pith. sign in

arxiv: 2606.08014 · v1 · pith:ADC3QOKMnew · submitted 2026-06-06 · 💻 cs.CV · cs.AI

GVC-Seg: Training-Free 3D Instance Segmentation via Geometric Visual Correspondence

classification 💻 cs.CV cs.AI
keywords instancesegmentationbiasconfidencecorrespondencegeometricgvc-segmodels
0
0 comments X
read the original abstract

Accurate 3D instance segmentation in point cloud data is critical for machine vision applications. Recent advancements leverage multiple pre-trained foundation models to generate 3D proposals, followed by the application of proposal aggregation methods, which significantly enhance performance. However, they often produce sub-optimal results due to inherent variations in confidence levels across different segmentation models, resulting in a bias toward the model with higher confidence. This bias is inherently model-dependent and is influenced by factors such as data preprocessing techniques and training strategies. To address this bias, we propose a novel, training-free 3D instance segmentation approach via Geometric Visual Correspondence (GVC-Seg), which exploits the correspondence between 3D geometric cues and 2D visual cues to mitigate the confidence bias. Additionally, a 3D proposal generation module and a mask-aware CLIP feature extraction module are introduced during the instance mask generation and instance semantic reasoning, respectively. In this way, GVC-Seg enhances proposal quality assessment, ensuring unbiased ensemble learning across different models. Extensive experiments demonstrate that our method achieves state-of-the-art performance on several challenging benchmarks, while also exhibiting strong potential in open-vocabulary semantic segmentation settings.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.