Seungjun Lee · Zihan Wang · Yunsong Wang · Gim Hee Lee
National University of Singapore

Build and understand at Once! By taking over 300 streaming images, our EmbodiedSplat reconstructs whole-scene open-vocabulary 3DGS in online manner at up to 5-6 FPS per-frame processing time. Reconstructed scene supports diverse perception tasks such as open-vocabulary 3D semantic segmentation, 2D-rendered semantic segmentation and novel-view color synthesis with depth rendering.

• [2026/02/21] EmbodiedSplat is accepted to CVPR 2026 🔥. The code will be released before June.

• Release the code of EmbodiedSplat

If you find our code or paper useful, please cite

@article{lee2026embodiedsplat,
  title={EmbodiedSplat: Online Feed-Forward Semantic 3DGS for Open-Vocabulary 3D Scene Understanding},
  author={Lee, Seungjun and Wang, Zihan and Wang, Yunsong and Lee, Gim Hee},
  journal={arXiv preprint arXiv:2603.04254},
  year={2026}
}