Open-Vocabulary 3D Segmentation

Follow this topic Ask about this topic

Momentum

5 papers in the last four weeks, against 2 the four weeks before. 0.1% of all new papers.

Jul 6Week of Sep 21

Latest papers 26

All topics

Lang3DSeg: Annotation-Free Open-Vocabulary 3D Segmentation with Point Transformers
Oct 1, 2026Cigdem Kokenoz, Amir Salarpour, Alkim Domeke +5Open-Vocabulary 3D Segmentation Interactive 3D Segmentation
Department of Automotive Engineering, Clemson University, Greenville, SC, USA. · School of Computing, Clemson University, Clemson, SC, USA.
EviSplat: Preserving Multi-View Evidence in 3D Gaussian Splatting for Open-Vocabulary Segmentation
Sep 28, 2026Sungho Moon, Kota Shimomura, Junwoo Park +4Open-Vocabulary 3D Segmentation 3D Scene Understanding
DGIST, Daegu, Republic of Korea · Chubu University, Japan · Elith Inc., Japan +2
SplatLabel: Pseudo-Labelling through 4D Gaussian Splatting
Sep 24, 2026Nitya Nanvani, Andras Palffy, Holger Caesar3D Semantic Occupancy Prediction Open-Vocabulary 3D Segmentation
Perciv AI, The Netherlands · Delft University of Technology, The Netherlands
Hybrid Gaussians for Robust Open-Vocabulary 3D Segmentation with Multi-View Object Association and Boundary Refinement
Sep 23, 2026Xueqi Qiu, Yueming Sun, Tianyu Zhang +2Open-Vocabulary 3D Segmentation 3D Gaussian
Department of Computer Science, Durham University, Durham, United Kingdom · Shanghai Jiao Tong University, Shanghai, China
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 Segmentation Adm-Fusion
Korea Advanced Institute of Science and Technology (KAIST).
UniPart: Towards Zero-shot Language-Grounded 3D Part Segmentation for Embodied Interaction
Sep 14, 2026Xinqiang Yu, Zekun qi, Jiawei He +6Open-Vocabulary 3D Segmentation Robotic Manipulation
NLPR, Institute of Automation, Chinese Academy of Sciences, China · Galbot Inc., China · Beijing Academy of Artificial Intelligence, China +3
VOIM: Training-Free Open-Vocabulary 3D Instance Mapping for RGB-D and Monocular SLAM
Sep 1, 2026Sangmin Song, Sarath Kodagoda, Marc G. Carmichael +43D Mapping Open-Vocabulary 3D Segmentation
Robotics Institute, Faculty of Engineering and Information Technology, University of Technology Sydney, Ultimo NSW 2007, Australia · Smart Sensing and Robotics Laboratory (SensR Lab), Centre for Advanced Manufacturing Technology, School of Engineering, Design and Built Environment, Kingswood NSW 2747, Australia · Guide Dogs New South Wales/Australian Capital Territory, Sydney NSW, Australia
LEGO: Leveled Language Gaussian Splatting
Aug 10, 2026Yuning Peng, Haiping Wang, Yuan Liu +3Open-Vocabulary 3D Segmentation Spatial Reasoning
Wuhan University · Hong Kong University of Science and Technology
Prior-SG: Task and Prior Driven Region Segmentation for Scene Graphs in Arbitrarily-Structured Environments
Aug 6, 2026Giorgio Tonetti, Laurent Kneip, Abel Gawel +13D Scene Graphs Open-Vocabulary 3D Segmentation
RAI Institute · ETH Zurich
Group-wise Supervision with Focal-Dice Loss for Long-Tailed Indoor Semantic Occupancy Prediction
Jul 31, 2026Qi Zheng, Zihuang Su, Xiao Pan3D Semantic Occupancy Prediction Open-Vocabulary 3D Segmentation
Guangdong Key Laboratory of Intelligent Information Processing, College of Electronics and Information Engineering, Shenzhen University, Shenzhen 518060, China
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 +1Open-Vocabulary 3D Segmentation Zero-Shot
Interdisciplinary Program in AI, Seoul National University
Relation-Centric Open-Vocabulary 3D Gaussian Segmentation
Jul 1, 2026Eunsung Cha, Hyunjoon Lee, Jaesik ParkOpen-Vocabulary 3D Segmentation Interactive 3D Segmentation
Seoul National University, Republic of Korea
Depth-Only Open-Vocabulary 3D Semantic Segmentation For Privacy-Preserving Robotic Applications
Jul 1, 2026Xuying Huang, Sicong Pan, Maren BennewitzOpen-Vocabulary 3D Segmentation Semantic Segmentation
Humanoid Robots Lab, University of Bonn, the Lamarr Institute for Machine Learning and Artificial Intelligence, and the Center for Robotics, Bonn, Germany
Open-Vocabulary and Referring Segmentation for 3D Gaussians Using 2D Detectors
Jun 29, 2026Jameel Hassan, Yasiru Ranasinghe, Vishal PatelOpen-Vocabulary 3D Segmentation 3D Gaussian
Johns Hopkins University
SAD-GS: Learning Reliable 3D Semantic Gaussian Fields via Dynamic Geo-Semantic Anchoring
Jun 28, 2026Yufei Zhang, Chenlu Zhan, Gaoang Wang +1Open-Vocabulary 3D Segmentation 3D Gaussian
Zhejiang University
Open-Vocabulary BEV Segmentation with 3D-Aware Geometric Constraints
Jun 23, 2026Hojun Choi, Seulbin Hwang, Dae Jung Kim +3Bird'S-Eye View Open-Vocabulary 3D Segmentation
KAIST AI, South Korea · NAVER LABS, South Korea
EPS3D: End-to-End Feed-Forward 3D Panoptic Segmentation
Jun 8, 2026Runsong Zhu, Jiaxin Guo, Xiaoyang Guo +9Open-Vocabulary 3D Segmentation 3D Scene Understanding
The Chinese University of Hong Kong, HK SAR, China · Hong Kong Centre for Logistics Robotics, HK SAR, China · Horizon Robotics, China +2
GVC-Seg: Training-Free 3D Instance Segmentation via Geometric Visual Correspondence
Jun 6, 2026Liang Xu, Fangjing Wang, Jinyu Yang +1Open-Vocabulary 3D Segmentation Point Clouds
Victoria University of Wellington, New Zealand · Department of Computer Science and Engineering, Southern University of Science and Technology, Shenzhen 518055, China · Harbin Institute of Technology, Shenzhen, China
T-FunS3D: Task-Driven Hierarchical Open-Vocabulary 3D Functionality Segmentation
Jun 4, 2026Jingkun Feng, Reza SabzevariOpen-Vocabulary 3D Segmentation 3D Generation
P4MARS Lab at the Faculty of Aerospace Engineering, Delft University of Technology
GeoSAM-3D: Geodesic Prompt Propagation for Open-Vocabulary 3D Scene Segmentation from Monocular Video
May 30, 2026Arun SharmaOpen-Vocabulary 3D Segmentation Monocular Video
University of Minnesota, Twin Cities
GIBLy: Improving 3D Semantic Segmentation through an Architecture-Agnostic Lightweight Geometric Inductive Bias Layer
May 22, 2026Diogo Lavado, Alessandra Micheletti, Clàudia SoaresOpen-Vocabulary 3D Segmentation Geometric Priors
NOVA School of Science and Technology, Portugal · Universit`a degli Studi di Milano, Italy
FUS3DMaps: Scalable and Accurate Open-Vocabulary Semantic Mapping by 3D Fusion of Voxel- and Instance-Level Layers
May 5, 2026Timon Homberger, Finn Lukas Busch, Jesús Gerardo Ortega Peimbert +2Open-Vocabulary 3D Segmentation 3D Mapping
Division of Robotics, Perception, and Learning, KTH Royal Institute of Technology, Sweden
SpaCeFormer: Fast Proposal-Free Open-Vocabulary 3D Instance Segmentation
Apr 22, 2026Chris Choy, Junha Lee, Chunghyun Park +2Open-Vocabulary 3D Segmentation Spatio-Temporal Transformers
NVIDIA · POSTECH
JOPP-3D: Joint Open Vocabulary Semantic Segmentation on Point Clouds and Panoramas
Mar 6, 2026Sandeep Inuganti, Hideaki Kanayama, Kanta Shimizu +4Open-Vocabulary 3D Segmentation Open-Vocabulary Segmentation
German Research Center for Artificial Intelligence, DFKI, Germany · RPTU Kaiserslautern, Germany · Ricoh Company, Ltd. Japan +1
Ov3R: Open-Vocabulary Semantic 3D Reconstruction from RGB Videos
Jul 29, 2025Ziren Gong, Xiaohan Li, Fabio Tosi +4Open-Vocabulary 3D Segmentation 3D Generation
University of Bologna · USTC · BIT +1
OV-MAP: Open-Vocabulary Zero-Shot 3D Instance Segmentation Map for Robots
Jun 13, 2025Juno Kim, Yesol Park, Hye-Jung Yoon +1Open-Vocabulary 3D Segmentation 3D Mapping
Interdisciplinary Program in AI, Seoul National University · Artificial Intelligence Institute, Seoul National University · Department of Computer Science, Seoul National University

