PPF-FoldNet: Unsupervised Learning of Rotation Invariant 3D Local Descriptors

Deng, Haowen; Birdal, Tolga; Ilić, Slobodan

doi:10.48550/arxiv.1808.10322

Cited by 13 publications

(19 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Unlike the recent success of deep learning-based 3D keypoint descriptors [7,6,16,38,36,11], most existing 3D keypoint detectors remain hand-crafted. A comprehensive review and evaluation of existing hand-crafted 3D keypoint detectors can be found in [32].…”

Section: Related Workmentioning

confidence: 99%

“…It seems evidential that all the above mentioned problems with hand-crafted detectors for 3D point clouds can be resolved by the highly successful data-driven deep net-works. However, very few deep learning-based 3D keypoint detectors exist (only one deep learning-based approach [36] exists to date) in contrast to its increasing success on learning 3D keypoint descriptors [7,6,38,16]. This is due to the lack of ground truth training datasets to supervise deep learning-based detectors on 3D point clouds.…”

Section: Introductionmentioning

confidence: 99%

“…This is due to the lack of ground truth training datasets to supervise deep learning-based detectors on 3D point clouds. Unlike 3D descriptors that are supervised by easily available ground truth registered overlapping 3D point clouds [7,6,16,38,36,11], it is impossible for anyone to identify and label the "ground truth" keypoints on 3D point clouds. Consequently, most of the works on 3D descriptors [7,6,38,16] ignored the detector problem and are built on top of existing hand-crafted 3D detectors or uniform sampling.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

USIP: Unsupervised Stable Interest Point Detection From 3D Point Clouds

Lee

2019

2019 IEEE/CVF International Conference on Computer Vision (ICCV)

170

124

View full text Add to dashboard Cite

In this paper, we propose the USIP detector: an Unsupervised Stable Interest Point detector that can detect highly repeatable and accurately localized keypoints from 3D point clouds under arbitrary transformations without the need for any ground truth training data. Our USIP detector consists of a feature proposal network that learns stable keypoints from input 3D point clouds and their respective transformed pairs from randomly generated transformations. We provide degeneracy analysis of our USIP detector and suggest solutions to prevent it. We encourage high repeatability and accurate localization of the keypoints with a probabilistic chamfer loss that minimizes the distances between the detected keypoints from the training point cloud pairs. Extensive experimental results of repeatability tests on several simulated and real-world 3D point cloud datasets from Lidar, RGB-D and CAD models show that our USIP detector significantly outperforms existing hand-crafted and deep learning-based 3D keypoint detectors. Our code is available at the project website. 1 * now at nuTonomy: an APTIV company.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

USIP: Unsupervised Stable Interest Point Detection From 3D Point Clouds

Lee

2019

2019 IEEE/CVF International Conference on Computer Vision (ICCV)

170

124

View full text Add to dashboard Cite

show abstract

“…Compact Geometric Features (CGF) [11] uses histogram representation as network input to learn a compact local descriptor. PPFnet [4] and PPF-FoldNet [3] directly operate on points and uses a point pair feature encoding of the local 3D geometry into patches. 3DFeat-Net [8] proposes a weakly supervised net-work that learns both 3D feature detector and descriptor.…”

Section: Related Workmentioning

confidence: 99%

PCAN: 3D Attention Map Learning Using Contextual Information for Point Cloud Based Retrieval

Zhang

Xiao

2019

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

200

134

View full text Add to dashboard Cite

Point cloud based retrieval for place recognition is an emerging problem in vision field. The main challenge is how to find an efficient way to encode the local features into a discriminative global descriptor. In this paper, we propose a Point Contextual Attention Network (PCAN), which can predict the significance of each local point feature based on point context. Our network makes it possible to pay more attention to the task-relevent features when aggregating local features. Experiments on various benchmark datasets show that the proposed network can provide outperformance than current state-of-the-art approaches.

show abstract

“…PointNet [Qi et al, 2017b] and Point-Net++ [Qi et al, 2017c] are two architectures built specifically for learning from point sets. Other work on this task include Qi et al [2017a] and Deng et al [2018].…”

Section: Defensesmentioning

confidence: 99%

Adversarial shape perturbations on 3D point clouds

Liu

2019

Preprint

View full text Add to dashboard Cite

The importance of training robust neural network grows as 3D data is increasingly utilized in deep learning for vision tasks, like autonomous driving. We examine this problem from the perspective of the attacker, which is necessary in understanding how neural networks can be exploited, and thus defended. More specifically, we propose adversarial attacks based on solving different optimization problems, like minimizing the perceptibility of our generated adversarial examples, or maintaining a uniform density distribution of points across the adversarial object surfaces. Our four proposed algorithms for attacking 3D point cloud classification are all highly successful on existing neural networks, and we find that some of them are even effective against previously proposed point removal defenses.

show abstract

PPF-FoldNet: Unsupervised Learning of Rotation Invariant 3D Local Descriptors

Cited by 13 publications

References 32 publications

USIP: Unsupervised Stable Interest Point Detection From 3D Point Clouds

USIP: Unsupervised Stable Interest Point Detection From 3D Point Clouds

PCAN: 3D Attention Map Learning Using Contextual Information for Point Cloud Based Retrieval

Adversarial shape perturbations on 3D point clouds

Contact Info

Product

Resources

About