works on
diffusion models 1object-centric learning 1slot attention 1unsupervised object discovery 1visual foundation models 1

From the 1 of 4 linked papers with an AI index.

collaborators
Showing cs.CVShow all

1 paper · 1 filter

cs.CV2026

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…