Raw reconstruction
3 papers with code • 0 benchmarks • 0 datasets
Reconstruct RAW camera sensor readings from the corresponding sRGB images
Benchmarks
These leaderboards are used to track progress in Raw reconstruction
Most implemented papers
Model-Based Image Signal Processors via Learnable Dictionaries
mv-lab/AISP
•
•
Digital cameras transform sensor RAW readings into RGB images by means of their Image Signal Processor (ISP).
Learning sRGB-to-Raw-RGB De-rendering with Content-Aware Metadata
samsunglabs/content-aware-metadata
•
•
CVPR 2022
Our experiments show that our learned sampling can adapt to the image content to produce better raw reconstructions than existing methods.
Reversed Image Signal Processing and RAW Reconstruction. AIM 2022 Challenge Report
mv-lab/AISP
•
•
Cameras capture sensor RAW images and transform them into pleasant RGB images, suitable for the human eyes, using their integrated Image Signal Processor (ISP).
