360度全景图重建新方法，兼顾视觉质量与几何准确性
360-GeoGS: Geometrically Consistent Feed-Forward 3D Gaussian Splatting Reconstruction for 360 Images
- 引入深度-法向正则化，约束高斯点旋转缩放位置
- 在360图像上实现高保真渲染与几何一致性同步提升
- 适合需要精准三维感知的AR、机器人等应用
3D场景重建是增强现实、机器人和数字孪生等空间智能应用的基础。传统多视图立体视觉在视角稀疏或低纹理区域表现不佳，而神经渲染虽能生成高质量结果，但需逐场景优化且难以实时运行。显式3D高斯泼溅（3DGS）可实现高效渲染，但多数前馈变体侧重视觉质量，忽视几何一致性，影响表面重建精度与空间感知可靠性。本文提出一种面向360图像的新型前馈3DGS框架，能在保持高渲染质量的同时生成几何一致的高斯原语。通过引入深度-法向几何正则化，将渲染深度梯度与法向信息耦合，监督高斯点的旋转、尺度和位置，显著提升点云与表面精度。实验表明，该方法在维持高渲染质量的同时大幅改善几何一致性，为空间感知任务中的3D重建提供了有效解决方案。
原文摘要 · Abstract (English)
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.
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。