Single-Image HDR Reconstruction by Learning to Reverse the Camera Pipeline
This addresses the challenge of recovering missing details in under-/over-exposed regions for image processing applications, representing an incremental improvement over existing learning-based approaches.
The paper tackles the problem of reconstructing high dynamic range (HDR) images from single low dynamic range (LDR) images by learning to reverse the camera pipeline, achieving favorable performance against state-of-the-art methods.
Recovering a high dynamic range (HDR) image from a single low dynamic range (LDR) input image is challenging due to missing details in under-/over-exposed regions caused by quantization and saturation of camera sensors. In contrast to existing learning-based methods, our core idea is to incorporate the domain knowledge of the LDR image formation pipeline into our model. We model the HDRto-LDR image formation pipeline as the (1) dynamic range clipping, (2) non-linear mapping from a camera response function, and (3) quantization. We then propose to learn three specialized CNNs to reverse these steps. By decomposing the problem into specific sub-tasks, we impose effective physical constraints to facilitate the training of individual sub-networks. Finally, we jointly fine-tune the entire model end-to-end to reduce error accumulation. With extensive quantitative and qualitative experiments on diverse image datasets, we demonstrate that the proposed method performs favorably against state-of-the-art single-image HDR reconstruction algorithms.