# Thermal-NeRF: Neural Radiance Fields from an Infrared Camera

arXiv: https://arxiv.org/abs/2403.10340 · HTML: https://mlsanity.com/paper/2403.10340/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 42 references that are in the map.
- First posted on arXiv 15 Mar 2024.

## Builds on (most cited first, 19 of 19)

- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation](https://mlsanity.com/paper/1901.05103/) (2019)
- [Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fields](https://mlsanity.com/paper/2111.12077/) (2021)
- [NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstruction](https://mlsanity.com/paper/2106.10689/) (2021)
- [NeRF in the Wild: Neural Radiance Fields for Unconstrained Photo Collections](https://mlsanity.com/paper/2008.02268/) (2020)
- [Direct Voxel Grid Optimization: Super-fast Convergence for Radiance Fields Reconstruction](https://mlsanity.com/paper/2111.11215/) (2021)
- [Nerfstudio: A Modular Framework for Neural Radiance Field Development](https://mlsanity.com/paper/2302.04264/) (2023)
- [Latent-NeRF for Shape-Guided Generation of 3D Shapes and Textures](https://mlsanity.com/paper/2211.07600/) (2022)
- [Direct Sparse Odometry](https://mlsanity.com/paper/1607.02565/) (2016)
- [NeRF in the Dark: High Dynamic Range View Synthesis from Noisy Raw Images](https://mlsanity.com/paper/2111.13679/) (2021)
- [Neural Volumes: Learning Dynamic Renderable Volumes from Images](https://mlsanity.com/paper/1906.07751/) (2019)
- [Delicate Textured Mesh Recovery from NeRF via Adaptive Surface Refinement](https://mlsanity.com/paper/2303.02091/) (2023)
- [Improved Direct Voxel Grid Optimization for Radiance Fields Reconstruction](https://mlsanity.com/paper/2206.05085/) (2022)
- [NeRF-LOAM: Neural Implicit Representation for Large-Scale Incremental LiDAR Odometry and Mapping](https://mlsanity.com/paper/2303.10709/) (2023)
- [Cross-Spectral Neural Radiance Fields](https://mlsanity.com/paper/2209.00648/) (2022)
- [S3IM: Stochastic Structural SIMilarity and Its Unreasonable Effectiveness for Neural Fields](https://mlsanity.com/paper/2308.07032/) (2023)
- [NeRF-VINS: A Real-time Neural Radiance Field Map-based Visual-Inertial Navigation System](https://mlsanity.com/paper/2309.09295/) (2023)
- [ResNeRF: Geometry-Guided Residual Neural Radiance Field for Indoor Scene Novel View Synthesis](https://mlsanity.com/paper/2211.16211/) (2022)

## Built on by (most cited first, 21 of 21)

- [NeRFs in Robotics: A Survey](https://mlsanity.com/paper/2405.01333/) (2024)
- [Exploring Multi-modal Neural Scene Representations With Applications on Thermal Imaging](https://mlsanity.com/paper/2403.11865/) (2024)
- [ThermalGaussian: Thermal 3D Gaussian Splatting](https://mlsanity.com/paper/2409.07200/) (2024)
- [NeISF++: Neural Incident Stokes Field for Polarized Inverse Rendering of Conductors and Dielectrics](https://mlsanity.com/paper/2411.10189/) (2024)
- [NTR-Gaussian: Nighttime Dynamic Thermal Reconstruction with 4D Gaussian Splatting Based on Thermodynamics](https://mlsanity.com/paper/2503.03115/) (2025)
- [Deep Depth Estimation from Thermal Image: Dataset, Benchmark, and Challenges](https://mlsanity.com/paper/2503.22060/) (2025)
- [HADAR-Based Thermal Infrared Hyperspectral Image Restoration](https://mlsanity.com/paper/2605.13664/) (2026)
- [UnMix-NeRF: Spectral Unmixing Meets Neural Radiance Fields](https://mlsanity.com/paper/2506.21884/) (2025)
- [Towards Integrating Multi-Spectral Imaging with Gaussian Splatting](https://mlsanity.com/paper/2509.00989/) (2025)
- [GANESH: Generalizable NeRF for Lensless Imaging](https://mlsanity.com/paper/2411.04810/) (2024)
- [Thermal Polarimetric Multi-view Stereo](https://mlsanity.com/paper/2510.20972/) (2025)
- [TeX-NeRF: Neural Radiance Fields from Pseudo-TeX Vision](https://mlsanity.com/paper/2410.04873/) (2024)
- [Veta-GS: View-dependent deformable 3D Gaussian Splatting for thermal infrared Novel-view Synthesis](https://mlsanity.com/paper/2505.19138/) (2025)
- [PhotonSplat: 3D Scene Reconstruction and Colorization from SPAD Sensors](https://mlsanity.com/paper/2506.21680/) (2025)
- [LoGoColor: Local-Global 3D Colorization for 360deg Scenes](https://mlsanity.com/paper/2512.09278/) (2025)
- [360-GeoGS: Geometrically Consistent Feed-Forward 3D Gaussian Splatting Reconstruction for 360 Images](https://mlsanity.com/paper/2601.02102/) (2026)
- [ThermoSplat: Cross-Modal 3D Gaussian Splatting with Feature Modulation and Geometry Decoupling](https://mlsanity.com/paper/2601.15897/) (2026)
- [Thermal is Always Wild: Characterizing and Addressing Challenges in Thermal-Only Novel View Synthesis](https://mlsanity.com/paper/2603.20448/) (2026)
- [Unpaired RGB-Thermal Gaussian-Splatting Using Visual Geometric Transformers](https://mlsanity.com/paper/2606.05491/) (2026)
- [MeGAS: Thermomechanical Dynamic Gaussian Splatting for Thermophysical Scene Editing](https://mlsanity.com/paper/2606.23455/) (2026)
- [Learning Spectral and Polarimetric Clues for One-to-Multimodal Novel View Synthesis](https://mlsanity.com/paper/2607.02372/) (2026)

## Abstract (arXiv)

In recent years, Neural Radiance Fields (NeRFs) have demonstrated significant potential in encoding highly-detailed 3D geometry and environmental appearance, positioning themselves as a promising alternative to traditional explicit representation for 3D scene reconstruction. However, the predominant reliance on RGB imaging presupposes ideal lighting conditions: a premise frequently unmet in robotic applications plagued by poor lighting or visual obstructions. This limitation overlooks the capabilities of infrared (IR) cameras, which excel in low-light detection and present a robust alternative under such adverse scenarios. To tackle these issues, we introduce Thermal-NeRF, the first method that estimates a volumetric scene representation in the form of a NeRF solely from IR imaging. By leveraging a thermal mapping and structural thermal constraint derived from the thermal characteristics of IR imaging, our method showcasing unparalleled proficiency in recovering NeRFs in visually degraded scenes where RGB-based methods fall short. We conduct extensive experiments to demonstrate that Thermal-NeRF can achieve superior quality compared to existing methods. Furthermore, we contribute a dataset for IR-based NeRF applications, paving the way for future research in IR NeRF reconstruction.