When Regression Meets Manifold Learning for Object Recognition and Pose Estimation

Bui, Mai; Zakharov, Sergey; Albarqouni, Shadi; Ilić, Slobodan; Navab, Nassir

doi:10.1109/icra.2018.8460654

Cited by 28 publications

(17 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Surface normal is also used as an additional modality in [6]. Another way of using depth information is to treat it as an extra image depth channel (RGBD) and feed it into a CNN [5], [24], [6], [7], [8], or random forest [21], [1], [22] or a fully connected sparse autoencoder [25] for feature extraction. Depth is also used to create point clouds, which are used for generating pose hypotheses with 3D-3D correspondences and ICP refinement in [12].…”

Section: Related Workmentioning

confidence: 99%

“…[16] propose to regress translation and rotation with the same network. Quaternions are used as the rotation representation for regression [11], [16], [8]. Bui et al [8] propose to use L2 loss function for rotation learning.…”

Section: Related Workmentioning

confidence: 99%

“…These learned features are used for inferring 6D object poses. Similarly, CNNs can also be applied to RGB-D images and treat depth information as an additional channel for feature learning [5], [6], [7], [8]. However, in some scenarios, color information may not be available, and depth information is not in the 2-dimensional matrix format (e.g., laser range finder data), which can be easily processed with CNN-based systems.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

6D Object Pose Regression via Supervised Learning on Point Clouds

Gao

Lauri

Wang

et al. 2020

Preprint

View full text Add to dashboard Cite

This paper addresses the task of estimating the 6 degrees of freedom pose of a known 3D object from depth information represented by a point cloud. Deep features learned by convolutional neural networks from color information have been the dominant features to be used for inferring object poses, while depth information receives much less attention. However, depth information contains rich geometric information of the object shape, which is important for inferring the object pose. We use depth information represented by point clouds as the input to both deep networks and geometry-based pose refinement and use separate networks for rotation and translation regression. We argue that the axis-angle representation is a suitable rotation representation for deep learning, and use a geodesic loss function for rotation regression. Ablation studies show that these design choices outperform alternatives such as the quaternion representation and L2 loss, or regressing translation and rotation with the same network. Our simple yet effective approach clearly outperforms state-of-the-art methods on the YCB-video dataset.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

6D Object Pose Regression via Supervised Learning on Point Clouds

Gao

Lauri

Wang

et al. 2020

Preprint

View full text Add to dashboard Cite

show abstract

“…For example, [15] proposes a descriptor for object templates, based on image and depth gradients. Deep Learning has also been applied to such approach, by learning to compute a descriptor from pairs or triplets of object images [34,1,36,5]. Like ours, these approaches do not require re-training, as it only requires to compute the descriptors for images of the new objects.…”

Section: D Object Detection and Pose Estimation From Color Imagesmentioning

confidence: 99%

CorNet: Generic 3D Corners for 6D Pose Estimation of New Objects without Retraining

Pitteri

Ilić

Lepetit

2019

2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW)

Self Cite

View full text Add to dashboard Cite

We present a novel approach to the detection and 3D pose estimation of objects in color images. Its main contribution is that it does not require any training phases nor data for new objects, while state-of-the-art methods typically require hours of training time and hundreds of training registered images. Instead, our method relies only on the objects' geometries. Our method focuses on objects with prominent corners, which covers a large number of industrial objects. We first learn to detect object corners of various shapes in images and also to predict their 3D poses, by using training images of a small set of objects. To detect a new object in a given image, we first identify its corners from its CAD model; we also detect the corners visible in the image and predict their 3D poses. We then introduce a RANSAC-like algorithm that robustly and efficiently detects and estimates the object's 3D pose by matching its corners on the CAD model with their detected counterparts in the image. Because we also estimate the 3D poses of the corners in the image, detecting only 1 or 2 corners is sufficient to estimate the pose of the object, which makes the approach robust to occlusions. We finally rely on a final check that exploits the full 3D geometry of the objects, in case multiple objects have the same corner spatial arrangement. The advantages of our approach make it particularly attractive for industrial contexts, and we demonstrate our approach on the challenging T-LESS dataset.

show abstract

“…With the success of deep learning in object recognition, deep neural network has been gradually applied to objects' 6D pose estimation. Multiple end-to-end CNN-based neural networks [10]- [13] have been proposed to map RGB images to 6D poses directly. Although end-to-end poses regression methods are simple, it is not clear whether such end-to-end algorithms have learned enough feature representations for pose estimation.…”

Section: Introductionmentioning

confidence: 99%

Fast and Accurate Spacecraft Pose Estimation From Single Shot Space Imagery Using Box Reliability and Keypoints Existence Judgments

Huo

Zhang

2020

IEEE Access

View full text Add to dashboard Cite

Real-time 6DOF (6 Degree of Freedom) pose estimation of an uncooperative spacecraft is an important part of proximity operations, e.g., space debris removal, spacecraft rendezvous and docking, on-orbit servicing, etc. In this paper, a novel efficient deep learning based approach is proposed to estimate the 6DOF pose of uncooperative spacecraft using monocular-vision measurement. Firstly, we introduce a new lightweight YOLO-liked CNN to detect spacecraft and predict 2D locations of the projected keypoints of a prior reconstructed 3D model in real-time. Then, we design two novel models for predicting the bounding box (bbox) reliability scores and the probability of keypoints existence. The two models not only significantly reduce the false positive, but also speed up convergence. Finally, the 6DOF pose is estimated and refined using Perspective-n-Point and geometric optimizer. Results demonstrate that the proposed approach achieves 73.2% average precision and 77.6% average recall for spacecraft detection on the SPEED dataset after only 200 training epochs. For the pose estimation task, the mean rotational error is 0.6812 • , and the mean translation error is 0.0320m. The proposed approach achieves competitive pose estimation performance and extreme lightweight (∼ 0.89 million learnable weights in total) on the SPEED dataset while being efficient for real-time applications.

show abstract

When Regression Meets Manifold Learning for Object Recognition and Pose Estimation

Cited by 28 publications

References 16 publications

6D Object Pose Regression via Supervised Learning on Point Clouds

6D Object Pose Regression via Supervised Learning on Point Clouds

CorNet: Generic 3D Corners for 6D Pose Estimation of New Objects without Retraining

Fast and Accurate Spacecraft Pose Estimation From Single Shot Space Imagery Using Box Reliability and Keypoints Existence Judgments

Contact Info

Product

Resources

About