Sampling Theory for Super-Resolution with Implicit Neural Representations
Implicit neural representations (INRs) have emerged as a powerful tool for solving inverse problems in computer vision and computational imaging. INRs represent images as continuous domain functions realized by a neural network taking spatial coordinates as inputs. However, unlike traditional pixel representations, little is known about the sample complexity of estimating images using INRs in the context of linear inverse problems. Towards this end, we study the sampling requirements for recovery of a continuous domain image from its low-pass Fourier samples by fitting a single hidden-layer INR with ReLU activation and a Fourier features layer using a generalized form of weight decay regularization. Our key insight is to relate minimizers of this non-convex parameter space optimization problem to minimizers of a convex penalty defined over an infinite-dimensional space of measures. We identify a sufficient number of Fourier samples for which an image realized by an INR is exactly recoverable by solving the INR training problem. To validate our theory, we empirically assess the probability of achieving exact recovery of images realized by low-width single hidden-layer INRs, and illustrate the performance of INRs on super-resolution recovery of continuous domain phantom images.
Code (1)
Tasks
Super-ResolutionMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Towards a Sampling Theory for Implicit Neural Representations
Implicit neural representations (INRs) have emerged as a powerful tool for solving inverse problems in computer vision and computational imaging. INRs represent images as continuous domain functions realized by a neural …
Super-ResolutionStereoINR: Cross-View Geometry Consistent Stereo Super Resolution with Implicit Neural Representation
Stereo image super-resolution (SSR) aims to enhance high-resolution details by leveraging information from stereo image pairs. However, existing stereo super-resolution (SSR) upsampling methods (e.g., pixel shuffle) ofte…
Image Super-ResolutionStereo Image Super-ResolutionSuper-ResolutionVideoINR: Learning Video Implicit Neural Representation for Continuous Space-Time Super-Resolution
Videos typically record the streaming and continuous visual data as discrete consecutive frames. Since the storage cost is expensive for videos of high fidelity, most of them are stored in a relatively low resolution and…
Space-time Video Super-resolutionSuper-ResolutionVideo Frame InterpolationVideo Super-ResolutionHIIF: Hierarchical Encoding based Implicit Image Function for Continuous Super-resolution
Recent advances in implicit neural representations (INRs) have shown significant promise in modeling visual signals for various low-vision tasks including image super-resolution (ISR). INR-based ISR methods typically lea…
Image Super-ResolutionSuper-ResolutionA Sampling Theory Perspective on Activations for Implicit Neural Representations
Implicit Neural Representations (INRs) have gained popularity for encoding signals as compact, differentiable entities. While commonly using techniques like Fourier positional encodings or non-traditional activation func…