Meta Transferring for Deblurring
This addresses the domain gap issue in deblurring for real-world applications where ground truth is unavailable, offering an incremental improvement over existing methods.
The paper tackles dynamic scene deblurring by proposing a reblur-deblur meta-transferring scheme for test-time adaptation without ground truth, using pseudo-sharp patches from blurred input and reblurring to generate training data, improving state-of-the-art models on benchmark datasets like DVD, REDS, and RealBlur.
Most previous deblurring methods were built with a generic model trained on blurred images and their sharp counterparts. However, these approaches might have sub-optimal deblurring results due to the domain gap between the training and test sets. This paper proposes a reblur-deblur meta-transferring scheme to realize test-time adaptation without using ground truth for dynamic scene deblurring. Since the ground truth is usually unavailable at inference time in a real-world scenario, we leverage the blurred input video to find and use relatively sharp patches as the pseudo ground truth. Furthermore, we propose a reblurring model to extract the homogenous blur from the blurred input and transfer it to the pseudo-sharps to obtain the corresponding pseudo-blurred patches for meta-learning and test-time adaptation with only a few gradient updates. Extensive experimental results show that our reblur-deblur meta-learning scheme can improve state-of-the-art deblurring models on the DVD, REDS, and RealBlur benchmark datasets.