRGB images but also allows recovering nearly perfect RAW data. Due to our framework's inherent reversibility, we can reconstruct realistic RAW data instead of synthesizing RAW data from sRGB images without any memory overhead. We also integrate a differentiable JPEG compression simulator that empowers our framework to reconstruct RAW data from JPEG images. Extensive quantitative and qualitative experiments on two DSLR demonstrate that our method obtains much higher quality in both rendered sRGB images and reconstructed RAW data than alternative methods.

arXiv commentAccepted to CVPR2021. Code available at: https://github.com/yzxing87/Invertible-ISP

References in corpus (5)

• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• HDR image reconstruction from a single exposure using deep CNNs
• DeepISP: Towards Learning an End-to-End Image Processing Pipeline
• Flow++: Improving Flow-Based Generative Models with Variational Dequantization and Architecture Design
• CameraNet: A Two-Stage Framework for Effective Camera ISP Learning