Fast Enhancement for Non-Uniform Illumination Images using Light-weight CNNs
This work addresses image quality issues in photography and vision applications, offering a fast and effective solution for handling varied lighting conditions, though it is incremental in its approach.
The paper tackles non-uniform illumination image enhancement by proposing a light-weight CNN that processes images through Retinex-based enhancement and fusion, achieving real-time performance at 50 fps for 0.5-megapixel images.
This paper proposes a new light-weight convolutional neural network (5k parameters) for non-uniform illumination image enhancement to handle color, exposure, contrast, noise and artifacts, etc., simultaneously and effectively. More concretely, the input image is first enhanced using Retinex model from dual different aspects (enhancing under-exposure and suppressing over-exposure), respectively. Then, these two enhanced results and the original image are fused to obtain an image with satisfactory brightness, contrast and details. Finally, the extra noise and compression artifacts are removed to get the final result. To train this network, we propose a semi-supervised retouching solution and construct a new dataset (82k images) contains various scenes and light conditions. Our model can enhance 0.5 mega-pixel (like 600*800) images in real time (50 fps), which is faster than existing enhancement methods. Extensive experiments show that our solution is fast and effective to deal with non-uniform illumination images.