脱离网格：用于前馈3D高斯散射的原始形检测
Off The Grid: Detection of Primitives for Feed-Forward 3D Gaussian Splatting
- Huawei Noah’s Ark Lab（华为诺亚方舟实验室）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
本文提出了一种前馈架构，通过子像素级检测3D高斯原始形，替代传统网格，提升质量和效率。结合预训练的3D重建模型，无需3D标注即可生成逼真3DGS场景，实现最先进的视图合成。
AI中文摘要：
前馈3D高斯散射（3DGS）模型能够实现实时场景生成，但受限于次优的像素对齐原始形放置，其依赖密集且刚性的网格，限制了质量和效率。我们引入了一种新的前馈架构，能够在子像素级别检测3D高斯原始形，用适应性的『脱离网格』分布替代像素网格。受关键点检测启发，我们的解码器学会在图像块内局部分布原始形。我们还提供了一种自适应密度机制，根据香农熵为每个块分配不同数量的原始形。我们将所提解码器与预训练的3D重建主干网络结合，并通过光度监督进行端到端训练，无需任何3D标注。所得无姿态模型在数秒内生成逼真3DGS场景，实现了前馈模型最先进的新视图合成。它在使用更少原始形的同时优于竞争对手，展示了更准确且高效的分配方式，能够捕捉细节并减少伪影。项目页面：https://arthurmoreau.github.io/OffTheGrid/.
英文摘要：
Feed-forward 3D Gaussian Splatting (3DGS) models enable real-time scene generation but are hindered by suboptimal pixel-aligned primitive placement, which relies on a dense, rigid grid that limits both quality and efficiency. We introduce a new feed-forward architecture that detects 3D Gaussian primitives at a sub-pixel level, replacing the pixel grid with an adaptive, ``Off-The-Grid" distribution. Inspired by keypoint detection, our decoder learns to locally distribute primitives across image patches. We also provide an Adaptive Density mechanism by assigning varying number of primitives per patch based on Shannon entropy. We combine the proposed decoder with a pre-trained 3D reconstruction backbone and train them end-to-end using photometric supervision without any 3D annotation. The resulting pose-free model generates photorealistic 3DGS scenes in seconds, achieving state-of-the-art novel view synthesis for feed-forward models. It outperforms competitors while using far fewer primitives, demonstrating a more accurate and efficient allocation that captures fine details and reduces artifacts. Project page: https://arthurmoreau.github.io/OffTheGrid/.
