Zobrazeno 1 - 10
of 732
pro vyhledávání: '"Yu, Jianhui"'
Current models for point cloud recognition demonstrate promising performance on synthetic datasets. However, real-world point cloud data inevitably contains noise, impacting model robustness. While recent efforts focus on enhancing robustness through
Externí odkaz:
http://arxiv.org/abs/2407.10806
Autor:
Lin, Haoyang, Zhu, Wenguo, Zhong, Yongchun, Tang, Jieyuan, Lu, Huihui, Yu, Jianhui, Zheng, Huadan
In this paper, the photoacoustic spectroscopy technique based on lithium niobate crystals is initially reported, to our knowledge. A novel dual-cantilever tuning fork structure and new electrodes have been designed using Y-cut 128{\deg} blackened lit
Externí odkaz:
http://arxiv.org/abs/2312.11491
Recent advances in zero-shot text-to-3D human generation, which employ the human model prior (eg, SMPL) or Score Distillation Sampling (SDS) with pre-trained text-to-image diffusion models, have been groundbreaking. However, SDS may provide inaccurat
Externí odkaz:
http://arxiv.org/abs/2310.09458
High-resolution remote sensing (HRS) semantic segmentation extracts key objects from high-resolution coverage areas. However, objects of the same category within HRS images generally show significant differences in scale and shape across diverse geog
Externí odkaz:
http://arxiv.org/abs/2305.12691
Text-driven generation models are flourishing in video generation and editing. However, face-centric text-to-video generation remains a challenge due to the lack of a suitable dataset containing high-quality videos and highly relevant texts. This pap
Externí odkaz:
http://arxiv.org/abs/2303.14717
Recent interest in point cloud analysis has led rapid progress in designing deep learning methods for 3D models. However, state-of-the-art models are not robust to rotations, which remains an unknown prior to real applications and harms the model per
Externí odkaz:
http://arxiv.org/abs/2302.02535
Recent investigations on rotation invariance for 3D point clouds have been devoted to devising rotation-invariant feature descriptors or learning canonical spaces where objects are semantically aligned. Examinations of learning frameworks for invaria
Externí odkaz:
http://arxiv.org/abs/2301.00149
Dense captioning in 3D point clouds is an emerging vision-and-language task involving object-level 3D scene understanding. Apart from coarse semantic class prediction and bounding box regression as in traditional 3D object detection, 3D dense caption
Externí odkaz:
http://arxiv.org/abs/2204.10688
Autor:
Zhang, Yu, Zhang, Wang, Lv, Zhan, Zhang, Yusen, Wu, Chunling, Lin, Ziqi, Li, Zhibin, Tang, Jieyuan, Zhu, Wenguo, Zheng, Huadan, Zhong, Yongchun, Fang, Junbin, Yu, Jianhui
Publikováno v:
In Optics and Laser Technology September 2024 176
Publikováno v:
In Journal of Cleaner Production 10 August 2024 466