提出无网格3D高斯点云检测，实现更精准高效的实时三维重建。
Off The Grid: Detection of Primitives for Feed-Forward 3D Gaussian Splatting
- 用关键点检测思路替代固定网格，实现亚像素级高斯原语分布。
- 仅用1/4的原语数量即达当前最优画质，显著减少伪影。
- 适合需要快速生成高质量3D场景的应用，如AR/VR与实时渲染。
前馈式3D高斯点云（3DGS）模型可实现实时场景生成，但受限于依赖密集刚性网格的像素对齐原语布局，影响质量与效率。本文提出一种新型前馈架构，实现亚像素级3D高斯原语检测，将传统网格替换为自适应的“无网格”分布。受关键点检测启发，解码器学习在图像块内局部分布原语，并引入基于香农熵的自适应密度机制，按块分配不同数量的原语。将所提解码器与预训练3D重建主干结合，采用光度监督端到端训练，无需任何3D标注。该无姿态模型可在数秒内生成逼真3DGS场景，在前馈模型中达到最先进的新视角合成效果。相比对手，使用更少原语的同时表现更优，展现出更精准高效的空间分配能力，能捕捉细微结构并降低伪影。项目页面：https://arthurmoreau.github.io/OffTheGrid/
原文摘要 · Abstract (English)
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/.
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。