ZeroSplat: Generalized Referring Segmentation in 3D Gaussian Splatting

• URL: http://arxiv.org/abs/2607.18801v1
• Date: Tue, 21 Jul 2026 07:27:10 GMT
• Title: ZeroSplat: Generalized Referring Segmentation in 3D Gaussian Splatting
• Abstract summary: We introduce the Generalized Referring 3D Gaussian Splatting (GR3DGS) task.<n> GR3DGS task requires segmenting arbitrary number of targets (0, 1, or $N$)<n>We propose ZeroSplat, a novel training-free and zero-feature framework.
• Score: 2.1327328379130885
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Recent advancements in 3D Gaussian Splatting (3DGS) have enabled language-guided scene understanding. However, existing Referring 3D Gaussian Splatting (R3DGS) methods are fundamentally restricted to single-target queries. To reflect the ambiguity of real-world instructions, we introduce the Generalized Referring 3D Gaussian Splatting Segmentation (GR3DGS) task, which requires dynamically segmenting an arbitrary number of targets (0, 1, or $N$). To facilitate comprehensive evaluation of this new task, we construct two new benchmarks: GR-LERF and GR-ScanNet. Crucially, existing R3DGS paradigms exhibit fundamental technical bottlenecks that severely limit their performance on the GR3DGS task: they lack intrinsic 3D point-level understanding by operating merely on 2D rendered pixels, and they incur prohibitive computational overhead by requiring per-scene optimization to embed heavy semantic features. To dismantle these bottlenecks, we propose ZeroSplat, a novel training-free and zero-feature framework. ZeroSplat lifts 2D Vision-Language Model (VLM) priors into 3D space through robust multi-view geometric constraints. This strategy enables intrinsic point-level understanding without incurring any additional feature storage. Extensive experiments demonstrate that ZeroSplat significantly outperforms state-of-the-art methods across generalized and single-target scenarios while maintaining exceptional efficiency. Project Page: https://inkmind-ai.github.io/ZeroSplat

Related papers

• AnchorSplat: Fast and Structure Consistent Detail Synthesis for Gaussian Splatting [45.65377534924918]
  3D Gaussian Splatting (3DGS) has emerged as a powerful representation for high-fidelity rendering.<n>Existing assets often suffer from quality bottlenecks such as missing details and texture noise.<n>We propose a novel 3D-native refinement paradigm named AnchorSplat.
  arXiv  Detail & Related papers  (2026-07-01T12:14:29Z)
• Ilov3Splat: Instance-Level Open-Vocabulary 3D Scene Understanding in Gaussian Splatting [32.46353940664006]
  Ilov3Splat is a framework for instance-level open-vocabulary 3D scene understanding built on 3D Gaussian Splatting (3D-GS)<n>We leverage multi-resolution hash embedding to efficiently encode language-aligned CLIP features.<n>At inference time, CLIP-encoded queries are matched against the learned features, followed by two-stage 3D clustering to retrieve relevant Gaussian groups.
  arXiv  Detail & Related papers  (2026-05-06T05:23:41Z)
• NG-GS: NeRF-Guided 3D Gaussian Splatting Segmentation [65.34304674634713]
  We introduce NG-GS, a framework for high-quality object segmentation in 3DGS that explicitly addresses boundary discretization.<n>We show that our method achieves photorealistic state-of-the-art performance, with significant gains in boundary mIoU.
  arXiv  Detail & Related papers  (2026-04-16T07:14:07Z)
• ReferSplat: Referring Segmentation in 3D Gaussian Splatting [60.73702075842278]
  Referring 3D Gaussian Splatting (R3DGS)<n>Task aims to segment target objects in a 3D Gaussian scene based on natural language descriptions.<n>To address these challenges, we propose ReferSplat, a framework that explicitly models 3D Gaussian points with natural language expressions.
  arXiv  Detail & Related papers  (2025-08-11T17:59:30Z)
• SAGOnline: Segment Any Gaussians Online [17.33447710659887]
  3D Gaussian Splatting (3DGS) has emerged as a powerful paradigm for explicit 3D scene representation.<n>Current methods suffer from prohibitive computational costs, limited 3D spatial reasoning, and an inability to track multiple objects simultaneously.<n>We present Segment Any Gaussians Online (SAGOnline), a lightweight and zero-shot framework for real-time 3D segmentation in Gaussian scenes.
  arXiv  Detail & Related papers  (2025-08-11T17:38:50Z)
• Training-Free Hierarchical Scene Understanding for Gaussian Splatting with Superpoint Graphs [16.153129392697885]
  We introduce a training-free framework that constructs a superpoint graph directly from Gaussian primitives.<n>The superpoint graph partitions the scene into spatially compact and semantically coherent regions, forming view-consistent 3D entities.<n>Our method achieves state-of-the-art open-vocabulary segmentation performance, with semantic field reconstruction completed over $30times$ faster.
  arXiv  Detail & Related papers  (2025-04-17T17:56:07Z)
• SuperGSeg: Open-Vocabulary 3D Segmentation with Structured Super-Gaussians [77.77265204740037]
  3D Gaussian Splatting has recently gained traction for its efficient training and real-time rendering.<n>We introduce SuperGSeg, a novel approach that fosters cohesive, context-aware scene representation.<n>SuperGSeg outperforms prior works on both open-vocabulary object localization and semantic segmentation tasks.
  arXiv  Detail & Related papers  (2024-12-13T16:01:19Z)
• Occam's LGS: An Efficient Approach for Language Gaussian Splatting [57.00354758206751]
  We show that the complicated pipelines for language 3D Gaussian Splatting are simply unnecessary.<n>We apply Occam's razor to the task at hand, leading to a highly efficient weighted multi-view feature aggregation technique.
  arXiv  Detail & Related papers  (2024-12-02T18:50:37Z)
• Bootstraping Clustering of Gaussians for View-consistent 3D Scene Understanding [59.51535163599723]
  FreeGS is an unsupervised semantic-embedded 3DGS framework that achieves view-consistent 3D scene understanding without the need for 2D labels.<n>FreeGS performs comparably to state-of-the-art methods while avoiding the complex data preprocessing workload.
  arXiv  Detail & Related papers  (2024-11-29T08:52:32Z)
• SAGD: Boundary-Enhanced Segment Anything in 3D Gaussian via Gaussian Decomposition [66.56357905500512]
  3D Gaussian Splatting has emerged as an alternative 3D representation for novel view synthesis.<n>We propose SAGD, a conceptually simple yet effective boundary-enhanced segmentation pipeline for 3D-GS.<n>Our approach achieves high-quality 3D segmentation without rough boundary issues, which can be easily applied to other scene editing tasks.
  arXiv  Detail & Related papers  (2024-01-31T14:19:03Z)
• Segment Any 3D Gaussians [85.93694310363325]
  This paper presents SAGA, a highly efficient 3D promptable segmentation method based on 3D Gaussian Splatting (3D-GS)<n>Given 2D visual prompts as input, SAGA can segment the corresponding 3D target represented by 3D Gaussians within 4 ms.<n>We show that SAGA achieves real-time multi-granularity segmentation with quality comparable to state-of-the-art methods.
  arXiv  Detail & Related papers  (2023-12-01T17:15:24Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.