JPEG Information Regularized Deep Image Prior for Denoising
This addresses a specific bottleneck in DIP-based denoising for computer vision applications, but it is incremental as it builds on existing DIP methods.
The paper tackled the challenge of early stopping in deep image prior (DIP) for image denoising without ground-truth images by proposing to monitor JPEG file size as a proxy metric for noise levels, showing it effectively guides optimization.
Image denoising is a representative image restoration task in computer vision. Recent progress of image denoising from only noisy images has attracted much attention. Deep image prior (DIP) demonstrated successful image denoising from only a noisy image by inductive bias of convolutional neural network architectures without any pre-training. The major challenge of DIP based image denoising is that DIP would completely recover the original noisy image unless applying early stopping. For early stopping without a ground-truth clean image, we propose to monitor JPEG file size of the recovered image during optimization as a proxy metric of noise levels in the recovered image. Our experiments show that the compressed image file size works as an effective metric for early stopping.