Sparse View Distractor-Free Gaussian Splatting

• URL: http://arxiv.org/abs/2603.01603v1
• Date: Mon, 02 Mar 2026 08:32:32 GMT
• Title: Sparse View Distractor-Free Gaussian Splatting
• Authors: Yi Gu, Zhaorui Wang, Jiahang Cao, Jiaxu Wang, Mingle Zhao, Dongjun Ye, Renjing Xu,
• Abstract summary: 3D Gaussian Splatting (3DGS) enables efficient training and fast novel view in static environments.<n>We propose a framework to enhance distractor-free 3DGS under sparse-view conditions by incorporating rich prior information.
• Score: 31.812029183156245
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 3D Gaussian Splatting (3DGS) enables efficient training and fast novel view synthesis in static environments. To address challenges posed by transient objects, distractor-free 3DGS methods have emerged and shown promising results when dense image captures are available. However, their performance degrades significantly under sparse input conditions. This limitation primarily stems from the reliance on the color residual heuristics to guide the training, which becomes unreliable with limited observations. In this work, we propose a framework to enhance distractor-free 3DGS under sparse-view conditions by incorporating rich prior information. Specifically, we first adopt the geometry foundation model VGGT to estimate camera parameters and generate a dense set of initial 3D points. Then, we harness the attention maps from VGGT for efficient and accurate semantic entity matching. Additionally, we utilize Vision-Language Models (VLMs) to further identify and preserve the large static regions in the scene. We also demonstrate how these priors can be seamlessly integrated into existing distractor-free 3DGS methods. Extensive experiments confirm the effectiveness and robustness of our approach in mitigating transient distractors for sparse-view 3DGS training.

Related papers

• GaussExplorer: 3D Gaussian Splatting for Embodied Exploration and Reasoning [55.826192239140596]
  GaussExplorer is a framework for embodied exploration and reasoning built on 3D Gaussian Splatting (3DGS)<n>We introduce Vision-Language Models (VLMs) on top of 3DGS to enable question-driven exploration and reasoning within 3D scenes.
  arXiv  Detail & Related papers  (2026-01-19T15:17:58Z)
• LOST-3DSG: Lightweight Open-Vocabulary 3D Scene Graphs with Semantic Tracking in Dynamic Environments [1.5391321019692432]
  LOST-3DSG is a lightweight open-vocabulary 3D scene graph designed to track dynamic objects in real-world environments.<n>Our method adopts a semantic approach to entity tracking based on word2vec and sentence embeddings.<n>We evaluate our method through qualitative and quantitative experiments conducted in a real 3D environment using a TIAGo robot.
  arXiv  Detail & Related papers  (2026-01-06T10:44:19Z)
• Towards Physically Executable 3D Gaussian for Embodied Navigation [37.428618598143395]
  SAGE-3D is a new paradigm that upgrades 3DGS into an executable, semantically and physically aligned environment.<n>It comprises two components: (1) Object-Centric Semantic Grounding, which adds object-level fine-grained annotations to 3DGS; and (2) Physics-Aware Execution Jointing, which embeds collision objects into 3DGS.<n>We release InteriorGS, containing 1K object-annotated 3DGS indoor scene data, and introduce SAGE-Bench, the first 3DGS-based VLN benchmark with 2M VLN data.
  arXiv  Detail & Related papers  (2025-10-24T10:05:00Z)
• VGGT-X: When VGGT Meets Dense Novel View Synthesis [27.397168758449904]
  We study the problem of applying 3D Foundation Models (3DFMs) to dense Novel View Synthesis (NVS)<n>Our study reveals that naively scaling 3DFMs to dense views encounters two fundamental barriers: dramatically increasing VRAM burden and imperfect outputs that degrade 3D training.<n>We introduce VGGT-X, incorporating a memory-efficient VGGT implementation that scales to 1,000+ images, an adaptive global alignment for VGGT output enhancement, and robust 3DGS training practices.
  arXiv  Detail & Related papers  (2025-09-29T17:59:59Z)
• FastVGGT: Training-Free Acceleration of Visual Geometry Transformer [83.67766078575782]
  VGGT is a state-of-the-art feed-forward visual geometry model.<n>We propose FastVGGT, which leverages token merging in the 3D domain through a training-free mechanism for accelerating VGGT.<n>With 1000 input images, FastVGGT achieves a 4x speedup over VGGT while mitigating error accumulation in long-sequence scenarios.
  arXiv  Detail & Related papers  (2025-09-02T17:54:21Z)
• Intern-GS: Vision Model Guided Sparse-View 3D Gaussian Splatting [95.61137026932062]
  Intern-GS is a novel approach to enhance the process of sparse-view Gaussian splatting.<n>We show that Intern-GS achieves state-of-the-art rendering quality across diverse datasets.
  arXiv  Detail & Related papers  (2025-05-27T05:17:49Z)
• Steepest Descent Density Control for Compact 3D Gaussian Splatting [72.54055499344052]
  3D Gaussian Splatting (3DGS) has emerged as a powerful real-time, high-resolution novel view.<n>We propose a theoretical framework that demystifies and improves density control in 3DGS.<n>We introduce SteepGS, incorporating steepest density control, a principled strategy that minimizes loss while maintaining a compact point cloud.
  arXiv  Detail & Related papers  (2025-05-08T18:41:38Z)
• EVolSplat: Efficient Volume-based Gaussian Splatting for Urban View Synthesis [61.1662426227688]
  Existing NeRF and 3DGS-based methods show promising results in achieving photorealistic renderings but require slow, per-scene optimization.<n>We introduce EVolSplat, an efficient 3D Gaussian Splatting model for urban scenes that works in a feed-forward manner.
  arXiv  Detail & Related papers  (2025-03-26T02:47:27Z)
• Dense Point Clouds Matter: Dust-GS for Scene Reconstruction from Sparse Viewpoints [9.069919085326]
  3D Gaussian Splatting (3DGS) has demonstrated remarkable performance in scene synthesis and novel view synthesis tasks. In this study, we present Dust-GS, a novel framework specifically designed to overcome the limitations of 3DGS in sparse viewpoint conditions.
  arXiv  Detail & Related papers  (2024-09-13T07:59:15Z)
• SpotlessSplats: Ignoring Distractors in 3D Gaussian Splatting [44.42317312908314]
  3D Gaussian Splatting (3DGS) is a promising technique for 3D reconstruction, offering efficient training and rendering speeds. Current methods require highly controlled environments to meet the inter-view consistency assumption of 3DGS. We present SpotLessSplats, an approach that leverages pre-trained and general-purpose features coupled with robust optimization to effectively ignore transient distractors.
  arXiv  Detail & Related papers  (2024-06-28T17:07:11Z)
• DOGS: Distributed-Oriented Gaussian Splatting for Large-Scale 3D Reconstruction Via Gaussian Consensus [56.45194233357833]
  We propose DoGaussian, a method that trains 3DGS distributedly. Our method accelerates the training of 3DGS by 6+ times when evaluated on large-scale scenes.
  arXiv  Detail & Related papers  (2024-05-22T19:17:58Z)

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.