Recover and Identify: A Generative Dual Model for Cross-Resolution Person Re-Identification
This addresses a practical problem in real-world surveillance systems where resolution mismatch degrades person re-identification performance.
The paper tackles cross-resolution person re-identification by proposing a generative adversarial network that learns resolution-invariant representations and recovers missing details in low-resolution images, achieving state-of-the-art performance on five benchmark datasets, particularly with unseen input resolutions.
Person re-identification (re-ID) aims at matching images of the same identity across camera views. Due to varying distances between cameras and persons of interest, resolution mismatch can be expected, which would degrade person re-ID performance in real-world scenarios. To overcome this problem, we propose a novel generative adversarial network to address cross-resolution person re-ID, allowing query images with varying resolutions. By advancing adversarial learning techniques, our proposed model learns resolution-invariant image representations while being able to recover the missing details in low-resolution input images. The resulting features can be jointly applied for improving person re-ID performance due to preserving resolution invariance and recovering re-ID oriented discriminative details. Our experiments on five benchmark datasets confirm the effectiveness of our approach and its superiority over the state-of-the-art methods, especially when the input resolutions are unseen during training.