In: British Machine Vision Conference. British Machine Vision Conference (BMVC-2021), November 22-25, United Kingdom, British Machine Vision Conference, 11/2021.
Zusammenfassung
Piece-wise 3D planar reconstruction provides holistic scene understanding of man-made environments, especially for indoor scenarios. Most recent approaches focused on improving the segmentation and reconstruction results by introducing advanced network architectures but overlooked the dual characteristics of piece-wise planes as objects and geometric models. Different from other existing approaches, we start from enforcing cross-task consistency for our multi-task convolutional neural network, PlaneRecNet, which integrates a single-stage instance segmentation network for piece-wise planar segmentation and a depth decoder to reconstruct the scene from a single RGB image. To achieve this, we introduce several novel loss functions (geometric constraint) that jointly improve the accuracy of piece-wise planar segmentation and depth estimation. Meanwhile, a novel Plane Prior Attention module is used to guide depth estimation with the awareness of plane instances. Exhaustive experiments are conducted in this work to validate the effectiveness and efficiency of our method.
@inproceedings{pub11908,
author = {
Xie, Yaxu
and
Shu, Fangwen
and
Pagani, Alain
and
Rambach, Jason Raphael
and
Stricker, Didier
},
title = {PlaneRecNet: Multi-Task Learning with Cross-Task Consistency for Piece-Wise Plane Detection and Reconstruction from a Single RGB Image},
booktitle = {British Machine Vision Conference. British Machine Vision Conference (BMVC-2021), November 22-25, United Kingdom},
year = {2021},
month = {11},
publisher = {British Machine Vision Conference}
}
Deutsches Forschungszentrum für Künstliche Intelligenz German Research Center for Artificial Intelligence