Filters








81 Hits in 5.3 sec

Latent-Space Laplacian Pyramids for Adversarial Representation Learning with 3D Point Clouds [article]

Vage Egiazarian, Savva Ignatyev, Alexey Artemov, Oleg Voynov, Andrey Kravchenko, Youyi Zheng, Luiz Velho, Evgeny Burnaev
2019 arXiv   pre-print
In this work, we propose to employ the latent-space Laplacian pyramid representation within a hierarchical generative model for 3D point clouds.  ...  We combine the recently proposed latent-space GAN and Laplacian GAN architectures to form a multi-scale model capable of generating 3D point clouds at increasing levels of detail.  ...  Latent-Space Laplacian Pyramids for Adversarial Representation Learning with 3D  ... 
arXiv:1912.06466v1 fatcat:mqgtoxcfsradxmn723t52johti

Comprehensive Review of Deep Learning-Based 3D Point Cloud Completion Processing and Analysis [article]

Ben Fei, Weidong Yang, Wenming Chen, Zhijun Li, Yikang Li, Tao Ma, Xing Hu, Lipeng Ma
2022 arXiv   pre-print
Point cloud completion is a generation and estimation issue derived from the partial point clouds, which plays a vital role in the applications in 3D computer vision.  ...  The progress of deep learning (DL) has impressively improved the capability and robustness of point cloud completion.  ...  The effective latent space representations of the point cloud provide important and fundamental information that can be utilized for 3D shape reconstruction. Wen et al.  ... 
arXiv:2203.03311v2 fatcat:e2kvryolufearetp4ujlw2gwwy

Adversarial Self-Supervised Scene Flow Estimation

Victor Zuanazzi, Joris van Vugt, Olaf Booij, Pascal Mettes
2020 2020 International Conference on 3D Vision (3DV)  
This work proposes a metric learning approach for selfsupervised scene flow estimation. Scene flow estimation is the task of estimating 3D flow vectors for consecutive 3D point clouds.  ...  To that end, we seek for a self-supervised approach, where a network learns a latent metric to distinguish between points translated by flow estimations and the target point cloud.  ...  Building upon the power of deep learning to learn implicit representations, various architectures have been proposed that learn an abstract representation of a 3D point cloud, which can then be used for  ... 
doi:10.1109/3dv50981.2020.00115 fatcat:h7kgp2s6jvgx5j7lsk2qdjptaq

Adversarial Self-Supervised Scene Flow Estimation [article]

Victor Zuanazzi, Joris van Vugt, Olaf Booij, Pascal Mettes
2020 arXiv   pre-print
This work proposes a metric learning approach for self-supervised scene flow estimation. Scene flow estimation is the task of estimating 3D flow vectors for consecutive 3D point clouds.  ...  To that end, we seek for a self-supervised approach, where a network learns a latent metric to distinguish between points translated by flow estimations and the target point cloud.  ...  Building upon the power of deep learning to learn implicit representations, various architectures have been proposed that learn an abstract representation of a 3D point cloud, which can then be used for  ... 
arXiv:2011.00551v1 fatcat:ouisgpxghvgotoiehixt3j74tu

Spectral-GANs for High-Resolution 3D Point-cloud Generation [article]

Sameera Ramasinghe, Salman Khan, Nick Barnes, Stephen Gould
2020 arXiv   pre-print
Current deep generative models for 3D data generally work on simplified representations (e.g., voxelized objects) and cannot deal with the inherent redundancy and irregularity in point-clouds.  ...  In this paper, we develop a principled approach to synthesize 3D point-clouds using a spectral-domain Generative Adversarial Network (GAN).  ...  [1] use a GAN framework for 3D point-cloud distribution modelling in the data and auto-encoder latent space, Yang et al.  ... 
arXiv:1912.01800v2 fatcat:hu6u7jhq3fgxvattdooez6gbyq

Dense 3D Point Cloud Reconstruction Using a Deep Pyramid Network [article]

Priyanka Mandikal, R. Venkatesh Babu
2019 arXiv   pre-print
In this work, we introduce DensePCR, a deep pyramidal network for point cloud reconstruction that hierarchically predicts point clouds of increasing resolution.  ...  Although this technique can handle low-resolution point clouds, it is not a viable solution for generating dense, high-resolution outputs.  ...  [4] proposed a generative adversarial network to generate realistic images based on a Laplacian pyramid framework (LAPGAN). Lai et al.  ... 
arXiv:1901.08906v1 fatcat:cb3og2jk3rgmtngtjo5cfxu7uu

2021 Index IEEE Transactions on Image Processing Vol. 30

2021 IEEE Transactions on Image Processing  
The Author Index contains the primary entry for each item, listed under the first author's name.  ...  ., +, TIP 2021 921-933 Data structures HSGAN: Hierarchical Graph Learning for Point Cloud Generation. Li, Y., +, TIP 2021 4540-4554 Hypergraph Spectral Analysis and Processing in 3D Point Cloud.  ...  ., +, TIP 2021 418-430 Optical radar Hierarchical Attention Learning of Scene Flow in 3D Point Clouds.  ... 
doi:10.1109/tip.2022.3142569 fatcat:z26yhwuecbgrnb2czhwjlf73qu

