首页/论文/2005.00865

arXiv 2005.008652020-05-02eess.IVcs.LGstat.ML

Neural Differential Equations for Single Image Super-resolution

Hugging Face；Czech Technical University in Prague（布拉格捷克理工大学）

Teven Le Scao

备注：: 7 pages, 5 figures, ICLR 2020 Workshop on Integration of Deep Neural Models and Differential Equations

阅读 PDF ↗

arXiv 页面 ↗HTML 原文 ↗

英文摘要相关论文

英文摘要：

Although Neural Differential Equations have shown promise on toy problems such as MNIST, they have yet to be successfully applied to more challenging tasks. Inspired by variational methods for image restoration relying on partial differential equations, we choose to benchmark several forms of Neural DEs and backpropagation methods on single image super-resolution. The adjoint method previously proposed for gradient estimation has no theoretical stability guarantees; we find a practical case where this makes it unusable, and show that discrete sensitivity analysis has better stability. In our experiments, differential models match the performance of a state-of-the art super-resolution model.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

阅读原文

阅读 PDF ↗

arXiv 页面 ↗HTML 原文 ↗

本文内容

英文摘要相关论文

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

继续探索

相关论文

用于学习偏微分方程的物理知情神经算子

Physics-Informed Neural Operator for Learning Partial Differential Equations

California Institute of Technology（加州理工学院）；Nvidia Corporation（英伟达公司）

提出PINO方法，结合粗分辨率数据与高分辨率PDE约束学习解算子，实现零样本超分辨率且在无数据场景中优于PINN。

2023-07-29cs.LGcs.NAmath.NA

Multiwavelet-based Operator Learning for Differential Equations

University of Southern California（南加利福尼亚大学）

The solution of a partial differential equation can be obtained by computing the inverse operator map between the input and the solution space. Towards this end, we introduce a \textit{multiwavelet-based neural operator learning scheme} that compresses the associated operator's kernel using fine-grained wavelets. By explicitly embedding the inverse multiwavelet filters, we learn the projection of the kernel onto fixed multiwavelet polynomial bases. The projected kernel is trained at multiple scales derived from using repeated computation of multiwavelet transform. This allows learning the comp…

2021-10-10cs.LGmath.AP

Fourier Neural Operator for Parametric Partial Differential Equations

Caltech（加州理工学院）

The classical development of neural networks has primarily focused on learning mappings between finite-dimensional Euclidean spaces. Recently, this has been generalized to neural operators that learn mappings between function spaces. For partial differential equations (PDEs), neural operators directly learn the mapping from any functional parametric dependence to the solution. Thus, they learn an entire family of PDEs, in contrast to classical methods which solve one instance of the equation. In this work, we formulate a new neural operator by parameterizing the integral kernel directly in Fou…

2021-05-17cs.LGcs.NAmath.NA

MRF-PINN: A Multi-Receptive-Field convolutional physics-informed neural network for solving partial differential equations

Beihang University（北京航空航天大学）

Compared with conventional numerical approaches to solving partial differential equations (PDEs), physics-informed neural networks (PINN) have manifested the capability to save development effort and computational cost, especially in scenarios of reconstructing the physics field and solving the inverse problem. Considering the advantages of parameter sharing, spatial feature extraction and low inference cost, convolutional neural networks (CNN) are increasingly used in PINN. However, some challenges still remain as follows. To adapt convolutional PINN to solve different PDEs, considerable effo…

2022-09-16cs.LGmath.APphysics.comp-ph

Progressive Image Super-Resolution via Neural Differential Equation

Hanyang University（汉阳大学）

We propose a new approach for the image super-resolution (SR) task that progressively restores a high-resolution (HR) image from an input low-resolution (LR) image on the basis of a neural ordinary differential equation. In particular, we newly formulate the SR problem as an initial value problem, where the initial value is the input LR image. Unlike conventional progressive SR methods that perform gradual updates using straightforward iterative mechanisms, our SR process is formulated in a concrete manner based on explicit modeling with a much clearer understanding. Our method can be easily i…

