Pith. sign in

REVIEW 10 cited by

OpenGaussian: Towards Point-Level 3D Gaussian-based Open Vocabulary Understanding

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2406.02058 v2 pith:6HCRYJR4 submitted 2024-06-04 cs.CV cs.RO

Yanmin Wu , Jiarui Meng , Haijie Li , Chenming Wu , Yahao Shi , Xinhua Cheng , Chen Zhao , Haocheng Feng
show 3 more authors
Errui Ding Jingdong Wang Jian Zhang
This is my paper
classification cs.CVcs.RO
keywords featurefeaturesopenpoint-levelunderstandingmethodopengaussianvocabulary
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

This paper introduces OpenGaussian, a method based on 3D Gaussian Splatting (3DGS) capable of 3D point-level open vocabulary understanding. Our primary motivation stems from observing that existing 3DGS-based open vocabulary methods mainly focus on 2D pixel-level parsing. These methods struggle with 3D point-level tasks due to weak feature expressiveness and inaccurate 2D-3D feature associations. To ensure robust feature presentation and 3D point-level understanding, we first employ SAM masks without cross-frame associations to train instance features with 3D consistency. These features exhibit both intra-object consistency and inter-object distinction. Then, we propose a two-stage codebook to discretize these features from coarse to fine levels. At the coarse level, we consider the positional information of 3D points to achieve location-based clustering, which is then refined at the fine level. Finally, we introduce an instance-level 3D-2D feature association method that links 3D points to 2D masks, which are further associated with 2D CLIP features. Extensive experiments, including open vocabulary-based 3D object selection, 3D point cloud understanding, click-based 3D object selection, and ablation studies, demonstrate the effectiveness of our proposed method. The source code is available at our project page: https://3d-aigc.github.io/OpenGaussian

Discussion (0). Sign in to comment.

Forward citations

Cited by 10 Pith papers

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

  1. CF3: Compact and Fast 3D Feature Fields

    cs.CV 2025-08 conditional novelty 6.0 of 10

    CF3 builds a compact 3D feature field from a pre-trained 3DGS by feature lifting, per-Gaussian autoencoding, and adaptive sparsification, matching baseline segmentation quality with roughly 5% of the Gaussians.

  2. ObjectGS: Object-aware Scene Reconstruction and Scene Understanding via Gaussian Splatting

    cs.GR 2025-07 conditional novelty 6.0 of 10

    ObjectGS unifies 3D Gaussian scene reconstruction with object-level segmentation by binding each object to local anchors with fixed one-hot ID encodings, improving open-vocabulary and panoptic segmentation.

  3. InstaScene: Towards Complete 3D Instance Decomposition and Reconstruction from Cluttered Scenes

    cs.CV 2025-07 conditional novelty 6.0 of 10

    InstaScene combines Gaussian-based instance decomposition with generative completion to produce complete, scene-aligned 3D object models from cluttered scenes.

  4. VoteSplat: Hough Voting Gaussian Splatting for 3D Scene Understanding

    cs.GR 2025-06 conditional novelty 6.0 of 10

    VoteSplat embeds per-Gaussian 3D offset vectors, supervises them with SAM mask centers, and clusters the resulting 3D votes to segment and localize objects in Gaussian Splatting scenes.

  5. DSG-World: Learning a 3D Gaussian World Model from Dual State Videos

    cs.CV 2025-06 conditional novelty 6.0 of 10

    DSG-World builds two segmented 3D Gaussian fields from two scene states and trains them with mutual consistency, enabling novel-state simulation without inpainting or dense capture.

  6. OGGSplat: Open Gaussian Growing for Generalizable Reconstruction with Expanded Field-of-View

    cs.CV 2025-06 conditional novelty 6.0 of 10

    A method that grows open-vocabulary 3D Gaussians beyond the input view cone by bidirectionally consistent RGB and semantic diffusion inpainting.

  7. LangScene-X: Reconstruct Generalizable 3D Language-Embedded Scenes with TriMap Video Diffusion

    cs.CV 2025-07 conditional novelty 5.0 of 10

    LangScene-X generates RGB, normal, and semantic videos from sparse views to reconstruct 3D language-embedded Gaussian fields that support open-ended text queries.

  8. SurgTPGS: Semantic 3D Surgical Scene Understanding with Text Promptable Gaussian Splatting

    eess.IV 2025-06 conditional novelty 5.0 of 10

    SurgTPGS is a text-promptable 3D Gaussian Splatting pipeline that segments surgical instruments and anatomy from natural-language queries at interactive frame rates.

  9. Hi-LSplat: Hierarchical 3D Language Gaussian Splatting

    cs.CV 2025-06 conditional novelty 5.0 of 10

    Hi-LSplat trains language-augmented 3D Gaussians with a three-level semantic tree and instance/part contrastive losses, improving open-vocabulary 3D segmentation and localization on eight datasets.

  10. OmniIndoor3D: Comprehensive Indoor 3D Reconstruction

    cs.CV 2025-05 conditional novelty 5.0 of 10

    OmniIndoor3D jointly optimizes appearance, geometry, and panoptic labels in a single set of 3D Gaussians initialized from RGB-D camera depth, reporting state-of-the-art numbers on ScanNet and ScanNet++.

Pith tools