3D Object Detection From Monocular Images
5 papers with code • 2 benchmarks • 2 datasets
This is the task of detecting 3D objects from monocular images (as opposed to LiDAR based counterparts). It is usually associated with autonomous driving based tasks.
( Image credit: Orthographic Feature Transform for Monocular 3D Object Detection )
This allows us to reason holistically about the spatial configuration of the scene in a domain where scale is consistent and distances between objects are meaningful.
In this paper, we propose a Geometry Uncertainty Projection Network (GUP Net) to tackle the error amplification problem at both inference and training stages.
We present ROCA, a novel end-to-end approach that retrieves and aligns 3D CAD models from a shape database to a single input image.
As a result, DEVIANT is equivariant to the depth translations in the projective manifold whereas vanilla networks are not.