Benjamin Coors
Papers
1
Total Citations
360
H-Index
1
About
Benjamin Coors is a leading researcher in computer vision and deep learning, with a particular focus on spherical representations for omnidirectional imagery. His most influential work, "SphereNet: Learning Spherical Representations for Detection and Classification in Omnidirectional Images" (2018), has garnered over 360 citations, establishing him as a key figure in adapting convolutional neural networks to non-Euclidean geometries. Coors pioneered methods for processing 360-degree images by developing spherical convolutional kernels that account for distortion inherent in wide-angle captures, enabling robust object detection and classification in immersive environments. This contribution has proven critical for autonomous navigation, virtual reality, and robotics, where traditional planar CNNs fail. Beyond SphereNet, his research consistently bridges geometric deep learning with practical applications, advancing how machines perceive and interact with panoramic visual data. Coors’ work not only solves fundamental challenges in spherical signal processing but also inspires new directions in equivariant neural network design. His high citation count reflects the transformative impact of his ideas on both academic research and industry adoption, making him a pivotal voice in the evolution of computer vision for non-planar domains.
Research Focus
Key Achievements
Top Papers
- 1