Metraipolis › archive › dc_a2ef9032cdc8

Object Concepts Emerge from Motion — arXiv:2609.04348

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.04348
License (as archived): CC0-1.0
Archived: 2026-10-16T23:33:19.402Z
SHA-256 of the archived text: e06986b2e64eec38650ed52e88759b953f470541b4930b6b91777ba326d7e204
Stable URL of this page: https://metraipolis.com/documento/dc_a2ef9032cdc8

How to cite

Object Concepts Emerge from Motion — arXiv:2609.04348 — arXiv (en), https://arxiv.org/abs/2609.04348 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_a2ef9032cdc8 (Metraipolis archive dc_a2ef9032cdc8, sha256 e06986b2e64eec38650ed52e88759b953f470541b4930b6b91777ba326d7e204)

BibTeX

@misc{dca2ef9032cdc8,
  title = {Object Concepts Emerge from Motion — arXiv:2609.04348},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.04348},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_a2ef9032cdc8; sha256 e06986b2e64eec38650ed52e88759b953f470541b4930b6b91777ba326d7e204},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.04348. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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 requires neither human annotations nor camera calibration. We first obtain 195 million pseudo-labeled frames from 7,163 hours of driving and web videos, then expand the supervision to 421 million frames with Motion-Verified Self-Training, which combines model proposals with motion evidence. We train encoders up to Swin-H and distill the learned representations into a family of Swin backbones. Across monocular depth estimation, 3D object detection, 3D occupancy prediction, and end-to-end planning, the resulting models achieve competitive or superior performance relative to supervised and self-supervised pretraining baselines, with particularly strong transfer on geometry- and instance-sensitive tasks. These results show that motion-derived supervision can teach static image encoders to represent visual instances, providing a complementary direction for scalable visual pretraining.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-07 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2609.04348 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-16T23:16:11.377Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-07?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).