InstanceGaussian: Appearance-Semantic Joint Gaussian Representation for 3D Instance-Level Perception

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Li, Haijie, Wu, Yanmin, Meng, Jiarui, Gao, Qiankun, Zhang, Zhiyao, Wang, Ronggang, Zhang, Jian
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916690115166208
author Li, Haijie
Wu, Yanmin
Meng, Jiarui
Gao, Qiankun
Zhang, Zhiyao
Wang, Ronggang
Zhang, Jian
author_facet Li, Haijie
Wu, Yanmin
Meng, Jiarui
Gao, Qiankun
Zhang, Zhiyao
Wang, Ronggang
Zhang, Jian
contents 3D scene understanding has become an essential area of research with applications in autonomous driving, robotics, and augmented reality. Recently, 3D Gaussian Splatting (3DGS) has emerged as a powerful approach, combining explicit modeling with neural adaptability to provide efficient and detailed scene representations. However, three major challenges remain in leveraging 3DGS for scene understanding: 1) an imbalance between appearance and semantics, where dense Gaussian usage for fine-grained texture modeling does not align with the minimal requirements for semantic attributes; 2) inconsistencies between appearance and semantics, as purely appearance-based Gaussians often misrepresent object boundaries; and 3) reliance on top-down instance segmentation methods, which struggle with uneven category distributions, leading to over- or under-segmentation. In this work, we propose InstanceGaussian, a method that jointly learns appearance and semantic features while adaptively aggregating instances. Our contributions include: i) a novel Semantic-Scaffold-GS representation balancing appearance and semantics to improve feature representations and boundary delineation; ii) a progressive appearance-semantic joint training strategy to enhance stability and segmentation accuracy; and iii) a bottom-up, category-agnostic instance aggregation approach that addresses segmentation challenges through farthest point sampling and connected component analysis. Our approach achieves state-of-the-art performance in category-agnostic, open-vocabulary 3D point-level segmentation, highlighting the effectiveness of the proposed representation and training strategies. Project page: https://lhj-git.github.io/InstanceGaussian/
format Preprint
id arxiv_https___arxiv_org_abs_2411_19235
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle InstanceGaussian: Appearance-Semantic Joint Gaussian Representation for 3D Instance-Level Perception
Li, Haijie
Wu, Yanmin
Meng, Jiarui
Gao, Qiankun
Zhang, Zhiyao
Wang, Ronggang
Zhang, Jian
Computer Vision and Pattern Recognition
3D scene understanding has become an essential area of research with applications in autonomous driving, robotics, and augmented reality. Recently, 3D Gaussian Splatting (3DGS) has emerged as a powerful approach, combining explicit modeling with neural adaptability to provide efficient and detailed scene representations. However, three major challenges remain in leveraging 3DGS for scene understanding: 1) an imbalance between appearance and semantics, where dense Gaussian usage for fine-grained texture modeling does not align with the minimal requirements for semantic attributes; 2) inconsistencies between appearance and semantics, as purely appearance-based Gaussians often misrepresent object boundaries; and 3) reliance on top-down instance segmentation methods, which struggle with uneven category distributions, leading to over- or under-segmentation. In this work, we propose InstanceGaussian, a method that jointly learns appearance and semantic features while adaptively aggregating instances. Our contributions include: i) a novel Semantic-Scaffold-GS representation balancing appearance and semantics to improve feature representations and boundary delineation; ii) a progressive appearance-semantic joint training strategy to enhance stability and segmentation accuracy; and iii) a bottom-up, category-agnostic instance aggregation approach that addresses segmentation challenges through farthest point sampling and connected component analysis. Our approach achieves state-of-the-art performance in category-agnostic, open-vocabulary 3D point-level segmentation, highlighting the effectiveness of the proposed representation and training strategies. Project page: https://lhj-git.github.io/InstanceGaussian/
title InstanceGaussian: Appearance-Semantic Joint Gaussian Representation for 3D Instance-Level Perception
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2411.19235