Probabilistic orientation estimation with matrix Fisher distributions

06/17/2020
by   D. Mohlin, et al.
0

This paper focuses on estimating probability distributions over the set of 3D rotations (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 output the parameters for a matrix Fisher distribution since these parameters are homeomorphic to R^9. By using a negative log likelihood loss for this distribution 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 applicable datasets, namely Pascal3D+, ModelNet10-SO(3) and UPNA head pose.

READ FULL TEXT

page 7

page 13

page 15

page 19

research
11/19/2021

Probabilistic Regression with Huber Distributions

In this paper we describe a probabilistic method for estimating the posi...
research
03/17/2022

On the Pitfalls of Heteroscedastic Uncertainty Estimation with Probabilistic Neural Networks

Capturing aleatoric uncertainty is a critical part of many machine learn...
research
04/28/2023

On Closed-Form expressions for the Fisher-Rao Distance

The Fisher-Rao distance is the geodesic distance between probability dis...
research
10/27/2021

Evidential Softmax for Sparse Multimodal Distributions in Deep Generative Models

Many applications of generative models rely on the marginalization of th...
research
10/03/2021

Hierarchical Kinematic Probability Distributions for 3D Human Shape and Pose Estimation from Images in the Wild

This paper addresses the problem of 3D human body shape and pose estimat...
research
03/03/2023

Uncertainty Estimation by Fisher Information-based Evidential Deep Learning

Uncertainty estimation is a key factor that makes deep learning reliable...
research
04/13/2018

Distribution Regression Network

We introduce our Distribution Regression Network (DRN) which performs re...

Please sign up or login with your details

Forgot password? Click here to reset