Vehicle Pose Estimation

20 papers with code • 4 benchmarks • 4 datasets

Most implemented papers

3D Bounding Box Estimation Using Deep Learning and Geometry

smallcorgi/3D-Deepbox CVPR 2017

In contrast to current techniques that only regress the 3D orientation of an object, our method first regresses relatively stable 3D object properties using a deep convolutional neural network and then combines these estimates with geometric constraints provided by a 2D object bounding box to produce a complete 3D bounding box.

M3D-RPN: Monocular 3D Region Proposal Network for Object Detection

garrickbrazil/M3D-RPN ICCV 2019

Understanding the world in 3D is a critical component of urban autonomous driving.

Learning Depth-Guided Convolutions for Monocular 3D Object Detection

dingmyu/D4LCN CVPR 2020

3D object detection from a single image without LiDAR is a challenging task due to the lack of accurate depth information.

RTM3D: Real-time Monocular 3D Detection from Object Keypoints for Autonomous Driving

Banconxuan/RTM3D ECCV 2020

Different from these approaches, our method predicts the nine perspective keypoints of a 3D bounding box in image space, and then utilize the geometric relationship of 3D and 2D perspectives to recover the dimension, location, and orientation in 3D space.

Kinematic 3D Object Detection in Monocular Video

Nicholasli1995/EgoNet ECCV 2020

In this work, we propose a novel method for monocular video-based 3D object detection which carefully leverages kinematic motion to improve precision of 3D localization.

Subcategory-aware Convolutional Neural Networks for Object Proposals and Detection

xiaohaoChen/rrc_detection 16 Apr 2016

In CNN-based object detection methods, region proposal becomes a bottleneck when objects exhibit significant scale variation, occlusion or truncation.

BoxCars: Improving Fine-Grained Recognition of Vehicles using 3-D Bounding Boxes in Traffic Surveillance

JakubSochor/BoxCars 2 Mar 2017

We also show that our method outperforms the state-of-the-art methods for fine-grained recognition.

Monocular 3D Object Detection Leveraging Accurate Proposals and Shape Reconstruction

ZhixinLai/3D-detection-with-monocular-RGB-image CVPR 2019

We present MonoPSR, a monocular 3D object detection method that leverages proposals and shape reconstruction.

Occlusion-Net: 2D/3D Occluded Keypoint Localization Using Graph Networks

dineshreddy91/Occlusion_Net CVPR 2019

Central to this work is a trifocal tensor loss that provides indirect self-supervision for occluded keypoint locations that are visible in other views of the object.