2021 Index IEEE Transactions on Multimedia Vol. 23

2021 IEEE transactions on multimedia  
The Author Index contains the primary entry for each item, listed under the first author's name.  ...  Ouyang, Learning Localized Representations of Point Clouds With Graph-Convolutional Generative Adversarial Networks.  ...  Li, G., +, TMM 2021 3035-3047 Learning Localized Representations of Point Clouds With Graph-Convolu-tional Generative Adversarial Networks.  ... 
doi:10.1109/tmm.2022.3141947 fatcat:lil2nf3vd5ehbfgtslulu7y3lq

2020 Index IEEE Transactions on Image Processing Vol. 29

2020 IEEE Transactions on Image Processing  
., +, TIP 2020 2258-2270 Image coding 3D Point Cloud Attribute Compression Using Geometry-Guided Sparse Representation.  ...  ., +, TIP 2020 8055-8068 Graph theory 3D Point Cloud Denoising Using Graph Laplacian Regularization of a Low Dimensional Manifold Model.  ... 
doi:10.1109/tip.2020.3046056 fatcat:24m6k2elprf2nfmucbjzhvzk3m

A Review on Deep Learning Techniques for Video Prediction [article]

Sergiu Oprea, Pablo Martinez-Gonzalez, Alberto Garcia-Garcia, John Alejandro Castro-Vargas, Sergio Orts-Escolano, Jose Garcia-Rodriguez, Antonis Argyros
2020 arXiv   pre-print
Defined as a self-supervised learning task, video prediction represents a suitable framework for representation learning, as it demonstrated potential capabilities for extracting meaningful representations  ...  Motivated by the increasing interest in this task, we provide a review on the deep learning methods for prediction in video sequences.  ...  The future 3d segmented point clouds are obtained by transforming the previous point clouds with the predicted ego-motion.  ... 
arXiv:2004.05214v2 fatcat:weerbkanmjb4dn6wkn5o4b5aia

3D Dense Face Alignment with Fused Features by Aggregating CNNs and GCNs [article]

Yanda Meng, Xu Chen, Dongxu Gao, Yitian Zhao, Xiaoyun Yang, Yihong Qiao, Xiaowei Huang, Yalin Zheng
2022 arXiv   pre-print
for the benefit of direct feature learning of 3D face mesh.  ...  This is achieved by seamlessly combining standard convolutional neural networks (CNNs) with Graph Convolution Networks (GCNs).  ...  We calculate the bounding box from the ground truth point cloud and crop the rendered image to 256×256, and we follow [7] to choose 19K points of face region for evaluation.  ... 
arXiv:2203.04643v1 fatcat:toyy4fcrrrg73batvoparlad7u

Deep Learning for LiDAR Point Clouds in Autonomous Driving: A Review [article]

Ying Li, Lingfei Ma, Zilong Zhong, Fei Liu, Dongpu Cao, Jonathan Li, Michael A. Chapman
2020 arXiv   pre-print
Although several published research papers focus on specific topics in computer vision for autonomous vehicles, to date, no general survey on deep learning applied in LiDAR point clouds for autonomous  ...  However, automated processing uneven, unstructured, noisy, and massive 3D point clouds is a challenging and tedious task.  ...  Besides, we also would like to thank anonymous reviewers for their insightful comments and suggestions.  ... 
arXiv:2005.09830v1 fatcat:zrja5sgtsvgulpnp7p7t4kxq54

Towards Monocular Neural Facial Depth Estimation: Past, Present, and Future

Faisal Khan, Muhammad Ali Farooq, Waseem Shariff, Shubhajit Basak, Peter Corcoran
2022 IEEE Access  
In addition, an SoA neural model for facial depth estimation is proposed, along with a detailed comparison evaluation and, where feasible, direct comparison of facial depth estimation methods to serve  ...  The new loss function used in the proposed method helps the network to learn the facial regions resulting in an accurate depth prediction.  ...  Using point-wise addition, this depth residual is gradually integrated with the middle depth map, which is the result of the higher level of the Laplacian pyramid.  ... 
doi:10.1109/access.2022.3158950 fatcat:q3ocwmmvpzhmbm4jamqackj4em

Table of contents

2020 IEEE Transactions on Image Processing  
Hwang 4130 Point Cloud Denoising via Feature Graph Laplacian Regularization ........... C. Dinesh, G. Cheung, and I. V.  ...  Qiu 3458 3D Point Cloud Denoising Using Graph Laplacian Regularization of a Low Dimensional Manifold Model ........... ........................................................................... J.  ... 
doi:10.1109/tip.2019.2940372 fatcat:h23ul2rqazbstcho46uv3lunku

Shape Completion Using 3D-Encoder-Predictor CNNs and Shape Synthesis

Angela Dai, Charles Ruizhongtai Qi, Matthias NieBner
2017 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)  
The network is trained to predict and fill in missing data, and operates on an implicit surface representation that encodes both known and unknown space.  ...  We then correlate these intermediary results with 3D geometry from a shape database at test time.  ...  We also show intermediate results where we only use the 3D-EPN w/o 3D shape synthesis. Input is visualized at 32 3 ; however, for Kazhdan et al. [14] and Rock et al. [32] , we use the 128 3 input.  ... 
doi:10.1109/cvpr.2017.693 dblp:conf/cvpr/DaiQN17 fatcat:th4cmo4jlnh4fpe4ilcbdm6hsq
« Previous Showing results 1 — 15 out of 81 results