用于大视场角重建的自标定Gaussian Splatting
Self-Calibrating Gaussian Splatting for Large Field of View Reconstruction
AI总结：
本文提出一种自标定框架，联合优化相机参数、镜头畸变和3D Gaussian表示，通过混合网络和立方体贴图重采样策略，实现大视场角图像的高质量高效场景重建。
摘要：
本文提出一种自标定框架，联合优化相机参数、镜头畸变和3D Gaussian表示，实现准确高效的场景重建。具体而言，该技术能从广角镜头拍摄的大视场角（FOV）图像中实现高质量场景重建，允许使用较少数量的图像对场景进行建模。该方法引入一种利用混合网络建模复杂镜头畸变的新方法，该网络结合了可逆残差网络和显式网格。此设计有效正则化了优化过程，比传统相机模型实现了更高的精度。此外，我们提出一种基于立方体贴图的重采样策略，以支持大FOV图像而不牺牲分辨率或引入畸变伪影。该方法兼容Gaussian Splatting的快速光栅化，适应多种相机镜头畸变，并在合成和真实数据集上展现了最先进的性能。
英文摘要：
In this paper, we present a self-calibrating framework that jointly optimizes camera parameters, lens distortion and 3D Gaussian representations, enabling accurate and efficient scene reconstruction. In particular, our technique enables high-quality scene reconstruction from Large field-of-view (FOV) imagery taken with wide-angle lenses, allowing the scene to be modeled from a smaller number of images. Our approach introduces a novel method for modeling complex lens distortions using a hybrid network that combines invertible residual networks with explicit grids. This design effectively regularizes the optimization process, achieving greater accuracy than conventional camera models. Additionally, we propose a cubemap-based resampling strategy to support large FOV images without sacrificing resolution or introducing distortion artifacts. Our method is compatible with the fast rasterization of Gaussian Splatting, adaptable to a wide variety of camera lens distortion, and demonstrates state-of-the-art performance on both synthetic and real-world datasets.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
