Wavelet-Space Representations for Neural Super-Resolution in Rendering Pipelines

• URL: http://arxiv.org/abs/2508.16024v3
• Date: Sat, 20 Sep 2025 13:56:49 GMT
• Title: Wavelet-Space Representations for Neural Super-Resolution in Rendering Pipelines
• Authors: Prateek Poudel, Prashant Aryal, Kirtan Kunwar, Navin Nepal, Dinesh Baniya Kshatri,
• Abstract summary: We introduce a formulation that predicts stationary wavelet coefficients rather than directly regressing RGB values.<n>Wavelet-domain neural super-resolution provides a principled and efficient path toward higher-quality real-time rendering.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We investigate the use of wavelet-space feature decomposition in neural super-resolution for rendering pipelines. Building on recent neural upscaling frameworks, we introduce a formulation that predicts stationary wavelet coefficients rather than directly regressing RGB values. This frequency-aware decomposition separates low- and high-frequency components, enabling sharper texture recovery and reducing blur in challenging regions. Unlike conventional wavelet transforms, our use of the stationary wavelet transform (SWT) preserves spatial alignment across subbands, allowing the network to integrate G-buffer attributes and temporally warped history frames in a shift-invariant manner. The predicted coefficients are recombined through inverse wavelet synthesis, producing resolution-consistent reconstructions across arbitrary scale factors. We conduct extensive evaluations and ablations, showing that incorporating SWT improves both fidelity and perceptual quality with only modest overhead, while remaining compatible with standard rendering architectures. Taken together, our results suggest that wavelet-domain neural super-resolution provides a principled and efficient path toward higher-quality real-time rendering, with broader implications for neural rendering and graphics applications.

