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

arXiv: https://arxiv.org/abs/2603.20448 · HTML: https://mlsanity.com/paper/2603.20448/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 28 of its 46 references that are in the map.
- First posted on arXiv 20 Mar 2026.

## Builds on (most cited first, 28 of 28)

- [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023)
- [Instant Neural Graphics Primitives with a Multiresolution Hash Encoding](https://mlsanity.com/paper/2201.05989/) (2022)
- [Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fields](https://mlsanity.com/paper/2103.13415/) (2021)
- [Plenoxels: Radiance Fields without Neural Networks](https://mlsanity.com/paper/2112.05131/) (2021)
- [NeRF in the Wild: Neural Radiance Fields for Unconstrained Photo Collections](https://mlsanity.com/paper/2008.02268/) (2020)
- [BARF: Bundle-Adjusting Neural Radiance Fields](https://mlsanity.com/paper/2104.06405/) (2021)
- [NeRF in the Dark: High Dynamic Range View Synthesis from Noisy Raw Images](https://mlsanity.com/paper/2111.13679/) (2021)
- [gsplat: An Open-Source Library for Gaussian Splatting](https://mlsanity.com/paper/2409.06765/) (2024)
- [WildGaussians: 3D Gaussian Splatting in the Wild](https://mlsanity.com/paper/2407.08447/) (2024)
- [Gaussian in the Wild: 3D Gaussian Splatting for Unconstrained Image Collections](https://mlsanity.com/paper/2403.15704/) (2024)
- [SWAG: Splatting in the Wild images with Appearance-conditioned Gaussians](https://mlsanity.com/paper/2403.10427/) (2024)
- [Wild-GS: Real-Time Novel View Synthesis from Unconstrained Photo Collections](https://mlsanity.com/paper/2406.10373/) (2024)
- [Splatfacto-W: A Nerfstudio Implementation of Gaussian Splatting for Unconstrained Photo Collections](https://mlsanity.com/paper/2407.12306/) (2024)
- [GauStudio: A Modular Framework for 3D Gaussian Splatting and Beyond](https://mlsanity.com/paper/2403.19632/) (2024)
- [Thermal-NeRF: Neural Radiance Fields from an Infrared Camera](https://mlsanity.com/paper/2403.10340/) (2024)
- [Neural Radiance Field in Autonomous Driving: A Survey](https://mlsanity.com/paper/2404.13816/) (2024)
- [NeRFs in Robotics: A Survey](https://mlsanity.com/paper/2405.01333/) (2024)
- [Thermal3D-GS: Physics-induced 3D Gaussians for Thermal Infrared Novel-view Synthesis](https://mlsanity.com/paper/2409.08042/) (2024)
- [Exploring Multi-modal Neural Scene Representations With Applications on Thermal Imaging](https://mlsanity.com/paper/2403.11865/) (2024)
- [Maximizing Self-supervision from Thermal Image for Effective Self-supervised Learning of Depth and Ego-motion](https://mlsanity.com/paper/2201.04387/) (2022)
- [ThermalNeRF: Thermal Radiance Fields](https://mlsanity.com/paper/2407.15337/) (2024)
- [Leveraging Thermal Modality to Enhance Reconstruction in Low-Light Conditions](https://mlsanity.com/paper/2403.14053/) (2024)
- [Thermal Image Processing via Physics-Inspired Deep Networks](https://mlsanity.com/paper/2108.07973/) (2021)
- [Radiance Fields in XR: A Survey on How Radiance Fields are Envisioned and Addressed for XR Research](https://mlsanity.com/paper/2508.04326/) (2025)
- [SmokeSeer: 3D Gaussian Splatting for Smoke Removal and Scene Reconstruction](https://mlsanity.com/paper/2509.17329/) (2025)
- [Pixel-Wise Motion Deblurring of Thermal Videos](https://mlsanity.com/paper/2006.04973/) (2020)
- [ThermoNeRF: Joint RGB and Thermal Novel View Synthesis for Building Facades using Multimodal Neural Radiance Fields](https://mlsanity.com/paper/2403.12154/) (2024)
- [TeX-NeRF: Neural Radiance Fields from Pseudo-TeX Vision](https://mlsanity.com/paper/2410.04873/) (2024)

## Abstract (arXiv)

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.