Fieldscale: Locality-Aware Field-based Adaptive Rescaling for Thermal Infrared Image

TL;DR

Fieldscale introduces a locality-aware 2D field-based rescaling method for thermal infrared images, enhancing image quality by considering both pixel intensity and spatial context, outperforming previous global methods.

Contribution

It presents a novel locality-aware 2D field approach for adaptive pixel gain determination, improving thermal image rescaling quality over prior global methods.

Findings

Improves image quality assessment scores

Enhances downstream task performance

Produces spatially consistent 8-bit images

Abstract

Thermal infrared (TIR) cameras are emerging as promising sensors in safety-related fields due to their robustness against external illumination. However, RAW TIR image has 14 bits of pixel depth and needs to be rescaled into 8 bits for general applications. Previous works utilize a global 1D look-up table to compute pixel-wise gain solely based on its intensity, which degrades image quality by failing to consider the local nature of the heat. We propose Fieldscale, a rescaling based on locality-aware 2D fields where both the intensity value and spatial context of each pixel within an image are embedded. It can adaptively determine the pixel gain for each region and produce spatially consistent 8-bit rescaled images with minimal information loss and high visibility. Consistent performance improvement on image quality assessment and two other downstream tasks support the effectiveness and usability of Fieldscale. All the codes are publicly opened to facilitate research advancements in this field. https://github.com/hyeonjaegil/fieldscale