Related papers

• FreNBRDF: A Frequency-Rectified Neural Material Representation [2.915959924872987]
  We introduce FreNBRDF, a frequency-rectified neural material representation.<n>We propose a novel frequency-rectified loss, derived from a frequency analysis of neural materials, and incorporate it into a generalizable and adaptive reconstruction and editing pipeline.
  arXiv  Detail & Related papers  (2025-07-01T06:48:50Z)
• FADPNet: Frequency-Aware Dual-Path Network for Face Super-Resolution [70.61549422952193]
  Face super-resolution (FSR) under limited computational costs remains an open problem.<n>Existing approaches typically treat all facial pixels equally, resulting in suboptimal allocation of computational resources.<n>We propose FADPNet, a Frequency-Aware Dual-Path Network that decomposes facial features into low- and high-frequency components.
  arXiv  Detail & Related papers  (2025-06-17T02:33:42Z)
• SpINRv2: Implicit Neural Representation for Passband FMCW Radars [0.15193212081459279]
  We present SpINRv2, a neural framework for high-fidelity volumetric reconstruction using Frequency-Modulated Continuous-Wave radar.<n>Our core contribution is a fully differentiable frequency-domain forward model that captures the complex radar response using closed-form synthesis.<n>We introduce sparsity and regularization to disambiguate sub-bin ambiguities that arise at fine range resolutions.
  arXiv  Detail & Related papers  (2025-06-09T19:21:27Z)
• Freqformer: Image-Demoiréing Transformer via Efficient Frequency Decomposition [83.40450475728792]
  We present Freqformer, a Transformer-based framework specifically designed for image demoir'eing through targeted frequency separation.<n>Our method performs an effective frequency decomposition that explicitly splits moir'e patterns into high-frequency spatially-localized textures and low-frequency scale-robust color distortions.<n>Experiments on various demoir'eing benchmarks demonstrate that Freqformer achieves state-of-the-art performance with a compact model size.
  arXiv  Detail & Related papers  (2025-05-25T12:23:10Z)
• Neural BRDF Importance Sampling by Reparameterization [43.47134538369479]
  This paper introduces a re parameterization-based formulation of neural BRDF importance sampling.<n>It seamlessly integrates into the standard rendering pipeline with precise generation of BRDF samples.<n>Our method achieves the best variance reduction in neural BRDF renderings while maintaining high inference speeds.
  arXiv  Detail & Related papers  (2025-05-13T22:23:55Z)
• Wavelet-based Variational Autoencoders for High-Resolution Image Generation [0.0]
  Variational Autoencoders (VAEs) are powerful generative models capable of learning compact latent representations.<n>In this paper, we explore a novel wavelet-based approach (Wavelet-VAE) in which the latent space is constructed using multi-scale Haar wavelet coefficients.
  arXiv  Detail & Related papers  (2025-04-16T13:51:41Z)
• SpINR: Neural Volumetric Reconstruction for FMCW Radars [0.15193212081459279]
  We introduce SpINR, a novel framework for volumetric reconstruction using Frequency-Modulated Continuous-Wave (FMCW) radar data.<n>We demonstrate that SpINR significantly outperforms classical backprojection methods and existing learning-based approaches.
  arXiv  Detail & Related papers  (2025-03-30T04:44:57Z)
• Dual-domain Modulation Network for Lightweight Image Super-Resolution [26.992373105057684]
  Lightweight image super-resolution (SR) aims to reconstruct high-resolution images from low-resolution images under limited computational costs.<n>Existing frequency-based SR methods cannot balance the reconstruction of overall structures and high-frequency parts.<n>We show that introducing both wavelet and Fourier information allows our model to consider both high-frequency features and overall SR structure reconstruction while reducing costs.
  arXiv  Detail & Related papers  (2025-03-13T04:59:46Z)
• Spatial Annealing for Efficient Few-shot Neural Rendering [73.49548565633123]
  We introduce an accurate and efficient few-shot neural rendering method named textbfSpatial textbfAnnealing regularized textbfNeRF (textbfSANeRF)<n>By adding merely one line of code, SANeRF delivers superior rendering quality and much faster reconstruction speed compared to current few-shot neural rendering methods.
  arXiv  Detail & Related papers  (2024-06-12T02:48:52Z)
• VoxNeRF: Bridging Voxel Representation and Neural Radiance Fields for Enhanced Indoor View Synthesis [73.50359502037232]
  VoxNeRF is a novel approach to enhance the quality and efficiency of neural indoor reconstruction and novel view synthesis.<n>We propose an efficient voxel-guided sampling technique that allocates computational resources to selectively the most relevant segments of rays.<n>Our approach is validated with extensive experiments on ScanNet and ScanNet++.
  arXiv  Detail & Related papers  (2023-11-09T11:32:49Z)
• Neural Poisson Surface Reconstruction: Resolution-Agnostic Shape Reconstruction from Point Clouds [53.02191521770926]
  We introduce Neural Poisson Surface Reconstruction (nPSR), an architecture for shape reconstruction that addresses the challenge of recovering 3D shapes from points. nPSR exhibits two main advantages: First, it enables efficient training on low-resolution data while achieving comparable performance at high-resolution evaluation. Overall, the neural Poisson surface reconstruction not only improves upon the limitations of classical deep neural networks in shape reconstruction but also achieves superior results in terms of reconstruction quality, running time, and resolution agnosticism.
  arXiv  Detail & Related papers  (2023-08-03T13:56:07Z)
• Spatial-Frequency U-Net for Denoising Diffusion Probabilistic Models [89.76587063609806]
  We study the denoising diffusion probabilistic model (DDPM) in wavelet space, instead of pixel space, for visual synthesis. By explicitly modeling the wavelet signals, we find our model is able to generate images with higher quality on several datasets.
  arXiv  Detail & Related papers  (2023-07-27T06:53:16Z)
• Machine learning for phase-resolved reconstruction of nonlinear ocean wave surface elevations from sparse remote sensing data [37.69303106863453]
  We propose a novel approach for phase-resolved wave surface reconstruction using neural networks. Our approach utilizes synthetic yet highly realistic training data on uniform one-dimensional grids.
  arXiv  Detail & Related papers  (2023-05-18T12:30:26Z)
• Synthetic Wave-Geometric Impulse Responses for Improved Speech Dereverberation [69.1351513309953]
  We show that accurately simulating the low-frequency components of Room Impulse Responses (RIRs) is important to achieving good dereverberation. We demonstrate that speech dereverberation models trained on hybrid synthetic RIRs outperform models trained on RIRs generated by prior geometric ray tracing methods.
  arXiv  Detail & Related papers  (2022-12-10T20:15:23Z)
• FreqNet: A Frequency-domain Image Super-Resolution Network with Dicrete Cosine Transform [16.439669339293747]
  Single image super-resolution(SISR) is an ill-posed problem that aims to obtain high-resolution (HR) output from low-resolution (LR) input. Despite the high peak signal-to-noise ratios(PSNR) results, it is difficult to determine whether the model correctly adds desired high-frequency details. We propose FreqNet, an intuitive pipeline from the frequency domain perspective, to solve this problem.
  arXiv  Detail & Related papers  (2021-11-21T11:49:12Z)
• Universal Face Restoration With Memorized Modulation [73.34750780570909]
  This paper proposes a Restoration with Memorized Modulation (RMM) framework for universal Blind Face Restoration (BFR) We apply random noise as well as unsupervised wavelet memory to adaptively modulate the face-enhancement generator. Experimental results show the superiority of the proposed method compared with the state-of-the-art methods, and a good generalization in the wild.
  arXiv  Detail & Related papers  (2021-10-03T15:55:07Z)
• Fourier Space Losses for Efficient Perceptual Image Super-Resolution [131.50099891772598]
  We show that it is possible to improve the performance of a recently introduced efficient generator architecture solely with the application of our proposed loss functions. We show that our losses' direct emphasis on the frequencies in Fourier-space significantly boosts the perceptual image quality. The trained generator achieves comparable results with and is 2.4x and 48x faster than state-of-the-art perceptual SR methods RankSRGAN and SRFlow respectively.
  arXiv  Detail & Related papers  (2021-06-01T20:34:52Z)

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.