Fieldscale: Locality-Aware Field-based Adaptive Rescaling for Thermal Infrared Image
This work addresses image quality degradation in thermal infrared imaging for safety-related applications, representing an incremental improvement over previous global methods.
The paper tackles the problem of rescaling 14-bit thermal infrared images to 8 bits by proposing Fieldscale, a locality-aware method that uses 2D fields to embed intensity and spatial context, resulting in improved image quality with minimal information loss and high visibility.
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