English

Identifiable Object Representations under Spatial Ambiguities

Machine Learning 2025-06-10 v1 Computer Vision and Pattern Recognition

Abstract

Modular object-centric representations are essential for *human-like reasoning* but are challenging to obtain under spatial ambiguities, *e.g. due to occlusions and view ambiguities*. However, addressing challenges presents both theoretical and practical difficulties. We introduce a novel multi-view probabilistic approach that aggregates view-specific slots to capture *invariant content* information while simultaneously learning disentangled global *viewpoint-level* information. Unlike prior single-view methods, our approach resolves spatial ambiguities, provides theoretical guarantees for identifiability, and requires *no viewpoint annotations*. Extensive experiments on standard benchmarks and novel complex datasets validate our method's robustness and scalability.

Keywords

Cite

@article{arxiv.2506.07806,
  title  = {Identifiable Object Representations under Spatial Ambiguities},
  author = {Avinash Kori and Francesca Toni and Ben Glocker},
  journal= {arXiv preprint arXiv:2506.07806},
  year   = {2025}
}
R2 v1 2026-07-01T03:07:07.151Z