Efficient Object-centric Representation Learning with Pre-trained Geometric Prior
This work addresses the problem of object discovery in videos for applications in complex real-world scenarios, representing an incremental improvement over existing approaches.
The paper tackles the challenge of object-centric representation learning in complex video scenes by proposing a weakly-supervised framework that leverages pre-trained geometric priors, achieving performance comparable to supervised methods on synthetic benchmarks.
This paper addresses key challenges in object-centric representation learning of video. While existing approaches struggle with complex scenes, we propose a novel weakly-supervised framework that emphasises geometric understanding and leverages pre-trained vision models to enhance object discovery. Our method introduces an efficient slot decoder specifically designed for object-centric learning, enabling effective representation of multi-object scenes without requiring explicit depth information. Results on synthetic video benchmarks with increasing complexity in terms of objects and their movement, object occlusion and camera motion demonstrate that our approach achieves comparable performance to supervised methods while maintaining computational efficiency. This advances the field towards more practical applications in complex real-world scenarios.