Thermal is Always Wild: Characterizing and Addressing Challenges in Thermal-Only Novel View Synthesis

TL;DR

This paper addresses the challenges of thermal-only novel view synthesis by introducing a preprocessing pipeline that stabilizes thermal data, leading to state-of-the-art results without dataset-specific tuning.

Contribution

The authors propose a lightweight preprocessing and splatting pipeline that enhances thermal data for improved view synthesis, overcoming low dynamic range and photometric fluctuations.

Findings

Achieves state-of-the-art performance on thermal-only NVS benchmarks.

Does not require dataset-specific tuning.

Effectively stabilizes thermal imagery for view synthesis.

Abstract

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.