Zobrazeno 1 - 10
of 35
pro vyhledávání: '"Jiang, Chenhan"'
Score Distillation Sampling (SDS) by well-trained 2D diffusion models has shown great promise in text-to-3D generation. However, this paradigm distills view-agnostic 2D image distributions into the rendering distribution of 3D representation for each
Externí odkaz:
http://arxiv.org/abs/2407.12291
Autor:
Jiang, Chenhan
3D content creation plays a vital role in various applications, such as gaming, robotics simulation, and virtual reality. However, the process is labor-intensive and time-consuming, requiring skilled designers to invest considerable effort in creatin
Externí odkaz:
http://arxiv.org/abs/2405.09431
Autor:
Zeng, Yihan, Jiang, Chenhan, Mao, Jiageng, Han, Jianhua, Ye, Chaoqiang, Huang, Qingqiu, Yeung, Dit-Yan, Yang, Zhen, Liang, Xiaodan, Xu, Hang
Contrastive Language-Image Pre-training, benefiting from large-scale unlabeled text-image pairs, has demonstrated great performance in open-world vision understanding tasks. However, due to the limited Text-3D data pairs, adapting the success of 2D V
Externí odkaz:
http://arxiv.org/abs/2303.12417
Autor:
Chen, Runjian, Mu, Yao, Xu, Runsen, Shao, Wenqi, Jiang, Chenhan, Xu, Hang, Li, Zhenguo, Luo, Ping
Unsupervised contrastive learning for indoor-scene point clouds has achieved great successes. However, unsupervised learning point clouds in outdoor scenes remains challenging because previous methods need to reconstruct the whole scene and capture p
Externí odkaz:
http://arxiv.org/abs/2206.04028
Publikováno v:
In Measurement January 2025 242 Part A
Autor:
Mao, Jiageng, Niu, Minzhe, Jiang, Chenhan, Liang, Hanxue, Chen, Jingheng, Liang, Xiaodan, Li, Yamin, Ye, Chaoqiang, Zhang, Wei, Li, Zhenguo, Yu, Jie, Xu, Hang, Xu, Chunjing
Current perception models in autonomous driving have become notorious for greatly relying on a mass of annotated data to cover unseen cases and address the long-tail problem. On the other hand, learning from unlabeled large-scale collected data and i
Externí odkaz:
http://arxiv.org/abs/2106.11037
Unsupervised pre-training aims at learning transferable features that are beneficial for downstream tasks. However, most state-of-the-art unsupervised methods concentrate on learning global representations for image-level classification tasks instead
Externí odkaz:
http://arxiv.org/abs/2103.04814
Autor:
Wang, Bochao, Xu, Hang, Zhang, Jiajin, Chen, Chen, Fang, Xiaozhi, Xu, Yixing, Kang, Ning, Hong, Lanqing, Jiang, Chenhan, Cai, Xinyue, Li, Jiawei, Zhou, Fengwei, Li, Yong, Liu, Zhicheng, Chen, Xinghao, Han, Kai, Shu, Han, Song, Dehua, Wang, Yunhe, Zhang, Wei, Xu, Chunjing, Li, Zhenguo, Liu, Wenzhi, Zhang, Tong
Automated Machine Learning (AutoML) is an important industrial solution for automatic discovery and deployment of the machine learning models. However, designing an integrated AutoML system faces four great challenges of configurability, scalability,
Externí odkaz:
http://arxiv.org/abs/2011.01507
Most advances in medical lesion detection network are limited to subtle modification on the conventional detection network designed for natural images. However, there exists a vast domain gap between medical images and natural images where the medica
Externí odkaz:
http://arxiv.org/abs/2003.08770
Detecting dense landmarks for diverse clothes, as a fundamental technique for clothes analysis, has attracted increasing research attention due to its huge application potential. However, due to the lack of modeling underlying semantic layout constra
Externí odkaz:
http://arxiv.org/abs/1910.01923