# AnyThermal: Towards Learning Universal Representations for Thermal Perception

arXiv: https://arxiv.org/abs/2602.06203 · HTML: https://mlsanity.com/paper/2602.06203/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 32 of its 38 references that are in the map.
- First posted on arXiv 5 Feb 2026.

## Builds on (most cited first, 30 of 32)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [SAM 2: Segment Anything in Images and Videos](https://mlsanity.com/paper/2408.00714/) (2024)
- [FaceNet: A Unified Embedding for Face Recognition and Clustering](https://mlsanity.com/paper/1503.03832/) (2015)
- [Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfer](https://mlsanity.com/paper/1907.01341/) (2019)
- [ImageBind: One Embedding Space To Bind Them All](https://mlsanity.com/paper/2305.05665/) (2023)
- [NetVLAD: CNN architecture for weakly supervised place recognition](https://mlsanity.com/paper/1511.07247/) (2015)
- [Understanding How Dimension Reduction Tools Work: An Empirical Approach to Deciphering t-SNE, UMAP, TriMAP, and PaCMAP for Data Visualization](https://mlsanity.com/paper/2012.04456/) (2020)
- [FoundationStereo: Zero-Shot Stereo Matching](https://mlsanity.com/paper/2501.09898/) (2025)
- [MixVPR: Feature Mixing for Visual Place Recognition](https://mlsanity.com/paper/2303.02190/) (2023)
- [Optimal Transport Aggregation for Visual Place Recognition](https://mlsanity.com/paper/2311.15937/) (2023)
- [Segment Any Point Cloud Sequences by Distilling Vision Foundation Models](https://mlsanity.com/paper/2306.09347/) (2023)
- [R2Former: Unified Retrieval and Reranking Transformer for Place Recognition](https://mlsanity.com/paper/2304.03410/) (2023)
- [PST900: RGB-Thermal Calibration, Dataset and Segmentation Network](https://mlsanity.com/paper/1909.10980/) (2019)
- [Three Pillars improving Vision Foundation Model Distillation for Lidar](https://mlsanity.com/paper/2310.17504/) (2023)
- [HeatNet: Bridging the Day-Night Domain Gap in Semantic Segmentation with Thermal Images](https://mlsanity.com/paper/2003.04645/) (2020)
- [ViViD++: Vision for Visibility Dataset](https://mlsanity.com/paper/2204.06183/) (2022)
- [Caltech Aerial RGB-Thermal Dataset in the Wild](https://mlsanity.com/paper/2403.08997/) (2024)
- [MAC-VO: Metrics-aware Covariance for Learning-based Stereo Visual Odometry](https://mlsanity.com/paper/2409.09479/) (2024)
- [Unsupervised RGB-to-Thermal Domain Adaptation via Multi-Domain Attention Network](https://mlsanity.com/paper/2210.04367/) (2022)
- [Long-range UAV Thermal Geo-localization with Satellite Imagery](https://mlsanity.com/paper/2306.02994/) (2023)
- [UniLoc: Towards Universal Place Recognition Using Any Single Modality](https://mlsanity.com/paper/2412.12079/) (2024)
- [What Makes a Good Dataset for Knowledge Distillation?](https://mlsanity.com/paper/2411.12817/) (2024)
- [FIReStereo: Forest InfraRed Stereo Dataset for UAS Depth Perception in Visually Degraded Environments](https://mlsanity.com/paper/2409.07715/) (2024)
- [OdomBeyondVision: An Indoor Multi-modal Multi-platform Odometry Dataset Beyond the Visible Spectrum](https://mlsanity.com/paper/2206.01589/) (2022)
- [Online Self-Supervised Thermal Water Segmentation for Aerial Vehicles](https://mlsanity.com/paper/2307.09027/) (2023)
- [MonoTher-Depth: Enhancing Thermal Depth Estimation via Confidence-Aware Distillation](https://mlsanity.com/paper/2504.16127/) (2025)
- [M2P2: A Multi-Modal Passive Perception Dataset for Off-Road Mobility in Extreme Low-Light Conditions](https://mlsanity.com/paper/2410.01105/) (2024)

## Built on by (most cited first, 5 of 5)

- [SegFly: A Dataset and 2D-3D-2D Paradigm for Aerial RGB-Thermal Semantic Segmentation at Scale](https://mlsanity.com/paper/2603.17920/) (2026)
- [DarkVGGT: Seeing Through Darkness Using Thermal Geometry](https://mlsanity.com/paper/2606.11326/) (2026)
- [Route-MHT: Multimodal Transformer Guardrails for Thermal Visual Place Recognition](https://mlsanity.com/paper/2607.04745/) (2026)
- [Hub-Spectral Activation of Latent Multimodal Knowledge](https://mlsanity.com/paper/2609.17094/) (2026)
- [Structure-Aware Matching for Robust UAV Thermal-to-Satellite Geo-Localization](https://mlsanity.com/paper/2610.12835/) (2026)

## Abstract (arXiv)

We present AnyThermal, a thermal backbone that captures robust task-agnostic thermal features suitable for a variety of tasks such as cross-modal place recognition, thermal segmentation, and monocular depth estimation using thermal images. Existing thermal backbones that follow task-specific training from small-scale data result in utility limited to a specific environment and task. Unlike prior methods, AnyThermal can be used for a wide range of environments (indoor, aerial, off-road, urban) and tasks, all without task-specific training. Our key insight is to distill the feature representations from visual foundation models such as DINOv2 into a thermal encoder using thermal data from these multiple environments. To bridge the diversity gap of the existing RGB-Thermal datasets, we introduce the TartanRGBT platform, the first open-source data collection platform with synced RGB-Thermal image acquisition. We use this payload to collect the TartanRGBT dataset - a diverse and balanced dataset collected in 4 environments. We demonstrate the efficacy of AnyThermal and TartanRGBT, achieving state-of-the-art results with improvements of up to 36% across diverse environments and downstream tasks on existing datasets.