LangSplat: 3D Language Gaussian Splatting
Tsinghua University · Harvard University Press
Abstract
Humans live in a 3D world and commonly use natural language to interact with a 3D scene. Modeling a 3D language field to support open-ended language queries in 3D has gained increasing attention recently. This paper introduces LangSplat, which constructs a 3D language field that enables precise and efficient open-vocabulary querying within 3D spaces. Unlike existing methods that ground CLIP language embeddings in a NeRF model, LangSplat advances the field by utilizing a collection of 3D Gaussians, each encoding language features distilled from CLIP, to represent the language field. By employing a tile-based splatting technique for rendering language features, we circumvent the costly rendering process inherent…
Citation impact
- FWCI
- 37.31
- Percentile
- 100%
- References
- 61
Authors
5Topics & keywords
- Computer science
- Gaussian
- Computer graphics (images)
- Physics