Deep Bingham Networks: Dealing with Uncertainty and Ambiguity in Pose Estimation

12/20/2020
by   Haowen Deng, et al.
7

In this work, we introduce Deep Bingham Networks (DBN), a generic framework that can naturally handle pose-related uncertainties and ambiguities arising in almost all real life applications concerning 3D data. While existing works strive to find a single solution to the pose estimation problem, we make peace with the ambiguities causing high uncertainty around which solutions to identify as the best. Instead, we report a family of poses which capture the nature of the solution space. DBN extends the state of the art direct pose regression networks by (i) a multi-hypotheses prediction head which can yield different distribution modes; and (ii) novel loss functions that benefit from Bingham distributions on rotations. This way, DBN can work both in unambiguous cases providing uncertainty information, and in ambiguous scenes where an uncertainty per mode is desired. On a technical front, our network regresses continuous Bingham mixture models and is applicable to both 2D data such as images and to 3D data such as point clouds. We proposed new training strategies so as to avoid mode or posterior collapse during training and to improve numerical stability. Our methods are thoroughly tested on two different applications exploiting two different modalities: (i) 6D camera relocalization from images; and (ii) object pose estimation from 3D point clouds, demonstrating decent advantages over the state of the art. For the former we contributed our own dataset composed of five indoor scenes where it is unavoidable to capture images corresponding to views that are hard to uniquely identify. For the latter we achieve the top results especially for symmetric objects of ModelNet dataset.

READ FULL TEXT

page 1

page 7

page 8

page 13

page 14

page 17

page 18

page 19

research
04/09/2020

6D Camera Relocalization in Ambiguous Scenes via Continuous Multimodal Inference

We present a multimodal camera relocalization framework that captures am...
research
11/03/2022

StereoPose: Category-Level 6D Transparent Object Pose Estimation from Stereo Images via Back-View NOCS

Most existing methods for category-level pose estimation rely on object ...
research
03/28/2023

GP3D: Generalized Pose Estimation in 3D Point Clouds: A case study on bin picking

In this paper, we present GP3D, a novel network for generalized pose est...
research
05/08/2018

A Mixed Classification-Regression Framework for 3D Pose Estimation from 2D Images

3D pose estimation from a single 2D image is an important and challengin...
research
05/30/2023

A Probabilistic Rotation Representation for Symmetric Shapes With an Efficiently Computable Bingham Loss Function

In recent years, a deep learning framework has been widely used for obje...
research
06/10/2021

Implicit-PDF: Non-Parametric Representation of Probability Distributions on the Rotation Manifold

Single image pose estimation is a fundamental problem in many vision and...
research
12/02/2019

Mixture Dense Regression for Object Detection and Human Pose Estimation

Mixture models are well-established machine learning approaches that, in...

Please sign up or login with your details

Forgot password? Click here to reset