Patch-Craft Self-Supervised Training for Correlated Image Denoising
Supervised neural networks are known to achieve excellent results in various image restoration tasks. However, such training requires datasets composed of pairs of corrupted images and their corresponding ground truth targets. Unfortunately, such data is not available in many applications. For the task of image denoising in which the noise statistics is unknown, several self-supervised training methods have been proposed for overcoming this difficulty. Some of these require knowledge of the noise model, while others assume that the contaminating noise is uncorrelated, both assumptions are too limiting for many practical needs. This work proposes a novel self-supervised training technique suitable for the removal of unknown correlated noise. The proposed approach neither requires knowledge of the noise model nor access to ground truth targets. The input to our algorithm consists of easily captured bursts of noisy shots. Our algorithm constructs artificial patch-craft images from these bursts by patch matching and stitching, and the obtained crafted images are used as targets for the training. Our method does not require registration of the images within the burst. We evaluate the proposed framework through extensive experiments with synthetic and real image noise.
Code (1)
Tasks
DenoisingImage DenoisingImage RestorationPatch MatchingSimilar Papers 제목 키워드 기반
PatchRot: A Self-Supervised Technique for Training Vision Transformers
Vision transformers require a huge amount of labeled data to outperform convolutional neural networks. However, labeling a huge dataset is a very expensive process. Self-supervised learning techniques alleviate this prob…
Self-Supervised LearningLearning to Rank Patches for Unbiased Image Redundancy Reduction
Images suffer from heavy spatial redundancy because pixels in neighboring regions are spatially correlated. Existing approaches strive to overcome this limitation by reducing less meaningful image regions. However, curre…
Image ReconstructionInductive BiasLearning-To-RankConcept-wise Fine-tuning Matters in Preventing Negative Transfer
A multitude of prevalent pre-trained models mark a major milestone in the development of artificial intelligence, while fine-tuning has been a common practice that enables pretrained models to figure prominently in a wid…
Patch Craft: Video Denoising by Deep Modeling and Patch Matching
The non-local self-similarity property of natural images has been exploited extensively for solving various image processing problems. When it comes to video sequences, harnessing this force is even more beneficial due t…
Color Image DenoisingDenoisingPatch MatchingVideo DenoisingCross-Level Multi-Instance Distillation for Self-Supervised Fine-Grained Visual Categorization
High-quality annotation of fine-grained visual categories demands great expert knowledge, which is taxing and time consuming. Alternatively, learning fine-grained visual representation from enormous unlabeled images (e.g…
Fine-Grained Visual CategorizationKnowledge DistillationMultiple Instance LearningSelf-Supervised Learning