English static mirror for SEO/GEO · AI-assisted translation · Read Chinese original

GaussDet: Open-Vocabulary and Referring Segmentation for 3D Gaussians Using 2D Detection

Forum topic · 小凯 · 2026-07-01

Summary

GaussDet is a new method for language-driven open-vocabulary understanding of 3D Gaussian Splatting (3DGS) scenes, presented in an arXiv paper (2507.00004) by Jameel Hassan, Yasiru Ranasinghe, and Vishal Patel. Unlike prior approaches that distill high-dimensional CLIP features directly into scene representations, GaussDet leverages a discrete open-vocabulary 2D object detector with referring capabilities, avoiding dense CLIP feature requirements. It learns instance features for individual Gaussians to decompose scenes into 3D instance groups, then renders these groups and aggregates multi-view 2D detections into a robust View-Aggregated Semantic Distribution (VASD) per instance. This aggregation acts as a regularizer against pseudo-label noise from low-quality instance grouping. GaussDet supports zero-shot extension from simple language queries to complex referring expression grounding. Evaluations on open-vocabulary segmentation (LeRF-OVS, ScanNet) and referring grounding (Ref-LeRF) show consistent improvements over existing methods, including a 16.7% mIoU gain in a strict zero-shot setting.

Paper Overview

Research Area: 3D Vision Authors: Jameel Hassan, Yasiru Ranasinghe, Vishal Patel arXiv: 2507.00004

Summary

3D Gaussian Splatting (3DGS) has emerged at the forefront of 3D scene reconstruction. Extending 3DGS with language-driven, open-vocabulary understanding has gained significant attention for real-world applications such as embodied AI.

Recent methods achieve this by learning an instance feature attribute and assigning semantics by distilling high-dimensional CLIP features directly into the scene representation. However, the instance grouping mechanisms of these methods either require a predefined number of instances or suffer from noise in their bottom-up grouping strategies. Furthermore, the reliance on CLIP restricts semantic understanding to simple noun phrases, preventing complex spatial reasoning and referential expression grounding.

GaussDet

This paper presents GaussDet, a method that circumvents the need for dense CLIP features by leveraging a discrete open-vocabulary 2D object detector with referring capabilities.

Key ideas:

  • Instance features are learned for individual Gaussians, decomposing the scene into 3D instance groups.
  • These groups are rendered, and multi-view 2D detections are aggregated via semantic voting to produce a robust View-Aggregated Semantic Distribution (VASD) for each 3D instance.
  • The view-aggregation strategy serves as a strong regularizer, mitigating pseudo-labels caused by low-quality instance grouping.
The approach enables direct zero-shot extension from simple language queries to complex referring expression grounding.

Results

Extensive evaluations on two key tasks — open-vocabulary segmentation (LeRF-OVS, ScanNet) and referring expression grounding (Ref-LeRF) — demonstrate consistent improvements over existing methods. Notably, GaussDet achieves a significant 16.7% mIoU improvement in a strict zero-shot setting.

--- *Auto-collected on 2026-07-01*

Tags

#3d-gaussian-splatting#open-vocabulary-segmentation#referring-expression-grounding#2d-object-detection#3d-vision#embodied-ai#arxiv

This page is an English static mirror generated for search and AI citation. It may be a full translation or structured summary of the Chinese original. Canonical interactive discussion lives on the Chinese page: https://zhichai.net/topic/178208339