Comprehensive review of deep learning-based 3d point cloud completion processing and analysis

B Fei, W Yang, WM Chen, Z Li, Y Li… - IEEE Transactions …, 2022 - ieeexplore.ieee.org
Point cloud completion is a generation and estimation issue derived from the partial point
clouds, which plays a vital role in the applications of 3D computer vision. The progress of …

Hyperbolic chamfer distance for point cloud completion

F Lin, Y Yue, S Hou, X Yu, Y Xu… - Proceedings of the …, 2023 - openaccess.thecvf.com
Chamfer distance (CD) is a standard metric to measure the shape dissimilarity between
point clouds in point cloud completion, as well as a loss function for (deep) learning …

Proxyformer: Proxy alignment assisted point cloud completion with missing part sensitive transformer

S Li, P Gao, X Tan, M Wei - … of the IEEE/CVF conference on …, 2023 - openaccess.thecvf.com
Problems such as equipment defects or limited viewpoints will lead the captured point
clouds to be incomplete. Therefore, recovering the complete point clouds from the partial …

High fidelity 3d hand shape reconstruction via scalable graph frequency decomposition

T Luan, Y Zhai, J Meng, Z Li, Z Chen… - Proceedings of the …, 2023 - openaccess.thecvf.com
Despite the impressive performance obtained by recent single-image hand modeling
techniques, they lack the capability to capture sufficient details of the 3D hand mesh. This …

InfoCD: a contrastive chamfer distance loss for point cloud completion

F Lin, Y Yue, Z Zhang, S Hou… - Advances in …, 2023 - proceedings.neurips.cc
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 …

Neusdfusion: A spatial-aware generative model for 3d shape completion, reconstruction, and generation

R Cui, W Liu, W Sun, S Wang, T Shang, Y Li… - … on Computer Vision, 2024 - Springer
Abstract 3D shape generation aims to produce innovative 3D content adhering to specific
conditions and constraints. Existing methods often decompose 3D shapes into a sequence …

Weakly supervised class-agnostic motion prediction for autonomous driving

R Li, H Shi, Z Fu, Z Wang, G Lin - Proceedings of the IEEE …, 2023 - openaccess.thecvf.com
Understanding the motion behavior of dynamic environments is vital for autonomous driving,
leading to increasing attention in class-agnostic motion prediction in LiDAR point clouds …

Democratising 2d sketch to 3d shape retrieval through pivoting

PN Chowdhury, AK Bhunia, A Sain… - Proceedings of the …, 2023 - openaccess.thecvf.com
This paper studies the problem of 2D sketch to 3D shape retrieval, but with a focus on
democratising the process. We would like this democratisation to happen on two fronts:(i) to …

Learning geometric transformation for point cloud completion

S Zhang, X Liu, H **e, L Nie, H Zhou, D Tao… - International Journal of …, 2023 - Springer
Point cloud completion aims to estimate the missing shape from a partial point cloud.
Existing encoder-decoder based generative models usually reconstruct the complete point …

Neuralvdb: High-resolution sparse volume representation using hierarchical neural networks

D Kim, M Lee, K Museth - ACM Transactions on Graphics, 2024 - dl.acm.org
We introduce NeuralVDB, which improves on an existing industry standard for efficient
storage of sparse volumetric data, denoted VDB [Museth], by leveraging recent …