Thermal Chameleon: Task-Adaptive Tone-mapping for Radiometric Thermal-Infrared images

TL;DR

Thermal Chameleon Network (TCNet) introduces a task-adaptive tone-mapping method for RAW thermal infrared images, improving generalization across tasks without relying on scene priors or extensive preprocessing.

Contribution

The paper presents TCNet, a novel neural network that adaptively tone-maps TIR images for different tasks, eliminating the need for heuristic rescaling and prior scene knowledge.

Findings

Enhanced performance in object detection and depth estimation tasks.

Minimal computational overhead and easy integration.

Improved generalization across various TIR image applications.

Abstract

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