SLGaussian: Fast Language Gaussian Splatting in Sparse Views

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Chen, Kangjie, Dai, BingQuan, Qin, Minghan, Zhang, Dongbin, Li, Peihao, Zou, Yingshuang, Wang, Haoqian
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866916903512965120
author Chen, Kangjie
Dai, BingQuan
Qin, Minghan
Zhang, Dongbin
Li, Peihao
Zou, Yingshuang
Wang, Haoqian
author_facet Chen, Kangjie
Dai, BingQuan
Qin, Minghan
Zhang, Dongbin
Li, Peihao
Zou, Yingshuang
Wang, Haoqian
contents 3D semantic field learning is crucial for applications like autonomous navigation, AR/VR, and robotics, where accurate comprehension of 3D scenes from limited viewpoints is essential. Existing methods struggle under sparse view conditions, relying on inefficient per-scene multi-view optimizations, which are impractical for many real-world tasks. To address this, we propose SLGaussian, a feed-forward method for constructing 3D semantic fields from sparse viewpoints, allowing direct inference of 3DGS-based scenes. By ensuring consistent SAM segmentations through video tracking and using low-dimensional indexing for high-dimensional CLIP features, SLGaussian efficiently embeds language information in 3D space, offering a robust solution for accurate 3D scene understanding under sparse view conditions. In experiments on two-view sparse 3D object querying and segmentation in the LERF and 3D-OVS datasets, SLGaussian outperforms existing methods in chosen IoU, Localization Accuracy, and mIoU. Moreover, our model achieves scene inference in under 30 seconds and open-vocabulary querying in just 0.011 seconds per query.
format Preprint
id arxiv_https___arxiv_org_abs_2412_08331
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle SLGaussian: Fast Language Gaussian Splatting in Sparse Views
Chen, Kangjie
Dai, BingQuan
Qin, Minghan
Zhang, Dongbin
Li, Peihao
Zou, Yingshuang
Wang, Haoqian
Computer Vision and Pattern Recognition
3D semantic field learning is crucial for applications like autonomous navigation, AR/VR, and robotics, where accurate comprehension of 3D scenes from limited viewpoints is essential. Existing methods struggle under sparse view conditions, relying on inefficient per-scene multi-view optimizations, which are impractical for many real-world tasks. To address this, we propose SLGaussian, a feed-forward method for constructing 3D semantic fields from sparse viewpoints, allowing direct inference of 3DGS-based scenes. By ensuring consistent SAM segmentations through video tracking and using low-dimensional indexing for high-dimensional CLIP features, SLGaussian efficiently embeds language information in 3D space, offering a robust solution for accurate 3D scene understanding under sparse view conditions. In experiments on two-view sparse 3D object querying and segmentation in the LERF and 3D-OVS datasets, SLGaussian outperforms existing methods in chosen IoU, Localization Accuracy, and mIoU. Moreover, our model achieves scene inference in under 30 seconds and open-vocabulary querying in just 0.011 seconds per query.
title SLGaussian: Fast Language Gaussian Splatting in Sparse Views
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2412.08331