no code implementations • 19 Jan 2024 • Zuoyue Li, Zhenqiang Li, Zhaopeng Cui, Marc Pollefeys, Martin R. Oswald
Directly generating scenes from satellite imagery offers exciting possibilities for integration into applications like games and map services.
no code implementations • 23 Jul 2022 • Zuoyue Li, Tianxing Fan, Zhenqiang Li, Zhaopeng Cui, Yoichi Sato, Marc Pollefeys, Martin R. Oswald
We introduce a scalable framework for novel view synthesis from RGB-D images with largely incomplete scene coverage.
no code implementations • 14 Jul 2022 • Boming Zhao, Bangbang Yang, Zhenyang Li, Zuoyue Li, Guofeng Zhang, Jiashu Zhao, Dawei Yin, Zhaopeng Cui, Hujun Bao
Expanding an existing tourist photo from a partially captured scene to a full scene is one of the desired experiences for photography applications.
no code implementations • 22 Dec 2021 • Zuria Bauer, Zuoyue Li, Sergio Orts-Escolano, Miguel Cazorla, Marc Pollefeys, Martin R. Oswald
Building upon the recent progress in novel view synthesis, we propose its application to improve monocular depth estimation.
Ranked #27 on Monocular Depth Estimation on KITTI Eigen split
1 code implementation • 1 Sep 2021 • Zhenqiang Li, Weimin WANG, Zuoyue Li, Yifei HUANG, Yoichi Sato
The attribution method provides a direction for interpreting opaque neural networks in a visual way by identifying and visualizing the input regions/pixels that dominate the output of a network.
no code implementations • ICCV 2021 • Zuoyue Li, Zhenqiang Li, Zhaopeng Cui, Rongjun Qin, Marc Pollefeys, Martin R. Oswald
For geometrical and temporal consistency, our approach explicitly creates a 3D point cloud representation of the scene and maintains dense 3D-2D correspondences across frames that reflect the geometric scene configuration inferred from the satellite view.
2 code implementations • 1 May 2020 • Zhenqiang Li, Weimin WANG, Zuoyue Li, Yifei HUANG, Yoichi Sato
''Making black box models explainable'' is a vital problem that accompanies the development of deep learning networks.
no code implementations • ICCV 2019 • Zuoyue Li, Jan Dirk Wegner, Aurélien Lucchi
We propose a new approach, named PolyMapper, to circumvent the conventional pixel-wise segmentation of (aerial) images and predict objects in a vector representation directly.