Reasoning about uncertain orientations is one of the core problems in many perception tasks such as object pose estimation or motion estimation.
We propose DeepV2D, an end-to-end deep learning architecture for predicting depth from video.
One of the reasons for the success of convolutional networks is their equivariance/invariance under translations.
This paper proposes a RANSAC-based algorithm for determining the axial rotation angle of an object from a pair of its tomographic projections.
In this work, we demonstrate the benefit of using geometric information from synthetic images, coupled with scene depth information, to recover the scale in depth and ego-motion estimation from monocular videos.
We present a practical backend for stereo visual SLAM which can simultaneously discover individual rigid bodies and compute their motions in dynamic environments.