Hybrid Gaussians for Robust Open-Vocabulary 3D Segmentation with Multi-View Object Association and Boundary Refinement

2026-09-23

AI Summary

该研究通过引入Hybrid Gaussians解决开放词汇3D分割中的多视图对象关联不稳定和语义区分度低的问题，结合观察融合、语义对比学习及边界重构优化方法。

Abstract

Open-vocabulary 3D segmentation localizes objects from free-form text queries, but remains challenging in real image sequences: incomplete or noisy 2D supervision destabilizes multi-view identity assignment, while full-scene semantic learning weakens object-level discriminability. We introduce Hybrid Gaussians, a unified 3D representation jointly modeling object association and language-aligned semantics. Its Multi-View Object Association mechanism combines Observation Fusion and Semantic Contrastive Learning to improve identity consistency and semantic discrimination. Boundary Reconstruction Optimization further refines local boundary structure to improve contour quality. Experiments on LERF and 3D-OVS demonstrate strong quantitative and qualitative performance. Our method achieves 59.1\% mIoU on LERF, yielding a 13.4\% relative gain over the baseline. Project page: https://nora202.github.io/hybridgaussians.

Problem

• Open-vocabulary 3D segmentation
• Multi-View Object Association
• Boundary Refinement

Innovation

• Hybrid Gaussians
• Multi-View Object Association
• Boundary Reconstruction Optimization
• Semantic Contrastive Learning