Surface reconstruction from point clouds: A survey and a benchmark

Z Huang, Y Wen, Z Wang, J Ren… - IEEE transactions on …, 2024 - ieeexplore.ieee.org
Reconstruction of a continuous surface of two-dimensional manifold from its raw, discrete
point cloud observation is a long-standing problem in computer vision and graphics …

A Survey of Non‐Rigid 3D Registration

B Deng, Y Yao, RM Dyke, J Zhang - Computer Graphics Forum, 2022 - Wiley Online Library
Non‐rigid registration computes an alignment between a source surface with a target
surface in a non‐rigid manner. In the past decade, with the advances in 3D sensing …

Local implicit grid representations for 3d scenes

C Jiang, A Sud, A Makadia, J Huang… - Proceedings of the …, 2020 - openaccess.thecvf.com
Shape priors learned from data are commonly used to reconstruct 3D objects from partial or
noisy data. Yet no such shape priors are available for indoor scenes, since typical 3D …

Pcn: Point completion network

W Yuan, T Khot, D Held, C Mertz… - … conference on 3D vision …, 2018 - ieeexplore.ieee.org
Shape completion, the problem of estimating the complete geometry of objects from partial
observations, lies at the core of many vision and robotics applications. In this work, we …

Morphing and sampling network for dense point cloud completion

M Liu, L Sheng, S Yang, J Shao, SM Hu - Proceedings of the AAAI …, 2020 - ojs.aaai.org
Abstract 3D point cloud completion, the task of inferring the complete geometric shape from
a partial point cloud, has been attracting attention in the community. For acquiring high …

Shape completion using 3d-encoder-predictor cnns and shape synthesis

A Dai, C Ruizhongtai Qi… - Proceedings of the IEEE …, 2017 - openaccess.thecvf.com
We introduce a data-driven approach to complete partial 3D shapes through a combination
of volumetric deep neural networks and 3D shape synthesis. From a partially-scanned input …

Neural scene flow prior

X Li, J Kaesemodel Pontes… - Advances in Neural …, 2021 - proceedings.neurips.cc
Before the deep learning revolution, many perception algorithms were based on runtime
optimization in conjunction with a strong prior/regularization penalty. A prime example of this …

A survey of surface reconstruction from point clouds

M Berger, A Tagliasacchi, LM Seversky… - Computer graphics …, 2017 - Wiley Online Library
The area of surface reconstruction has seen substantial progress in the past two decades.
The traditional problem addressed by surface reconstruction is to recover the digital …

Scancomplete: Large-scale scene completion and semantic segmentation for 3d scans

A Dai, D Ritchie, M Bokeloh, S Reed… - Proceedings of the …, 2018 - openaccess.thecvf.com
We introduce ScanComplete, a novel data-driven approach for taking an incomplete 3D
scan of a scene as input and predicting a complete 3D model along with per-voxel semantic …

High-resolution shape completion using deep neural networks for global structure and local geometry inference

X Han, Z Li, H Huang… - Proceedings of the …, 2017 - openaccess.thecvf.com
We propose a data-driven method for recovering missing parts of 3D shapes. Our method is
based on a new deep learning architecture consisting of two sub-networks: a global …