Neural Differential Equations for Single Image Super-resolution
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Image RestorationImage Super-ResolutionSensitivitySuper-ResolutionSimilar Papers 제목 키워드 기반
ODE-Inspired Network Design for Single Image Super-Resolution
Single image super-resolution, as a high dimensional structured prediction problem, aims to characterize fine-grain information given a low-resolution sample. Recent advances in convolutional neural networks are introduc…
Image Super-ResolutionStructured PredictionSuper-ResolutionFace Super-Resolution Using Stochastic Differential Equations
Diffusion models have proven effective for various applications such as images, audio and graph generation. Other important applications are image super-resolution and the solution of inverse problems. More recently, som…
Face RecognitionGraph GenerationImage Super-ResolutionSSIM+1Super-resolving sparse observations in partial differential equations: A physics-constrained convolutional neural network approach
We propose the physics-constrained convolutional neural network (PC-CNN) to infer the high-resolution solution from sparse observations of spatiotemporal and nonlinear partial differential equations. Results are shown fo…
Super-ResolutionAn Operator Learning Framework for Spatiotemporal Super-resolution of Scientific Simulations
In numerous contexts, high-resolution solutions to partial differential equations are required to capture faithfully essential dynamics which occur at small spatiotemporal scales, but these solutions can be very difficul…
Operator learningSuper-ResolutionFNOSeg3D: Resolution-Robust 3D Image Segmentation with Fourier Neural Operator
Due to the computational complexity of 3D medical image segmentation, training with downsampled images is a common remedy for out-of-memory errors in deep learning. Nevertheless, as standard spatial convolution is sensit…
Image SegmentationMedical Image SegmentationSemantic SegmentationSuper-Resolution