WHU-MARS：面向任意场景行人重识别的多光谱空地基准
WHU-MARS: A Multispectral Aerial-Ground Benchmark Towards Any-Scenario Person Re-Identification
WHU-MARS 提供了覆盖 RGB/近红外/热红外 × 地面/无人机视角的统一异构图库，可直接用于评测「单模型跨任意模态-视角组合检索」；其 ProCA+GPD 思路（先把多视角特征聚成模态中心再对齐到身份中心，并用全局身份原型做对比）可作为处理模态/视角域偏置的通用表征对齐手段迁移到其他跨域检索任务。
原文依据 given a query from any (modality, viewpoint) scenario, a single model retrieves the same identity from a heterogeneous gallery spanning all scenarios
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论近期的行人重识别（ReID）利用多模态、多视角的异构感知来提升跨多样条件的鲁棒性。然而，大多数方法针对预先定义的场景对（例如可见光-红外或空地），并分别训练任务专用模型。相比之下，真实系统往往需要在覆盖所有场景的图库中进行查询，这使得此类设计效率低下且部署复杂。为弥合这一差距，我们提出任意场景行人重识别（AS-ReID）：给定来自任意（模态、视角）场景的查询，由单一模型从横跨所有场景的异构图库中检索出同一身份。AS-ReID 的进展受两个因素制约：(i) 缺乏覆盖广泛场景、与真实世界对齐的基准；(ii) 在多样场景下学习兼具强类内凝聚性与强类间判别性的表征存在挑战。为此，我们构建了 WHU-MARS，一个多光谱空地基准，包含 2,337 个身份、434,620 张图像，由地面与无人机平台上的 RGB、近红外和热红外相机采集。WHU-MARS 覆盖昼夜、多个季节和多样天气，可支持 AS-ReID 以及传统 ReID 任务。我们进一步提出统一对齐与判别（UAD）框架。渐进中心对齐（ProCA）将多视角特征聚合为模态中心，再将其对齐到身份中心以减少场景偏置。全局原型判别（GPD）将样本与全局身份原型进行对比，以施加大幅间隔判别。大量实验凸显了 WHU-MARS 的挑战性，并证明了 UAD 在 AS-ReID 上的有效性。
英文原文摘要 1740 字符
Recent person re-identification (ReID) leverages heterogeneous sensing with multiple modalities and viewpoints to improve robustness across diverse conditions. However, most approaches target predefined scenario pairs (e.g., visible-infrared or aerial-ground) and train separate task-specific models. In contrast, real-world systems often query against galleries that cover all scenarios, making such designs inefficient and complex to deploy. To bridge this gap, we introduce Any-Scenario ReID (AS-ReID): given a query from any (modality, viewpoint) scenario, a single model retrieves the same identity from a heterogeneous gallery spanning all scenarios. Progress toward AS-ReID is limited by two factors: (i) the lack of a real-world-aligned benchmark with broad scenario coverage, and (ii) the challenge of learning representations with strong intra-identity cohesion and inter-identity discrimination under diverse scenarios. To this end, we construct WHU-MARS, a multispectral aerial-ground benchmark with 2,337 identities and 434,620 images captured by RGB, near-infrared, and thermal infrared cameras on both ground and UAV platforms. WHU-MARS spans day-night, multiple seasons, and diverse weather, enabling AS-ReID as well as conventional ReID tasks. We further propose the Unified Alignment and Discrimination (UAD) framework. Progressive Center Alignment (ProCA) aggregates multi-view features into modality centers and then aligns them toward identity centers to reduce scenario bias. Global Prototype Discrimination (GPD) contrasts samples against global identity prototypes to enforce large-margin discrimination. Extensive experiments highlight the challenges of WHU-MARS and demonstrate the effectiveness of UAD on AS-ReID.