AFUNet: Cross-Iterative Alignment-Fusion Synergy for HDR Reconstruction via Deep Unfolding Paradigm

• URL: http://arxiv.org/abs/2506.23537v2
• Date: Sat, 05 Jul 2025 15:16:34 GMT
• Title: AFUNet: Cross-Iterative Alignment-Fusion Synergy for HDR Reconstruction via Deep Unfolding Paradigm
• Authors: Xinyue Li, Zhangkai Ni, Wenhan Yang,
• Abstract summary: Existing learning-based methods effectively reconstruct HDR images from multi-exposure LDR inputs with extended dynamic range and improved detail.<n>We propose the cross-iterative Alignment and Fusion deep Unfolding Network (AFUNet) to address these limitations.<n>Our method formulates multi-exposure HDR reconstruction from a Maximum A Posteriori (MAP) estimation perspective.
• Score: 41.09028235123695
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Existing learning-based methods effectively reconstruct HDR images from multi-exposure LDR inputs with extended dynamic range and improved detail, but they rely more on empirical design rather than theoretical foundation, which can impact their reliability. To address these limitations, we propose the cross-iterative Alignment and Fusion deep Unfolding Network (AFUNet), where HDR reconstruction is systematically decoupled into two interleaved subtasks -- alignment and fusion -- optimized through alternating refinement, achieving synergy between the two subtasks to enhance the overall performance. Our method formulates multi-exposure HDR reconstruction from a Maximum A Posteriori (MAP) estimation perspective, explicitly incorporating spatial correspondence priors across LDR images and naturally bridging the alignment and fusion subproblems through joint constraints. Building on the mathematical foundation, we reimagine traditional iterative optimization through unfolding -- transforming the conventional solution process into an end-to-end trainable AFUNet with carefully designed modules that work progressively. Specifically, each iteration of AFUNet incorporates an Alignment-Fusion Module (AFM) that alternates between a Spatial Alignment Module (SAM) for alignment and a Channel Fusion Module (CFM) for adaptive feature fusion, progressively bridging misaligned content and exposure discrepancies. Extensive qualitative and quantitative evaluations demonstrate AFUNet's superior performance, consistently surpassing state-of-the-art methods. Our code is available at: https://github.com/eezkni/AFUNet

Related papers

• UniFuse: A Unified All-in-One Framework for Multi-Modal Medical Image Fusion Under Diverse Degradations and Misalignments [20.348314952092792]
  Current multimodal medical image fusion typically assumes that source images are of high quality and perfectly aligned at the pixel level.<n>By embedding a degradation-aware prompt learning module, UniFuse seamlessly integrates multi-directional information from input images.<n>We propose a Universal Feature Restoration & Fusion module, incorporating the Adaptive LoRA Synergistic Network (ALSN) based on LoRA principles.
  arXiv  Detail & Related papers  (2025-06-28T02:44:22Z)
• A Fusion-Guided Inception Network for Hyperspectral Image Super-Resolution [4.487807378174191]
  We propose a single-image super-resolution model called the Fusion-Guided Inception Network (FGIN)<n>Specifically, we first employ a spectral-spatial fusion module to effectively integrate spectral and spatial information.<n>An Inception-like hierarchical feature extraction strategy is used to capture multiscale spatial dependencies.<n>To further enhance reconstruction quality, we incorporate an optimized upsampling module that combines bilinear with depthwise separable convolutions.
  arXiv  Detail & Related papers  (2025-05-06T11:15:59Z)
• Improving Bracket Image Restoration and Enhancement with Flow-guided Alignment and Enhanced Feature Aggregation [32.69740459810521]
  We present the IREANet, which improves the multiple exposure and aggregation with a Flow-guide Feature Alignment Module (FFAM) and an Enhanced Feature Aggregation Module (EFAM) Our experimental evaluations demonstrate that the proposed IREANet shows state-of-the-art performance compared with previous methods.
  arXiv  Detail & Related papers  (2024-04-16T07:46:55Z)
• Improving Misaligned Multi-modality Image Fusion with One-stage Progressive Dense Registration [67.23451452670282]
  Misalignments between multi-modality images pose challenges in image fusion. We propose a Cross-modality Multi-scale Progressive Dense Registration scheme. This scheme accomplishes the coarse-to-fine registration exclusively using a one-stage optimization.
  arXiv  Detail & Related papers  (2023-08-22T03:46:24Z)
• Enhancing Low-light Light Field Images with A Deep Compensation Unfolding Network [52.77569396659629]
  This paper presents the deep compensation network unfolding (DCUNet) for restoring light field (LF) images captured under low-light conditions. The framework uses the intermediate enhanced result to estimate the illumination map, which is then employed in the unfolding process to produce a new enhanced result. To properly leverage the unique characteristics of LF images, this paper proposes a pseudo-explicit feature interaction module.
  arXiv  Detail & Related papers  (2023-08-10T07:53:06Z)
• Searching a Compact Architecture for Robust Multi-Exposure Image Fusion [55.37210629454589]
  Two major stumbling blocks hinder the development, including pixel misalignment and inefficient inference. This study introduces an architecture search-based paradigm incorporating self-alignment and detail repletion modules for robust multi-exposure image fusion. The proposed method outperforms various competitive schemes, achieving a noteworthy 3.19% improvement in PSNR for general scenarios and an impressive 23.5% enhancement in misaligned scenarios.
  arXiv  Detail & Related papers  (2023-05-20T17:01:52Z)
• Light Field Reconstruction via Deep Adaptive Fusion of Hybrid Lenses [67.01164492518481]
  This paper explores the problem of reconstructing high-resolution light field (LF) images from hybrid lenses. We propose a novel end-to-end learning-based approach, which can comprehensively utilize the specific characteristics of the input. Our framework could potentially decrease the cost of high-resolution LF data acquisition and benefit LF data storage and transmission.
  arXiv  Detail & Related papers  (2021-02-14T06:44:47Z)
• Deep Selective Combinatorial Embedding and Consistency Regularization for Light Field Super-resolution [93.95828097088608]
  Light field (LF) images acquired by hand-held devices usually suffer from low spatial resolution. The high-dimensionality characteristic and complex geometrical structure of LF images make the problem more challenging than traditional single-image SR. We propose a novel learning-based LF spatial SR framework to explore the coherence among LF sub-aperture images. Experimental results over both synthetic and real-world LF datasets demonstrate the significant advantage of our approach over state-of-the-art methods.
  arXiv  Detail & Related papers  (2020-09-26T08:34:37Z)
• MFIF-GAN: A New Generative Adversarial Network for Multi-Focus Image Fusion [29.405149234582623]
  Multi-Focus Image Fusion (MFIF) is a promising technique to obtain all-in-focus images. One of the research trends of MFIF is to avoid the defocus spread effect (DSE) around the focus/defocus boundary (FDB) We propose a network termed MFIF-GAN to generate focus maps in which the foreground region are correctly larger than the corresponding objects.
  arXiv  Detail & Related papers  (2020-09-21T09:36:34Z)

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.