Disp R-CNN: Stereo 3D Object Detection via Shape Prior Guided Instance Disparity Estimation

04/07/2020
by   Jiaming Sun, et al.
6

In this paper, we propose a novel system named Disp R-CNN for 3D object detection from stereo images. Many recent works solve this problem by first recovering a point cloud with disparity estimation and then apply a 3D detector. The disparity map is computed for the entire image, which is costly and fails to leverage category-specific prior. In contrast, we design an instance disparity estimation network (iDispNet) that predicts disparity only for pixels on objects of interest and learns a category-specific shape prior for more accurate disparity estimation. To address the challenge from scarcity of disparity annotation in training, we propose to use a statistical shape model to generate dense disparity pseudo-ground-truth without the need of LiDAR point clouds, which makes our system more widely applicable. Experiments on the KITTI dataset show that, even when LiDAR ground-truth is not available at training time, Disp R-CNN achieves competitive performance and outperforms previous state-of-the-art methods by 20

READ FULL TEXT

page 4

page 8

research
09/17/2019

Object-Centric Stereo Matching for 3D Object Detection

Safe autonomous driving requires reliable 3D object detection-determinin...
research
08/18/2021

Object Disparity

Most of stereo vision works are focusing on computing the dense pixel di...
research
03/29/2021

Detecting and Mapping Trees in Unstructured Environments with a Stereo Camera and Pseudo-Lidar

We present a method for detecting and mapping trees in noisy stereo came...
research
09/21/2018

Computationally efficient dense moving object detection based on reduced space disparity estimation

Computationally efficient moving object detection and depth estimation f...
research
07/20/2023

OCTraN: 3D Occupancy Convolutional Transformer Network in Unstructured Traffic Scenarios

Modern approaches for vision-centric environment perception for autonomo...
research
12/31/2021

Sparse LiDAR Assisted Self-supervised Stereo Disparity Estimation

Deep stereo matching has made significant progress in recent years. Howe...
research
07/01/2022

Leveraging Monocular Disparity Estimation for Single-View Reconstruction

We present a fine-tuning method to improve the appearance of 3D geometri...

Please sign up or login with your details

Forgot password? Click here to reset