RPBA-Net: An Interpretable Residual Pyramid Bilateral Affine Network for RAW-Domain ISP Enhancement

• URL: http://arxiv.org/abs/2605.03626v1
• Date: Tue, 05 May 2026 10:55:31 GMT
• Title: RPBA-Net: An Interpretable Residual Pyramid Bilateral Affine Network for RAW-Domain ISP Enhancement
• Abstract summary: RPBA-Net is an interpretable residual pyramid bilateral affine network for RAW-domain ISP enhancement.<n>It performs residual affine base reconstruction by estimating a base RGB representation and learning identity-guided residual affine corrections.<n>It further builds pyramid bilateral affine grids and combines guide-driven autoregressive adaptive slicing with adaptive cross-layer fusion.
• Score: 24.32028637382679
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: To address module fragmentation, uninterpretable mappings, and deployment constraints in RAW-domain demosaicing, color correction, and detail enhancement, this paper proposes RPBA-Net, an interpretable residual pyramid bilateral affine network for RAW-domain ISP enhancement. Given packed RAW as input, the method performs residual affine base reconstruction by estimating a base RGB representation and learning identity-guided residual affine corrections, thereby unifying demosaicing and enhancement. It further builds pyramid bilateral affine grids and combines guide-driven autoregressive adaptive slicing with adaptive cross-layer fusion to hierarchically model global tone restoration and local texture enhancement. In addition, smoothness, cross-scale consistency, and magnitude regularization terms are introduced to improve model stability, controllability, and structural interpretability. Extensive experiments demonstrate that RPBA-Net surpasses representative RAW-to-sRGB methods and achieves state-of-the-art performance in reconstruction fidelity and perceptual quality, while maintaining low model complexity and strong deployment potential for mobile and embedded platforms.

