SOURCE-LINKED INTELLIGENCE

Object Concepts Emerge from Motion

arXiv · AI, language, vision and robotics · article · Sep 3, 2026 · UTC

Object-centric visual representations are important for physical-world perception, but existing visual pretraining methods often capture semantic categories without preserving the identity and coherence of individual instances. We present a biologically inspired framework that learns object-centric representations for single images from raw videos. Our approach uses motion boundaries as a source of object-level grouping: off-the-shelf optical flow and clustering produce pseudo-instance masks, which supervise a single-image encoder with pixel-level pairwise metric learning. The framework requir

Read original source ↗ Open in workspace

recordType

paper

region

Global