Learning Arbitrary-Scale RAW Image Downscaling with Wavelet-based Recurrent Reconstruction

• URL: http://arxiv.org/abs/2507.23219v1
• Date: Thu, 31 Jul 2025 03:17:10 GMT
• Title: Learning Arbitrary-Scale RAW Image Downscaling with Wavelet-based Recurrent Reconstruction
• Authors: Yang Ren, Hai Jiang, Wei Li, Menglong Yang, Heng Zhang, Zehua Sheng, Qingsheng Ye, Shuaicheng Liu,
• Abstract summary: We propose a wavelet-based recurrent reconstruction framework to fulfill arbitrary-scale RAW image downscaling.<n>We introduce the Realistic Non-Integer RAW Downscaling (Real-NIRD) dataset, featuring a non-integer downscaling factor of 1.3$times$.<n>Our method outperforms existing state-of-the-art competitors both quantitatively and visually.
• Score: 31.56360631121638
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Image downscaling is critical for efficient storage and transmission of high-resolution (HR) images. Existing learning-based methods focus on performing downscaling within the sRGB domain, which typically suffers from blurred details and unexpected artifacts. RAW images, with their unprocessed photonic information, offer greater flexibility but lack specialized downscaling frameworks. In this paper, we propose a wavelet-based recurrent reconstruction framework that leverages the information lossless attribute of wavelet transformation to fulfill the arbitrary-scale RAW image downscaling in a coarse-to-fine manner, in which the Low-Frequency Arbitrary-Scale Downscaling Module (LASDM) and the High-Frequency Prediction Module (HFPM) are proposed to preserve structural and textural integrity of the reconstructed low-resolution (LR) RAW images, alongside an energy-maximization loss to align high-frequency energy between HR and LR domain. Furthermore, we introduce the Realistic Non-Integer RAW Downscaling (Real-NIRD) dataset, featuring a non-integer downscaling factor of 1.3$\times$, and incorporate it with publicly available datasets with integer factors (2$\times$, 3$\times$, 4$\times$) for comprehensive benchmarking arbitrary-scale image downscaling purposes. Extensive experiments demonstrate that our method outperforms existing state-of-the-art competitors both quantitatively and visually. The code and dataset will be released at https://github.com/RenYangSCU/ASRD.

Related papers

• Plug-and-Play Tri-Branch Invertible Block for Image Rescaling [11.457556028893329]
  High-resolution (HR) images are commonly downscaled to low-resolution (LR) to reduce bandwidth, followed by upscaling to restore their original details.<n>Recent advancements in image rescaling algorithms have employed invertible neural networks (INNs) to create a unified framework for downscaling and upscaling.<n>We propose a plug-and-play tri-branch invertible block (T-InvBlocks) that decomposes the low-frequency branch into luminance (Y) and chrominance (CbCr) components.
  arXiv  Detail & Related papers  (2024-12-18T05:14:13Z)
• Unveiling Hidden Details: A RAW Data-Enhanced Paradigm for Real-World Super-Resolution [56.98910228239627]
  Real-world image super-resolution (Real SR) aims to generate high-fidelity, detail-rich high-resolution (HR) images from low-resolution (LR) counterparts. Existing Real SR methods primarily focus on generating details from the LR RGB domain, often leading to a lack of richness or fidelity in fine details. We pioneer the use of details hidden in RAW data to complement existing RGB-only methods, yielding superior outputs.
  arXiv  Detail & Related papers  (2024-11-16T13:29:50Z)
• Timestep-Aware Diffusion Model for Extreme Image Rescaling [47.89362819768323]
  We propose a novel framework called Timestep-Aware Diffusion Model (TADM) for extreme image rescaling.<n>TADM performs rescaling operations in the latent space of a pre-trained autoencoder.<n>It effectively leverages powerful natural image priors learned by a pre-trained text-to-image diffusion model.
  arXiv  Detail & Related papers  (2024-08-17T09:51:42Z)
• DGNet: Dynamic Gradient-Guided Network for Water-Related Optics Image Enhancement [77.0360085530701]
  Underwater image enhancement (UIE) is a challenging task due to the complex degradation caused by underwater environments. Previous methods often idealize the degradation process, and neglect the impact of medium noise and object motion on the distribution of image features. Our approach utilizes predicted images to dynamically update pseudo-labels, adding a dynamic gradient to optimize the network's gradient space.
  arXiv  Detail & Related papers  (2023-12-12T06:07:21Z)
• RBSR: Efficient and Flexible Recurrent Network for Burst Super-Resolution [57.98314517861539]
  Burst super-resolution (BurstSR) aims at reconstructing a high-resolution (HR) image from a sequence of low-resolution (LR) and noisy images. In this paper, we suggest fusing cues frame-by-frame with an efficient and flexible recurrent network.
  arXiv  Detail & Related papers  (2023-06-30T12:14:13Z)
• Self-Asymmetric Invertible Network for Compression-Aware Image Rescaling [6.861753163565238]
  In real-world applications, most images are compressed for transmission. We propose the Self-Asymmetric Invertible Network (SAIN) for compression-aware image rescaling.
  arXiv  Detail & Related papers  (2023-03-04T08:33:46Z)
• DCS-RISR: Dynamic Channel Splitting for Efficient Real-world Image Super-Resolution [15.694407977871341]
  Real-world image super-resolution (RISR) has received increased focus for improving the quality of SR images under unknown complex degradation. Existing methods rely on the heavy SR models to enhance low-resolution (LR) images of different degradation levels. We propose a novel Dynamic Channel Splitting scheme for efficient Real-world Image Super-Resolution, termed DCS-RISR.
  arXiv  Detail & Related papers  (2022-12-15T04:34:57Z)
• Hierarchical Conditional Flow: A Unified Framework for Image Super-Resolution and Image Rescaling [139.25215100378284]
  We propose a hierarchical conditional flow (HCFlow) as a unified framework for image SR and image rescaling. HCFlow learns a mapping between HR and LR image pairs by modelling the distribution of the LR image and the rest high-frequency component simultaneously. To further enhance the performance, other losses such as perceptual loss and GAN loss are combined with the commonly used negative log-likelihood loss in training.
  arXiv  Detail & Related papers  (2021-08-11T16:11:01Z)
• Deep Burst Super-Resolution [165.90445859851448]
  We propose a novel architecture for the burst super-resolution task. Our network takes multiple noisy RAW images as input, and generates a denoised, super-resolved RGB image as output. In order to enable training and evaluation on real-world data, we additionally introduce the BurstSR dataset.
  arXiv  Detail & Related papers  (2021-01-26T18:57:21Z)
• Frequency Consistent Adaptation for Real World Super Resolution [64.91914552787668]
  We propose a novel Frequency Consistent Adaptation (FCA) that ensures the frequency domain consistency when applying Super-Resolution (SR) methods to the real scene. We estimate degradation kernels from unsupervised images and generate the corresponding Low-Resolution (LR) images. Based on the domain-consistent LR-HR pairs, we train easy-implemented Convolutional Neural Network (CNN) SR models.
  arXiv  Detail & Related papers  (2020-12-18T08:25:39Z)
• Deep Generative Adversarial Residual Convolutional Networks for Real-World Super-Resolution [31.934084942626257]
  We propose a deep Super-Resolution Residual Convolutional Generative Adversarial Network (SRResCGAN) It follows the real-world degradation settings by adversarial training the model with pixel-wise supervision in the HR domain from its generated LR counterpart. The proposed network exploits the residual learning by minimizing the energy-based objective function with powerful image regularization and convex optimization techniques.
  arXiv  Detail & Related papers  (2020-05-03T00:12:38Z)

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.