Learning-Based Dequantization For Image Restoration Against Extremely Poor Illumination
This addresses image restoration for applications in low-light photography, but appears incremental as it builds on existing machine learning approaches.
The paper tackles the problem of recovering image details lost due to A/D quantization under poor illumination, proposing a method that compensates illumination and uses a DCNN to restore missing details, achieving recovery from synthetic data.
All existing image enhancement methods, such as HDR tone mapping, cannot recover A/D quantization losses due to insufficient or excessive lighting, (underflow and overflow problems). The loss of image details due to A/D quantization is complete and it cannot be recovered by traditional image processing methods, but the modern data-driven machine learning approach offers a much needed cure to the problem. In this work we propose a novel approach to restore and enhance images acquired in low and uneven lighting. First, the ill illumination is algorithmically compensated by emulating the effects of artificial supplementary lighting. Then a DCNN trained using only synthetic data recovers the missing detail caused by quantization.