BPnP: Further Empowering End-to-End Learning with Back-Propagatable Geometric Optimization
In this paper we present BPnP, a novel method to do back-propagation through a PnP solver. We show that the gradients of such geometric optimization process can be computed using the Implicit Function Theorem as if it is differentiable. Furthermore, we develop a residual-conformity trick to make end-to-end pose regression using BPnP smooth and stable. We also propose a "march in formation" algorithm which successfully uses BPnP for keypoint regression. Our invention opens a door to vast possibilities. The ability to incorporate geometric optimization in end-to-end learning will greatly boost its power and promote innovations in various computer vision tasks.
NurtureToken New!

Token crowdsale for this paper ends in

Buy Nurture Tokens

Authors

Are you an author of this paper? Check the Twitter handle we have for you is correct.

Bo Chen (edit)
Tat-Jun Chin (add twitter)
Nan Li (add twitter)
Ask The Authors

Ask the authors of this paper a question or leave a comment.

Read it. Rate it.
#1. Which part of the paper did you read?

#2. The paper contains new data or analyses that is openly accessible?
#3. The conclusion is supported by the data and analyses?
#4. The conclusion is of scientific interest?
#5. The result is likely to lead to future research?

Github
User:
None (add)
Repo:
None (add)
Stargazers:
0
Forks:
0
Open Issues:
0
Network:
0
Subscribers:
0
Language:
None
Youtube
Link:
None (add)
Views:
0
Likes:
0
Dislikes:
0
Favorites:
0
Comments:
0
Other
Sample Sizes (N=):
Inserted:
Words Total:
Words Unique:
Source:
Abstract:
None
09/15/19 06:04PM
2,680
837
Tweets
hitsgub: RT @arxiv_cscv: BPnP: Further Empowering End-to-End Learning with Back-Propagatable Geometric Optimization https://t.co/rJ25OBcvPD
KagamiSho: RT @arxiv_cscv: BPnP: Further Empowering End-to-End Learning with Back-Propagatable Geometric Optimization https://t.co/rJ25OBcvPD
arxivml: "BPnP: Further Empowering End-to-End Learning with Back-Propagatable Geometric Optimization", Bo Chen, Tat-Jun Chin… https://t.co/0fAIJcsqtn
GiseopK: RT @arxiv_cscv: BPnP: Further Empowering End-to-End Learning with Back-Propagatable Geometric Optimization https://t.co/rJ25OBcvPD
arxiv_cscv: BPnP: Further Empowering End-to-End Learning with Back-Propagatable Geometric Optimization https://t.co/rJ25OBcvPD
Images
Related