Robust Face Super-Resolution and Recognition Through Multi-Feature Aggregation in Diffusion Models
Quick Answer
This paper shows that FASR++ is a novel diffusion-model-based super-resolution algorithm that enhances facial recognition in low-quality surveillance images by aggregating features from multiple low-resolution inputs.
Quick Take
FASR++ is a novel diffusion-model-based super-resolution algorithm that enhances facial recognition in low-quality surveillance images by aggregating features from multiple low-resolution inputs. It achieves state-of-the-art results on standard datasets, significantly improving PSNR, SSIM, and LPIPS metrics, thus addressing the challenges posed by low resolution, occlusions, and varying illumination.
Key Points
- FASR++ minimizes identity distortions in facial recognition tasks.
- Utilizes multiple low-quality images to enhance super-resolution output.
- Achieves state-of-the-art performance on face recognition benchmarks.
- Improves image quality metrics like PSNR, SSIM, and LPIPS.
- Addresses challenges in surveillance environments effectively.
Paper Resources
📖 Reader Mode
~2 min readAbstract:Images acquired in surveillance environments often suffer from conditions such as low resolution, variations in pose, irregular illumination, and occlusions. Due to the low quality of these images, face recognition algorithms often struggle. This major limitation can be addressed by employing super-resolution techniques that enhance the details of the image. However, due to the high degree of difficulty of the problem, most super-resolution algorithms tend to cause distortions in the image and in the individual's identity. Thus, additional information must be incorporated into the processing to improve recognition robustness. In this regard, surveillance cameras can capture multiple images, even at low quality, and the data extracted from these images, such as consecutive video frames, can significantly enhance both super-resolution and facial recognition. In this work, we introduce FASR++, a diffusion-model-based super-resolution algorithm. It leverages a reference low-resolution image and features extracted from multiple auxiliary low-quality images to generate a super-resolved output, minimizing distortions in the individual's identity. Our approach recovers facial features without explicitly providing soft attributes or computing a function gradient to guide the reconstruction process. FASR++ generates high-quality images that can considerably improve performance in face recognition tasks when used as a pre-processing step. We validate our approach on two standard face recognition datasets and attain state-of-the-art results for verification, face recognition, and image quality metrics such as PSNR, SSIM, and LPIPS.
| Subjects: | Computer Vision and Pattern Recognition (cs.CV) |
| Cite as: | arXiv:2607.05702 [cs.CV] |
| (or arXiv:2607.05702v1 [cs.CV] for this version) | |
| https://doi.org/10.48550/arXiv.2607.05702 arXiv-issued DOI via DataCite (pending registration) |
|
| Journal reference: | Journal of the Brazilian Computer Society, vol. 32, no. 1, pp. 1457-1470, 2026 |
| Related DOI: | https://doi.org/10.5753/jbcs.2026.5884
DOI(s) linking to related resources |
Submission history
From: Rayson Laroca [view email]
[v1]
Mon, 6 Jul 2026 23:49:55 UTC (5,514 KB)
— Originally published at arxiv.org
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.CV
See more →LLM-Guided ANN Index Optimization for Human-Object Interaction Retrieval
A phase-aware LLM agent optimizes human-object interaction retrieval, outperforming Optuna TPE by 33.3% and VDTuner by 34.2% on the HICO-DET benchmark. This method enhances throughput by 15.3x over UniIR and demonstrates strong transferability across vector database management systems.