AnyThermal: Towards Learning Universal Representations for Thermal Perception
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866908816741761024 |
|---|---|
| author | Maheshwari, Parv Karhade, Jay Chawla, Yogesh Adu, Isaiah Heisen, Florian Porco, Andrew Jong, Andrew Liu, Yifei Pitla, Santosh Scherer, Sebastian Wang, Wenshan |
| author_facet | Maheshwari, Parv Karhade, Jay Chawla, Yogesh Adu, Isaiah Heisen, Florian Porco, Andrew Jong, Andrew Liu, Yifei Pitla, Santosh Scherer, Sebastian Wang, Wenshan |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_06203 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | AnyThermal: Towards Learning Universal Representations for Thermal Perception Maheshwari, Parv Karhade, Jay Chawla, Yogesh Adu, Isaiah Heisen, Florian Porco, Andrew Jong, Andrew Liu, Yifei Pitla, Santosh Scherer, Sebastian Wang, Wenshan Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning Robotics 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. |
| title | AnyThermal: Towards Learning Universal Representations for Thermal Perception |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning Robotics |
| url | https://arxiv.org/abs/2602.06203 |