Surveillance Facial Image Quality Assessment: A Multi-dimensional Dataset and Lightweight Model

2026-02-07

IEEE transactions on circuits and systems for video technology (Print)

AI Summary

Existing facial image quality assessment (FIQA) methods struggle to simultaneously preserve visual quality and identity fidelity in surveillance scenarios, hindering reliable face verification. To address this challenge, this work presents the first systematic study of the problem, introducing SFIQA-Bench—a real-world, multidimensional benchmark comprising six subjective quality annotations. Furthermore, we propose SFIQA-Assessor, a lightweight multitask model that jointly regresses multiple quality dimensions through cross-view feature interaction and learnable task tokens. Experimental results demonstrate that our approach significantly outperforms general-purpose image quality assessment (IQA) and existing FIQA methods on the proposed benchmark, effectively meeting the demands of multidimensional quality evaluation in practical surveillance applications.

Technology Category

• Computer Vision: Multi-modal Vision
• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Machine Learning: Large Multimodal Models (LMMs)

Application Category

• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Security and Privacy: Large-scale security measurements
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets

Abstract

Surveillance facial images are often captured under unconstrained conditions, resulting in severe quality degradation due to factors such as low resolution, motion blur, occlusion, and poor lighting. Although recent face restoration techniques applied to surveillance cameras can significantly enhance visual quality, they often compromise fidelity (i.e., identity-preserving features), which directly conflicts with the primary objective of surveillance images -- reliable identity verification. Existing facial image quality assessment (FIQA) predominantly focus on either visual quality or recognition-oriented evaluation, thereby failing to jointly address visual quality and fidelity, which are critical for surveillance applications. To bridge this gap, we propose the first comprehensive study on surveillance facial image quality assessment (SFIQA), targeting the unique challenges inherent to surveillance scenarios. Specifically, we first construct SFIQA-Bench, a multi-dimensional quality assessment benchmark for surveillance facial images, which consists of 5,004 surveillance facial images captured by three widely deployed surveillance cameras in real-world scenarios. A subjective experiment is conducted to collect six dimensional quality ratings, including noise, sharpness, colorfulness, contrast, fidelity and overall quality, covering the key aspects of SFIQA. Furthermore, we propose SFIQA-Assessor, a lightweight multi-task FIQA model that jointly exploits complementary facial views through cross-view feature interaction, and employs learnable task tokens to guide the unified regression of multiple quality dimensions. The experiment results on the proposed dataset show that our method achieves the best performance compared with the state-of-the-art general image quality assessment (IQA) and FIQA methods, validating its effectiveness for real-world surveillance applications.

Problem

• Surveillance Facial Image Quality Assessment
• Fidelity
• Visual Quality
• Identity Verification
• FIQA

Innovation

• Surveillance Facial Image Quality Assessment
• Multi-dimensional Quality Benchmark
• Lightweight Multi-task Model
• Cross-view Feature Interaction
• Fidelity-aware FIQA