Thera: Aliasing-Free Arbitrary-Scale Super-Resolution with Neural Heat Fields

• URL: http://arxiv.org/abs/2311.17643v3
• Date: Sun, 09 Mar 2025 12:22:00 GMT
• Title: Thera: Aliasing-Free Arbitrary-Scale Super-Resolution with Neural Heat Fields
• Authors: Alexander Becker, Rodrigo Caye Daudt, Dominik Narnhofer, Torben Peters, Nando Metzger, Jan Dirk Wegner, Konrad Schindler,
• Abstract summary: Recent approaches to arbitrary-scale single image super-resolution (ASR) use neural fields to represent continuous signals that can be sampled at arbitrary resolutions.<n>Existing methods attempt to mitigate this by approximating an integral version of the field at each scaling factor, compromising both fidelity and generalization.<n>We introduce neural heat fields, a novel neural field formulation that inherently models a physically exact PSF.<n>Our formulation enables analytically correct anti-aliasing at any desired output resolution, and -- unlike supersampling -- at no additional cost.
• Score: 52.11475771410058
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Recent approaches to arbitrary-scale single image super-resolution (ASR) use neural fields to represent continuous signals that can be sampled at arbitrary resolutions. However, point-wise queries of neural fields do not naturally match the point spread function (PSF) of pixels, which may cause aliasing in the super-resolved image. Existing methods attempt to mitigate this by approximating an integral version of the field at each scaling factor, compromising both fidelity and generalization. In this work, we introduce neural heat fields, a novel neural field formulation that inherently models a physically exact PSF. Our formulation enables analytically correct anti-aliasing at any desired output resolution, and -- unlike supersampling -- at no additional cost. Building on this foundation, we propose Thera, an end-to-end ASR method that substantially outperforms existing approaches, while being more parameter-efficient and offering strong theoretical guarantees. The project page is at https://therasr.github.io.

