Advancements in point cloud data augmentation for deep learning: A survey
Deep learning (DL) has become one of the mainstream and effective methods for point
cloud analysis tasks such as detection, segmentation and classification. To reduce …
cloud analysis tasks such as detection, segmentation and classification. To reduce …
Hyperbolic deep learning in computer vision: A survey
Deep representation learning is a ubiquitous part of modern computer vision. While
Euclidean space has been the de facto standard manifold for learning visual …
Euclidean space has been the de facto standard manifold for learning visual …
InfoCD: a contrastive chamfer distance loss for point cloud completion
A point cloud is a discrete set of data points sampled from a 3D geometric surface. Chamfer
distance (CD) is a popular metric and training loss to measure the distances between point …
distance (CD) is a popular metric and training loss to measure the distances between point …
HyperSDFusion: Bridging Hierarchical Structures in Language and Geometry for Enhanced 3D Text2Shape Generation
Abstract 3D shape generation from text is a fundamental task in 3D representation learning.
The text-shape pairs exhibit a hierarchical structure where a general text like" chair" covers …
The text-shape pairs exhibit a hierarchical structure where a general text like" chair" covers …
ANF: Crafting Transferable Adversarial Point Clouds via Adversarial Noise Factorization
Transfer-based adversarial attacks involve generating adversarial point clouds in surrogate
models and transferring them to other models to assess 3D model robustness. However …
models and transferring them to other models to assess 3D model robustness. However …
Point Cloud Completion via Self-projected View Augmentation and Implicit Field Constraint
Recent advances in point cloud completion make it possible to simultaneously recover
complete shapes and fine details from partial point clouds captured by professional 3D …
complete shapes and fine details from partial point clouds captured by professional 3D …
Accounting for Hysteresis in the Forward Kinematics of Nonlinearly-Routed Tendon-Driven Continuum Robots via a Learned Deep Decoder Network
Tendon-driven continuum robots have been gaining popularity in medical applications due
to their ability to curve around complex anatomical structures, potentially reducing the …
to their ability to curve around complex anatomical structures, potentially reducing the …
PIXGAN-Drone: 3D Avatar of Human Body Reconstruction from Multi-View 2D Images
Study is being conducted on training Generative Adversarial Networks (GANs) from 2D
datasets to generate 3D human body avatars. Numerous applications, such as virtual reality …
datasets to generate 3D human body avatars. Numerous applications, such as virtual reality …
Terrain point cloud inpainting via signal decomposition
Y Xie, X Xie, Y Wang, Y Zhang, Z Lv - Computers & Graphics, 2024 - Elsevier
The rapid development of 3D acquisition technology has made it possible to obtain point
clouds of real-world terrains. However, due to limitations in sensor acquisition technology or …
clouds of real-world terrains. However, due to limitations in sensor acquisition technology or …
GeoFormer: Learning Point Cloud Completion with Tri-Plane Integrated Transformer
Point cloud completion aims to recover accurate global geometry and preserve fine-grained
local details from partial point clouds. Conventional methods typically predict unseen points …
local details from partial point clouds. Conventional methods typically predict unseen points …