Multi-Feature Aggregation in Diffusion Models for Enhanced Face Super-Resolution
This addresses the problem of enhancing low-resolution face images from surveillance for improved identification, though it is incremental as it builds on existing diffusion models with multi-feature aggregation.
The paper tackles face super-resolution in surveillance images with adverse conditions by developing a diffusion model that aggregates features from multiple low-quality images, achieving state-of-the-art performance on facial recognition and verification metrics on the CelebA and Quis-Campi datasets.
Super-resolution algorithms often struggle with images from surveillance environments due to adverse conditions such as unknown degradation, variations in pose, irregular illumination, and occlusions. However, acquiring multiple images, even of low quality, is possible with surveillance cameras. In this work, we develop an algorithm based on diffusion models that utilize a low-resolution image combined with features extracted from multiple low-quality images to generate a super-resolved image while minimizing distortions in the individual's identity. Unlike other algorithms, our approach recovers facial features without explicitly providing attribute information or without the need to calculate a gradient of a function during the reconstruction process. To the best of our knowledge, this is the first time multi-features combined with low-resolution images are used as conditioners to generate more reliable super-resolution images using stochastic differential equations. The FFHQ dataset was employed for training, resulting in state-of-the-art performance in facial recognition and verification metrics when evaluated on the CelebA and Quis-Campi datasets. Our code is publicly available at https://github.com/marcelowds/fasr