360-GeoGS：用于360图像的几何一致前馈3D高斯点溅重建
360-GeoGS: Geometrically Consistent Feed-Forward 3D Gaussian Splatting Reconstruction for 360 Images
- Shanghai Key Laboratory of Navigation and Location Based Services（上海导航与基于位置的服务关键实验室）
- Shanghai Jiao Tong University（上海交通大学）
- State Key Laboratory of Submarine Geoscience（海底地球科学国家重点实验室）
- School of Automation and Intelligent Sensing（自动化与智能感知学院）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
本文提出了一种用于360图像的前馈3DGS框架，通过深度-法线几何正则化提升几何一致性，实现高质量的3D重建。
AI中文摘要：
3D场景重建是空间智能应用如AR、机器人和数字孪生的基础。传统多视图立体在稀疏视角或低纹理区域表现不佳，而神经渲染方法虽然能产生高质量结果，但需要每场景优化且缺乏实时效率。显式3D高斯点溅（3DGS）实现了高效的渲染，但大多数前馈变体侧重于视觉质量而非几何一致性，限制了准确表面重建和空间感知任务的整体可靠性。本文提出了一种新的用于360图像的前馈3DGS框架，能够生成几何一致的高斯原始体，同时保持高质量的渲染效果。引入了深度-法线几何正则化，将渲染的深度梯度与法线信息耦合，监督高斯旋转、尺度和位置，以提高点云和表面精度。实验结果表明，所提方法在保持高质量渲染效果的同时显著提高了几何一致性，为空间感知任务中的3D重建提供了有效解决方案。
英文摘要：
3D scene reconstruction is fundamental for spatial intelligence applications such as AR, robotics, and digital twins. Traditional multi-view stereo struggles with sparse viewpoints or low-texture regions, while neural rendering approaches, though capable of producing high-quality results, require per-scene optimization and lack real-time efficiency. Explicit 3D Gaussian Splatting (3DGS) enables efficient rendering, but most feed-forward variants focus on visual quality rather than geometric consistency, limiting accurate surface reconstruction and overall reliability in spatial perception tasks. This paper presents a novel feed-forward 3DGS framework for 360 images, capable of generating geometrically consistent Gaussian primitives while maintaining high rendering quality. A Depth-Normal geometric regularization is introduced to couple rendered depth gradients with normal information, supervising Gaussian rotation, scale, and position to improve point cloud and surface accuracy. Experimental results show that the proposed method maintains high rendering quality while significantly improving geometric consistency, providing an effective solution for 3D reconstruction in spatial perception tasks.
