Collaborative Feature Aggregation for Face Super-Resolution and Robust Re-Identification

2026-07-30

AI Summary

This work addresses the challenge of blurry and distorted outputs in face super-resolution from low-resolution or multi-view inputs, which severely degrades performance in face recognition and re-identification. To mitigate this, the authors propose a Transformer-based collaborative feature aggregation mechanism that integrates temporal or multi-view observations to construct a unified identity representation. Coupled with a cascaded super-resolution network, the framework enables progressive high-resolution face reconstruction. This approach is the first to jointly model multi-view or temporal coherence with cascaded super-resolution, significantly enhancing both face super-resolution quality and re-identification accuracy while preserving identity consistency. Extensive experiments demonstrate its superiority over state-of-the-art methods, validating the effectiveness of the proposed joint identity-aware reconstruction and progressive restoration strategy.

Abstract

We propose a novel collaborative approach for face super-resolution (SR) and robust person re-identification from sequential or multi-view facial images. Traditional SR methods often suffer from blurring and distortion in faces recovered from poor-quality images due to low resolution. Image- and video-based facial SR methods using facial landmarks or segmentation also have similar challenges. To overcome these limitations, we leverage multiple correlated facial observations, across time or viewpoints, by introducing a transformer-based collaborative feature aggregation method that unifies identity features from multi-sequence or multi-view data. This allows faces in multiple sequences of an individual to contribute to accurately estimating common facial features. Furthermore, we propose a cascade SR network to progressively restore the high-resolution image of the target's face with gradual facial feature unification. The unified identity representation is further utilized in person re-identification scenarios, enabling accurate matching even under severe image degradation. The exhaustive experimental results and comparisons show that our method outperforms other state-of-the-art methods, demonstrating consistent improvements in both face super-resolution and re-identification performance. Our work highlights the effectiveness of joint identity reconstruction and progressive image restoration from multiple facial inputs in enhancing downstream visual recognition tasks.

Problem

• face super-resolution
• person re-identification
• low-resolution images
• image degradation
• multi-view facial images

Innovation

• collaborative feature aggregation
• face super-resolution
• person re-identification
• transformer-based fusion
• multi-view facial reconstruction