Positive2Negative: Breaking the Information-Lossy Barrier in Self-Supervised Single Image Denoising
School of Computer Science and Technology, Beijing Institute of Technology（北京理工大学计算机科学与技术学院）；School of Artificial Intelligence, Beijing Normal University（北京师范大学人工智能学院）；Aerospace Information Research Institute, Chinese Academy of Sciences（中国科学院空天信息创新研究院）
图像去噪可提升图像质量，是各类计算摄影应用中的基础技术。由于真实场景中难以获取干净图像，亟需开发仅依赖含噪图像、尤其是单张含噪图像的自监督图像去噪方法。现有自监督图像去噪范式（Noise2Noise和Noise2Void）严重依赖下采样、掩码等存在信息损失的操作，最终导致去噪性能不佳。本文提出一种新型自监督单图像去噪范式Positive2Negative，旨在打破信息损失壁垒。该范式包含两个核心步骤：重加噪数据构建（Renoised Data Construction, RDC）和去噪一致性监督（Denoised Consistency Supervision, DCS）。RDC利用预测得到的噪声对预测的去噪图像进行重加噪，构建出多张含噪图像，完整保留了原始图像的所有信息。DCS确保多张去噪图像之间的一致性，监督网络学习鲁棒的去噪能力。本文提出的Positive2Negative范式在自监督单图像去噪任务上取得了当前最优性能，同时速度提升显著。代码已公开发布于https://github.com/Li-Tong-621/P2N。
英文摘要：
Image denoising enhances image quality, serving as a foundational technique across various computational photography applications. The obstacle to clean image acquisition in real scenarios necessitates the development of self-supervised image denoising methods only depending on noisy images, especially a single noisy image. Existing self-supervised image denoising paradigms (Noise2Noise and Noise2Void) rely heavily on information-lossy operations, such as downsampling and masking, culminating in low quality denoising performance. In this paper, we propose a novel self-supervised single image denoising paradigm, Positive2Negative, to break the information-lossy barrier. Our paradigm involves two key steps: Renoised Data Construction (RDC) and Denoised Consistency Supervision (DCS). RDC renoises the predicted denoised image by the predicted noise to construct multiple noisy images, preserving all the information of the original image. DCS ensures consistency across the multiple denoised images, supervising the network to learn robust denoising. Our Positive2Negative paradigm achieves state-of-the-art performance in self-supervised single image denoising with significant speed improvements. The code is released to the public at https://github.com/Li-Tong-621/P2N.
The Hong Kong Univeristy of Science and Technology（香港科技大学）
High levels of noise usually exist in today's captured images due to the relatively small sensors equipped in the smartphone cameras, where the noise brings extra challenges to lossy image compression algorithms. Without the capacity to tell the difference between image details and noise, general image compression methods allocate additional bits to explicitly store the undesired image noise during compression and restore the unpleasant noisy image during decompression. Based on the observations, we optimize the image compression algorithm to be noise-aware as joint denoising and compression t…
Sciences and Technologies of Image and Telecommunications High Institute of Biotechnology Sfax（斯法克斯生物技术高等研究所图像与电信科学技术学院）
Image compression helps in storing the transmitted data in proficient way by decreasing its redundancy. This technique helps in transferring more digital or multimedia data over internet as it increases the storage space. It is important to maintain the image quality even if it is compressed to certain extent. Depend upon this the image compression is classified into two categories : lossy and lossless image compression. There are many lossy digital image compression techniques exists. Among this Incremental Self Organizing Map is a familiar one. The good pictures quality can be retrieved if i…
Structure-Adaptive Sparse Diffusion in Voxel Space for 3D Medical Image Enhancement
Department of Electrical and Computer Engineering, University of Florida, Gainesville, FL, USA（佛罗里达大学电气与计算机工程系）；Department of Medicine, University of Florida, Gainesville, FL, USA（佛罗里达大学医学系）；Department of Biomedical Engineering, University of Florida, Gainesville, FL, USA（佛罗里达大学生物医学工程系）；Research Computing, University of Florida, Gainesville, FL, USA（佛罗里达大学研究计算中心）；NVIDIA, Santa Clara, CA, USA（英伟达）
We propose a simple, interpretable framework for solving a wide range of image reconstruction problems such as denoising and deconvolution. Given a corrupted input image, the model synthesizes a spatially varying linear filter which, when applied to the input image, reconstructs the desired output. The model parameters are learned using supervised or self-supervised training. We test this model on three tasks: non-uniform motion blur removal, lossy-compression artifact reduction and single image super resolution. We demonstrate that our model substantially outperforms state-of-the-art methods …
Xidian University（西安电子科技大学）；West Virginia University（西弗吉尼亚大学）
Deep neural networks (DNNs) based methods have achieved great success in single image super-resolution (SISR). However, existing state-of-the-art SISR techniques are designed like black boxes lacking transparency and interpretability. Moreover, the improvement in visual quality is often at the price of increased model complexity due to black-box design. In this paper, we present and advocate an explainable approach toward SISR named model-guided deep unfolding network (MoG-DUN). Targeting at breaking the coherence barrier, we opt to work with a well-established image prior named nonlocal auto-…
An ongoing trend in generative modelling research has been to push sample resolutions higher whilst simultaneously reducing computational requirements for training and sampling. We aim to push this trend further via the combination of techniques - each component representing the current pinnacle of efficiency in their respective areas. These include vector-quantized GAN (VQ-GAN), a vector-quantization (VQ) model capable of high levels of lossy - but perceptually insignificant - compression; hourglass transformers, a highly scaleable self-attention model; and step-unrolled denoising autoencoder…
Compressed Image Generation with Denoising Diffusion Codebook Models
Faculty of Computer Science, Technion -- Israel Institute of Technology, Haifa, Israel（计算机科学系，技术离子理工学院——以色列理工学院，海法，以色列）；Faculty of Electrical and Computer Engineering, Technion -- Israel Institute of Technology, Haifa, Israel（电气与计算机工程系，技术离子理工学院——以色列理工学院，海法，以色列）
