cs.CVNov 18, 2026

Identity World Model: Recognizing People in an Imagined Latent World

Authors: Dingqiang Ye, Kartik Narayan, Vishal M. Patel

Organizations: Johns Hopkins University

Abstract

Whole-body human recognition has advanced rapidly with large vision models. However, existing methods remain fragile under real-world variations, as they tie identity to transient cues such as clothing, texture, pose, or viewpoint. We argue that a robust recognizer should not merely learn to ignore these cues, but imagine how a person would be represented if they changed. To this end, we propose IDWorld, an identity world model: just as a latent world model predicts the features of a scene after an action, IDWorld predicts how a person would be represented under a changed condition. In a single forward pass, IDWorld imagines these counterfactual features under shared canonical conditions, such as the same outfit, a fixed view, or a bare silhouette, without rendering any pixels. Compared with explicit imagination in pixels, this latent imagination keeps nearly the same accuracy while being over 11x faster, at 5.9 ms per frame. Since each imagined condition has its own strengths, IDWorld then fuses them adaptively, weighting each condition for every probe-gallery pair. Extensive experiments show that IDWorld achieves state-of-the-art results on CCPG and CCGR-MINI, outperforms the compared methods on MEVID, and generalizes best to CASIA-B* and SUSTech1K, with the best mAP on CCVID. These results suggest identity world models offer a simple yet effective path to robust recognition. Code will be released.

Figures & tables

Explore similar work

CardsList
  1. Thinking Before Matching: A Reinforcement Reasoning Paradigm Towards General Person Re-Identification

    Apr 21, 2026Quan Zhang, Jingze Wu, Jialong Wang +3Person Re-Identification

  2. NearID: Identity Representation Learning via Near-identity Distractors

    Apr 2, 2026Aleksandar Cvejic, Rameen Abdal, Abdelrahman Eldesokey +2Representation LearningVisual Representation Learning

  3. WithEveryone: Unified Planning and Identity Grounding for Group Image Generation

    Aug 20, 2026Hengyuan Xu, Qixun Wang, Yiji Cheng +4Subject-Driven Image GenerationImage Generation