Depth estimation from spherical imagery seeks to reconstruct three-dimensional structure across a full 360° field of view. Conventional perspective techniques must be adapted to account for the radial ...

Current computer vision tasks based on deep learning require a huge amount of data with annotations for model training or testing, especially in some dense estimation tasks, such as optical flow ...

The proposed method takes as input the focal stack and camera settings, and establishes a cost volume based on a lens defocus model. This design enables depth estimation with different camera settings ...

Computer vision continues to be one of the most dynamic and impactful fields in artificial intelligence. Thanks to breakthroughs in deep learning, architecture design and data efficiency, machines are ...

Northwestern engineers have unveiled an energy-efficient camera called SpiderCam that estimates depth in the same way that ...