Planercnn: 3d plane detection and reconstruction from a single image

C Liu, K Kim, J Gu, Y Furukawa… - Proceedings of the …, 2019 - openaccess.thecvf.com
This paper proposes a deep neural architecture, PlaneRCNN, that detects and reconstructs
piecewise planar regions from a single RGB image. PlaneRCNN employs a variant of Mask …

Deep implicit moving least-squares functions for 3D reconstruction

SL Liu, HX Guo, H Pan, PS Wang… - Proceedings of the …, 2021 - openaccess.thecvf.com
Point set is a flexible and lightweight representation widely used for 3D deep learning.
However, their discrete nature prevents them from representing continuous and fine …

Guiding monocular depth estimation using depth-attention volume

L Huynh, P Nguyen-Ha, J Matas, E Rahtu… - Computer Vision–ECCV …, 2020 - Springer
Recovering the scene depth from a single image is an ill-posed problem that requires
additional priors, often referred to as monocular depth cues, to disambiguate different 3D …

End-to-end wireframe parsing

Y Zhou, H Qi, Y Ma - Proceedings of the IEEE/CVF …, 2019 - openaccess.thecvf.com
We present a conceptually simple yet effective algorithm to detect wireframes in a given
image. Compared to the previous methods which first predict an intermediate heat map and …

Structure-slam: Low-drift monocular slam in indoor environments

Y Li, N Brasch, Y Wang, N Navab… - IEEE Robotics and …, 2020 - ieeexplore.ieee.org
In this letter a low-drift monocular SLAM method is proposed targeting indoor scenarios,
where monocular SLAM often fails due to the lack of textured surfaces. Our approach …