2020
Autolabeling 3D Objects With Differentiable Rendering of SDF Shape Priors
CVPR 2020oral
We present an automatic annotation pipeline to recover 9D cuboids and 3D shapes from pre-trained off-the-shelf 2D detectors and sparse LIDAR data. Our autolabeling method solves an ill-posed inverse problem by considering learned shape priors and optimizing geometric and physical parameters. To addr…