Construction is becoming increasingly digitized with the integration of BIM, generative architecture design, laser scans and AR/VR visualization pipelines.
Here is the collection of the latest papers from Computer Vision and Pattern Recognition (CVPR) conference that took place in June 2018 at Salt Lake City, UT.
NOTE: Other papers and notable materials from workshops and tutorials that was presented at CVPR 2018 you can find in my previous CVPR 2018 Notes.
-
Hybrid Camera Pose Estimation. Federico Camposeco, Andrea Cohen, Marc Pollefeys, Torsten Sattler, [pdf]
-
LayoutNet: Reconstructing the 3D Room Layout From a Single RGB Image. Chuhang Zou, Alex Colburn, Qi Shan, Derek Hoiem, [pdf]
-
Very Large-Scale Global SfM by Distributed Motion Averaging. Siyu Zhu, Runze Zhang, Lei Zhou, Tianwei Shen, Tian Fang, Ping Tan, Long Quan, [pdf]
-
Large-Scale Point Cloud Semantic Segmentation With Superpoint Graphs. Loic Landrieu, Martin Simonovsky, [pdf]
-
PointNetVLAD: Deep Point Cloud Based Retrieval for Large-Scale Place Recognition. Mikaela Angelina Uy, Gim Hee Lee, [pdf]
-
DOTA: A Large-Scale Dataset for Object Detection in Aerial Images. Gui-Song Xia, Xiang Bai, Jian Ding, Zhen Zhu, Serge Belongie, Jiebo Luo, Mihai Datcu, Marcello Pelillo, Liangpei Zhang, [pdf]
-
Reflection Removal for Large-Scale 3D Point Clouds. Jae-Seong Yun, Jae-Young Sim, [pdf]
-
Im2Struct: Recovering 3D Shape Structure From a Single RGB Image. Chengjie Niu, Jun Li, Kai Xu, [pdf]