3DGS Segmentation

3DGS: 3D Gaussian Splatting

Follow this topic Ask about this topic

Latest papers

15 papers2 papers in the last four weeks, against 1 the four weeks before. 0.0% of all new papers.

DIGS: Distribution-Informed Gaussian Splatting for Training-Free Open-Vocabulary 3D Segmentation
Oct 12, 2026Zhifan Zeng, Wenbo Xiao, Arcot Sowmya +1Open-Vocabulary 3D Segmentation 3DGS Segmentation
UNSW Sydney · CSIRO
PePESeg3D: Perception Prior Enhances Multi-Scale Segmentation for 3D Gaussian Splatting
Sep 23, 2026Sungjae Choi, Seunghee Koh, Junmo Kim3D Gaussian Splatting 3D Reconstruction
School of Electrical Engineering Korea Advanced Institute of Science and Technology (KAIST) Daejeon, South Korea
VCAR: Training-Free 3DGS Segmentation via View Completeness and Axis-Aware Boundary Refinement
Aug 31, 2026Kun Cao, Di Wang, Haibin Zhu +43D Gaussian Splatting 3DGS Segmentation
Jinan University · Zhuhai, China
Seed2GS: Camera-Free, Training-Free Object Extraction from 3D Gaussian Scenes via a Single Reference-View Grounding
Aug 12, 2026Zongjian Ding, Yudong Gao, Jiale Liu +73D Gaussian Splatting Open-Vocabulary 3D Segmentation
University of Chinese Academy of Sciences · Institute of Information Engineering, Chinese Academy of Sciences · 4The Hong Kong University of Science and Technology +2
CDSeg: A Renderable Gaussian Carrier for Image-to-3D Label Transfer
Aug 6, 2026Wentao Sun, Yiping Chen, Zhengsen Xu +23D Point Cloud Segmentation 3D Semantic Segmentation
Department of Systems Design Engineering, University of Waterloo, N2L 3G1 Waterloo, Canada · School of Geospatial Engineering and Science, Sun Yat-sen University, 519082 Zhuhai, China · Department of Geomatics Engineering, University of Calgary, T2N 1N4 Calgary, Canada
ZeroSplat: Generalized Referring Segmentation in 3D Gaussian Splatting
Jul 21, 2026Jiayu Ding, Meilu Song, Xiaoyi Zhang +33D Gaussian Splatting Open-Vocabulary 3D Segmentation
Peking University · North China Electric Power University · China University of Geosciences
Online Segment 3D Gaussians via Launching Virtual Drones
Jul 2, 2026Liwei Liao, Rongjie Wang, Ronggang Wang3D Gaussian Splatting 3DGS Segmentation
Guangdong Provincial Key Laboratory of Ultra High Definition Immersive Media Technology, Shenzhen Graduate School, Peking University, Shenzhen, China · Pengcheng Laboratory, Shenzhen, China · Peking University, Beijing, China
Relation-Centric Open-Vocabulary 3D Gaussian Segmentation
Jul 1, 2026Eunsung Cha, Hyunjoon Lee, Jaesik Park3D Gaussian Splatting Open-Vocabulary 3D Segmentation
Seoul National University, Republic of Korea
Do Gaussian Scenes Contain Enough Structure for Intrinsic Segmentation?
Jun 17, 2026Mohamed Rayan Barhdadi, Hasan Yazar, Erchin Serpedin +23D Gaussian Splatting Image Segmentation
Texas A&M University · Istanbul Technical University · Hamad Bin Khalifa University
OP2GS: Object-Aware 3D Gaussian Splatting with Dual-Opacity Primitives
May 19, 2026Guiyu Liu, Niklas Vaara, Janne Mustaniemi +23D Gaussian Splatting Open-Vocabulary 3D Segmentation
Center for Machine Vision and Signal Analysis, University of Oulu, Finland · Aalto University, Finland
Robust Prior-Guided Segmentation for Editable 3D Gaussian Splatting
May 15, 2026Raushan Joshi, Jean-Yves Guillemaut3D Gaussian Splatting 3D Scene Editing
University of Surrey, Guildford, Surrey, UK
NG-GS: NeRF-Guided 3D Gaussian Splatting Segmentation
Apr 16, 2026Yi He, Tao Wang, Yi Jin +33D Gaussian Splatting 3DGS Segmentation
Key Laboratory of Big Data and Artificial Intelligence in Transportation, Ministry of Education; School of Computer and Information Technology, Beijing Jiaotong University, Beijing 100044, China · Department of Artificial Intelligence, Westlake University, Hangzhou 310030, China
FaceParts: Segmentation and Editing of Gaussian Splatting
Mar 25, 2026Tymoteusz Zapała, Julia Farganus, Dominik Galus +33DGS Segmentation 3D Part Segmentation
Wrocław University of Science and Technology, Poland · Jagiellonian University, Poland
B $^3$ -Seg: Camera-Free, Training-Free 3DGS Segmentation via Analytic EIG and Beta-Bernoulli Bayesian Updates
Feb 19, 2026Hiromichi Kamata, Samuel Arthur Munro, Fuminori Homma3DGS Segmentation Open-Vocabulary 3D Segmentation
Sony Group Corporation, Tokyo, Japan · Pixomondo, London, United Kingdom
PointGauss: Point Cloud-Guided Multi-Object Segmentation for Gaussian Splatting
Aug 1, 2025Wentao Sun, Yiping Chen, John S. Zelek +13D Gaussian Splatting 3DGS Segmentation
University of Waterloo, Waterloo, ON N2L 3G1, Canada · Sun Yat-Sen University, Zhuhai 519082, China

Oct 12, 2026J/K move · Enter open · S save

DIGS: Distribution-Informed Gaussian Splatting for Training-Free Open-Vocabulary 3D Segmentation

Zhifan Zeng, Wenbo Xiao, Arcot Sowmya, Changming Sun

UNSW Sydney · CSIRO

Open-Vocabulary 3D Segmentation 3DGS Segmentation 3D Instance Segmentation 3D Gaussian Splatting Language-Embedded 3DGS

Open paper AskPDF arXiv

Open-vocabulary 3D Gaussian segmentation typically binds semantic features to the per-Gaussian state via per-scene gradient training (1-4 h) or the more recent closed-form distillation. Both commit each primitive to a single feature; therefore, boundary Gaussians spanning multiple 2D instances are forced into a hard decision that degrades retrieval accuracy and yields unstable mask boundaries at render time. We present DIGS, a training-free framework with two stages, class-agnostic mapping and multi-modal encoding, that decouples instance discovery from linguistic naming. At the Gaussian level, our distribution-informed representation maintains an explicit top-

M

label distribution per primitive, updated by a tempered Dirichlet rule; preservation of multi-peaked label distributions at boundary primitives allows a late-argmax renderer to recover clean instance boundaries. A bidirectional state machine aggregates these distributions into a persistent class-agnostic instance ontology. The instance-level encoding stage then fuses the CLIP visual embedding of each instance's isolated 3D footprint with the CLIP-text embedding of an LLM-generated attribute description, disambiguating visually similar instances. On a single A100, DIGS completes mapping and instance encoding on LERF-OVS in 1.0-3.2 min per scene, depending on whether LLM fusion is enabled, and serves native 3D queries in 5.4 ms. It reaches 71.95% mean mIoU on LERF-OVS, outperforming both the training-free SFS and training-based LaGa baselines. DIGS also achieves the highest mean mIoU on LERF-Mask and 3D-OVS and surpasses Gaga and ObjectGS on Replica under their respective evaluation protocols. Code is available at https://github.com/ZephyrZos/DIGS.