Eliminating topological errors in neural network rotation estimation using self-selecting ensembles
- 1 August 2021
- journal article
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Graphics
- Vol. 40 (4), 1-21
- https://doi.org/10.1145/3476576.3476752
Abstract
No abstract availableFunding Information
- Army Research Office (W911NF-20-2-0053)
- U.S. Army Research Laboratory (W911NF-14-D-0005)
- CONIX Research Center
- ONR YIP (N00014-17-S-FO14)
This publication has 6 references indexed in Scilit:
- On the Continuity of Rotation Representations in Neural NetworksPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2019
- Deep Kinematic Pose RegressionPublished by Springer Science and Business Media LLC ,2016
- Render for CNN: Viewpoint Estimation in Images Using CNNs Trained with Rendered 3D Model ViewsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2015
- Viewpoints and keypointsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2015
- Efficient and Flexible Sampling with Blue Noise Properties of Triangular MeshesIEEE Transactions on Visualization and Computer Graphics, 2012
- A minimal atlas for the rotation group SO(3)GEM - International Journal on Geomathematics, 2011