ViewSplat: 用于前馈合成的视图自适应3D高斯散射
ViewSplat: View-Adaptive 3D Gaussian Splatting for Feed-Forward Synthesis
- University of Seoul（首尔市立大学）
- Korea Electronics Technology Institute（韩国电子技术研究院）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
ViewSplat通过视图自适应的3D高斯散射方法提升未置位图像的视图合成精度，采用视图依赖的残差更新机制，实现高保真度的实时渲染。
AI中文摘要：
我们提出了ViewSplat，一种用于从未置位图像中生成新视图的视图自适应3D高斯散射网络。尽管最近的前馈3D高斯散射显著加速了3D场景重建，但存在基本保真度差距。我们归因于单步前馈网络的容量有限，无法回归满足所有视角的静态高斯基元。为解决这一限制，我们从静态基元回归转向视图自适应散射。与刚性的高斯表示不同，我们的流程学习了视图自适应的潜在表示。具体而言，ViewSplat首先预测基础高斯基元以及场景条件化的视图MLP权重。在渲染过程中，这些MLP以目标视角坐标为输入，并预测每个高斯属性（即3D位置、尺度、旋转、不透明度和颜色）的视图依赖残差更新。这种机制，我们称之为视图自适应散射，使每个基元能够修正初始估计误差，从而有效捕捉高保真度的外观。大量实验表明，ViewSplat在保持快速推理和实时渲染的同时实现了最先进的保真度；我们的大型主干变体在推理时以15 FPS运行，在渲染时以90 FPS运行。我们的项目页面可在https://cvlab-uos.github.io/ViewSplat上找到。
英文摘要：
We present ViewSplat, a view-adaptive 3D Gaussian splatting network for novel view synthesis from unposed images. While recent feed-forward 3D Gaussian splatting has significantly accelerated 3D scene reconstruction by bypassing per-scene optimization, a fundamental fidelity gap remains. We attribute this gap to the limited capacity of single-step feed-forward networks to regress static Gaussian primitives that satisfy all viewpoints. To address this limitation, we shift the paradigm from static primitive regression to view-adaptive splatting. Instead of a rigid Gaussian representation, our pipeline learns a view-adaptive latent representation. Specifically, ViewSplat initially predicts base Gaussian primitives alongside the weights of scene-conditioned View MLPs. During rendering, these MLPs take target-view coordinates as input and predict view-dependent residual updates for each Gaussian attribute (i.e., 3D position, scale, rotation, opacity, and color). This mechanism, which we term view-adaptive splatting, allows each primitive to rectify initial estimation errors, effectively capturing high-fidelity appearances. Extensive experiments demonstrate that ViewSplat achieves state-of-the-art fidelity while maintaining fast inference and real-time rendering; our large backbone variant runs at 15 FPS during inference and 90 FPS during rendering. Our project page is available at https://cvlab-uos.github.io/ViewSplat.
