用无监督方法融合多曝光图像，重建高质量HDR影像
HDR Image Reconstruction using an Unsupervised Fusion Model
- 通过卷积神经网络融合过曝与欠曝图像的互补信息
- 无需真实HDR图像训练，提升实际应用可行性
- 自定义损失函数优化重建精度，视觉效果更优
高动态范围（HDR）成像旨在还原自然场景中人类视觉可感知的宽广亮度范围，而传统数码相机因动态范围有限，常无法完整捕捉。为此，我们提出一种基于深度学习的多曝光融合方法用于生成HDR图像。该方法输入一组不同曝光的低动态范围（LDR）图像，通常为一张过曝和一张欠曝图像，利用卷积神经网络（CNN）学习融合其互补信息：欠曝图像保留亮区细节，过曝图像保存暗区信息，网络有效结合二者以重建高质量HDR输出。模型采用无监督方式训练，不依赖真实HDR图像，提升了在真实场景中应用的可行性。我们使用多曝光融合结构相似性指数（MEF-SSIM）评估结果，表明本方法在视觉质量上优于现有融合技术。此外，引入定制化损失函数以增强重建保真度并优化模型性能。
原文摘要 · Abstract (English)
High Dynamic Range (HDR) imaging aims to reproduce the wide range of brightness levels present in natural scenes, which the human visual system can perceive but conventional digital cameras often fail to capture due to their limited dynamic range. To address this limitation, we propose a deep learning-based multi-exposure fusion approach for HDR image generation. The method takes a set of differently exposed Low Dynamic Range (LDR) images, typically an underexposed and an overexposed image, and learns to fuse their complementary information using a convolutional neural network (CNN). The underexposed image preserves details in bright regions, while the overexposed image retains information in dark regions; the network effectively combines these to reconstruct a high-quality HDR output. The model is trained in an unsupervised manner, without relying on ground-truth HDR images, making it practical for real-world applications where such data is unavailable. We evaluate our results using the Multi-Exposure Fusion Structural Similarity Index Measure (MEF-SSIM) and demonstrate that our approach achieves superior visual quality compared to existing fusion methods. A customized loss function is further introduced to improve reconstruction fidelity and optimize model performance.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。