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 2108.08623cs.CV
收藏

VolumeFusion:深度融合三维场景重建

VolumeFusion: Deep Depth Fusion for 3D Scene Reconstruction

KAIST(韩国科学技术院);DGIST(大邱庆北科学技术院)

Jaesung Choe, Sunghoon Im, Francois Rameau, Minjun Kang, In So Kweon

摘要:

传统的多视图立体视觉技术从一组标定的视图重建3D场景时,依赖于两个不同的阶段:局部深度图计算和全局深度图融合。最近的研究集中在通过使用传统深度融合方法或通过回归截断符号距离函数(TSDF)的直接3D重建网络进行深度估计的深度神经架构。在本文中,我们主张用深度神经网络复制传统的两阶段框架,以提高结果的可解释性和准确性。如前所述,我们的网络分两步操作:1)使用深度MVS技术对局部深度图进行局部计算,以及2)深度图和图像的特征融合以构建单个TSDF体积。为了提高从非常不同的视点(例如,大基线和旋转),我们引入了一个旋转不变的3D卷积核,称为PosedConv。通过在ScanNet数据集上进行的一系列实验,强调了所提出的架构的有效性,其中我们的方法与传统和深度学习技术相比具有优势。

英文摘要:

To reconstruct a 3D scene from a set of calibrated views, traditional multi-view stereo techniques rely on two distinct stages: local depth maps computation and global depth maps fusion. Recent studies concentrate on deep neural architectures for depth estimation by using conventional depth fusion method or direct 3D reconstruction network by regressing Truncated Signed Distance Function (TSDF). In this paper, we advocate that replicating the traditional two stages framework with deep neural networks improves both the interpretability and the accuracy of the results. As mentioned, our network operates in two steps: 1) the local computation of the local depth maps with a deep MVS technique, and, 2) the depth maps and images' features fusion to build a single TSDF volume. In order to improve the matching performance between images acquired from very different viewpoints (e.g., large-baseline and rotations), we introduce a rotation-invariant 3D convolution kernel called PosedConv. The effectiveness of the proposed architecture is underlined via a large series of experiments conducted on the ScanNet dataset where our approach compares favorably against both traditional and deep learning techniques.

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。

↑