Thermal Chameleon: Task-Adaptive Tone-mapping for Radiometric Thermal-Infrared images
This work addresses the challenge of enhancing thermal-infrared image quality for navigation in outdoor environments, offering a modular solution that is incremental over existing tone-mapping methods.
The paper tackles the problem of poor texture and low contrast in thermal-infrared images by introducing a task-adaptive tone-mapping approach that eliminates the need for heuristic preprocessing and prior knowledge, resulting in improved generalization performance across object detection and monocular depth estimation with minimal computational overhead.
Thermal Infrared (TIR) imaging provides robust perception for navigating in challenging outdoor environments but faces issues with poor texture and low image contrast due to its 14/16-bit format. Conventional methods utilize various tone-mapping methods to enhance contrast and photometric consistency of TIR images, however, the choice of tone-mapping is largely dependent on knowing the task and temperature dependent priors to work well. In this paper, we present Thermal Chameleon Network (TCNet), a task-adaptive tone-mapping approach for RAW 14-bit TIR images. Given the same image, TCNet tone-maps different representations of TIR images tailored for each specific task, eliminating the heuristic image rescaling preprocessing and reliance on the extensive prior knowledge of the scene temperature or task-specific characteristics. TCNet exhibits improved generalization performance across object detection and monocular depth estimation, with minimal computational overhead and modular integration to existing architectures for various tasks. Project Page: https://github.com/donkeymouse/ThermalChameleon