From Zero to Detail: Deconstructing Ultra-High-Definition Image Restoration from Progressive Spectral Perspective

• URL: http://arxiv.org/abs/2503.13165v1
• Date: Mon, 17 Mar 2025 13:39:51 GMT
• Title: From Zero to Detail: Deconstructing Ultra-High-Definition Image Restoration from Progressive Spectral Perspective
• Authors: Chen Zhao, Zhizhou Chen, Yunzhe Xu, Enxuan Gu, Jian Li, Zili Yi, Qian Wang, Jian Yang, Ying Tai,
• Abstract summary: ERR comprises three collaborative sub-networks: the zero-frequency enhancer (ZFE), the low-frequency restorer (LFR), and the high-frequency refiner (HFR)<n>Specifically, the ZFE integrates global priors to learn global mapping, while the LFR restores low-frequency information, emphasizing reconstruction of coarse-grained content.<n>The HFR employs our designed frequency-windowed kolmogorov-arnold networks (FW-KAN) to refine textures and details, producing high-quality image restoration.
• Score: 38.94762644896294
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Ultra-high-definition (UHD) image restoration faces significant challenges due to its high resolution, complex content, and intricate details. To cope with these challenges, we analyze the restoration process in depth through a progressive spectral perspective, and deconstruct the complex UHD restoration problem into three progressive stages: zero-frequency enhancement, low-frequency restoration, and high-frequency refinement. Building on this insight, we propose a novel framework, ERR, which comprises three collaborative sub-networks: the zero-frequency enhancer (ZFE), the low-frequency restorer (LFR), and the high-frequency refiner (HFR). Specifically, the ZFE integrates global priors to learn global mapping, while the LFR restores low-frequency information, emphasizing reconstruction of coarse-grained content. Finally, the HFR employs our designed frequency-windowed kolmogorov-arnold networks (FW-KAN) to refine textures and details, producing high-quality image restoration. Our approach significantly outperforms previous UHD methods across various tasks, with extensive ablation studies validating the effectiveness of each component. The code is available at \href{https://github.com/NJU-PCALab/ERR}{here}.

