Real-Time Variational Fisheye Stereo without Rectification and Undistortion
This work addresses the problem of efficient 3D mapping for robotics applications like navigation and autonomous driving, offering an incremental improvement by extending existing variational methods to handle fisheye cameras without rectification.
The paper tackles dense 3D mapping from fisheye cameras by proposing a real-time variational stereo method that avoids explicit rectification and undistortion, achieving real-time processing on GPUs and showing advantages over rectified and non-rectified methods.
Dense 3D maps from wide-angle cameras is beneficial to robotics applications such as navigation and autonomous driving. In this work, we propose a real-time dense 3D mapping method for fisheye cameras without explicit rectification and undistortion. We extend the conventional variational stereo method by constraining the correspondence search along the epipolar curve using a trajectory field induced by camera motion. We also propose a fast way of generating the trajectory field without increasing the processing time compared to conventional rectified methods. With our implementation, we were able to achieve real-time processing using modern GPUs. Our results show the advantages of our non-rectified dense mapping approach compared to rectified variational methods and non-rectified discrete stereo matching methods.