Absolute Pose

Absolute pose estimation aims to determine the precise location and orientation of a camera (or other sensor) within a 3D environment using image data and/or other sensor inputs. Current research focuses on improving the accuracy and efficiency of pose estimation, particularly in challenging scenarios like those with limited features, significant viewpoint changes, or noisy data, employing techniques such as geometric algorithms, deep learning models (including transformers and convolutional neural networks), and fusion of multiple sensor modalities (e.g., visual-inertial). These advancements have significant implications for applications like augmented reality, robotics, autonomous navigation, and 3D scene reconstruction, enabling more robust and reliable operation in complex environments.

Papers

May 21, 2024

PoseGravity: Pose Estimation from Points and Lines with Axis Prior
Akshay Chandrasekhar
Pose Estimation Exceptional Point Camera Model Best Fit Line Absolute Pose Line Feature Closed Form Solution Rotation Matrix

May 13, 2024

JointLoc: A Real-time Visual Localization Framework for Planetary UAVs Based on Joint Relative and Absolute Pose Estimation
Xubo Luo, Xue Wan, Yixing Gao, Yaolin Tian, Wei Zhang, Leizheng Shu
Visual Localization Joint Framework Orb Slam3 Absolute Pose

April 25, 2024

Efficient Solution of Point-Line Absolute Pose
Petr Hruby, Timothy Duff, Marc Pollefeys
Pose Estimation Efficient Approach Point Correspondence Extrinsic Camera Absolute Pose Minimal Problem

March 17, 2024

Order-One Rolling Shutter Cameras
Marvin Anas Hahn, Kathlén Kohn, Orlando Marigliano, Tomas Pajdla
Rolling Shutter Relative Camera Absolute Pose

February 29, 2024

On the Existence of Static Equilibria of a Cable-Suspended Load with Non-stopping Flying Carriers
Chiara Gabellieri, Antonio Franchi
Aerial Manipulation Plane Feature Absolute Pose Cable Suspended Cable Force

February 7, 2024

Efficient Invariant Kalman Filter for Inertial-based Odometry with Large-sample Environmental Measurements
Xinghan Li, Haoying Li, Guangyang Zeng, Qingcheng Zeng, Xiaoqiang Ren, Chao Yang, Junfeng Wu
Long Term Kalman Filter Inertial Odometry Absolute Pose Invariant Kalman

January 21, 2024

MobileARLoc: On-device Robust Absolute Localisation for Pervasive Markerless Mobile AR
Changkun Liu, Yukun Zhao, Tristan Braud
Augmented Reality Visual Inertial Odometry Absolute Pose High Accuracy Localization

December 11, 2023

ManiPose: Manifold-Constrained Multi-Hypothesis 3D Human Pose Estimation
Cédric Rommel, Victor Letzelter, Nermin Samet, Renaud Marlet, Matthieu Cord, Patrick Pérez, Eduardo Valle
3D Pose Monocular 3D Non Linear Manifold Absolute Pose

September 27, 2023

Q-REG: End-to-End Trainable Point Cloud Registration with Surface Curvature
Shengze Jin, Daniel Barath, Marc Pollefeys, Iro Armeni
End to End Point Cloud Registration Absolute Pose Correspondence Matching Rigid Motion

August 22, 2023

Coarse-to-Fine Multi-Scene Pose Regression with Transformers
Yoli Shavit, Ron Ferens, Yosi Keller
Transformer Megatron Decepticons Coarse to Fine Pose Regression Pose Prediction Convolutional Backbone Absolute Pose Multi Scene Absolute Pose Regressors

August 21, 2023

Spectral Graphormer: Spectral Graph-based Transformer for Egocentric Two-Hand Reconstruction using Multi-View Color Images
Tze Ho Elden Tse, Franziska Mueller, Zhengyang Shen, Danhang Tang, Thabo Beeler, Mingsong Dou, Yinda Zhang, Sasa Petrovic, Hyung Jin Chang, Jonathan Taylor, Bardia Doosti
Color Image Absolute Pose Spectral Transformer Graphormer Reactivity Model Parametric Hand Model Multi View RGB

August 18, 2023

3D Model-free Visual Localization System from Essential Matrix under Local Planar Motion
Yanmei Jiao, Binxin Zhang, Peng Jiang, Chaoqun Wang, Rong Xiong, Yue Wang
3D Content Visual Localization Absolute Pose Visual Relocalization Local Motion

April 14, 2023

Fusing Structure from Motion and Simulation-Augmented Pose Regression from Optical Flow for Challenging Indoor Environments
Felix Ott, Lucas Heublein, David Rügamer, Bernd Bischl, Christopher Mutschler
Optical Flow Motion Information Relative Pose Pose Regression Pose Prediction Absolute Pose Absolute Pose Regression Relative Pose Regression

February 14, 2023

MSDA: Monocular Self-supervised Domain Adaptation for 6D Object Pose Estimation
Dingding Cai, Janne Heikkilä, Esa Rahtu
Synthetic to Real 6D Object Pose Estimation Synthetic RGB Absolute Pose Pose Label Self Supervised Domain Adaptation

November 20, 2022

A Lightweight Domain Adaptive Absolute Pose Regressor Using Barlow Twins Objective
Praveen Kumar Rajendran, Quoc-Vinh Lai-Dang, Luiz Felipe Vecchietti, Dongsoo Har
Cross Domain Convolutional Backbone Absolute Pose Barlow Twin Absolute Pose Regression Absolute Pose Regressors

November 14, 2022

Robust Collaborative 3D Object Detection in Presence of Pose Errors
Yifan Lu, Quanhao Li, Baoan Liu, Mehrdad Dianati, Chen Feng, Siheng Chen, Yanfeng Wang
Speech Presence Pose Graph Absolute Pose Collaborative 3D Object Detection Pose Error

September 29, 2022

Partially calibrated semi-generalized pose from hybrid point correspondences
Snehal Bhayani, Viktor Larsson, Torsten Sattler, Janne Heikkila, Zuzana Kukelova
Human Pose Point Correspondence Absolute Pose Perspective Camera Generalized Camera

August 1, 2022

Benchmarking Visual-Inertial Deep Multimodal Fusion for Relative Pose Regression and Odometry-aided Absolute Pose Regression
Felix Ott, Nisha Lakshmana Raichur, David Rügamer, Tobias Feigl, Heiko Neumann, Bernd Bischl, Christopher Mutschler
Visual Odometry Visual Inertial Localization Task Absolute Pose Absolute Pose Regression Relative Pose Regression

June 13, 2022

TC-SfM: Robust Track-Community-Based Structure-from-Motion
Lei Wang, Linlin Ge, Shan Luo, Zihan Yan, Zhaopeng Cui, Jieqing Feng
3D Scene Structure From Motion 3D Structure Relative Camera Absolute Pose