Oct 1, 2026, cs.CVJ/K move · Enter open · S save

Lang3DSeg: Annotation-Free Open-Vocabulary 3D Segmentation with Point Transformers

Cigdem Kokenoz, Amir Salarpour, Alkim Domeke, Christopher Salas+4

Department of Automotive Engineering, Clemson University, Greenville, SC, USA. · School of Computing, Clemson University, Clemson, SC, USA.

Open-Vocabulary 3D Segmentation Interactive 3D Segmentation Open-Vocabulary Segmentation Transformer Architectures

Open paper AskPDF arXiv

Accurate 3D semantic perception is critical for safe autonomous navigation. However, supervised LiDAR segmentation remains tied to closed taxonomies and to the cost of point-wise manual annotation. Open-vocabulary methods avoid that cost by projecting the output of 2D vision-language models onto LiDAR and distilling it into a 3D network. These methods rely almost exclusively on voxel-based sparse convolutions, and point transformers have so far been limited to indoor environments, where 3D data is dense and bounded. We present Lang3DSeg, which establishes a point transformer as the backbone for annotation-free open-vocabulary segmentation of outdoor 3D LiDAR, and is trained from scratch without geometric pre-training. This training paradigm necessitates addressing the inherent noise in 2D-to-3D label projections; specifically, naive projection often suffers from depth ambiguity, where points behind an object are erroneously assigned its semantic label. We therefore composite masks using an explicit class-priority rule and truncate each projected instance at the first gap in its depth distribution, correcting the projection error directly rather than averaging it over registered sequences. Lang3DSeg achieves 52.8% mIoU on nuScenes validation and 41.4% on SemanticKITTI, the highest among published annotation-free methods on both benchmarks. Every 3D semantic segmentation is on a single LiDAR sweep, and inference operates in real-time without running vision-language models.

Momentum

Related topics

Latest papers 26