Geometric primitives in LiDAR point clouds: A review

S Xia, D Chen, R Wang, J Li… - IEEE Journal of Selected …, 2020 - ieeexplore.ieee.org
To the best of our knowledge, the most recent light detection and ranging (lidar)-based
surveys have been focused only on specific applications such as reconstruction and …

P3depth: Monocular depth estimation with a piecewise planarity prior

V Patil, C Sakaridis, A Liniger… - Proceedings of the …, 2022 - openaccess.thecvf.com
Monocular depth estimation is vital for scene understanding and downstream tasks. We
focus on the supervised setup, in which ground-truth depth is available only at training time …

Enforcing geometric constraints of virtual normal for depth prediction

W Yin, Y Liu, C Shen, Y Yan - Proceedings of the IEEE/CVF …, 2019 - openaccess.thecvf.com
Monocular depth prediction plays a crucial role in understanding 3D scene geometry.
Although recent methods have achieved impressive progress in evaluation metrics such as …

Mesh r-cnn

G Gkioxari, J Malik, J Johnson - Proceedings of the IEEE …, 2019 - openaccess.thecvf.com
Rapid advances in 2D perception have led to systems that accurately detect objects in real-
world images. However, these systems make predictions in 2D, ignoring the 3D structure of …

Matterport3d: Learning from rgb-d data in indoor environments

A Chang, A Dai, T Funkhouser, M Halber… - arXiv preprint arXiv …, 2017 - arxiv.org
Access to large, diverse RGB-D datasets is critical for training RGB-D scene understanding
algorithms. However, existing datasets still cover only a limited number of views or a …

Scaling and benchmarking self-supervised visual representation learning

P Goyal, D Mahajan, A Gupta… - Proceedings of the ieee …, 2019 - openaccess.thecvf.com
Self-supervised learning aims to learn representations from the data itself without explicit
manual supervision. Existing efforts ignore a crucial aspect of self-supervised learning-the …

Transformer-based attention networks for continuous pixel-wise prediction

G Yang, H Tang, M Ding, N Sebe… - Proceedings of the …, 2021 - openaccess.thecvf.com
While convolutional neural networks have shown a tremendous impact on various computer
vision tasks, they generally demonstrate limitations in explicitly modeling long-range …

Scannet: Richly-annotated 3d reconstructions of indoor scenes

A Dai, AX Chang, M Savva, M Halber… - Proceedings of the …, 2017 - openaccess.thecvf.com
A key requirement for leveraging supervised deep learning methods is the availability of
large, labeled datasets. Unfortunately, in the context of RGB-D scene understanding, very …

A point set generation network for 3d object reconstruction from a single image

H Fan, H Su, LJ Guibas - Proceedings of the IEEE …, 2017 - openaccess.thecvf.com
Generation of 3D data by deep neural network has been attracting increasing attention in
the research community. The majority of extant works resort to regular representations such …

Pattern-affinitive propagation across depth, surface normal and semantic segmentation

Z Zhang, Z Cui, C Xu, Y Yan… - Proceedings of the …, 2019 - openaccess.thecvf.com
In this paper, we propose a novel Pattern-Affinitive Propagation (PAP) framework to jointly
predict depth, surface normal and semantic segmentation. The motivation behind it comes …