Overview

3D instance segmentation assigns scene elements to individual objects, often alongside semantic labels, so robots and mapping systems can reason about cluttered or incomplete environments. Common approaches use point-cloud networks with query-based mask decoders or superpoint clustering, while newer pipelines lift 2D foundation-model masks across views or learn object identities in 3D Gaussian scenes. Indoor benchmarks such as ScanNet and ScanNet200, outdoor driving datasets such as SemanticKITTI and nuScenes, and domain-specific forest and biomedical data test these methods in different settings. A central challenge is balancing accurate, consistent object boundaries and open-vocabulary generalization with limited labels, occlusion, and the speed and memory demands of large scenes.

Latest papers

CardsList

68 papers6 papers in the last four weeks, down 40% on the four weeks before. 0.0% of all new papers.

  1. WHU-Road3D: A dataset and benchmark towards fine-grained road surface mapping

    Nov 19, 2026Xiaoxin Mi, Zhen Cao, Chong Liu +5Multimodal DatasetAutonomous Driving Datasets

  2. InterRSGaussian: Interactive Multi-view Instance Segmentation for 3D Remote Sensing Scenes

    Nov 16, 2026Zipeng Qi, Zhengxia Zou, Zhenwei ShiInstance SegmentationRemote Sensing Image Segmentation

  3. From Geometry to Function: A Multi-Task LiDAR Benchmark Dataset for Semantic and Functional Parsing of Urban Facades

    Nov 5, 2026Abdiaziz Muse, Tooba Javed, Tao Pu +23D Scene Understanding3D Semantic Segmentation

  4. BhopalMLS: A LiDAR Dataset for Semantic Scene Understanding in Heterogeneous Urban Environments

    Nov 3, 2026Pyare Lal Chauhan, Vaibhav Kumar, Bharat Lohani3D Scene Understanding3D Point Cloud Segmentation

  5. DeSpatial: The devil of Agentic Spatial Reasoning Lies in 3D Itself

    Oct 14, 2026Yifei Liu, Xiaolong Zhou, Ziyang Gong +83D Spatial Reasoning3D Scene Understanding

  6. Geometry-Guided Semantic Reconstruction for 3D Instance Segmentation

    Oct 12, 2026Yuanhao Su, Shaofeng Zhang3D Instance SegmentationFeature Fusion

  7. ForestQuery: Boundary-Aware and Spatially Anchored Query Learning for Unified Forest Point Cloud Segmentation

    Oct 2, 2026Zhihao Zhan, Le Tao, Yifei Tian +23D Point Cloud Segmentation3D Semantic Segmentation

  8. A Fully Automatic Pipeline for 3D Dendrite Instance Segmentation in SBF-SEM

    Oct 2, 2026Zewen Zhuo, Ilya Belevich, Eija Jokitalo +23D Instance SegmentationInstance Segmentation

  9. RYOPO: Bringing End-to-End Category-Level Object Pose Estimation into Real Time

    Oct 2, 2026Hakjin Lee, Junghoon Seo, Jaehoon SimObject Pose Estimation3D Instance Segmentation

  10. EviSplat: Preserving Multi-View Evidence in 3D Gaussian Splatting for Open-Vocabulary Segmentation

    Sep 28, 2026Sungho Moon, Kota Shimomura, Junwoo Park +43D Gaussian SplattingLanguage-Embedded 3DGS

  11. From Alignment to Fusion in 3D Vision-Language

    Sep 23, 2026Xueqi Qiu, Xingyu Miao, Jingjing Deng +33D Representation LearningVision-Language Alignment

  12. SAM-V: Geometry-Aware Segment Anything for Multi-View Instance Segmentation

    Sep 21, 2026Jiangshan Gong, Yuqun Wu, Qiqian Fu +4Multi-View ConsistencyInstance Segmentation

  13. Toward a foundation model for forest point clouds

    Sep 21, 2026Yuanwen Yue, Stefano Puliti, Damien Robert +73D Foundation ModelsPoint Cloud Classification

  14. SomaNet: Weakly Supervised Learning for Instance Soma Segmentation in 3D Electron Microscopy with Partial Annotations

    Sep 19, 2026Mohammad Khateri, Morteza Ghahremani, Jussi Tohka +1Electron MicroscopyInstance Segmentation

  15. SenseFuse: Label-Free Fusion of Image and Shape Encoders for Open-Vocabulary 3D Instance Segmentation

    Sep 17, 2026Euiseok Han, Tri Ton, Hwanhee Kim +2Open-Vocabulary 3D SegmentationMultimodal Fusion

  16. Instance Segmentation and Fine-grained Classification for Urban Buildings with Adaptive Region Dividing and Spatially-Supervised Contrastive Learning

    Sep 17, 2026Weiyuan Zhang, Qi Zhang, Hui HuangContrastive LearningPoint Cloud Classification

  17. VOIM: Training-Free Open-Vocabulary 3D Instance Mapping for RGB-D and Monocular SLAM

    Sep 1, 2026Sangmin Song, Sarath Kodagoda, Marc G. Carmichael +4Simultaneous Localization and MappingOpen-Vocabulary 3D Segmentation

  18. AQ3D: Adaptive Query Transformer for 3D Instance Segmentation

    Aug 31, 2026Keno Moenck, Thorsten Schüppstuhl3D ViTs3D Instance Segmentation

  19. CedarCypress3D: an annotated UAV-LiDAR dataset of individual trees in planted cedar and cypress forests

    Aug 31, 2026Katsuto Shimizu, Fumiaki Kitahara, Tomohiro Nishizono +8Instance Segmentation3D Semantic Segmentation

  20. GroupForward: Building Referable 3D Scenes via Instance-Grouped Feed-Forward Gaussian Splatting

    Aug 18, 2026Qijian Tian, Zimeng Wu, Xuhong Wang +23D Referring SegmentationFeed-Forward 3D Reconstruction

  21. Emergent 3D Instance Segmentation from Self-Supervised Point Transformers

    Aug 16, 2026Ted Lentsch, Santiago Montiel-Marín, Holger Caesar +1Self-Supervised Point Cloud Learning3D Instance Segmentation

  22. InstanceSplat: Instance-Aware Feed-Forward 3D Gaussian Splatting for Scene Understanding

    Aug 7, 2026Minchao Jiang, Xiaoxuan Ma, Shunyu Jia +33D Gaussian SplattingOpen-Vocabulary 3D Segmentation

  23. CDIS: Cross-Dimensional Class-Agnostic 3D Instance Segmentation via 2D Mask Tracking and 3D-2D Projection Merging

    Jul 20, 2026Juno Kim, Hye-Jung Yoon, Yesol Park +13D Instance Segmentation

  24. Consistent Scene Understanding in 3D Gaussian Splatting via Multi-Cue Mask Refinement

    Jul 2, 2026Hyunjoon Park, Donghyeon ChoMulti-View Consistency3D Gaussian Splatting