Related papers

• Two-Scale Localized PCA-Net: Coarse-Global and Local-Residual Representations for Artifact-Reduced PDE Operator Learning [0.21847754147782886]
  Two-Scale Localized PCA-Net decomposes the solution into a coarse-global component and local residual corrections.<n>It substantially reduces reconstruction error and visible block artifacts relative to plain and overlap-based localized PCA-Net.
  arXiv  Detail & Related papers  (2026-09-07T22:36:24Z)
• Improving Visual Representation Alignment Generation with GRPO [51.071351994330605]
  diffusion transformers have demonstrated strong image synthesis capabilities but remain inefficient to train due to weak alignment.<n>We propose VRPO, a reinforcement-based optimization strategy that replaces REPA's static alignment loss with a generative representation policy optimization objective.<n>Our VRPO-driven training seamlessly integrates into diffusion transformers, introducing negligible cost and preserving full compatibility with SiT and DiT architectures.
  arXiv  Detail & Related papers  (2026-05-30T07:21:40Z)
• Beyond Point-Wise Matching: Structural Representation Alignment for Accelerating Diffusion Transformers [93.3976834364707]
  We propose sREPA, a structural REPresentation Alignment framework to enforce consistency in the relational geometry of feature maps.<n>By encouraging the model to internalize holistic spatial layouts and structural correlations from pre-trained features, sREPA achieves faster and more stable convergence.
  arXiv  Detail & Related papers  (2026-05-16T12:01:04Z)
• HIR-ALIGN: Enhancing Hyperspectral Image Restoration via Diffusion-Based Data Generation [50.46910397782266]
  Hyperspectral image (HSI) restoration is crucial for reliable analysis, as real HSIs suffer from degradations like noise, blur, and resolution loss.<n>We present HIR-ALIGN, a plug-and-play target-adaptive augmentation framework that enhances hyperspectral image restoration by augmenting limited training images with synthetic data that closely matches the target distribution using no extra data.
  arXiv  Detail & Related papers  (2026-05-13T14:14:13Z)
• DegBins: Degradation-Driven Binning for Depth Super-Resolution [57.61783461543096]
  DegBins is a novel DSR framework that leverages degradation-driven binning to adaptively enhance residual modeling.<n>DegBins consistently outperforms existing state-of-the-art methods in terms of accuracy, robustness, and generalization.
  arXiv  Detail & Related papers  (2026-05-10T16:17:11Z)
• Efficient Image Super-Resolution with Multi-Scale Spatial Adaptive Attention Networks [3.4782736103257323]
  This paper introduces a lightweight image super-resolution (SR) network, termed the Multi-scale Spatial Adaptive Attention Network (MSAAN)<n>The core of our approach is a novel Multi-scale Spatial Adaptive Attention Module (MSAA), designed to jointly model fine-grained local details and long-range contextual dependencies.
  arXiv  Detail & Related papers  (2026-02-22T07:47:39Z)
• Bidirectional Reward-Guided Diffusion for Real-World Image Super-Resolution [79.35296000454694]
  Diffusion-based super-resolution can synthesize rich details, but models trained on synthetic paired data often fail on real-world LR images.<n>We propose Bird-SR, a reward-guided diffusion framework that formulates super-resolution as trajectory-level preference optimization.<n>Experiments on real-world SR benchmarks demonstrate that Bird-SR consistently outperforms state-of-the-art methods in perceptual quality.
  arXiv  Detail & Related papers  (2026-02-05T19:21:45Z)
• UniMRSeg: Unified Modality-Relax Segmentation via Hierarchical Self-Supervised Compensation [104.59740403500132]
  Multi-modal image segmentation faces real-world deployment challenges from incomplete/corrupted modalities degrading performance.<n>We propose a unified modality-relax segmentation network (UniMRSeg) through hierarchical self-supervised compensation (HSSC)<n>Our approach hierarchically bridges representation gaps between complete and incomplete modalities across input, feature and output levels.
  arXiv  Detail & Related papers  (2025-09-19T17:29:25Z)
• Unfolding Framework with Complex-Valued Deformable Attention for High-Quality Computer-Generated Hologram Generation [15.017958264826511]
  Computer-generated holography (CGH) has gained wide attention with deep learning-based algorithms.<n>In this paper, we propose a Deep Unfolding Network (DUN) that decomposes gradient descent into two modules.
  arXiv  Detail & Related papers  (2025-08-29T14:21:22Z)
• RemixFusion: Residual-based Mixed Representation for Large-scale Online RGB-D Reconstruction [22.84127950120426]
  RemixFusion is a novel residual-based mixed representation for scene reconstruction and camera pose estimation.<n>In particular, we propose a residual-based map representation comprised of an explicit coarse TSDF grid and an implicit neural module.<n>Our method surpasses all state-of-the-art ones, including those based either on explicit or implicit representations.
  arXiv  Detail & Related papers  (2025-07-23T15:27:09Z)
• RealRep: Generalized SDR-to-HDR Conversion via Attribute-Disentangled Representation Learning [51.19027658873778]
  High-Dynamic-Range Wide-Color-Gamut (WCG) technology is becoming increasingly widespread, driving a growing need for converting Standard Dynamic Range (SDR) content to HDR.<n>Existing methods rely on fixed tone mapping operators, which struggle to handle the diverse appearances and degradations commonly present in real-world SDR content.<n>We propose a generalized SDR-to- attribute framework that enhances robustness by learning construct-disentangled representations.
  arXiv  Detail & Related papers  (2025-05-12T08:08:58Z)
• RUN: Reversible Unfolding Network for Concealed Object Segmentation [61.13528324971598]
  reversible strategies across both mask and RGB domains.<n>We propose the Reversible Unfolding Network (RUN), which applies reversible strategies across both mask and RGB domains.
  arXiv  Detail & Related papers  (2025-01-30T22:19:15Z)
• Iterative Soft Shrinkage Learning for Efficient Image Super-Resolution [91.3781512926942]
  Image super-resolution (SR) has witnessed extensive neural network designs from CNN to transformer architectures. This work investigates the potential of network pruning for super-resolution iteration to take advantage of off-the-shelf network designs and reduce the underlying computational overhead. We propose a novel Iterative Soft Shrinkage-Percentage (ISS-P) method by optimizing the sparse structure of a randomly network at each and tweaking unimportant weights with a small amount proportional to the magnitude scale on-the-fly.
  arXiv  Detail & Related papers  (2023-03-16T21:06:13Z)

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.