Related papers

• FiDeSR: High-Fidelity and Detail-Preserving One-Step Diffusion Super-Resolution [11.03986460753769]
  We propose FiDeSR, a high-fidelity and detail-preserving one-step diffusion super-resolution framework.<n>During training, we introduce a detail-aware weighting strategy that adaptively emphasizes regions where the model exhibits higher prediction errors.<n>During inference, low- and high-frequency adaptive enhancers further refine the reconstruction without requiring model retraining.
  arXiv  Detail & Related papers  (2026-03-03T07:34:49Z)
• One-Shot Refiner: Boosting Feed-forward Novel View Synthesis via One-Step Diffusion [57.824020826432815]
  We present a novel framework for high-fidelity novel view synthesis (NVS) from sparse images.<n>We design a Dual-Domain Detail Perception Module, which enables handling high-resolution images without being limited by the ViT backbone.<n>We develop a feature-guided diffusion network, which can preserve high-frequency details during the restoration process.
  arXiv  Detail & Related papers  (2026-01-20T17:11:55Z)
• Latent Harmony: Synergistic Unified UHD Image Restoration via Latent Space Regularization and Controllable Refinement [89.99237142387655]
  We introduce LH-VAE, which enhances semantic robustness through visual semantic constraints and progressive degradations.<n>Latent Harmony is a two-stage framework that redefines VAEs for UHD restoration by jointly regularizing the latent space and enforcing high-frequency-aware reconstruction.<n>Experiments show Latent Harmony achieves state-of-the-art performance across UHD and standard-resolution tasks, effectively balancing efficiency, perceptual quality, and reconstruction accuracy.
  arXiv  Detail & Related papers  (2025-10-09T08:54:26Z)
• Progressive Flow-inspired Unfolding for Spectral Compressive Imaging [11.638690628451647]
  Coded aperture snapshot spectral imaging (CASSI) retrieves a 3D hyperspectral image (HSI) from a single 2D compressed measurement.<n>Recent deep unfolding networks (DUNs) have achieved the state of the art in CASSI reconstruction.<n>Inspired by diffusion trajectories and flow matching, we propose a novel trajectory-controllable unfolding framework.
  arXiv  Detail & Related papers  (2025-09-15T16:10:50Z)
• RTR-GS: 3D Gaussian Splatting for Inverse Rendering with Radiance Transfer and Reflection [16.81533668816093]
  RTR-GS is a novel inverse rendering framework capable of robustly rendering objects with arbitrary reflectance properties, decomposing BRDF and lighting, and delivering credible relighting results.<n>We show that our method enhances novel view synthesis, normal estimation, decomposition, and relighting while maintaining efficient training inference process.
  arXiv  Detail & Related papers  (2025-07-10T13:13:08Z)
• 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)
• HS-SLAM: Hybrid Representation with Structural Supervision for Improved Dense SLAM [38.82194947459594]
  NeRF-based SLAM has recently achieved promising results in tracking and reconstruction. We present HS-SLAM to tackle these problems. We propose a hybrid encoding network that combines the complementary strengths of hash-grid, tri-planes, and one-blob.
  arXiv  Detail & Related papers  (2025-03-27T17:59:54Z)
• 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)
• HFGS: 4D Gaussian Splatting with Emphasis on Spatial and Temporal High-Frequency Components for Endoscopic Scene Reconstruction [13.012536387221669]
  Robot-assisted minimally invasive surgery benefits from enhancing dynamic scene reconstruction, as it improves surgical outcomes. NeRF have been effective in scene reconstruction, but their slow inference speeds and lengthy training durations limit their applicability. 3D Gaussian Splatting (3D-GS) based methods have emerged as a recent trend, offering rapid inference capabilities and superior 3D quality. In this paper, we propose HFGS, a novel approach for deformable endoscopic reconstruction that addresses these challenges from spatial and temporal frequency perspectives.
  arXiv  Detail & Related papers  (2024-05-28T06:48:02Z)
• RaFE: Generative Radiance Fields Restoration [38.602849644666165]
  NeRF (Neural Radiance Fields) has demonstrated tremendous potential in novel view synthesis and 3D reconstruction. Previous methods for NeRF restoration are tailored for specific degradation type, ignoring the generality of restoration. We propose a generic radiance fields restoration pipeline, named RaFE, which applies to various types of degradations.
  arXiv  Detail & Related papers  (2024-04-04T17:59:50Z)
• NeRF-VPT: Learning Novel View Representations with Neural Radiance Fields via View Prompt Tuning [63.39461847093663]
  We propose NeRF-VPT, an innovative method for novel view synthesis to address these challenges. Our proposed NeRF-VPT employs a cascading view prompt tuning paradigm, wherein RGB information gained from preceding rendering outcomes serves as instructive visual prompts for subsequent rendering stages. NeRF-VPT only requires sampling RGB data from previous stage renderings as priors at each training stage, without relying on extra guidance or complex techniques.
  arXiv  Detail & Related papers  (2024-03-02T22:08:10Z)
• VQ-NeRF: Vector Quantization Enhances Implicit Neural Representations [25.88881764546414]
  VQ-NeRF is an efficient pipeline for enhancing implicit neural representations via vector quantization. We present an innovative multi-scale NeRF sampling scheme that concurrently optimize the NeRF model at both compressed and original scales. We incorporate a semantic loss function to improve the geometric fidelity and semantic coherence of our 3D reconstructions.
  arXiv  Detail & Related papers  (2023-10-23T01:41:38Z)
• VolRecon: Volume Rendering of Signed Ray Distance Functions for Generalizable Multi-View Reconstruction [64.09702079593372]
  VolRecon is a novel generalizable implicit reconstruction method with Signed Ray Distance Function (SRDF) On DTU dataset, VolRecon outperforms SparseNeuS by about 30% in sparse view reconstruction and achieves comparable accuracy as MVSNet in full view reconstruction.
  arXiv  Detail & Related papers  (2022-12-15T18:59:54Z)
• Over-and-Under Complete Convolutional RNN for MRI Reconstruction [57.95363471940937]
  Recent deep learning-based methods for MR image reconstruction usually leverage a generic auto-encoder architecture. We propose an Over-and-Under Complete Convolu?tional Recurrent Neural Network (OUCR), which consists of an overcomplete and an undercomplete Convolutional Recurrent Neural Network(CRNN) The proposed method achieves significant improvements over the compressed sensing and popular deep learning-based methods with less number of trainable parameters.
  arXiv  Detail & Related papers  (2021-06-16T15:56:34Z)
• Non-local Meets Global: An Iterative Paradigm for Hyperspectral Image Restoration [66.68541690283068]
  We propose a unified paradigm combining the spatial and spectral properties for hyperspectral image restoration. The proposed paradigm enjoys performance superiority from the non-local spatial denoising and light computation complexity. Experiments on HSI denoising, compressed reconstruction, and inpainting tasks, with both simulated and real datasets, demonstrate its superiority.
  arXiv  Detail & Related papers  (2020-10-24T15:53:56Z)
• Hyperspectral Image Super-resolution via Deep Progressive Zero-centric Residual Learning [62.52242684874278]
  Cross-modality distribution of spatial and spectral information makes the problem challenging. We propose a novel textitlightweight deep neural network-based framework, namely PZRes-Net. Our framework learns a high resolution and textitzero-centric residual image, which contains high-frequency spatial details of the scene.
  arXiv  Detail & Related papers  (2020-06-18T06:32:11Z)

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.