用高斯过程增强3D高斯点云，减少渲染伪影
GP-GS: Gaussian Processes Densification for 3D Gaussian Splatting
- 将点云补全建模为连续回归，用高斯过程预测3D位置与颜色
- 通过自适应采样和不确定性过滤，提升重建质量，最高增益1.12 dB PSNR
- 适合追求高质量3D重建的科研与工业用户
3D高斯溅射（3DGS）实现逼真渲染，但因稀疏的结构光恢复（SfM）初始化导致伪影。为此，我们提出基于高斯过程（GP）的补全框架GP-GS。GP-GS将点云补全视为连续回归问题，利用高斯过程学习从2D像素坐标到3D位置与颜色属性的局部映射。采用自适应邻域采样策略生成候选像素，同时利用GP预测的不确定性过滤不可靠预测，有效降低噪声并保留几何结构。在合成与真实世界基准上的大量实验表明，GP-GS持续提升重建质量与渲染保真度，相比强基线最高提升1.12 dB PSNR。
原文摘要 · Abstract (English)
3D Gaussian Splatting (3DGS) enables photorealistic rendering but suffers from artefacts due to sparse Structure-from-Motion (SfM) initialisation. To address this limitation, we propose GP-GS, a Gaussian Process (GP) based densification framework for 3DGS optimisation. GP-GS formulates point cloud densification as a continuous regression problem, where a GP learns a local mapping from 2D pixel coordinates to 3D position and colour attributes. An adaptive neighbourhood-based sampling strategy generates candidate pixels for inference, while GP-predicted uncertainty is used to filter unreliable predictions, reducing noise and preserving geometric structure. Extensive experiments on synthetic and real-world benchmarks demonstrate that GP-GS consistently improves reconstruction quality and rendering fidelity, achieving up to 1.12 dB PSNR improvement over strong baselines.
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。