
DY
Dingqiang Ye, Kartik Narayan, Vishal M. Patel
· 1 min read
ResearcharXiv cs.CV
Identity World Model: Recognizing People in an Imagined Latent World
arXiv:2611.25204v1 Announce Type: new
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.
Original source
This story was published by arXiv cs.CV and written by Dingqiang Ye, Kartik Narayan, Vishal M. Patel. SyncAI.news shows a preview; the complete article is on the publisher's site.
Read the full story on arxiv.org


