Invertible Image Signal Processing
Authors:
- 1 June 2021
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 6283-6292
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 re-construct 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.Keywords
All Related Versions
This publication has 27 references indexed in Scilit:
- Burst photography for high dynamic range and low-light imaging on mobile camerasACM Transactions on Graphics, 2016
- Deep joint demosaicking and denoisingACM Transactions on Graphics, 2016
- Learning joint demosaicing and denoising based on sequential energy minimization2016
- Convolutional Color Constancy2015
- FlexISPACM Transactions on Graphics, 2014
- Intrinsic images in the wildACM Transactions on Graphics, 2014
- Local Laplacian filtersACM Transactions on Graphics, 2011
- High Dynamic Range Image Display With Halo and Clipping PreventionIEEE Transactions on Image Processing, 2010
- Clipped noisy images: Heteroskedastic modeling and practical denoisingSignal Processing, 2009
- Photographic tone reproduction for digital images2002