仅用一张曝光的低动态范围图像，实现高动态范围新视角合成。
High Dynamic Range Novel View Synthesis with Single Exposure
- 基于低动态范围成像原理设计双模块，实现亮度信息双向转换。
- 在单张图像条件下，重建效果超越已有方法，避免多曝光缺陷。
- 可无缝集成现有新视角合成模型，适合图像生成与三维重建研究者。
高动态范围新视角合成（HDR-NVS）旨在从低动态范围（LDR）图像构建3D场景的高动态范围模型。传统方法依赖多曝光LDR图像以覆盖场景中亮暗区域，但存在运动伪影（如鬼影、模糊）及采集存储成本高的问题。本文首次提出单曝光HDR-NVS问题，仅使用单张曝光的LDR图像进行训练。为此，我们提出Mono-HDR-3D方法，包含两个基于LDR成像原理设计的专用模块：一个将LDR颜色映射为HDR，另一个将HDR图像转换回LDR，从而在闭环中实现无监督学习。该方法作为元算法，可无缝集成至现有NVS模型。大量实验表明，Mono-HDR-3D显著优于先前方法。代码将公开。
原文摘要 · Abstract (English)
High Dynamic Range Novel View Synthesis (HDR-NVS) aims to establish a 3D scene HDR model from Low Dynamic Range (LDR) imagery. Typically, multiple-exposure LDR images are employed to capture a wider range of brightness levels in a scene, as a single LDR image cannot represent both the brightest and darkest regions simultaneously. While effective, this multiple-exposure HDR-NVS approach has significant limitations, including susceptibility to motion artifacts (e.g., ghosting and blurring), high capture and storage costs. To overcome these challenges, we introduce, for the first time, the single-exposure HDR-NVS problem, where only single exposure LDR images are available during training. We further introduce a novel approach, Mono-HDR-3D, featuring two dedicated modules formulated by the LDR image formation principles, one for converting LDR colors to HDR counterparts, and the other for transforming HDR images to LDR format so that unsupervised learning is enabled in a closed loop. Designed as a meta-algorithm, our approach can be seamlessly integrated with existing NVS models. Extensive experiments show that Mono-HDR-3D significantly outperforms previous methods. Source code will be released.
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。