无需配对数据，用自监督方法从低动态范围图还原高动态范围图像。
A Cycle Ride to HDR: Semantics Aware Self-Supervised Framework for Unpaired LDR-to-HDR Image Reconstruction
- 构建循环一致的生成对抗网络，结合语义感知与自监督学习。
- 在无配对数据下达到当前最优性能，有效消除过曝和伪影。
- 适合做图像增强、摄影后期处理的研究者与开发者参考。
从低动态范围（LDR）图像重建高动态范围（HDR）图像是计算机视觉的重要任务。现有方法多依赖高质量的配对数据集，而真实场景中难以获取此类数据。本文提出CycleHDR，一种基于自监督的非配对学习框架，利用未配对的LDR与HDR数据进行训练。该方法改进了语义一致性与循环一致性对抗架构，引入新型去伪影及曝光感知生成器，并设计编码器与损失函数以保持语义一致性。这是首个在自监督设置下实现语义与上下文感知的LDR-to-HDR重建方法，在多个基准数据集上表现领先，能生成高质量的HDR图像。
原文摘要 · Abstract (English)
Reconstruction of High Dynamic Range (HDR) from Low Dynamic Range (LDR) images is an important computer vision task. There is a significant amount of research utilizing both conventional non-learning methods and modern data-driven approaches, focusing on using both single-exposed and multi-exposed LDR for HDR image reconstruction. However, most current state-of-the-art methods require high-quality paired {LDR;HDR} datasets with limited literature use of unpaired datasets, that is, methods that learn the LDR-HDR mapping between domains. This paper proposes CycleHDR, a method that integrates self-supervision into a modified semantic- and cycle-consistent adversarial architecture that utilizes unpaired LDR and HDR datasets for training. Our method introduces novel artifact- and exposure-aware generators to address visual artifact removal. It also puts forward an encoder and loss to address semantic consistency, another under-explored topic. CycleHDR is the first to use semantic and contextual awareness for the LDR-HDR reconstruction task in a self-supervised setup. The method achieves state-of-the-art performance across several benchmark datasets and reconstructs high-quality HDR images. The official website of this work is available at: https://github.com/HrishavBakulBarua/Cycle-HDR
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。