TY - GEN
T1 - Spiking Neural Network Based Object Pose Alignment
AU - Yadav, Sushant
AU - Chundawat, Chandarjeet Singh
AU - Chaudhary, Santosh
AU - Kumar, Rajesh
N1 - Publisher Copyright:
© The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.
PY - 2025
Y1 - 2025
N2 - Object pose alignment, a prerequisite for many computer vision tasks, e.g., face recognition, 3D face reconstruction, robotics, augmented reality, etc. There are lot of research to address this issue, still, there are still numerous issues regarding the problem. Among which one of them is the computational efficiency. To address this issue, this article proposes a novel method for object pose alignment of 6 DoF with Spiking Neural Network (SNN). SNNs are biologically inspired neural networks which replace traditional networks through their energy efficiency and event-driven processing mechanism. The method uses SNN to predict the translation and rotation coordinates for the base position to align with the ground truth pose. The proposed method shows potential by reducing the computational cost by almost 10% and the final results of the problem are represented in the result section, representing the initial pose and the aligned pose after training with SNN.
AB - Object pose alignment, a prerequisite for many computer vision tasks, e.g., face recognition, 3D face reconstruction, robotics, augmented reality, etc. There are lot of research to address this issue, still, there are still numerous issues regarding the problem. Among which one of them is the computational efficiency. To address this issue, this article proposes a novel method for object pose alignment of 6 DoF with Spiking Neural Network (SNN). SNNs are biologically inspired neural networks which replace traditional networks through their energy efficiency and event-driven processing mechanism. The method uses SNN to predict the translation and rotation coordinates for the base position to align with the ground truth pose. The proposed method shows potential by reducing the computational cost by almost 10% and the final results of the problem are represented in the result section, representing the initial pose and the aligned pose after training with SNN.
KW - 3D computer vision
KW - Object pose alignment
KW - Spiking neural network
UR - https://www.scopus.com/pages/publications/105016140133
U2 - 10.1007/978-981-96-5955-5_33
DO - 10.1007/978-981-96-5955-5_33
M3 - Conference contribution
AN - SCOPUS:105016140133
SN - 9789819659548
T3 - Lecture Notes in Networks and Systems
SP - 389
EP - 397
BT - Soft Computing
A2 - Kumar, Rajesh
A2 - Verma, Ajit Kumar
A2 - Verma, Om Prakash
A2 - Rajpurohit, Jitendra
PB - Springer Science and Business Media Deutschland GmbH
T2 - 9th International Conference on Soft Computing: Theories and Applications, SoCTA 2024
Y2 - 27 December 2024 through 29 December 2024
ER -