AnchorSplat：带三维几何先验的前馈三维高斯泼溅
AnchorSplat: Feed-Forward 3D Gaussian Splatting With 3D Geometric Priors
把像素对齐的高斯表示换成由稀疏点云/体素/RGB-D 点云引导的锚点对齐高斯表示，使高斯数量与图像分辨率、视角数解耦，可直接用于场景级前馈重建与新视角合成，降低高斯原语数量同时提升视角一致性。
原文依据 AnchorSplat introduces an anchor-aligned Gaussian representation guided by 3D geometric priors
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论近期的前馈高斯重建模型采用像素对齐的表述方式，将每个二维像素映射为一个三维高斯，使高斯表示与输入图像紧密耦合。本文提出 AnchorSplat，一种用于场景级重建的新型前馈三维高斯泼溅（3DGS）框架，直接在三维空间中表示场景。AnchorSplat 引入由三维几何先验（例如稀疏点云、体素或 RGB-D 点云）引导的锚点对齐高斯表示，从而获得更具几何感知能力、可渲染且与图像分辨率和视角数量无关的三维高斯。该设计大幅减少了所需高斯的数量，在提升重建保真度的同时改善了计算效率。除锚点对齐设计外，我们还使用高斯精化器（Gaussian Refiner），仅通过少量前向传播即可调整中间高斯。在 ScanNet++ v2 新视角合成基准上的实验展示了当前最优（SOTA）性能，以更好的视角一致性和显著更少的高斯原语数量优于先前方法。
英文原文摘要 1078 字符
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 Gaussians 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.