paper-with-me

Papers

Segment Any 3D Gaussians

2023-12-01 · Jiazhong Cen, Jiemin Fang, Chen Yang, Lingxi Xie, Xiaopeng Zhang, Wei Shen, Qi Tian

This paper presents SAGA (Segment Any 3D GAussians), a highly efficient 3D promptable segmentation method based on 3D Gaussian Splatting (3D-GS). Given 2D visual prompts as input, SAGA can segment the corresponding 3D target represented by 3D Gaussians within 4 ms. This is achieved by attaching an scale-gated affinity feature to each 3D Gaussian to endow it a new property towards multi-granularity segmentation. Specifically, a scale-aware contrastive training strategy is proposed for the scale-gated affinity feature learning. It 1) distills the segmentation capability of the Segment Anything Model (SAM) from 2D masks into the affinity features and 2) employs a soft scale gate mechanism to deal with multi-granularity ambiguity in 3D segmentation through adjusting the magnitude of each feature channel according to a specified 3D physical scale. Evaluations demonstrate that SAGA achieves real-time multi-granularity segmentation with quality comparable to state-of-the-art methods. As one of the first methods addressing promptable segmentation in 3D-GS, the simplicity and effectiveness of SAGA pave the way for future advancements in this field. Our code will be released.

📄 PDF Abstract BibTeX arXiv:2312.00860

Code (0)

등록된 구현이 없습니다.

Tasks

Interactive SegmentationScene UnderstandingSegmentation

Methods 이 논문이 사용한 방법론

SAGA SAGA is a method in the spirit of SAG, SDCA, MISO and SVRG, a set of recently proposed incremental gradient algorithms with fast linear convergence rates. SAGA improves on the…

Similar Papers 제목 키워드 기반

Learning Segmented 3D Gaussians via Efficient Feature Unprojection for Zero-shot Neural Scene Segmentation

2024-01-11 · Bin Dou, Tianyu Zhang, Zhaohui Wang, Yongjia Ma 외

Zero-shot neural scene segmentation, which reconstructs 3D neural segmentation field without manual annotations, serves as an effective way for scene understanding. However, existing models, especially the efficient 3D G…

DecoderPanoptic SegmentationScene SegmentationScene Understanding+4

GaussianTrimmer: Online Trimming Boundaries for 3DGS Segmentation

2026-01-19 · Liwei Liao, Ronggang Wang arxiv

With the widespread application of 3D Gaussians in 3D scene representation, 3D scene segmentation methods based on 3D Gaussians have also gradually emerged. However, existing 3D Gaussian segmentation methods basically se…

Scene Segmentation

Segment Any 4D Gaussians

2024-07-05 · Shengxiang Ji, Guanjun Wu, Jiemin Fang, Jiazhong Cen 외

Modeling, understanding, and reconstructing the real world are crucial in XR/VR. Recently, 3D Gaussian Splatting (3D-GS) methods have shown remarkable success in modeling and understanding 3D scenes. Similarly, various 4…

Segmentation

Contrastive Gaussian Clustering: Weakly Supervised 3D Scene Segmentation

2024-04-19 · Myrna C. Silva, Mahtab Dahaghin, Matteo Toso, Alessio Del Bue

We introduce Contrastive Gaussian Clustering, a novel approach capable of provide segmentation masks from any viewpoint and of enabling 3D segmentation of the scene. Recent works in novel-view synthesis have shown how to…

ClusteringContrastive LearningNovel View SynthesisScene Segmentation+1

SuperGSeg: Open-Vocabulary 3D Segmentation with Structured Super-Gaussians

2024-12-13 · Siyun Liang, Sen Wang, Kunyi Li, Michael Niemeyer 외

3D Gaussian Splatting has recently gained traction for its efficient training and real-time rendering. While the vanilla Gaussian Splatting representation is mainly designed for view synthesis, more recent works investig…

GPUObject LocalizationScene UnderstandingSegmentation+1