Multi-Feature Aggregation in Diffusion Models for Enhanced Face Super-Resolution

Abstract

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

Accepted for presentation at the Conference on Graphics, Patterns and Images (SIBGRAPI) 2024

References in corpus (8)

• SMOTE: Synthetic Minority Over-sampling Technique
• An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
• A Robust Real-Time Automatic License Plate Recognition Based on the YOLO Detector
• Benchmark for License Plate Character Segmentation
• On the Cross-dataset Generalization in License Plate Recognition
• Vehicle-Rear: A New Dataset to Explore Feature Fusion for Vehicle Identification Using Convolutional Neural Networks
• Do We Train on Test Data? The Impact of Near-Duplicates on License Plate Recognition
• Leveraging Model Fusion for Improved License Plate Recognition

Cited by in corpus (3)

• Toward Advancing License Plate Super-Resolution in Real-World Scenarios: A Dataset and Benchmark
• LPLC: A Dataset for License Plate Legibility Classification
• Toward Unified Fine-Grained Vehicle Classification and Automatic License Plate Recognition