PARTNER: Level up the Polar Representation for LiDAR 3D Object Detection
This work addresses a specific bottleneck in LiDAR detection for autonomous vehicles, offering incremental improvements over existing polar-based methods.
The paper tackles the feature distortion problem in polar-based LiDAR 3D object detection by proposing PARTNER, which uses global representation re-alignment and instance-level geometric information, resulting in performance improvements of 3.68% and 9.15% on Waymo and ONCE datasets.
Recently, polar-based representation has shown promising properties in perceptual tasks. In addition to Cartesian-based approaches, which separate point clouds unevenly, representing point clouds as polar grids has been recognized as an alternative due to (1) its advantage in robust performance under different resolutions and (2) its superiority in streaming-based approaches. However, state-of-the-art polar-based detection methods inevitably suffer from the feature distortion problem because of the non-uniform division of polar representation, resulting in a non-negligible performance gap compared to Cartesian-based approaches. To tackle this issue, we present PARTNER, a novel 3D object detector in the polar coordinate. PARTNER alleviates the dilemma of feature distortion with global representation re-alignment and facilitates the regression by introducing instance-level geometric information into the detection head. Extensive experiments show overwhelming advantages in streaming-based detection and different resolutions. Furthermore, our method outperforms the previous polar-based works with remarkable margins of 3.68% and 9.15% on Waymo and ONCE validation set, thus achieving competitive results over the state-of-the-art methods.