← Back to papers
2020 NIPS NeurIPS 2020

Probabilistic Orientation Estimation with Matrix Fisher Distributions

Abstract

This paper focuses on estimating probability distributions over the set of 3D ro- tations (SO(3)) using deep neural networks. Learning to regress models to the set of rotations is inherently difficult due to differences in topology between R^N and SO(3). We overcome this issue by using a neural network to out- put the parameters for a matrix Fisher distribution since these parameters are homeomorphic to R^9 . By using a negative log likelihood loss for this distri- bution we get a loss which is convex with respect to the network outputs. By optimizing this loss we improve state-of-the-art on several challenging applica- ble datasets, namely Pascal3D+, ModelNet10-SO(3). Our code is available at https://github.com/Davmo049/Publicproborientationestimationwith_matrix fisherdistributions

🌉 Interdisciplinary Bridge — Artificial Intelligence and Computer Vision and Deep Learning and Machine Learning
🧭 Keyword Pioneer — matrix fisher distribution
🐝 Cross-Pollinator — Artificial Intelligence, Computer Science, Computer Vision, Data Science & Analytics, Deep Learning, Healthcare & Medicine, Interdisciplinary, Knowledge & Reasoning, Machine Learning, Mathematics & Optimization, Natural Language Processing, Reinforcement Learning, Robotics, Security & Privacy, Speech & Audio

Authors

David Mohlin , Josephine Sullivan , Gérald Bianchi

Topics

Artificial Intelligence > Bayesian & Probabilistic > Probabilistic Modeling Deep Learning > Architectures > Neural Networks Computer Vision > Analysis > 3D Vision Machine Learning > Bayesian & Probabilistic > Probabilistic Modeling Deep Learning > Learning Types > Representation Learning

Keywords

probabilistic modeling deep neural network 3d rotation orientation estimation matrix fisher distribution negative log likelihood
Download PDF

Related papers

Higher-Order Spectral Clustering of Directed Graphs 2020
Self-Supervised MultiModal Versatile Networks 2020
Multi-Robot Collision Avoidance under Uncertainty with Probabilistic Safety Barrier Certificates 2020
Causal Intervention for Weakly-Supervised Semantic Segmentation 2020
Taming Discrete Integration via the Boon of Dimensionality 2020