arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新，休息一下吧，周末愉快~~
arXiv 2410.11285cs.CV

使用无人机捕获的360度图像与3D Gaussian Splatting的可扩展室内新视角合成

Scalable Indoor Novel-View Synthesis using Drone-Captured 360 Imagery with 3D Gaussian Splatting

UC Berkeley（加州大学伯克利分校）

Yuanbo Chen, Chengyu Zhang, Jason Wang, Xuefan Gao, Avideh Zakhor

备注：
Accepted to ECCV 2024 S3DSGR Workshop
阅读 PDF
arXiv 页面 ↗HTML 原文 ↗

AI总结：

本文提出一种基于3D Gaussian Splatting的可扩展流水线，利用无人机捕获的360度视频进行室内新视角合成，通过分治策略和由粗到细的对齐策略实现大型场景的高质量并行重建。

摘要：

大型、复杂、多层室内场景的场景重建和新视角合成是一项具有挑战性且耗时的任务。先前的方法利用无人机进行数据捕获，并使用辐射场进行场景重建，这两者都存在一些挑战。首先，为了使用无人机的前置摄像头捕获多样的视角，一些方法让无人机以不稳定的“之”字形飞行，这阻碍了无人机驾驶并在捕获的数据中产生运动模糊。其次，大多数辐射场方法不易扩展到任意大数量的图像。本文提出了一种高效且可扩展的流水线，使用3D Gaussian Splatting从无人机捕获的360度视频进行室内新视角合成。360度摄像头捕获广泛的视角集合，允许在简单直接的无人机轨迹下进行全面的场景捕获。为了将我们的方法扩展到大型场景，我们设计了一种分治策略，自动将场景分割为可以单独且并行重建的较小块。我们还提出了一种由粗到细的对齐策略，以无缝地将这些块匹配在一起，组成整个场景。我们的实验表明，与先前的方法相比，在重建质量（即PSNR和SSIM）和计算时间方面都有显著改善。

英文摘要：

Scene reconstruction and novel-view synthesis for large, complex, multi-story, indoor scenes is a challenging and time-consuming task. Prior methods have utilized drones for data capture and radiance fields for scene reconstruction, both of which present certain challenges. First, in order to capture diverse viewpoints with the drone's front-facing camera, some approaches fly the drone in an unstable zig-zag fashion, which hinders drone-piloting and generates motion blur in the captured data. Secondly, most radiance field methods do not easily scale to arbitrarily large number of images. This paper proposes an efficient and scalable pipeline for indoor novel-view synthesis from drone-captured 360 videos using 3D Gaussian Splatting. 360 cameras capture a wide set of viewpoints, allowing for comprehensive scene capture under a simple straightforward drone trajectory. To scale our method to large scenes, we devise a divide-and-conquer strategy to automatically split the scene into smaller blocks that can be reconstructed individually and in parallel. We also propose a coarse-to-fine alignment strategy to seamlessly match these blocks together to compose the entire scene. Our experiments demonstrate marked improvement in both reconstruction quality, i.e. PSNR and SSIM, and computation time compared to prior approaches.

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。

↑