Deformable PV-RCNN: Improving 3D Object Detection with Learned Deformations

20 Aug 2020 • Prarthana Bhattacharyya • Krzysztof Czarnecki

We present Deformable PV-RCNN, a high-performing point-cloud based 3D object detector. Currently, the proposal refinement methods used by the state-of-the-art two-stage detectors cannot adequately accommodate differing object scales, varying point-cloud density, part-deformation and clutter... (read more)

PDF Abstract

Datasets


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
3D Object Detection KITTI Cars Moderate val Deformable PV-RCNN AP 83.3 # 4
3D Object Detection KITTI Cyclists Moderate val Deformable PV-RCNN AP 73.46 # 1
3D Object Detection KITTI Pedestrians Moderate val Deformable PV-RCNN AP 58.33 # 1

Methods used in the Paper


METHOD TYPE
Convolution
Convolutions
Deformable Convolution
Convolutions