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 results in unsupervised semantic scene completion predictions. The method is trained using multi-view self-supervision.

Please refer to our Github Repo.

If you find our work useful, please consider giving it a star ⭐ and citing our paper.