Digital cameras transform sensor RAW readings into RGB images by means of their Image Signal Processor (ISP).
We introduce a strategy that learns to jointly align and assess the alignment and exposure reliability using an HDR-aware, uncertainty-driven attention map that robustly merges the frames into a single high quality HDR image.
The breakthrough of contrastive learning (CL) has fueled the recent success of self-supervised learning (SSL) in high-level vision tasks on RGB images.
This paper reviews the first challenge on high-dynamic range (HDR) imaging that was part of the New Trends in Image Restoration and Enhancement (NTIRE) workshop, held in conjunction with CVPR 2021.
Together with a video discriminator, we also propose additional loss functions to further reinforce temporal consistency in the generated sequences.