Coarse-to-fine Framework for Generative MEF via Implicit Neural Representation

• URL: http://arxiv.org/abs/2607.17611v1
• Date: Mon, 20 Jul 2026 07:00:47 GMT
• Title: Coarse-to-fine Framework for Generative MEF via Implicit Neural Representation
• Abstract summary: Multi-exposure fusion (MEF) expands the luminance range beyond what a single exposure can capture.<n>We propose LIIFusion, a coarse-to-fine framework that balances fusion quality and efficiency in generative MEF.
• Score: 32.04311237687492
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Multi-exposure fusion (MEF) expands the luminance range beyond what a single exposure can capture. Combining images taken at different exposure levels requires handling geometric differences while naturally merging their complementary brightness information. It often demands generative completion where details are missing. Diffusion-based generative methods address these challenges, however, they are computationally expensive and struggle to preserve fine structures in saturated regions. We propose LIIFusion, a coarse-to-fine framework that balances fusion quality and efficiency in generative MEF. The coarse stage performs low resolution generative fusion, enhanced by an adaptive exposure correction that recovers structure lost in saturated over-exposed areas. The fine stage adapts a local implicit image function into a multi-exposure fusion function: conditioned on the HR OE/UE sources and the coarse output, it queries arbitrary target coordinates and fuses source evidence regardless of the HR input resolution. LIIFusion achieves up to 3.5$\times$ speed-up over existing generative methods while maintaining or improving structural fidelity and perceptual quality. We believe this framework provides an effective pathway toward making generative MEF more practical in real-world applications.

Related papers

• There and Back Again: A Flexible-Frame Transformer for Multi-Exposure Fusion [33.80456021651473]
  We propose FreeMEF, a flexible-frame transformer for multi-exposure fusion.<n>First, we introduce a recurrent state space module that sequentially fuses features from arbitrary sequences.<n>Second, we devise a global feature guided block (GFGB) incorporating an extremity-aware hybrid attention (EAHA) and an affine-injection feed-forward network (AFFN)
  arXiv  Detail & Related papers  (2026-06-26T09:54:00Z)
• Degradation-Robust Fusion: An Efficient Degradation-Aware Diffusion Framework for Multimodal Image Fusion in Arbitrary Degradation Scenarios [34.660999867031386]
  Complex degradations like noise, blur, and low resolution are typical challenges in real world image fusion tasks.<n>This paper proposes an efficient degradation aware diffusion framework for image fusion under arbitrary degradation scenarios.
  arXiv  Detail & Related papers  (2026-04-10T03:34:53Z)
• Reversible Efficient Diffusion for Image Fusion [66.35113261837469]
  Multi-modal image fusion aims to consolidate complementary information from diverse source images into a unified representation.<n>While diffusion models have demonstrated impressive generative capabilities in image generation, they often suffer from detail loss when applied to image fusion tasks.<n>This issue arises from the accumulation of noise errors inherent in the Markov process, leading to inconsistency and degradation in the fused results.<n>We propose the Reversible Efficient Diffusion (RED) model - an explicitly supervised training framework that inherits the powerful generative capability of diffusion models while avoiding the distribution estimation.
  arXiv  Detail & Related papers  (2026-01-28T05:14:55Z)
• Towards Unified Semantic and Controllable Image Fusion: A Diffusion Transformer Approach [99.80480649258557]
  DiTFuse is an instruction-driven framework that performs semantics-aware fusion within a single model.<n>Experiments on public IVIF, MFF, and MEF benchmarks confirm superior quantitative and qualitative performance, sharper textures, and better semantic retention.
  arXiv  Detail & Related papers  (2025-12-08T05:04:54Z)
• Efficient Rectified Flow for Image Fusion [48.330480065862474]
  We propose RFfusion, an efficient one-step diffusion model for image fusion based on Rectified Flow.<n>We also propose a task-specific variational autoencoder architecture tailored for image fusion.<n>Our method outperforms other state-of-the-art methods in terms of both inference speed and fusion quality.
  arXiv  Detail & Related papers  (2025-09-20T06:21:00Z)
• DDFusion:Degradation-Decoupled Fusion Framework for Robust Infrared and Visible Images Fusion [9.242363983469346]
  We propose a Degradation-Decoupled Fusion(DDFusion) framework.<n>DDFusion achieves superior fusion performance under both clean and degraded conditions.
  arXiv  Detail & Related papers  (2025-04-15T05:02:49Z)
• Unsupervised Learning Based Multi-Scale Exposure Fusion [9.152843503286796]
  Unsupervised learning based multi-scale exposure fusion (ULMEF) is efficient for fusing differently exposed low dynamic range (LDR) images into a higher quality LDR image for a high dynamic range scene. In this paper, novel loss functions are proposed for the ULMEF and they are defined by using all the images to be fused and other differently exposed images from the same HDR scene.
  arXiv  Detail & Related papers  (2024-09-26T13:29:40Z)
• Reti-Diff: Illumination Degradation Image Restoration with Retinex-based Latent Diffusion Model [59.08821399652483]
  Illumination degradation image restoration (IDIR) techniques aim to improve the visibility of degraded images and mitigate the adverse effects of deteriorated illumination. Among these algorithms, diffusion model (DM)-based methods have shown promising performance but are often burdened by heavy computational demands and pixel misalignment issues when predicting the image-level distribution. We propose to leverage DM within a compact latent space to generate concise guidance priors and introduce a novel solution called Reti-Diff for the IDIR task. Reti-Diff comprises two key components: the Retinex-based latent DM (RLDM) and the Retinex-guided transformer (RG
  arXiv  Detail & Related papers  (2023-11-20T09:55:06Z)
• 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)
• DDFM: Denoising Diffusion Model for Multi-Modality Image Fusion [144.9653045465908]
  We propose a novel fusion algorithm based on the denoising diffusion probabilistic model (DDPM) Our approach yields promising fusion results in infrared-visible image fusion and medical image fusion.
  arXiv  Detail & Related papers  (2023-03-13T04:06:42Z)

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.