Point Cloud Models

Panoptic-PolarNet is a point cloud segmentation framework for LiDAR point clouds. It learns both semantic segmentation and class-agnostic instance clustering in a single inference network using a polar Bird's Eye View (BEV) representation, enabling the authors to circumvent the issue of occlusion among instances in urban street scenes. We first encode the raw point cloud data with $K$ features into a fixed-size representation on the polar BEV map. Next, we use a single backbone encoder-decoder network to generate semantic prediction, center heatmap and offset regression. Finally, we merge these outputs via a voting-based fusion to yield the panoptic segmentation result.

Source: Panoptic-PolarNet: Proposal-free LiDAR Point Cloud Panoptic Segmentation


Paper Code Results Date Stars


Task Papers Share
Instance Segmentation 1 33.33%
Panoptic Segmentation 1 33.33%
Semantic Segmentation 1 33.33%


Component Type
🤖 No Components Found You can add them if they exist; e.g. Mask R-CNN uses RoIAlign