提升3D高斯点云语义分割边界精度，让物体轮廓更清晰。
GradiSeg: Gradient-Guided Gaussian Segmentation with Enhanced 3D Boundary Precision
- 用身份编码梯度指导高斯点密度分布，贴合物体边缘。
- 引入自适应邻居机制，防止边界附近点云异常扩散。
- 分割结果更准且可编辑，适合物体移除、替换等操作。
尽管3D高斯点阵能实现高质量实时渲染，现有基于高斯的3D语义分割方法在边界识别精度上仍面临重大挑战。为此，我们提出一种新型3DGS框架GradiSeg，引入身份编码以构建更深层的场景语义理解。方法包含两个关键模块：身份梯度引导稀疏化（IGD）与局部自适应K近邻（LA-KNN）。IGD模块通过监督身份编码的梯度，优化物体边界处的高斯分布，使其紧密贴合边界轮廓；同时，LA-KNN模块利用位置梯度自适应建立局部感知的身份编码传播机制，避免边界附近出现不规则的高斯扩散。通过全面实验验证，结果表明GradiSeg有效解决了边界相关问题，显著提升分割精度，且不损害场景重建质量。此外，该方法具备强鲁棒性分割能力与解耦的身份编码表示，特别适用于3D物体移除、替换等多种下游场景编辑任务。
原文摘要 · Abstract (English)
While 3D Gaussian Splatting enables high-quality real-time rendering, existing Gaussian-based frameworks for 3D semantic segmentation still face significant challenges in boundary recognition accuracy. To address this, we propose a novel 3DGS-based framework named GradiSeg, incorporating Identity Encoding to construct a deeper semantic understanding of scenes. Our approach introduces two key modules: Identity Gradient Guided Densification (IGD) and Local Adaptive K-Nearest Neighbors (LA-KNN). The IGD module supervises gradients of Identity Encoding to refine Gaussian distributions along object boundaries, aligning them closely with boundary contours. Meanwhile, the LA-KNN module employs position gradients to adaptively establish locality-aware propagation of Identity Encodings, preventing irregular Gaussian spreads near boundaries. We validate the effectiveness of our method through comprehensive experiments. Results show that GradiSeg effectively addresses boundary-related issues, significantly improving segmentation accuracy without compromising scene reconstruction quality. Furthermore, our method's robust segmentation capability and decoupled Identity Encoding representation make it highly suitable for various downstream scene editing tasks, including 3D object removal, swapping and so on.
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。