Back-propagatable PnP
This repo provides the code used in the paper
bash requirements.sh
Using BPnP is easy. Just add the following line in your code
bash import BPnP bpnp = BPnP.BPnP.applyThen you can use it as any autograd function in Pytorch.
To see the demos presented in the paper, run
bash python demoPoseEst.pyor
bash python demoSfM.pyor
bash python demoCamCali.py
@inproceedings{BPnP2020, Author = {Chen, Bo and Parra, Alvaro and Cao, Jiewei and Li, Nan and Chin, Tat-Jun}, Title = {End-to-End Learnable Geometric Vision by Backpropagating PnP Optimization}, Booktitle = {CVPR}, Year = {2020}}