Efficient Object-centric Representation Learning with Pre-trained Geometric Prior

TL;DR

This paper presents a weakly-supervised, object-centric video representation learning method that leverages pre-trained models and a novel slot decoder to effectively handle complex scenes without explicit depth data.

Contribution

It introduces a new framework combining geometric priors and pre-trained vision models with an efficient slot decoder for improved object discovery in videos.

Findings

Achieves comparable performance to supervised methods on synthetic benchmarks.

Handles complex scenes with multiple objects, occlusion, and camera motion.

Maintains computational efficiency for practical applications.

Abstract

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.