SMD-Nets: Stereo Mixture Density Networks
We propose a novel stereo matching framework aimed at improving depth accuracy near object boundaries and suited for disparity super-resolution
We propose a novel stereo matching framework aimed at improving depth accuracy near object boundaries and suited for disparity super-resolution
We use attention-based feature fusion to combine image and LiDAR representations.
A new family of metrics for evaluating Multi-Object Tracking.
A generative model structured into independent causal mechanisms produces images for training invariant classifiers.