无需外部语义信息，直接分离动态干扰物与静态场景。
DeSplat: Decomposed Gaussian Splatting for Distractor-Free Rendering
- 基于高斯体渲染自动分解干扰物与静态场景
- 在三个数据集上实现与先进方法相当的重建效果
- 保持高速渲染，适合实时应用或交互式场景
高斯点阵可实现静态3D环境下的快速新视角合成。然而，在真实场景中，干扰物或遮挡物会破坏多视角一致性假设，导致重建困难。现有方法依赖预训练模型提供的外部语义信息，带来额外计算开销。本文提出DeSplat，仅通过高斯原型的体渲染，直接分离干扰物与静态场景元素。在每个相机视图内初始化高斯点以重建视图相关的干扰物，并在α混合阶段分别建模静态3D场景与干扰物。DeSplat实现了显式的场景分离，性能接近现有最优无干扰方法，且不牺牲渲染速度。我们在三个基准数据集上验证了该方法在无干扰新视角合成中的有效性。
原文摘要 · Abstract (English)
Gaussian splatting enables fast novel view synthesis in static 3D environments. However, reconstructing real-world environments remains challenging as distractors or occluders break the multi-view consistency assumption required for accurate 3D reconstruction. Most existing methods rely on external semantic information from pre-trained models, introducing additional computational overhead as pre-processing steps or during optimization. In this work, we propose a novel method, DeSplat, that directly separates distractors and static scene elements purely based on volume rendering of Gaussian primitives. We initialize Gaussians within each camera view for reconstructing the view-specific distractors to separately model the static 3D scene and distractors in the alpha compositing stages. DeSplat yields an explicit scene separation of static elements and distractors, achieving comparable results to prior distractor-free approaches without sacrificing rendering speed. We demonstrate DeSplat's effectiveness on three benchmark data sets for distractor-free novel view synthesis. See the project website at https://aaltoml.github.io/desplat/.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。