Domain adaptation on point clouds via geometry-aware implicits

Y Shen, Y Yang, M Yan, H Wang… - Proceedings of the …, 2022‏ - openaccess.thecvf.com
As a popular geometric representation, point clouds have attracted much attention in 3D
vision, leading to many applications in autonomous driving and robotics. One important yet …

Point cloud pre-training with natural 3d structures

R Yamada, H Kataoka, N Chiba… - Proceedings of the …, 2022‏ - openaccess.thecvf.com
The construction of 3D point cloud datasets requires a great deal of human effort. Therefore,
constructing a largescale 3D point clouds dataset is difficult. In order to remedy this issue …

[HTML][HTML] An in-depth analysis of domain adaptation in computer and robotic vision

MH Tanveer, Z Fatima, S Zardari, D Guerra-Zubiaga - Applied Sciences, 2023‏ - mdpi.com
This review article comprehensively delves into the rapidly evolving field of domain
adaptation in computer and robotic vision. It offers a detailed technical analysis of the …

Scoda: Domain adaptive shape completion for real scans

Y Wu, Z Yan, C Chen, L Wei, X Li, G Li… - Proceedings of the …, 2023‏ - openaccess.thecvf.com
Abstract 3D shape completion from point clouds is a challenging task, especially from scans
of real-world objects. Considering the paucity of 3D shape ground truths for real scans …

Domain adaptive sampling for cross-domain point cloud recognition

Z Wang, W Li, D Xu - … Transactions on Circuits and Systems for …, 2023‏ - ieeexplore.ieee.org
Point cloud recognition has recently gained increasing research interest due to the huge
potential in real-world applications such as autonomous driving, robotics, etc. However, the …

Category-level adversaries for outdoor LiDAR point clouds cross-domain semantic segmentation

Z Yuan, C Wen, M Cheng, Y Su, W Liu… - IEEE Transactions …, 2022‏ - ieeexplore.ieee.org
Unsupervised domain adaptation (UDA) is a low-cost way to deal with the lack of
annotations in a new domain. For outdoor point clouds in urban transportation scenes, the …

Saluda: Surface-based automotive lidar unsupervised domain adaptation

B Michele, A Boulch, G Puy, TH Vu… - … Conference on 3D …, 2024‏ - ieeexplore.ieee.org
Learning models on one labeled dataset that generalize well on another domain is a difficult
task, as several shifts might happen between the data domains. This is notably the case for …

GPDAN: Grasp pose domain adaptation network for sim-to-real 6-DoF object gras**

L Zheng, W Ma, Y Cai, T Lu… - IEEE Robotics and …, 2023‏ - ieeexplore.ieee.org
In this letter, we propose a novel Grasp Pose Domain Adaptation Network (GPDAN) to
achieve sim-to-real domain adaptation for 6-DoF grasp pose detection. The main task of …

Prototype-guided multitask adversarial network for cross-domain LiDAR point clouds semantic segmentation

Z Yuan, M Cheng, W Zeng, Y Su, W Liu… - … on Geoscience and …, 2023‏ - ieeexplore.ieee.org
Unsupervised domain adaptation (UDA) segmentation aims to leverage labeled source data
to make accurate predictions on unlabeled target data. The key is to make the segmentation …

Sug: Single-dataset unified generalization for 3d point cloud classification

S Huang, B Zhang, B Shi, H Li, Y Li, P Gao - Proceedings of the 31st …, 2023‏ - dl.acm.org
Although Domain Generalization (DG) problem has been fast-growing in the 2D image
tasks, its exploration on 3D point cloud data is still insufficient and challenged by more …