Shift R-CNN: Deep Monocular 3D Object Detection with Closed-Form Geometric Constraints

05/23/2019
by   Andretti Naiden, et al.
1

We propose Shift R-CNN, a hybrid model for monocular 3D object detection, which combines deep learning with the power of geometry. We adapt a Faster R-CNN network for regressing initial 2D and 3D object properties and combine it with a least squares solution for the inverse 2D to 3D geometric mapping problem, using the camera projection matrix. The closed-form solution of the mathematical system, along with the initial output of the adapted Faster R-CNN are then passed through a final ShiftNet network that refines the result using our newly proposed Volume Displacement Loss. Our novel, geometrically constrained deep learning approach to monocular 3D object detection obtains top results on KITTI 3D Object Detection Benchmark, being the best among all monocular methods that do not use any pre-trained network for depth estimation.

READ FULL TEXT
research
03/01/2021

Categorical Depth Distribution Network for Monocular 3D Object Detection

Monocular 3D object detection is a key problem for autonomous vehicles, ...
research
07/29/2021

Learning Geometry-Guided Depth via Projective Modeling for Monocular 3D Object Detection

As a crucial task of autonomous driving, 3D object detection has made gr...
research
03/31/2021

GrooMeD-NMS: Grouped Mathematically Differentiable NMS for Monocular 3D Object Detection

Modern 3D object detectors have immensely benefited from the end-to-end ...
research
07/29/2021

Geometry Uncertainty Projection Network for Monocular 3D Object Detection

Geometry Projection is a powerful depth estimation method in monocular 3...
research
03/16/2022

MonoJSG: Joint Semantic and Geometric Cost Volume for Monocular 3D Object Detection

Due to the inherent ill-posed nature of 2D-3D projection, monocular 3D o...
research
07/20/2022

Densely Constrained Depth Estimator for Monocular 3D Object Detection

Estimating accurate 3D locations of objects from monocular images is a c...
research
04/24/2022

RealNet: Combining Optimized Object Detection with Information Fusion Depth Estimation Co-Design Method on IoT

Depth Estimation and Object Detection Recognition play an important role...

Please sign up or login with your details

Forgot password? Click here to reset