paper-with-me

홈 › Papers

KernelFusion: Assumption-Free Blind Super-Resolution via Patch Diffusion

2025-03-27 · Oliver Heinimann, Assaf Shocher, Tal Zimbalist, Michal Irani

Traditional super-resolution (SR) methods assume an `ideal'' downscaling SR-kernel (e.g., bicubic downscaling) between the high-resolution (HR) image and the low-resolution (LR) image. Such methods fail once the LR images are generated differently. Current blind-SR methods aim to remove this assumption, but are still fundamentally restricted to rather simplistic downscaling SR-kernels (e.g., anisotropic Gaussian kernels), and fail on more complex (out of distribution) downscaling degradations. However, using the correct SR-kernel is often more important than using a sophisticated SR algorithm. In `KernelFusion'' we introduce a zero-shot diffusion-based method that makes no assumptions about the kernel. Our method recovers the unique image-specific SR-kernel directly from the LR input image, while simultaneously recovering its corresponding HR image. KernelFusion exploits the principle that the correct SR-kernel is the one that maximizes patch similarity across different scales of the LR image. We first train an image-specific patch-based diffusion model on the single LR input image, capturing its unique internal patch statistics. We then reconstruct a larger HR image with the same learned patch distribution, while simultaneously recovering the correct downscaling SR-kernel that maintains this cross-scale relation between the HR and LR images. Empirical results show that KernelFusion vastly outperforms all SR baselines on complex downscaling degradations, where existing SotA Blind-SR methods fail miserably. By breaking free from predefined kernel assumptions, KernelFusion pushes Blind-SR into a new assumption-free paradigm, handling downscaling kernels previously thought impossible.

📄 PDF Abstract BibTeX arXiv:2503.21907

Code (0)

등록된 구현이 없습니다.

Tasks

Blind Super-ResolutionSuper-Resolution

Methods 이 논문이 사용한 방법론

Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…

Similar Papers 제목 키워드 기반

Two Heads Better than One: Dual Degradation Representation for Blind Super-Resolution

2025-11-21 · Hsuan Yuan, Shao-Yu Weng, I-Hsuan Lo, Wei-Chen Chiu 외 arxiv

Previous methods have demonstrated remarkable performance in single image super-resolution (SISR) tasks with known and fixed degradation (e.g., bicubic downsampling). However, when the actual degradation deviates from th…

Image Super-ResolutionBlind Super-Resolution

Blind Image Super-resolution with Elaborate Degradation Modeling on Noise and Kernel

2021-07-02 · CVPR 2022 1 · Zongsheng Yue, Qian Zhao, Jianwen Xie, Lei Zhang 외

While researches on model-based blind single image super-resolution (SISR) have achieved tremendous successes recently, most of them do not consider the image degradation sufficiently. Firstly, they always assume image n…

Image Super-ResolutionSuper-Resolution

DynaVSR: Dynamic Adaptive Blind Video Super-Resolution

2020-11-09 · Suyoung Lee, Myungsub Choi, Kyoung Mu Lee

Most conventional supervised super-resolution (SR) algorithms assume that low-resolution (LR) data is obtained by downscaling high-resolution (HR) data with a fixed known kernel, but such an assumption often does not hol…

Meta-LearningSuper-ResolutionVideo Super-Resolution

2025 TGRS A Self-Supervised Method for Seismic Random Noise Attenuation under Non-Pixelwise Independent Assumption

2025-05-11 · IEEE Transactions on Geoscience and Remote Sensing 2025 5 · Chuangji Meng; Jinghuai Gao; Wenting Shang; Yajun Tian

The attenuation of seismic field noise using self-supervised deep learning has gained attention due to its label-free training process. However, common self-supervised methods are limited by the pixelwise independence as…

A Self-Supervised Method for Attenuating Seismic Random and Tracewise Coherent Noise under the Non-Pixelwise Independence Assumption

2025-05-11 · IEEE Transactions on Geoscience and Remote Sensing 2025 5 · Chuangji Meng; Jinghuai Gao; Wenting Shang; Yajun Tian

The attenuation of seismic field noise using self-supervised deep learning has gained attention due to its label-free training process. However, common self-supervised methods are limited by the pixelwise independence as…

DenoisingGeophysics