Pose Estimation and 3D Reconstruction of Vehicles from Stereo-Images Using a Subcategory-Aware Shape Prior

@article{Coenen2021PoseEA,
  title={Pose Estimation and 3D Reconstruction of Vehicles from Stereo-Images Using a Subcategory-Aware Shape Prior},
  author={Max Coenen and Franz Rottensteiner},
  journal={ArXiv},
  year={2021},
  volume={abs/2107.10898}
}

Online Adaptation for Implicit Object Tracking and Shape Reconstruction in the Wild

A novel and unified framework which utilizes a neural implicit function to simultaneously track and reconstruct 3D objects in the wild and experiment with both Waymo and KITTI datasets and shows significant improvements over state-of-the-art methods for both tracking and shape reconstruction tasks.

JOINT ESTIMATION OF DEPTH AND ITS UNCERTAINTY FROM STEREO IMAGES USING BAYESIAN DEEP LEARNING

  • M. Mehltretter
  • Computer Science
    ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences
  • 2022
A holistic method to jointly estimate disparity and uncertainty is presented, taking into account both aleatoric and epistemic uncertainty, based on a Bayesian Neural Network, which is trained with variational inference using a probabilistic loss formulation.

References

SHOWING 1-10 OF 70 REFERENCES

Probabilistic Vehicle Reconstruction Using a Multi-Task CNN

  • Max CoenenF. Rottensteiner
  • Computer Science, Mathematics
    2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW)
  • 2019
A probabilistic approach for shape-aware 3D vehicle reconstruction from stereo images that leverages the outputs of a novel multi-task CNN that outputs probability distributions for the vehicle's orientation and for both, vehicle keypoints and wireframe edges.

DirectShape: Photometric Alignment of Shape Priors for Visual Vehicle Pose and Shape Estimation

This paper proposes a novel approach to jointly infer the 3D rigid-body poses and shapes of vehicles from stereo images of road scenes and demonstrates that the method significantly improves accuracy for several recent detection approaches.

Reconstructing vehicles from a single image: Shape priors for road scene understanding

Though the problem appears to be ill-posed, it is demonstrated that prior knowledge about how 3D shapes of vehicles project to an image can be used to reason about the reverse process, i.e., how shapes (back-)project from 2D to 3D.

Dense Reconstruction Using 3D Object Shape Priors

A formulation of monocular SLAM which combines live dense reconstruction with shape priors-based 3D tracking and reconstruction, and automatically augments the SLAM system with object specific identity, together with 6D pose and additional shape degrees of freedom for the object(s) of known class in the scene, combining image data and depth information for the pose and shape recovery.

Vehicle Pose and Shape Estimation Through Multiple Monocular Vision

The algorithm outperforms other existing monocular and stereo methods for vehicles' pose and shape estimation and provides a new and robust solution for off-board visual vehicle localization and tracking, which can be applied to massive surveillance camera networks for intelligent transportation.

PRECISE VEHICLE RECONSTRUCTION FOR AUTONOMOUS DRIVING APPLICATIONS

A shape prior is learned, consisting of vehicle geometry and appearance features, and a vehicle model is fit to initially detected vehicles by minimising an energy function, jointly incorporating 3D and 2D information to infer the model’s optimal and precise pose parameters.

DETECTION AND 3D MODELLING OF VEHICLES FROM TERRESTRIAL STEREO IMAGE PAIRS

This work tackles the detection and pose estimation of vehicles on the basis of street level stereo images, obtained from a moving vehicle by fitting an object specific vehicle model into the vehicle detections, and makes use of a deformable 3D active shape model learned from 3D CAD vehicle data in the model fitting approach.

Shape priors for real-time monocular object localization in dynamic environments

This paper presents a real-time monocular object localization system that estimates the shape and pose of dynamic objects in real- time, using video frames captured from a moving monocular camera, and presents a CNN architecture that performs precise keypoint localization.

Joint 3d Estimation of Vehicles and Scene Flow

A novel unified approach which reasons jointly about 3D scene flow as well as the pose, shape and motion of vehicles in the scene is proposed and the results provide a prove of concept and demonstrate the usefulness of the method.

Monocular 3D Object Detection Leveraging Accurate Proposals and Shape Reconstruction

MonopolyPSR, a monocular 3D object detection method that leverages proposals and shape reconstruction, is presented and a novel projection alignment loss is devised to jointly optimize these tasks in the neural network to improve 3D localization accuracy.
...