CubifAE-3D: Monocular Camera Space Cubification for Auto-Encoder based 3D Object Detection

7 Jun 2020  ·  Shubham Shrivastava, Punarjay Chakravarty ·

We introduce a method for 3D object detection using a single monocular image. Starting from a synthetic dataset, we pre-train an RGB-to-Depth Auto-Encoder (AE)... The embedding learnt from this AE is then used to train a 3D Object Detector (3DOD) CNN which is used to regress the parameters of 3D object poses after the encoder from the AE generates a latent embedding from the RGB image. We show that we can pre-train the AE using paired RGB and depth images from simulation data once and subsequently only train the 3DOD network using real data, comprising of RGB images and 3D object pose labels (without the requirement of dense depth). Our 3DOD network utilizes a particular `cubification' of 3D space around the camera, where each cuboid is tasked with predicting N object poses, along with their class and confidence values. The AE pre-training and this method of dividing the 3D space around the camera into cuboids give our method its name - CubifAE-3D. We demonstrate results for monocular 3D object detection in the Autonomous Vehicle (AV) use-case with the Virtual KITTI 2 and the KITTI datasets. read more

PDF Abstract
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Monocular 3D Object Detection KITTI Cars Hard CubifAE-3D AP Hard 6.42 # 3
Monocular 3D Object Detection KITTI Cars Moderate CubifAE-3D AP Medium 7.94 # 3
Monocular 3D Object Detection KITTI Pedestrian Hard CubifAE-3D AP Hard 4.82 # 2
Monocular 3D Object Detection KITTI Pedestrians Moderate val CubifAE-3D AP Medium 5.43 # 1
Monocular 3D Object Detection Virtual KITTI 2 CubifAE-3D mAP@0.3 86.6 # 1
mAP@0.5 66.7 # 1