From the 1 of 3 linked papers with an AI index.
3 papers
Slot-RAE: Streamlining Object-Centric Learning via Direct Representation Auto-Encoders
Alexandre Chapin, Emmanuel Dellandrea, Liming Chen
Slot-RAE is an object‑centric model that learns to decompose and reconstruct scenes directly in the feature space of frozen visual foundation models using a diffusion transformer d…
Is an object-centric representation beneficial for robotic manipulation ?
Alexandre Chapin, Emmanuel Dellandrea, Liming Chen
Object-centric representation (OCR) has recently become a subject of interest in the computer vision community for learning a structured representation of images and videos. It has…
Object-Centric Representations Improve Policy Generalization in Robot Manipulation
Alexandre Chapin, Bruno Machado, Emmanuel Dellandrea +1
Visual representations are central to the learning and generalization capabilities of robotic manipulation policies. While existing methods rely on global or dense features, such r…