Corpus ID: 128358503

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

@article{Wang2019DirectShapePA,
  title={DirectShape: Photometric Alignment of Shape Priors for Visual Vehicle Pose and Shape Estimation},
  author={Rui Wang and Nan Yang and J. St{\"u}ckler and Daniel Cremers},
  journal={ArXiv},
  year={2019},
  volume={abs/1904.10097}
}
3D scene understanding from images is a challenging problem which is encountered in robotics, augmented reality and autonomous driving scenarios. In this paper, we propose a novel approach to jointly infer the 3D rigid-body poses and shapes of vehicles from stereo images of road scenes. Unlike previous work that relies on geometric alignment of shapes with dense stereo reconstructions, our approach works directly on images and infers shape and pose efficiently through combined photometric and… Expand
Pose Estimation and 3D Reconstruction of Vehicles from Stereo-Images Using a Subcategory-Aware Shape Prior
TLDR
It is shown how 3D object reconstruction can profit from a more sophisticated shape prior and from a combined incorporation of different observation types inferred from the images, using a subcategory-aware deformable vehicle model that makes use of a prediction of the vehicle type for a more appropriate regularisation of theVehicle shape. Expand
Probabilistic Vehicle Reconstruction Using a Multi-Task CNN
TLDR
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. Expand
FroDO: From Detections to 3D Objects
TLDR
FroDO is a method for accurate 3D reconstruction of object instances from RGB video that infers their location, pose and shape in a coarse to fine manner to embed object shapes in a novel learnt shape space that allows seamless switching between sparse point cloud and dense DeepSDF decoding. Expand
DSP-SLAM: Object Oriented SLAM with Deep Shape Priors
TLDR
DSP-SLAM is proposed, an object-oriented SLAM system that builds a rich and accurate joint map of dense 3D models for foreground objects, and sparse landmark points to represent the background, and shows improvements in object pose and shape reconstruction with respect to recent deep prior-based reconstruction methods and reductions in camera tracking drift on the KITTI dataset. Expand
Disp R-CNN: Stereo 3D Object Detection via Shape Prior Guided Instance Disparity Estimation
TLDR
It is proposed to use a statistical shape model to generate dense disparity pseudo-ground-truth without the need of LiDAR point clouds, which makes the Disp R-CNN system more widely applicable. Expand
Monocular Differentiable Rendering for Self-Supervised 3D Object Detection
TLDR
This work presents a novel self-supervised method for textured 3D shape reconstruction and pose estimation of rigid objects with the help of strong shape priors and 2D instance masks for 3D object detection from monocular images. Expand
PerMO: Perceiving More at Once from a Single Image for Autonomous Driving
TLDR
This work presents a new part-based deformable vehicle model that is used for instance segmentation and automatically generate a dataset that contains dense correspondences between 2D images and 3D models, and presents a novel end-to-end deep neural network to predict dense 2D/3D mapping. Expand
ZoomNet: Part-Aware Adaptive Zooming Neural Network for 3D Object Detection
TLDR
A novel framework named ZoomNet for stereo imagery-based 3D detection, which surpasses all previous state-of-the-art methods by large margins and introduces to learn part locations as complementary features to improve the resistance against occlusion and put forward the 3D fitting score to better estimate the3D detection quality. Expand
Learning Monocular 3D Vehicle Detection Without 3D Bounding Box Labels
TLDR
This chapter proposes a network architecture and training procedure for learning monocular 3D object detection without 3D bounding box labels, and evaluates the proposed algorithm on the real-world KITTI dataset to achieve promising performance in comparison to state-of-the-art methods and superior performance to conventional baseline methods. Expand
Joint Deep Multi-Graph Matching and 3D Geometry Learning from Inhomogeneous 2D Image Collections
TLDR
This work proposes a trainable framework that takes advantage of graph neural networks for learning a deformable 3D geometry model from inhomogeneous image collections, i.e. a set of images that depict different instances of objects from the same category. Expand
...
1
2
...

References

SHOWING 1-10 OF 44 REFERENCES
Joint Object Pose Estimation and Shape Reconstruction in Urban Street Scenes Using 3D Shape Priors
TLDR
This work proposes a novel approach for using compact shape manifolds of the shape within an object class for object segmentation, pose and shape estimation and demonstrates that the shape manifold alignment method yields improved results over the initial stereo reconstruction and object detection method in depth and pose accuracy. Expand
SAMP: Shape and Motion Priors for 4D Vehicle Reconstruction
TLDR
This paper proposes to use 3D shape and motion priors to regularize the estimation of the trajectory and the shape of vehicles in sequences of stereo images, representing shapes by 3D signed distance functions and embed them in a low-dimensional manifold. Expand
Dense Reconstruction Using 3D Object Shape Priors
TLDR
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. Expand
3D-RCNN: Instance-Level 3D Object Reconstruction via Render-and-Compare
TLDR
A differentiable Render-and-Compare loss is proposed that allows 3D shape and pose to be learned with 2D supervision and produces a compact 3D representation of the scene, which can be readily used for applications like autonomous driving. Expand
Object-Centric Photometric Bundle Adjustment with Deep Shape Prior
TLDR
This paper introduces learned shape prior in the form of deep shape generators into Photometric Bundle Adjustment (PBA) and proposes to accommodate full 3D shape generated by the shape prior within the optimization-based inference framework, demonstrating impressive results. Expand
Stereo R-CNN Based 3D Object Detection for Autonomous Driving
TLDR
Experiments show that the proposed Stereo R-CNN method outperforms the state-of-the-art stereo-based method by around 30% AP on both 3D detection and 3D localization tasks. Expand
Automatic 3D Car Model Alignment for Mixed Image-Based Rendering
TLDR
A method is proposed that automatically identifies stock 3D models, aligns them in the 3D scene and performs morphing to better capture image contours, and shows significant improvement in image quality for free-viewpoint IBR, especially when moving far from the captured viewpoints. Expand
Joint 3D Object and Layout Inference from a Single RGB-D Image
TLDR
This work proposes a high-order graphical model and jointly reason about the layout, objects and superpixels in the image and demonstrates that the proposed method is able to infer scenes with a large degree of clutter and occlusions. Expand
Exploiting Object Similarity in 3D Reconstruction
TLDR
This paper takes advantage of the fact that the larger the reconstructed area, the more likely objects of similar type and shape will occur in the scene, to take advantage of shape similarity by localizing objects using detectors and jointly reconstructing them while learning a volumetric model of their shape. Expand
3D Bounding Box Estimation Using Deep Learning and Geometry
TLDR
Although conceptually simple, this method outperforms more complex and computationally expensive approaches that leverage semantic segmentation, instance level segmentation and flat ground priors and produces state of the art results for 3D viewpoint estimation on the Pascal 3D+ dataset. Expand
...
1
2
3
4
5
...