用神经Gabor增强高斯点，实现高频表面精准重建。
Neural Gabor Splatting: Enhanced Gaussian Splatting with Neural Gabor for High-frequency Surface Reconstruction
- 每个高斯点加轻量MLP，一次表示多种颜色变化。
- 在棋盘格等高频场景中，重建精度显著提升。
- 适合需要精细纹理重建的3D建模任务。
近年来，3D高斯点云（3DGS）成为3D重建与新视角合成的强大方法。其显式表示使用高斯原语，支持快速训练、实时渲染和便捷后处理。但3DGS存在关键缺陷：含高频外观细节的场景需大量原语，因每个原语仅能表示单一颜色，导致锐利色变处需多个原语。为此，我们提出神经Gabor点云，为每个高斯原语添加轻量多层感知机，以单个原语建模广泛的颜色变化。为进一步控制原语数量，引入频域感知密集化策略，基于频率能量选择需剪枝或克隆的原语。实验表明，该方法在标准基准（如Mip-NeRF360）及高频数据集（如棋盘格图案）上均实现精准重建，并通过全面消融研究验证有效性。
原文摘要 · Abstract (English)
Recent years have witnessed the rapid emergence of 3D Gaussian splatting (3DGS) as a powerful approach for 3D reconstruction and novel view synthesis. Its explicit representation with Gaussian primitives enables fast training, real-time rendering, and convenient post-processing such as editing and surface reconstruction. However, 3DGS suffers from a critical drawback: the number of primitives grows drastically for scenes with high-frequency appearance details, since each primitive can represent only a single color, requiring multiple primitives for every sharp color transition. To overcome this limitation, we propose neural Gabor splatting, which augments each Gaussian primitive with a lightweight multi-layer perceptron that models a wide range of color variations within a single primitive. To further control primitive numbers, we introduce a frequency-aware densification strategy that selects mismatch primitives for pruning and cloning based on frequency energy. Our method achieves accurate reconstruction of challenging high-frequency surfaces. We demonstrate its effectiveness through extensive experiments on both standard benchmarks, such as Mip-NeRF360 and High-Frequency datasets (e.g., checkered patterns), supported by comprehensive ablation studies.
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。