Interested in 3D DINO features from a single image or unsupervised scene understanding?🦖
Come by our SceneDINO poster at NeuSLAM today 14:15 (Kamehameha II) or Tue, 15:15 (Ex. Hall I 627)!
W/ Jevtić @fwimbauer.bsky.social @olvrhhn.bsky.social Rupprecht, @stefanroth.bsky.social @dcremers.bsky.social

Check out our blog post about SceneDINO 🦖
For more details, check out our project page, 🤗 demo, and the hashtag #ICCV2025 paper 🚀

🌍Project page: visinf.github.io/scenedino/
🤗Demo: visinf.github.io/scenedino/
📄Paper: arxiv.org/abs/2507.06230
@jev-aleks.bsky.social

✅ SceneDINO offers refined, high-resolution, and multi-view consistent (rendered) 2D features.

✅SceneDINO outperforms our unsupervised baseline (S4C + STEGO) in unsupervised SSC accuracy.
✅Linear probing our feature field leads to an SSC accuracy on par with 2D supervised S4C.

⚗️Distilling and clustering SceneDINO's feature field in 3D results in unsupervised semantic scene completion predictions.

🏋SceneDINO is trained to estimate an expressive 3D feature field using multi-view self-supervision and 2D DINO features.

🚀 SceneDINO is unsupervised and infers 3D geometry and features from a single image in a feed-forward manner. Distilling and clustering SceneDINO's 3D feature field lead to unsupervised semantic scene completion predictions.

🦖 We present “Feed-Forward SceneDINO for Unsupervised Semantic Scene Completion”. #ICCV2025
🌍: visinf.github.io/scenedino/
📃: arxiv.org/abs/2507.06230
🤗: huggingface.co/spaces/jev-a...
@jev-aleks.bsky.social @fwimbauer.bsky.social @olvrhhn.bsky.social @stefanroth.bsky.social @dcremers.bsky.social