LabelFormer: Object Trajectory Refinement for Offboard Perception from LiDAR Point Clouds. (arXiv:2311.01444v1 [cs.CV])

A major bottleneck to scaling-up training of self-driving perception systems
are the human annotations required for supervision. A promising alternative is
to leverage "auto-labelling" offboard perception models that are trained to
automatically generate annotations from raw LiDAR point clouds at a fraction of
the cost. Auto-labels are most commonly generated via a two-stage approach --
first objects are detected and tracked over time, and then each object
trajectory is passed to a learned refinement model to improve accuracy. Since
existing …

annotations arxiv auto cost driving generate human labelling labels lidar major perception raw scaling self-driving supervision systems training trajectory