Related papers

• Pixel to Gaussian: Ultra-Fast Continuous Super-Resolution with 2D Gaussian Modeling [50.34513854725803]
  Arbitrary-scale super-resolution (ASSR) aims to reconstruct high-resolution (HR) images from low-resolution (LR) inputs with arbitrary upsampling factors. We propose a novel ContinuousSR framework with a Pixel-to-Gaussian paradigm, which explicitly reconstructs 2D continuous HR signals from LR images using Gaussian Splatting.
  arXiv  Detail & Related papers  (2025-03-09T13:43:57Z)
• Adaptive Random Fourier Features Training Stabilized By Resampling With Applications in Image Regression [0.8947831206263182]
  We present an enhanced adaptive random Fourier features (ARFF) training algorithm for shallow neural networks. This method uses a particle filter type resampling technique to stabilize the training process and reduce sensitivity to parameter choices.
  arXiv  Detail & Related papers  (2024-10-08T22:08:03Z)
• GaussianSR: High Fidelity 2D Gaussian Splatting for Arbitrary-Scale Image Super-Resolution [29.49617080140511]
  Implicit neural representations (INRs) have significantly advanced the field of arbitrary-scale super-resolution (ASSR) of images. Most existing INR-based ASSR networks first extract features from the given low-resolution image using an encoder, and then render the super-resolved result via a multi-layer perceptron decoder. We propose a novel ASSR method named GaussianSR that overcomes this limitation through 2D Gaussian Splatting (2DGS)
  arXiv  Detail & Related papers  (2024-07-25T13:53:48Z)
• Boundary-aware Decoupled Flow Networks for Realistic Extreme Rescaling [49.215957313126324]
  Recently developed generative methods, including invertible rescaling network (IRN) based and generative adversarial network (GAN) based methods, have demonstrated exceptional performance in image rescaling. However, IRN-based methods tend to produce over-smoothed results, while GAN-based methods easily generate fake details. We propose Boundary-aware Decoupled Flow Networks (BDFlow) to generate realistic and visually pleasing results.
  arXiv  Detail & Related papers  (2024-05-05T14:05:33Z)
• CorresNeRF: Image Correspondence Priors for Neural Radiance Fields [45.40164120559542]
  CorresNeRF is a novel method that leverages image correspondence priors computed by off-the-shelf methods to supervise NeRF training. We show that this simple yet effective technique of using correspondence priors can be applied as a plug-and-play module across different NeRF variants.
  arXiv  Detail & Related papers  (2023-12-11T18:55:29Z)
• An Optimization-based Deep Equilibrium Model for Hyperspectral Image Deconvolution with Convergence Guarantees [71.57324258813675]
  We propose a novel methodology for addressing the hyperspectral image deconvolution problem. A new optimization problem is formulated, leveraging a learnable regularizer in the form of a neural network. The derived iterative solver is then expressed as a fixed-point calculation problem within the Deep Equilibrium framework.
  arXiv  Detail & Related papers  (2023-06-10T08:25:16Z)
• Local-to-Global Registration for Bundle-Adjusting Neural Radiance Fields [36.09829614806658]
  We propose L2G-NeRF, a Local-to-Global registration method for Neural Radiance Fields. Pixel-wise local alignment is learned in an unsupervised way via a deep network. Our method outperforms the current state-of-the-art in terms of high-fidelity reconstruction and resolving large camera pose misalignment.
  arXiv  Detail & Related papers  (2022-11-21T14:43:16Z)
• Deep Model-Based Super-Resolution with Non-uniform Blur [1.7188280334580197]
  We propose a state-of-the-art method for super-resolution with non-uniform blur. We first propose a fast deep plug-and-play algorithm, based on linearized ADMM splitting techniques. We unfold our iterative algorithm into a single network and train it end-to-end.
  arXiv  Detail & Related papers  (2022-04-21T13:57:21Z)
• NeRF-SR: High-Quality Neural Radiance Fields using Super-Sampling [82.99453001445478]
  We present NeRF-SR, a solution for high-resolution (HR) novel view synthesis with mostly low-resolution (LR) inputs. Our method is built upon Neural Radiance Fields (NeRF) that predicts per-point density and color with a multi-layer perceptron.
  arXiv  Detail & Related papers  (2021-12-03T07:33:47Z)
• Model Inspired Autoencoder for Unsupervised Hyperspectral Image Super-Resolution [25.878793557013207]
  This paper focuses on hyperspectral image (HSI) super-resolution that aims to fuse a low-spatial-resolution HSI and a high-spatial-resolution multispectral image. Existing deep learning-based approaches are mostly supervised that rely on a large number of labeled training samples. We make the first attempt to design a model inspired deep network for HSI super-resolution in an unsupervised manner.
  arXiv  Detail & Related papers  (2021-10-22T05:15:16Z)
• FOVEA: Foveated Image Magnification for Autonomous Navigation [53.69803081925454]
  We propose an attentional approach that elastically magnifies certain regions while maintaining a small input canvas. Our proposed method boosts the detection AP over standard Faster R-CNN, with and without finetuning. On the autonomous driving datasets Argoverse-HD and BDD100K, we show our proposed method boosts the detection AP over standard Faster R-CNN, with and without finetuning.
  arXiv  Detail & Related papers  (2021-08-27T03:07:55Z)
• Semi-Sparsity for Smoothing Filters [1.1404527665142667]
  We show a new semi-sparsity smoothing algorithm based on a novel sparsity-inducing framework. We show many benefits to a series of signal/image processing and computer vision applications.
  arXiv  Detail & Related papers  (2021-07-01T17:31:42Z)
• NeRF in detail: Learning to sample for view synthesis [104.75126790300735]
  Neural radiance fields (NeRF) methods have demonstrated impressive novel view synthesis. In this work we address a clear limitation of the vanilla coarse-to-fine approach -- that it is based on a performance and not trained end-to-end for the task at hand. We introduce a differentiable module that learns to propose samples and their importance for the fine network, and consider and compare multiple alternatives for its neural architecture.
  arXiv  Detail & Related papers  (2021-06-09T17:59:10Z)
• Sigma-Delta and Distributed Noise-Shaping Quantization Methods for Random Fourier Features [73.25551965751603]
  We prove that our quantized RFFs allow a high accuracy approximation of the underlying kernels. We show that the quantized RFFs can be further compressed, yielding an excellent trade-off between memory use and accuracy. We empirically show by testing the performance of our methods on several machine learning tasks that our method compares favorably to other state of the art quantization methods in this context.
  arXiv  Detail & Related papers  (2021-06-04T17:24:47Z)
• InfinityGAN: Towards Infinite-Resolution Image Synthesis [92.40782797030977]
  We present InfinityGAN, a method to generate arbitrary-resolution images. We show how it trains and infers patch-by-patch seamlessly with low computational resources.
  arXiv  Detail & Related papers  (2021-04-08T17:59:30Z)
• UltraSR: Spatial Encoding is a Missing Key for Implicit Image Function-based Arbitrary-Scale Super-Resolution [74.82282301089994]
  In this work, we propose UltraSR, a simple yet effective new network design based on implicit image functions. We show that spatial encoding is indeed a missing key towards the next-stage high-accuracy implicit image function. Our UltraSR sets new state-of-the-art performance on the DIV2K benchmark under all super-resolution scales.
  arXiv  Detail & Related papers  (2021-03-23T17:36:42Z)
• Image Inpainting with Learnable Feature Imputation [8.293345261434943]
  A regular convolution layer applying a filter in the same way over known and unknown areas causes visual artifacts in the inpainted image. We propose (layer-wise) feature imputation of the missing input values to a convolution. We present comparisons on CelebA-HQ and Places2 to current state-of-the-art to validate our model.
  arXiv  Detail & Related papers  (2020-11-02T16:05:32Z)
• End-to-end Interpretable Learning of Non-blind Image Deblurring [102.75982704671029]
  Non-blind image deblurring is typically formulated as a linear least-squares problem regularized by natural priors on the corresponding sharp picture's gradients. We propose to precondition the Richardson solver using approximate inverse filters of the (known) blur and natural image prior kernels.
  arXiv  Detail & Related papers  (2020-07-03T15:45:01Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.