2022-01-24cs.CVeess.IV

DWA：用于图像超分辨率的差分小波放大器

DWA: Differential Wavelet Amplifier for Image Super-Resolution

German Research Center for Artificial Intelligence (DFKI)（德国人工智能研究中心）；RPTU Kaiserslautern-Landau（凯撒斯劳滕-兰道莱茵-普法尔茨技术大学）

本研究提出用于图像超分辨率的即插即用差分小波放大器DWA，通过双卷积滤波器差值优化小波域特征提取，集成到现有模型中可提升经典SR任务性能，还能省去传统DWT步骤降低通道维度。

2023-07-10cs.AIcs.CVcs.LG

更多相关论文收起更多论文

HaDM-ST：用于空间转录组学生成的组织学辅助差分建模

HaDM-ST: Histology-Assisted Differential Modeling for Spatial Transcriptomics Generation

University of Cambridge, UK（剑桥大学，英国）；Northeastern University, Shenyang, China（东北大学，中国）

提出HaDM-ST框架，通过语义蒸馏网络、空间对齐模块和通道感知对抗学习器，结合H&E图像与低分辨率ST生成高分辨率ST，有效解决了特征分离、多模态对齐和基因变异建模的挑战。

2025-08-10cs.CVeess.IVq-bio.QM

Lossless Image Compression through Super-Resolution

The University of Texas at Austin（德克萨斯大学奥斯汀分校）

We introduce a simple and efficient lossless image compression algorithm. We store a low resolution version of an image as raw pixels, followed by several iterations of lossless super-resolution. For lossless super-resolution, we predict the probability of a high-resolution image, conditioned on the low-resolution input, and use entropy coding to compress this super-resolution operator. Super-Resolution based Compression (SReC) is able to achieve state-of-the-art compression rates with practical runtimes on large datasets. Code is available online at https://github.com/caoscott/SReC.

2020-04-06cs.CVcs.LGeess.IV

Semi-Supervised Super-Resolution

Indian Institute of Technology Kanpur（印度理工学院坎普尔分校）

Super-Resolution is the technique to improve the quality of a low-resolution photo by boosting its plausible resolution. The computer vision community has extensively explored the area of Super-Resolution. However, previous Super-Resolution methods require vast amounts of data for training which becomes problematic in domains where very few low-resolution, high-resolution pairs might be available. One such area is statistical downscaling, where super-resolution is increasingly being used to obtain high-resolution climate information from low-resolution data. Acquiring high-resolution climate d…

2022-04-19cs.CVeess.IV

高分辨率，请注意！改进自监督真实世界超分辨率

High-Resolution Be Aware! Improving the Self-Supervised Real-World Super-Resolution

National University of Singapore（新加坡国立大学）

本文针对真实世界自监督超分辨率中高分辨率知识缺失和退化建模不足的问题，提出基于结果质量的退化控制器和特征对齐正则化器，通过微调现成SR模型实现自然且感知性能领先的超分辨率结果。

2024-11-25cs.CVeess.IV

SRNR: Training neural networks for Super-Resolution MRI using Noisy high-resolution Reference data

Neural network (NN) based approaches for super-resolution MRI typically require high-SNR high-resolution reference data acquired in many subjects, which is time consuming and a barrier to feasible and accessible implementation. We propose to train NNs for Super-Resolution using Noisy Reference data (SRNR), leveraging the mechanism of the classic NN-based denoising method Noise2Noise. We systematically demonstrate that results from NNs trained using noisy and high-SNR references are similar for both simulated and empirical data. SRNR suggests a smaller number of repetitions of high-resolution r…

2022-11-10eess.IV

Real-World Single Image Super-Resolution Under Rainy Condition

Old Dominion University（老道明大学）

Image super-resolution is an important research area in computer vision that has a wide variety of applications including surveillance, medical imaging etc. Real-world signal image super-resolution has become very popular now-a-days due to its real-time application. There are still a lot of scopes to improve real-world single image super-resolution specially during challenging weather scenarios. In this paper, we have proposed a new algorithm to perform real-world single image super-resolution during rainy condition. Our proposed method can mitigate the influence of rainy conditions during ima…

2022-06-16cs.CVeess.IV