Thermal Infrared Image Inpainting via Edge-Aware Guidance
This addresses a domain-specific problem for applications using TIR images, such as surveillance or medical imaging, by introducing a novel method tailored to this data type.
The paper tackles the problem of inpainting missing regions in Thermal Infrared (TIR) images, where conventional methods produce distorted results, and proposes a deep-learning model called TIR-Fill that uses edge-aware guidance to achieve state-of-the-art performance on the FLIR thermal dataset.
Image inpainting has achieved fundamental advances with deep learning. However, almost all existing inpainting methods aim to process natural images, while few target Thermal Infrared (TIR) images, which have widespread applications. When applied to TIR images, conventional inpainting methods usually generate distorted or blurry content. In this paper, we propose a novel task -- Thermal Infrared Image Inpainting, which aims to reconstruct missing regions of TIR images. Crucially, we propose a novel deep-learning-based model TIR-Fill. We adopt the edge generator to complete the canny edges of broken TIR images. The completed edges are projected to the normalization weights and biases to enhance edge awareness of the model. In addition, a refinement network based on gated convolution is employed to improve TIR image consistency. The experiments demonstrate that our method outperforms state-of-the-art image inpainting approaches on FLIR thermal dataset.