Language Embedded 3D Gaussians for Open-Vocabulary Scene Understanding
This addresses the challenge of efficient and accurate scene understanding for applications like robotics and AR/VR, though it is incremental in improving existing language-embedded representations.
The paper tackles the problem of open-vocabulary querying in 3D scenes by introducing Language Embedded 3D Gaussians, which achieves the best visual quality and language querying accuracy while maintaining real-time rendering on a single GPU.
Open-vocabulary querying in 3D space is challenging but essential for scene understanding tasks such as object localization and segmentation. Language-embedded scene representations have made progress by incorporating language features into 3D spaces. However, their efficacy heavily depends on neural networks that are resource-intensive in training and rendering. Although recent 3D Gaussians offer efficient and high-quality novel view synthesis, directly embedding language features in them leads to prohibitive memory usage and decreased performance. In this work, we introduce Language Embedded 3D Gaussians, a novel scene representation for open-vocabulary query tasks. Instead of embedding high-dimensional raw semantic features on 3D Gaussians, we propose a dedicated quantization scheme that drastically alleviates the memory requirement, and a novel embedding procedure that achieves smoother yet high accuracy query, countering the multi-view feature inconsistencies and the high-frequency inductive bias in point-based representations. Our comprehensive experiments show that our representation achieves the best visual quality and language querying accuracy across current language-embedded representations, while maintaining real-time rendering frame rates on a single desktop GPU.