Results 11 to 20 of about 7,734,831 (297)
Deep Auxiliary Learning for Point Cloud Generation [PDF]
IEEE Access, 2020 Generation point cloud from single image is a classical problem in computer vision. The learning methods for this task often adopt local distance metrics as loss function, which means the generated points are not easy to meet the overall shape ...
Fei Hu +4 more
doaj +3 more sources
DiffusionPointLabel: Annotated Point Cloud Generation with Diffusion Model [PDF]
, 2022 Point cloud generation aims to synthesize point clouds that do not exist in supervised dataset. Generating a point cloud with certain semantic labels remains an under-explored problem.
Fu, Yunfei +5 more
core +3 more sources
HyperPocket: Generative Point Cloud Completion
2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2022 Scanning real-life scenes with modern registration devices typically give incomplete point cloud representations, mostly due to the limitations of the scanning process and 3D occlusions. Therefore, completing such partial representations remains a fundamental challenge of many computer vision applications.
Przemyslaw Spurek +7 more
openaire +3 more sources
Generative Models for 3D Point Clouds
CoRR, 2023 Point clouds are rich geometric data structures, where their three dimensional structure offers an excellent domain for understanding the representation learning and generative modeling in 3D space. In this work, we aim to improve the performance of point cloud latent-space generative models by experimenting with transformer encoders, latent-space flow
Lingjie Kong +2 more
openaire +2 more sources
Point Cloud Adversarial Perturbation Generation for Adversarial Attacks
IEEE Access, 2023 In recent years, 3D model analysis has made a revolutionary development. Point cloud contains rich 3D object geometry information, which is an important 3D object data format widely used in many applications. However, the irregularity and disorder of the
Fengmei He +3 more
doaj +1 more source
Point Cloud Generation with Continuous Conditioning
CoRR, 2022 Generative models can be used to synthesize 3D objects of high quality and diversity. However, there is typically no control over the properties of the generated object.This paper proposes a novel generative adversarial network (GAN) setup that generates 3D point cloud shapes conditioned on a continuous parameter.
Larissa T. Triess +4 more
openaire +3 more sources
3D Point Cloud Generation Based on Multi-Sensor Fusion
Applied Sciences, 2022 Traditional precise engineering surveys adopt manual static, discrete observation, which cannot meet the dynamic, continuous, high-precision and holographic fine measurements required for large-scale infrastructure construction, operation and maintenance,
Yulong Han +5 more
doaj +1 more source
, 2023 <p>This is a repository that contains LiDAR point cloud images for the "Person" category, along with a JSON file that relates the labels for this category, as well as the resulting segmentation mask images for each of the images. Finally,
Jhon Aparicio Mesa
core +3 more sources
EPiC-GAN: Equivariant point cloud generation for particle jets
SciPost Physics, 2023 With the vast data-collecting capabilities of current and future high-energy collider experiments, there is an increasing demand for computationally efficient simulations.
Erik Buhmann, Gregor Kasieczka, Jesse Thaler
doaj +1 more source
Generating 3D Adversarial Point Clouds [PDF]
2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2019 Deep neural networks are known to be vulnerable to adversarial examples which are carefully crafted instances to cause the models to make wrong predictions. While adversarial examples for 2D images and CNNs have been extensively studied, less attention has been paid to 3D data such as point clouds.
Chong Xiang 0001 +2 more
openaire +3 more sources