解决热成像新视角合成难题，提升夜间和恶劣环境下的视觉重建效果
Thermal is Always Wild: Characterizing and Addressing Challenges in Thermal-Only Novel View Synthesis
- 通过轻量级预处理扩展动态范围，稳定每帧光照
- 在无可见光引导下实现当前最佳热成像新视角合成效果
- 适用于夜间、雾霾等极端场景的视觉重建任务
热成像相机在黑暗和恶劣环境下仍能提供可靠视野，但其用于新视角合成（NVS）的难度远高于可见光图像。这主要源于廉价热传感器的两个特性：首先，热图像动态范围极低，削弱了外观线索并限制了优化可用的梯度；其次，热数据存在快速帧间光度波动与缓慢辐射漂移，二者共同导致对应关系估计不稳定，在视图合成中产生高频浮动伪影，尤其在缺乏RGB引导（仅靠相机位姿）时更为严重。基于此观察，我们提出一种轻量级预处理与点阵投射流水线，有效扩展可用动态范围并稳定每帧光度。该方法在多个热成像独有NVS基准上达到当前最优性能，且无需任何数据集特定调参。
原文摘要 · Abstract (English)
Thermal cameras provide reliable visibility in darkness and adverse conditions, but thermal imagery remains significantly harder to use for novel view synthesis (NVS) than visible-light images. This difficulty stems primarily from two characteristics of affordable thermal sensors. First, thermal images have extremely low dynamic range, which weakens appearance cues and limits the gradients available for optimization. Second, thermal data exhibit rapid frame-to-frame photometric fluctuations together with slow radiometric drift, both of which destabilize correspondence estimation and create high-frequency floater artifacts during view synthesis, particularly when no RGB guidance (beyond camera pose) is available. Guided by these observations, we introduce a lightweight preprocessing and splatting pipeline that expands usable dynamic range and stabilizes per-frame photometry. Our approach achieves state-of-the-art performance across thermal-only NVS benchmarks, without requiring any dataset-specific tuning.
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。