Thermal is Always Wild: Characterizing and Addressing Challenges in Thermal-Only Novel View Synthesis
This addresses the problem of reliable 3D scene reconstruction in darkness or adverse conditions for applications like surveillance or autonomous systems, representing a domain-specific incremental improvement.
The paper tackles the challenge of novel view synthesis using only thermal imagery, which suffers from low dynamic range and photometric instability, by introducing a lightweight preprocessing and splatting pipeline that expands dynamic range and stabilizes photometry. It achieves state-of-the-art performance on thermal-only benchmarks without dataset-specific tuning.
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.