Pose Estimation
Pose estimation, the task of determining the position and orientation of objects in space, is a core problem in computer vision with applications ranging from robotics and augmented reality to autonomous driving and medical imaging. Current research focuses on improving accuracy and robustness in challenging scenarios, such as occlusions, low-quality images, and unstructured environments, often employing deep learning models like transformers and convolutional neural networks, along with techniques like bundle adjustment and graph optimization for pose refinement. These advancements are driving progress in various fields by enabling more precise and reliable object manipulation, scene understanding, and human-computer interaction.
Papers
Learning Implicit Probability Distribution Functions for Symmetric Orientation Estimation from RGB Images Without Pose Labels
Arul Selvam Periyasamy, Luis Denninger, Sven Behnke
Simultaneous Multiple Object Detection and Pose Estimation using 3D Model Infusion with Monocular Vision
Congliang Li, Shijie Sun, Xiangyu Song, Huansheng Song, Naveed Akhtar, Ajmal Saeed Mian
Robust Monocular Localization of Drones by Adapting Domain Maps to Depth Prediction Inaccuracies
Priyesh Shukla, Sureshkumar S., Alex C. Stutts, Sathya Ravi, Theja Tulabandhula, Amit R. Trivedi
InGVIO: A Consistent Invariant Filter for Fast and High-Accuracy GNSS-Visual-Inertial Odometry
Changwu Liu, Chen Jiang, Haowen Wang
Parallel Inversion of Neural Radiance Fields for Robust Pose Estimation
Yunzhi Lin, Thomas Müller, Jonathan Tremblay, Bowen Wen, Stephen Tyree, Alex Evans, Patricio A. Vela, Stan Birchfield
FPGA Hardware Acceleration for Feature-Based Relative Navigation Applications
Ramchander Rao Bhaskara, Manoranjan Majji