Files
NoteNextra-origin/content/CSE5519/CSE5519_E1.md
2025-09-01 21:38:49 -05:00

32 lines
861 B
Markdown

# CSE5519 Topic E.1 2021 and before: Deep Learning for Geometric Computer Vision
> [!NOTE]
>
> This topic is presented by Me. and will be the most detailed one for this course, perhaps.
## PoseNet
A Convolutional Network for Real-Time 6-DOF Camera Relocalization (ICCV 2015)
[link to the paper](https://arxiv.org/pdf/1505.07427)
## Unsupervised Learning of Depth and Ego-Motion From Video
(CVPR 2017)
[link to the paper](https://openaccess.thecvf.com/content_cvpr_2017/papers/Zhou_Unsupervised_Learning_of_CVPR_2017_paper.pdf)
## GeoNet
Unsupervised Learning of Dense Depth, Optical Flow and Camera Pose (CVPR 2018)
[link to the paper](https://openaccess.thecvf.com/content_cvpr_2018/papers/Yin_GeoNet_Unsupervised_Learning_CVPR_2018_paper.pdf)
### Rigid structure constructor
### Non-rigid motion localizer
### Geometric consistency enforcement