Monocular 3D Object Detection Leveraging Accurate Proposals and Shape Reconstruction

04/02/2019
by   Jason Ku, et al.
0

We present MonoPSR, a monocular 3D object detection method that leverages proposals and shape reconstruction. First, using the fundamental relations of a pinhole camera model, detections from a mature 2D object detector are used to generate a 3D proposal per object in a scene. The 3D location of these proposals prove to be quite accurate, which greatly reduces the difficulty of regressing the final 3D bounding box detection. Simultaneously, a point cloud is predicted in an object centered coordinate system to learn local scale and shape information. However, the key challenge is how to exploit shape information to guide 3D localization. As such, we devise aggregate losses, including a novel projection alignment loss, to jointly optimize these tasks in the neural network to improve 3D localization accuracy. We validate our method on the KITTI benchmark where we set new state-of-the-art results among published monocular methods, including the harder pedestrian and cyclist classes, while maintaining efficient run-time.

READ FULL TEXT

page 1

page 3

page 6

page 8

page 11

page 12

research
03/23/2019

Monocular 3D Object Detection with Pseudo-LiDAR Point Cloud

Monocular 3D scene understanding tasks, such as object size estimation, ...
research
04/03/2023

Monocular 3D Object Detection with Bounding Box Denoising in 3D by Perceiver

The main challenge of monocular 3D object detection is the accurate loca...
research
07/20/2020

Object-Aware Centroid Voting for Monocular 3D Object Detection

Monocular 3D object detection aims to detect objects in a 3D physical wo...
research
04/26/2019

Deep Fitting Degree Scoring Network for Monocular 3D Object Detection

In this paper, we propose to learn a deep fitting degree scoring network...
research
08/27/2016

3D Object Proposals using Stereo Imagery for Accurate Object Class Detection

The goal of this paper is to perform 3D object detection in the context ...
research
01/11/2019

Mono3D++: Monocular 3D Vehicle Detection with Two-Scale 3D Hypotheses and Task Priors

We present a method to infer 3D pose and shape of vehicles from a single...
research
05/29/2019

Disentangling Monocular 3D Object Detection

In this paper we propose an approach for monocular 3D object detection f...

Please sign up or login with your details

Forgot password? Click here to reset