3D Pose Estimation and 3D Model Retrieval for Objects in the Wild

@article{Grabner20183DPE,
  title={3D Pose Estimation and 3D Model Retrieval for Objects in the Wild},
  author={Alexander Grabner and Peter M. Roth and Vincent Lepetit},
  journal={2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year={2018},
  pages={3022-3031}
}
We propose a scalable, efficient and accurate approach to retrieve 3D models for objects in the wild. [...] Key Method We first present a 3D pose estimation approach for object categories which significantly outperforms the state-of-the-art on Pascal3D+. Second, we use the estimated pose as a prior to retrieve 3D models which accurately represent the geometry of objects in RGB images.Expand
Location Field Descriptors: Single Image 3D Model Retrieval in the Wild
TLDR
This work presents Location Field Descriptors, a novel approach for single image 3D model retrieval in the wild that significantly outperform the state-of-the-art by up to 20% absolute in multiple 3D retrieval metrics. Expand
Learning a Disentangled Embedding for Monocular 3D Shape Retrieval and Pose Estimation
TLDR
This approach explicitly disentangles a shape vector and a pose vector, which alleviates both pose bias for 3D shape retrieval and categorical bias for pose estimation, and outperforming the previous state-of-the-art methods on both tasks. Expand
Efficient 3 D Pose Estimation and 3 D Model Retrieval
Retrieving 3D models for objects in 2D images is an increasingly important problem, driven by the recent emergence of large databases of 3D models such as ShapeNet [1]. However, this task isExpand
Segmentation-Driven 6D Object Pose Estimation
TLDR
This paper introduces a segmentation-driven 6D pose estimation framework where each visible part of the objects contributes a local pose prediction in the form of 2D keypoint locations and uses a predicted measure of confidence to combine these pose candidates into a robust set of 3D-to-2D correspondences. Expand
3D Pose Estimation Based on Reinforce Learning for 2D Image-Based 3D Model Retrieval
TLDR
A novel characteristic view selection model (CVSM) to address the 2D image-based 3D object retrieval problem and defines state, policy, action and reward functions to train an agent with the reinforcement learning framework, by which the agent can effectively reduce the computational cost of the characteristic viewselection and directly obtain the 3D model pose. Expand
Pose from Shape: Deep Pose Estimation for Arbitrary 3D Objects
TLDR
This work proposes a completely generic deep pose estimation approach, which does not require the network to have been trained on relevant categories, nor objects in a category to have a canonical pose, and demonstrates that this method boosts performances for supervised category pose estimation on standard benchmarks. Expand
Object Pose Estimation from Monocular Image using Multi-View Keypoint Correspondence
TLDR
This work proposes a data-efficient method which utilizes the geometric regularity of intraclass objects for pose estimation, which enables this method to achieve state-of-the-art performance on multiple real-image viewpoint estimation datasets, such as Pascal3D+ and ObjectNet3D. Expand
Tackling Two Challenges of 6D Object Pose Estimation: Lack of Real Annotated RGB Images and Scalability to Number of Objects
TLDR
This work addresses the main challenges for 6D object pose estimation and proposes a novel self-supervision method via pose consistency and applies additional parameterisation to a backbone network and distill knowledge from teachers to a student network for model compression. Expand
GP2C: Geometric Projection Parameter Consensus for Joint 3D Pose and Focal Length Estimation in the Wild
TLDR
This work combines deep learning techniques and geometric algorithms in a two-stage approach to estimate an initial focal length and establish 2D-3D correspondences from a single RGB image using a deep network and exploits the geometric prior given by the focal length for 3D pose estimation. Expand
3 D Scene Generation From Real-world Images
Scene understanding is critical in Computer Vision applications, particularly in settings like Augmented/Virtual Reality where interactions between the virtual environment and the physical world areExpand
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 35 REFERENCES
BB8: A Scalable, Accurate, Robust to Partial Occlusion Method for Predicting the 3D Poses of Challenging Objects without Using Depth
  • Mahdi Rad, V. Lepetit
  • Computer Science
  • 2017 IEEE International Conference on Computer Vision (ICCV)
  • 2017
TLDR
A novel method for 3D object detection and pose estimation from color images only that uses segmentation to detect the objects of interest in 2D even in presence of partial occlusions and cluttered background and is the first to report results on the Occlusion dataset using color imagesonly. Expand
Beyond PASCAL: A benchmark for 3D object detection in the wild
TLDR
PASCAL3D+ dataset is contributed, which is a novel and challenging dataset for 3D object detection and pose estimation, and on average there are more than 3,000 object instances per category. Expand
A Novel Representation of Parts for Accurate 3D Object Detection and Tracking in Monocular Images
TLDR
This work presents a method that estimates in real-time and under challenging conditions the 3D pose of a known object in the form of the 2D projections of a few control points, suitable for practical Augmented Reality applications even in industrial environments. 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
ObjectNet3D: A Large Scale Database for 3D Object Recognition
TLDR
A large scale database for 3D object recognition that consists of 100 categories, 90,127 images, 201,888 objects in these images and 44,147 3D shapes, which is useful for recognizing the 3D pose and 3D shape of objects from 2D images is contributed. Expand
6-DoF object pose from semantic keypoints
TLDR
A novel approach to estimating the continuous six degree of freedom (6-DoF) pose (3D translation and rotation) of an object from a single RGB image by combining semantic keypoints predicted by a convolutional network with a deformable shape model. Expand
Seeing 3D Chairs: Exemplar Part-Based 2D-3D Alignment Using a Large Dataset of CAD Models
TLDR
An exemplar-based 3D category representation is proposed, which can explicitly model chairs of different styles as well as the large variation in viewpoint, and an approach to establish part-based correspondences between 3D CAD models and real photographs is developed. Expand
Deep Exemplar 2D-3D Detection by Adapting from Real to Rendered Views
This paper presents an end-to-end convolutional neural network (CNN) for 2D-3D exemplar detection. We demonstrate that the ability to adapt the features of natural images to better align with thoseExpand
A coarse-to-fine model for 3D pose estimation and sub-category recognition
TLDR
A coarse-to-fine hierarchical representation is proposed, where each level of the hierarchy represents objects at a different level of granularity, which prevents performance loss, which is often caused by the increase in the number of parameters. Expand
Render for CNN: Viewpoint Estimation in Images Using CNNs Trained with Rendered 3D Model Views
TLDR
A scalable and overfit-resistant image synthesis pipeline, together with a novel CNN specifically tailored for the viewpoint estimation task, is proposed that can significantly outperform state-of-the-art methods on PASCAL 3D+ benchmark. Expand
...
1
2
3
4
...