pith. sign in

arxiv: 2306.13631 · v2 · pith:75E4WVQQnew · submitted 2023-06-23 · 💻 cs.CV

OpenMask3D: Open-Vocabulary 3D Instance Segmentation

classification 💻 cs.CV
keywords open-vocabularyinstancesegmentationopenmask3dmethodsobjectaddressexperiments
0
0 comments X
read the original abstract

We introduce the task of open-vocabulary 3D instance segmentation. Current approaches for 3D instance segmentation can typically only recognize object categories from a pre-defined closed set of classes that are annotated in the training datasets. This results in important limitations for real-world applications where one might need to perform tasks guided by novel, open-vocabulary queries related to a wide variety of objects. Recently, open-vocabulary 3D scene understanding methods have emerged to address this problem by learning queryable features for each point in the scene. While such a representation can be directly employed to perform semantic segmentation, existing methods cannot separate multiple object instances. In this work, we address this limitation, and propose OpenMask3D, which is a zero-shot approach for open-vocabulary 3D instance segmentation. Guided by predicted class-agnostic 3D instance masks, our model aggregates per-mask features via multi-view fusion of CLIP-based image embeddings. Experiments and ablation studies on ScanNet200 and Replica show that OpenMask3D outperforms other open-vocabulary methods, especially on the long-tail distribution. Qualitative experiments further showcase OpenMask3D's ability to segment object properties based on free-form queries describing geometry, affordances, and materials.

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.

Forward citations

Cited by 18 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Open-Vocabulary and Referring Segmentation for 3D Gaussians Using 2D Detectors

    cs.CV 2026-06 unverdicted novelty 7.0

    GaussDet enables open-vocabulary and referring segmentation in 3D Gaussians by learning instance features and aggregating votes from 2D detectors, improving referential grounding by 16.7% mIoU in zero-shot setting.

  2. 3AM: 3egment Anything with Geometric Consistency in Videos

    cs.CV 2026-01 unverdicted novelty 7.0

    3AM integrates MUSt3R 3D features into SAM2 via a Feature Merger and FOV-aware sampling to deliver geometry-consistent video object segmentation from RGB alone, with large gains on wide-baseline datasets.

  3. OpenTrack3D: Towards Accurate and Generalizable Open-Vocabulary 3D Instance Segmentation

    cs.CV 2025-12 unverdicted novelty 7.0

    OpenTrack3D achieves state-of-the-art open-vocabulary 3D instance segmentation by generating cross-view consistent proposals online with a visual-spatial tracker and replacing CLIP with an MLLM for improved compositio...

  4. Segment and Select: Vision-Language Segmentation in 3D Scenarios

    cs.CV 2026-06 unverdicted novelty 6.0

    SEGA3D improves 3D vision-language segmentation on ScanNet and Matterport3D by operating on fine-grained masks with LLM-assisted selection, claiming gains of 8.3 and 5.3 mIoU over prior top methods.

  5. Coarse Semantic Injection for LLM-Conditioned Structured Indoor Prediction

    cs.CV 2026-05 unverdicted novelty 6.0

    Coarse four-group semantic color coding (RGBB) appended to point clouds before tokenization improves LLM-based structured indoor prediction on Structured3D, SpatialLM, and ARKitScenes, especially for openings and furn...

  6. ClickSeg3D: Few-Click Interactive Segmentation via Semantic Embeddings

    cs.CV 2026-05 unverdicted novelty 6.0

    ClickSeg3D uses a point Transformer encoder and hierarchical mask decoder with semantic embeddings to enable single-pass multi-object 3D interactive segmentation from sparse points, reporting over 20% mIoU gains versu...

  7. ClickSeg3D: Few-Click Interactive Segmentation via Semantic Embeddings

    cs.CV 2026-05 unverdicted novelty 6.0

    A point-Transformer interactive 3D instance segmentation model handles multiple clicks jointly in one pass and reports over 20% mIoU gains versus baselines plus 8-10% cross-dataset improvement for one-click-per-instan...

  8. Memory Over Maps: 3D Object Localization Without Reconstruction

    cs.RO 2026-03 unverdicted novelty 6.0

    A map-free localization method stores posed RGB-D keyframes, retrieves and re-ranks them with a VLM, then fuses sparse depth for on-demand 3D target estimates, matching reconstruction-based performance on navigation b...

  9. TrianguLang: Geometry-Aware Semantic Consensus for Pose-Free 3D Localization

    cs.CV 2026-03 unverdicted novelty 6.0

    TrianguLang achieves state-of-the-art feed-forward text-guided 3D localization and segmentation by using predicted geometry to gate cross-view semantic correspondences without ground-truth poses.

  10. ShelfGaussian: Shelf-Supervised Open-Vocabulary Gaussian-based 3D Scene Understanding

    cs.CV 2025-12 unverdicted novelty 6.0

    ShelfGaussian achieves state-of-the-art zero-shot semantic occupancy prediction on Occ3D-nuScenes by jointly supervising Gaussian representations with vision foundation model features at 2D image and 3D scene levels.

  11. ObsGraph: Hierarchical Observation Representation for Embodied Reasoning and Exploration

    cs.CV 2026-06 unverdicted novelty 5.0

    ObsGraph is a hierarchical observation-centric scene graph that unifies representation, retrieval, and multi-scale exploration for embodied reasoning.

  12. Lightweight 3D Feature Pretraining by Bayesian Inversion of 2D Foundation Models

    cs.CV 2026-06 unverdicted novelty 5.0

    Casper3D is a backbone-agnostic variational model that infers stable 3D semantics from noisy 2D embeddings by treating them as observations of a latent 3D state and training via held-out viewpoint prediction.

  13. Geometric-Aware Hypergraph Reasoning for Novel Class Discovery in Point Cloud Segmentation

    cs.CV 2026-06 unverdicted novelty 5.0

    Hypergraph reasoning with geometric-aware prototypes for novel class discovery in point cloud segmentation.

  14. OSMa-Bench++: Toward Open-Ended Benchmarking of Semantic Mapping for Manipulation with Prompt-Generated Synthetic Scenes

    cs.CV 2026-05 unverdicted novelty 5.0

    OSMa-Bench++ generates prompt-based synthetic scenes and adapts them for extensible benchmarking of semantic mapping methods aimed at robotic manipulation.

  15. AgentGrounder: Zero-Shot 3D Visual Pointcloud Grounding using Multimodal Language Models

    cs.CV 2026-05 unverdicted novelty 5.0

    AgentGrounder performs zero-shot 3D visual grounding on colored point clouds via an offline object lookup table and an online agent that selectively retrieves, scores geometrically, and renders images on demand, repor...

  16. MV3DIS: Multi-View Mask Matching via 3D Guides for Zero-Shot 3D Instance Segmentation

    cs.CV 2026-04 unverdicted novelty 5.0

    MV3DIS uses 3D-guided mask matching and depth consistency to produce more consistent multi-view 2D masks that refine into accurate zero-shot 3D instances.

  17. LIVE-GS: LLM Powers Interactive VR Experience with Physics-Aware Gaussian Splatting

    cs.HC 2024-12 unverdicted novelty 5.0

    LIVE-GS uses an LLM to predict physical parameters from static Gaussian assets in 10 seconds for physics-aware VR interactions, validated by interviews, baseline comparisons, and user studies.

  18. Open-Architecture End-to-End System for Real-World Autonomous Robot Navigation

    cs.RO 2024-10 unverdicted novelty 4.0

    Presents an open ROS2-based end-to-end navigation system for quadruped robots achieving over 88% success in zero-shot real-world indoor navigation tasks using semantic scene graphs and LLM planning.