Generalized Recorrupted-to-Recorrupted: Self-Supervised Learning Beyond Gaussian Noise
Recorrupted-to-Recorrupted (R2R) has emerged as a methodology for training deep networks for image restoration in a self-supervised manner from noisy measurement data alone, demonstrating equivalence in expectation to the supervised squared loss in the case of Gaussian noise. However, its effectiveness with non-Gaussian noise remains unexplored. In this paper, we propose Generalized R2R (GR2R), extending the R2R framework to handle a broader class of noise distribution as additive noise like log-Rayleigh and address the natural exponential family including Poisson and Gamma noise distributions, which play a key role in many applications including low-photon imaging and synthetic aperture radar. We show that the GR2R loss is an unbiased estimator of the supervised loss and that the popular Stein's unbiased risk estimator can be seen as a special case. A series of experiments with Gaussian, Poisson, and Gamma noise validate GR2R's performance, showing its effectiveness compared to other self-supervised methods.
Code (2)
Tasks
DenoisingImage RestorationSelf-Supervised LearningSimilar Papers 제목 키워드 기반
Recorrupted-to-Recorrupted: Unsupervised Deep Learning for Image Denoising
Deep denoiser, the deep network for denoising, has been the focus of the recent development on image denoising. In the last few years, there is an increasing interest in developing unsupervised deep denoisers which o…
Data AugmentationDeep LearningDenoisingImage DenoisingLearning to Recorrupt: Noise Distribution Agnostic Self-Supervised Image Denoising
Self-supervised image denoising methods have traditionally relied on either architectural constraints or specialized loss functions that require prior knowledge of the noise distribution to avoid the trivial identity map…
Image DenoisingPrincipal Component Analysis-Based Terahertz Self-Supervised Denoising and Deblurring Deep Neural Networks
Terahertz (THz) systems inherently introduce frequency-dependent degradation effects, resulting in low-frequency blurring and high-frequency noise in amplitude images. Conventional image processing techniques cannot simu…
Self-Supervised LearningImproving Zero-shot Generalization in Offline Reinforcement Learning using Generalized Similarity Functions
Reinforcement learning (RL) agents are widely used for solving complex sequential decision making tasks, but still exhibit difficulty in generalizing to scenarios not seen during training. While prior online approaches d…
Contrastive LearningDecision MakingOffline RLreinforcement-learning+4PointJEM: Self-supervised Point Cloud Understanding for Reducing Feature Redundancy via Joint Entropy Maximization
Most deep learning-based point cloud processing methods are supervised and require large scale of labeled data. However, manual labeling of point cloud data is laborious and time-consuming. Self-supervised representation…
Representation Learning