LMMs Meet Object-Centric Vision: Understanding, Segmentation, Editing and Generation

Summary

This forum post shares a survey paper (arXiv: 2604.11789) examining the intersection of Large Multimodal Models (LMMs) and object-centric vision. While LMMs have made remarkable progress in general-purpose vision-language understanding, they remain limited in tasks requiring precise object-level grounding, fine-grained spatial reasoning, and controllable visual manipulation. Existing systems often struggle to identify the correct instance, preserve object identity across interactions, and localize or modify designated regions with high precision. The paper argues that object-centric vision offers a principled framework for addressing these challenges by enabling explicit representation and manipulation of visual entities. The survey comprehensively reviews recent advances across four major themes: object-centric visual understanding, referring segmentation, visual editing, and visual generation. Authors include Yuqian Yuan, Wenqiao Zhang, Yueting Zhuang, and Beng Chin Ooi, among others. The post was auto-collected on a Chinese tech forum and links to the full arXiv entry for readers seeking the complete survey.