Planar Surface Reconstruction from Sparse Views

Linyi Jin
Shengyi Qian
Andrew Owens
David F. Fouhey

University of Michigan

ICCV 2021 (Oral)


Given two RGB images with an unknown relationship, our system produces a coherent planar surface reconstruction of the scene in terms of 3D planes and relative camera pose. We show this reconstruction with the inferred left and right cameras in Blue and Red

The paper studies planar surface reconstruction of indoor scenes from two views with unknown camera pose. 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.


Interactive Results

View A
View B
Ground Truth


Toyota Research Institute (“TRI”) provided funds to assist the authors with their research but this article solely reflects the opinions and conclusions of its authors and not TRI or any other Toyota entity.

This webpage template originally made from some colorful folks. The interactive examples are powered by model-viewer.