Vehicle Pose Estimation
15 papers with code • 4 benchmarks • 3 datasets
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.
3D object detection from a single image without LiDAR is a challenging task due to the lack of accurate depth information.
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.
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
We also show that our method outperforms the state-of-the-art methods for fine-grained recognition.
We present MonoPSR, a monocular 3D object detection method that leverages proposals and shape reconstruction.
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.
We present a conceptually simple framework for 6DoF object pose estimation, especially for autonomous driving scenario.