paper-with-me

Papers

Self-Calibrated Variance-Stabilizing Transformations for Real-World Image Denoising

2024-07-24 · Sébastien Herbreteau, Michael Unser

Supervised deep learning has become the method of choice for image denoising. It involves the training of neural networks on large datasets composed of pairs of noisy and clean images. However, the necessity of training data that are specific to the targeted application constrains the widespread use of denoising networks. Recently, several approaches have been developed to overcome this difficulty by whether artificially generating realistic clean/noisy image pairs, or training exclusively on noisy images. In this paper, we show that, contrary to popular belief, denoising networks specialized in the removal of Gaussian noise can be efficiently leveraged in favor of real-world image denoising, even without additional training. For this to happen, an appropriate variance-stabilizing transform (VST) has to be applied beforehand. We propose an algorithm termed Noise2VST for the learning of such a model-free VST. Our approach requires only the input noisy image and an off-the-shelf Gaussian denoiser. We demonstrate through extensive experiments the efficiency and superiority of Noise2VST in comparison to existing methods trained in the absence of specific clean/noisy pairs.

📄 PDF Abstract BibTeX arXiv:2407.17399

Code (0)

등록된 구현이 없습니다.

Tasks

DenoisingImage Denoising

Similar Papers 제목 키워드 기반

Self-Supervised Learning based on Transformed Image Reconstruction for Equivariance-Coherent Feature Representation

2025-03-24 · Qin Wang, Benjamin Bruns, Hanno Scharr, Kai Krajsek

The equivariant behaviour of features is essential in many computer vision tasks, yet popular self-supervised learning (SSL) methods tend to constrain equivariance by design. We propose a self-supervised learning approac…

Image ReconstructionSelf-Supervised Learning

Equivariant Self-Supervised Learning: Encouraging Equivariance in Representations

2021-09-29 · ICLR 2022 4 · Rumen Dangovski, Li Jing, Charlotte Loh, Seungwook Han 외

In state-of-the-art self-supervised learning (SSL) pre-training produces semantically good representations by encouraging them to be invariant under meaningful transformations prescribed from human knowledge. In fact, th…

Self-Supervised Learning

SEIS: Subspace-based Equivariance and Invariance Scores for Neural Representations

2026-02-03 · Huahua Lin, Katayoun Farrahi, Xiaohao Cai arxiv

Understanding how neural representations respond to geometric transformations is essential for evaluating whether learned features preserve meaningful spatial structure. Existing approaches primarily assess robustness pr…

Multi-Task LearningData Augmentation

Learning Online Visual Invariances for Novel Objects via Supervised and Self-Supervised Training

2021-10-04 · Valerio Biscione, Jeffrey S. Bowers

Humans can identify objects following various spatial transformations such as scale and viewpoint. This extends to novel objects, after a single presentation at a single pose, sometimes referred to as online invariance. …

Data AugmentationTranslation

VeLU: Variance-enhanced Learning Unit for Deep Neural Networks

2025-04-21 · Ashkan Shakarami, Yousef Yeganeh, Azade Farshad, Lorenzo Nicolè 외

Activation functions are fundamental in deep neural networks and directly impact gradient flow, optimization stability, and generalization. Although ReLU remains standard because of its simplicity, it suffers from vanish…