Skip to content
AI News HubLIVE
Original source2 min read

Object Concepts Emerge from Motion

Summary

A biologically inspired framework learns object-centric visual representations from raw video without human annotations or camera calibration. Using optical-flow-based pseudo-instance masks, it scales from 195 million pseudo-labeled frames to 421 million via motion-verified self-training, and achieves strong transfer on geometry- and instance-sensitive tasks such as depth estimation, 3D detection, and planning.

SourcearXiv Computer VisionAuthor: Boshi Li, Xiaohui Wang, Xiaoyang Wu, Zhichao Li, Ya Yang, Naiyan Wang
Object Concepts Emerge from Motion
Report an error

The correction channel is not available yet. You can copy the article reference below for later.

Correction instructions
Read article

[Submitted on 3 Sep 2026]

Title:Object Concepts Emerge from Motion

View a PDF of the paper titled Object Concepts Emerge from Motion, by Boshi Li and 5 other authors

View PDF HTML (experimental)

Abstract: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.

Subjects:

Computer Vision and Pattern Recognition (cs.CV)

Cite as: arXiv:2609.04348 [cs.CV]

(or arXiv:2609.04348v1 [cs.CV] for this version)

https://doi.org/10.48550/arXiv.2609.04348

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Boshi Li [view email] [v1] Thu, 3 Sep 2026 18:11:53 UTC (9,972 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled Object Concepts Emerge from Motion, by Boshi Li and 5 other authors

View PDF

HTML (experimental)

TeX Source

view license

Current browse context:

cs.CV

new | recent | 2026-09

Change to browse by:

cs

References & Citations

NASA ADS

Google Scholar

Semantic Scholar

Loading...

Data provided by:

Bibliographic Tools

Bibliographic and Citation Tools

Bibliographic Explorer Toggle

Bibliographic Explorer (What is the Explorer?)

Connected Papers Toggle

Connected Papers (What is Connected Papers?)

Litmaps Toggle

Litmaps (What is Litmaps?)

scite.ai Toggle

scite Smart Citations (What are Smart Citations?)

Code, Data, Media

Code, Data and Media Associated with this Article

alphaXiv Toggle

alphaXiv (What is alphaXiv?)

Links to Code Toggle

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub Toggle

DagsHub (What is DagsHub?)

GotitPub Toggle

Gotit.pub (What is GotitPub?)

Huggingface Toggle

Hugging Face (What is Huggingface?)

ScienceCast Toggle

ScienceCast (What is ScienceCast?)

Demos

Demos

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)

Related Papers

Recommenders and Search Tools

Link to Influence Flower

Influence Flower (What are Influence Flowers?)

Core recommender toggle

CORE Recommender (What is CORE?)

Author

Venue

Institution

Topic

About arXivLabs

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)

Key points and analysis

Article intelligence

EngineersAdvanced

Key points

  • Motion boundaries from optical flow and clustering provide pseudo-instance supervision for a single-image encoder.
  • Training starts with 195M pseudo-labeled frames and expands to 421M frames using motion-verified self-training.
  • Encoders up to Swin-H are trained and distilled into Swin backbones.
  • Strong downstream results on monocular depth, 3D detection, 3D occupancy, and planning demonstrate instance-aware representations.

Highlights and analysis are generated automatically and may contain errors. Check the original source.