Multi-exposure HDR Imaging: A Review of Pixel-level and Feature-level Reconstruction Methods

• URL: http://arxiv.org/abs/2608.28674v1
• Date: Tue, 25 Aug 2026 06:05:20 GMT
• Title: Multi-exposure HDR Imaging: A Review of Pixel-level and Feature-level Reconstruction Methods
• Abstract summary: Multi-exposure is an efficient way to capture real-world high-dynamic-range ( HDR) scenes.<n>However, HDR imaging suffers from severe ghosting in dynamic scenes due to the temporal gap between sequential exposures.<n>In this article, we categorize the literature on two important topics on HDR imaging: multi-exposure fusion (MEF) and ghost removal.
• Score: 19.515009974648535
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Multi-exposure is an efficient way to capture real-world high-dynamic-range (HDR) scenes. However, HDR imaging suffers from severe ghosting artifacts in dynamic scenes due to the temporal gap between sequential exposures. In this article, we categorize the literature on two important topics on HDR imaging: multi-exposure fusion (MEF) and ghost removal. Conventional filter-based and data-driven methods are studied in pixel space and feature space. For popular deep learning-based approaches, we provide a granular taxonomy based on their alignment and fusion domains: pixel-space methods, which typically employ explicit motion compensation such as optical flow or spatial transformers, and feature-space methods, which leverage implicit alignment through deformable convolutions, attention mechanisms, or latent representation merging. Representative works are compared across different supervision settings, and key design principles are summarized. In addition, this survey summarizes commonly used datasets and evaluation metrics, discussing their applicability under diverse output forms. Finally, major bottlenecks and promising directions for future research are outlined.

Related papers

• Diff-Mosaic: Augmenting Realistic Representations in Infrared Small Target Detection via Diffusion Prior [63.64088590653005]
  We propose Diff-Mosaic, a data augmentation method based on the diffusion model. We introduce an enhancement network called Pixel-Prior, which generates highly coordinated and realistic Mosaic images. In the second stage, we propose an image enhancement strategy named Diff-Prior. This strategy utilizes diffusion priors to model images in the real-world scene.
  arXiv  Detail & Related papers  (2024-06-02T06:23:05Z)
• Semantic Aware Diffusion Inverse Tone Mapping [5.65968650127342]
  Inverse tone mapping attempts to boost captured Standard Dynamic Range (SDR) images back to High Dynamic Range ( HDR) We present a novel inverse tone mapping approach for mapping SDR images to HDR that generates lost details in clipped regions through a semantic-aware diffusion based inpainting approach.
  arXiv  Detail & Related papers  (2024-05-24T11:44:22Z)
• Generating Content for HDR Deghosting from Frequency View [56.103761824603644]
  Recent Diffusion Models (DMs) have been introduced in HDR imaging field. DMs require extensive iterations with large models to estimate entire images. We propose the Low-Frequency aware Diffusion (LF-Diff) model for ghost-free HDR imaging.
  arXiv  Detail & Related papers  (2024-04-01T01:32:11Z)
• Towards High-quality HDR Deghosting with Conditional Diffusion Models [88.83729417524823]
  High Dynamic Range (LDR) images can be recovered from several Low Dynamic Range (LDR) images by existing Deep Neural Networks (DNNs) techniques. DNNs still generate ghosting artifacts when LDR images have saturation and large motion. We formulate the HDR deghosting problem as an image generation that leverages LDR features as the diffusion model's condition.
  arXiv  Detail & Related papers  (2023-11-02T01:53:55Z)
• Self-Supervised High Dynamic Range Imaging with Multi-Exposure Images in Dynamic Scenes [58.66427721308464]
  Self is a self-supervised reconstruction method that only requires dynamic multi-exposure images during training. Self achieves superior results against the state-of-the-art self-supervised methods, and comparable performance to supervised ones.
  arXiv  Detail & Related papers  (2023-10-03T07:10:49Z)
• Alignment-free HDR Deghosting with Semantics Consistent Transformer [76.91669741684173]
  High dynamic range imaging aims to retrieve information from multiple low-dynamic range inputs to generate realistic output. Existing methods often focus on the spatial misalignment across input frames caused by the foreground and/or camera motion. We propose a novel alignment-free network with a Semantics Consistent Transformer (SCTNet) with both spatial and channel attention modules.
  arXiv  Detail & Related papers  (2023-05-29T15:03:23Z)
• Multi-Exposure HDR Composition by Gated Swin Transformer [8.619880437958525]
  This paper provides a novel multi-exposure fusion model based on Swin Transformer. We exploit the long distance contextual dependency in the exposure-space pyramid by the self-attention mechanism. Experiments show that our model achieves the accuracy on par with current top performing multi-exposure HDR imaging models.
  arXiv  Detail & Related papers  (2023-03-15T15:38:43Z)
• Deep Progressive Feature Aggregation Network for High Dynamic Range Imaging [24.94466716276423]
  We propose a deep progressive feature aggregation network for improving HDR imaging quality in dynamic scenes. Our method implicitly samples high-correspondence features and aggregates them in a coarse-to-fine manner for alignment. Experiments show that our proposed method can achieve state-of-the-art performance under different scenes.
  arXiv  Detail & Related papers  (2022-08-04T04:37:35Z)
• MC-Blur: A Comprehensive Benchmark for Image Deblurring [127.6301230023318]
  In most real-world images, blur is caused by different factors, e.g., motion and defocus. We construct a new large-scale multi-cause image deblurring dataset (called MC-Blur) Based on the MC-Blur dataset, we conduct extensive benchmarking studies to compare SOTA methods in different scenarios.
  arXiv  Detail & Related papers  (2021-12-01T02:10:42Z)
• Attention-Guided Progressive Neural Texture Fusion for High Dynamic Range Image Restoration [48.02238732099032]
  In this work, we propose an Attention-guided Progressive Neural Texture Fusion (APNT-Fusion) HDR restoration model. An efficient two-stream structure is proposed which separately focuses on texture feature transfer over saturated regions and multi-exposure tonal and texture feature fusion. A progressive texture blending module is designed to blend the encoded two-stream features in a multi-scale and progressive manner.
  arXiv  Detail & Related papers  (2021-07-13T16:07:00Z)
• PAS-MEF: Multi-exposure image fusion based on principal component analysis, adaptive well-exposedness and saliency map [0.0]
  With regular low dynamic range (LDR) capture/display devices, significant details may not be preserved in images due to the huge dynamic range of natural scenes. This study proposes an efficient multi-exposure fusion (MEF) approach with a simple yet effective weight extraction method. Experimental comparisons with existing techniques demonstrate that the proposed method produces very strong statistical and visual results.
  arXiv  Detail & Related papers  (2021-05-25T10:22:43Z)

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.