用3D几何先验实现高效3D高斯点云重建
AnchorSplat: Feed-Forward 3D Gaussian Splatting with 3D Geometric Priors
- 以3D几何先验为引导，构建与图像无关的锚点对齐高斯表示
- 仅需少量高斯素（1.2M）即达最佳视图一致性，效率显著提升
- 适合需要高保真、低参数量3D重建的场景建模应用
近期前馈高斯重建模型采用像素对齐的表述方式，将每个2D像素映射到一个3D高斯，使高斯表示与输入图像紧密耦合。本文提出AnchorSplat，一种新的前馈3D高斯点云渲染框架，直接在3D空间中表示场景。AnchorSplat引入由3D几何先验（如稀疏点云、体素或RGB-D点云）指导的锚点对齐高斯表示，生成更符合几何结构且与图像分辨率和视角数量无关的可渲染3D高斯。该设计大幅减少所需高斯数量，提升计算效率的同时增强重建保真度。此外，我们设计了高斯精炼器，仅通过几次前向传播即可调整中间高斯。在ScanNet++ v2 NVS基准测试中，该方法表现达到当前最优，以更少的高斯素（1.2M）实现更高的一致性视图重建。
原文摘要 · Abstract (English)
Recent feed-forward Gaussian reconstruction models adopt a pixel-aligned formulation that maps each 2D pixel to a 3D Gaussian, entangling Gaussian representations tightly with the input images. In this paper, we propose AnchorSplat, a novel feed-forward 3DGS framework for scene-level reconstruction that represents the scene directly in 3D space. AnchorSplat introduces an anchor-aligned Gaussian representation guided by 3D geometric priors (e.g., sparse point clouds, voxels, or RGB-D point clouds), enabling a more geometry-aware renderable 3D Gaussians that is independent of image resolution and number of views. This design substantially reduces the number of required Gaussians, improving computational efficiency while enhancing reconstruction fidelity. Beyond the anchor-aligned design, we utilize a Gaussian Refiner to adjust the intermediate Gaussiansy via merely a few forward passes. Experiments on the ScanNet++ v2 NVS benchmark demonstrate the SOTA performance, outperforming previous methods with more view-consistent and substantially fewer Gaussian primitives.
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。