Zobrazeno 1 - 10
of 55
pro vyhledávání: '"Cao, Haozhi"'
Non-rigid point cloud registration is a critical challenge in 3D scene understanding, particularly in surgical navigation. Although existing methods achieve excellent performance when trained on large-scale, high-quality datasets, these datasets are
Externí odkaz:
http://arxiv.org/abs/2410.22909
Dataset Distillation (DD) seeks to create a condensed dataset that, when used to train a model, enables the model to achieve performance similar to that of a model trained on the entire original dataset. It relieves the model training from processing
Externí odkaz:
http://arxiv.org/abs/2410.13311
LiDAR bundle adjustment (BA) is an effective approach to reduce the drifts in pose estimation from the front-end. Existing works on LiDAR BA usually rely on predefined geometric features for landmark representation. This reliance restricts generaliza
Externí odkaz:
http://arxiv.org/abs/2410.01618
Point cloud registration aims to provide estimated transformations to align point clouds, which plays a crucial role in pose estimation of various navigation systems, such as surgical guidance systems and autonomous vehicles. Despite the impressive p
Externí odkaz:
http://arxiv.org/abs/2410.00589
Autor:
Qi, Zhenghao, Yuan, Shenghai, Liu, Fen, Cao, Haozhi, Deng, Tianchen, Yang, Jianfei, Xie, Lihua
Recent advancements in 3D reconstruction and neural rendering have enhanced the creation of high-quality digital assets, yet existing methods struggle to generalize across varying object shapes, textures, and occlusions. While Next Best View (NBV) pl
Externí odkaz:
http://arxiv.org/abs/2409.16019
Autor:
Nguyen, Thien-Minh, Yuan, Shenghai, Nguyen, Thien Hoang, Yin, Pengyu, Cao, Haozhi, Xie, Lihua, Wozniak, Maciej, Jensfelt, Patric, Thiel, Marko, Ziegenbein, Justin, Blunder, Noel
Perception plays a crucial role in various robot applications. However, existing well-annotated datasets are biased towards autonomous driving scenarios, while unlabelled SLAM datasets are quickly over-fitted, and often lack environment and domain va
Externí odkaz:
http://arxiv.org/abs/2403.11496
Multi-modal test-time adaptation (MM-TTA) is proposed to adapt models to an unlabeled target domain by leveraging the complementary multi-modal inputs in an online manner. Previous MM-TTA methods for 3D segmentation rely on predictions of cross-modal
Externí odkaz:
http://arxiv.org/abs/2403.06461
Multi-modal unsupervised domain adaptation (MM-UDA) for 3D semantic segmentation is a practical solution to embed semantic understanding in autonomous systems without expensive point-wise annotations. While previous MM-UDA methods can achieve overall
Externí odkaz:
http://arxiv.org/abs/2309.11839
Autor:
Yin, Pengyu, Cao, Haozhi, Nguyen, Thien-Minh, Yuan, Shenghai, Zhang, Shuyang, Liu, Kangcheng, Xie, Lihua
One-shot LiDAR localization refers to the ability to estimate the robot pose from one single point cloud, which yields significant advantages in initialization and relocalization processes. In the point cloud domain, the topic has been extensively st
Externí odkaz:
http://arxiv.org/abs/2309.08914
Continual Test-Time Adaptation (CTTA) generalizes conventional Test-Time Adaptation (TTA) by assuming that the target domain is dynamic over time rather than stationary. In this paper, we explore Multi-Modal Continual Test-Time Adaptation (MM-CTTA) a
Externí odkaz:
http://arxiv.org/abs/2303.10457