Abstract
Aerial-Ground Person Re-IDentification (AG-ReID) aims to retrieve specific persons across cameras with different viewpoints. Previous works focus on designing discriminative ReID models to maintain identity consistency despite drastic changes in camera viewpoints. The core idea behind these methods is quite natural, but designing a view-robust network is a very challenging task. Moreover, they overlook the contribution of view-specific features in enhancing the model's capability to represent persons. To address these issues, we propose a novel two-stage feature learning framework named SD-ReID for AG-ReID, which takes advantage of the powerful understanding capacity of generative models, e.g., Stable Diffusion (SD), to generate view-specific features between different viewpoints. In the first stage, we train a simple ViT-based model to extract coarse-grained representations and controllable conditions. Then, in the second stage, we fine-tune the SD model to learn complementary representations guided by the controllable conditions. Furthermore, we propose the View-Refine Decoder (VRD) to obtain additional controllable conditions to generate missing cross-view features. Finally, we use the coarse-grained representations and all-view features generated by SD to retrieve target persons. Extensive experiments on the AG-ReID benchmarks demonstrate the effectiveness of our proposed SD-ReID. The source code will be available upon acceptance.
Abstract (translated)
Aerial-Ground Person Re-IDentification（AG-ReID）旨在跨不同视角的摄像头检索特定人物。之前的研究主要集中在设计具有区分性的ReID模型，以维持身份的一致性，即使在摄像机视点发生剧烈变化的情况下也不例外。这些方法的核心思想非常自然，但设计一个对视图鲁棒的网络是一项极具挑战性的任务。此外，它们忽略了视角特有特征对于提升模型表示人物能力的作用。 为了解决这些问题，我们提出了一种新的两阶段特征学习框架SD-ReID用于AG-ReID，该框架利用生成模型（如Stable Diffusion (SD)）的强大理解能力来生成不同视点之间的视角特定特征。在第一阶段中，我们训练一个基于ViT的简单模型以提取粗粒度表示和可控条件。然后，在第二阶段中，我们在可控条件下引导微调SD模型学习互补表示。此外，我们提出了视图细化解码器（VRD），用于获取额外的可控条件来生成缺失的跨视角特征。最后，我们使用由SD生成的所有视角特征以及粗粒度表示来进行目标人物检索。 在AG-ReID基准测试上的大量实验表明了我们提出的SD-ReID的有效性。源代码将在接受后提供。
URL
https://arxiv.org/abs/2504.09549
