We present an approach for the planar surface reconstruction of a scene from
images with limited overlap. This reconstruction task is challenging since it
requires jointly reasoning about single image 3D reconstruction, correspondence
between images, and the relative camera pose between images. Past work has
proposed optimization-based approaches. We introduce a simpler approach, the
PlaneFormer, that uses a transformer applied to 3D-aware plane tokens to
perform 3D reasoning. Our experiments show that our approach is substantially
more effective than prior work, and that several 3D-specific design decisions
are crucial for its success.

本文提出了一种用于从有限重叠的图像重建场景平面表面的方法，并介绍了一种新的基于 transformer 的简化方法，PlaneFormer，它是通过对 3D 感知平面记号应用变换器来进行 3D 推理。实验表明，本文的方法比之前的方法更加有效。

PlaneFormers：从稀疏视图到三维重建

PlaneFormers: From Sparse View Planes to 3D Reconstruction

The paper studies planar surface reconstruction of indoor scenes from two
views with unknown camera poses. While prior approaches have successfully
created object-centric reconstructions of many scenes, they fail to exploit
other structures, such as planes, which are typically the dominant components
of indoor scenes. In this paper, we reconstruct planar surfaces from multiple
views, while jointly estimating camera pose. Our experiments demonstrate that
our method is able to advance the state of the art of reconstruction from
sparse views, on challenging scenes from Matterport3D. Project site:
this https URL

本文提出一种在未知相机姿态下采用多视图重建室内场景中平面表面的方法，并且通过实验表明该方法在来自 Matterport3D 挑战性场景的稀疏视图的重建方面能够推进现有技术的发展。