Published on Tue May 14 2019

Monocular 3D Object Detection via Geometric Reasoning on Keypoints

Ivan Barabanau, Alexey Artemov, Evgeny Burnaev, Vyacheslav Murashkin

Monocular 3D object detection is well-known to be a challenging vision task. We build our multi-branch model around 2D keypoint detection in images. Our network performs in an end-to-end manner, simultaneously and interdependently estimating 2Dcharacteristics.

0
0
0
Abstract

Monocular 3D object detection is well-known to be a challenging vision task due to the loss of depth information; attempts to recover depth using separate image-only approaches lead to unstable and noisy depth estimates, harming 3D detections. In this paper, we propose a novel keypoint-based approach for 3D object detection and localization from a single RGB image. We build our multi-branch model around 2D keypoint detection in images and complement it with a conceptually simple geometric reasoning method. Our network performs in an end-to-end manner, simultaneously and interdependently estimating 2D characteristics, such as 2D bounding boxes, keypoints, and orientation, along with full 3D pose in the scene. We fuse the outputs of distinct branches, applying a reprojection consistency loss during training. The experimental evaluation on the challenging KITTI dataset benchmark demonstrates that our network achieves state-of-the-art results among other monocular 3D detectors.

Sun Apr 18 2021
Computer Vision
MonoGRNet: A General Framework for Monocular 3D Object Detection
0
0
0
Tue Apr 06 2021
Computer Vision
Objects are Different: Flexible Monocular 3D Object Detection
0
0
0
Mon Nov 26 2018
Computer Vision
MonoGRNet: A Geometric Reasoning Network for Monocular 3D Object Localization
MonoGRNet is a single, unified network composed of four task-specific subnetworks. It is responsible for 2D object detection, instance depth estimation (IDE), 3D localization and local corner regression.
0
0
0
Tue Dec 04 2018
Computer Vision
Estimating 6D Pose From Localizing Designated Surface Keypoints
In this paper, we present an accurate yet effective solution for 6D pose emphaticallyestimation from an RGB image. We obtain a 30% relative improvement in terms of ADD accuracy among methods without using refinement. We will make our code and models publicly available soon.
0
0
0
Wed Sep 02 2020
Computer Vision
Monocular 3D Detection with Geometric Constraints Embedding and Semi-supervised Training
We propose a novel single-shot and keypoints-based framework for monocular 3D objects detection using only RGB images, called KM3D-Net. We design a fully convolutional model to predict object keypoints, dimension, andorientation, and then combine these estimations with perspective geometry constraints to compute position attribute.
0
0
0
Mon Nov 30 2020
Computer Vision
Monocular 3D Object Detection with Sequential Feature Association and Depth Hint Augmentation
Monocular 3D object detection is a promising research topic for intelligent perception systems of autonomous driving. In this work, a single-stage keypoint-based network, named as FADNet, is presented to address the task. The contributions of this work are validated by conducting experiments.
0
0
0