Zobrazeno 1 - 10
of 36
pro vyhledávání: '"Ye, Yunfan"'
Autor:
Gu, Yuchao, Zhou, Yipin, Ye, Yunfan, Nie, Yixin, Yu, Licheng, Ma, Pingchuan, Lin, Kevin Qinghong, Shou, Mike Zheng
Natural language often struggles to accurately associate positional and attribute information with multiple instances, which limits current text-based visual generation models to simpler compositions featuring only a few dominant instances. To addres
Externí odkaz:
http://arxiv.org/abs/2411.17949
The unique artistic style is crucial to artists' occupational competitiveness, yet prevailing Art Commission Platforms rarely support style-based retrieval. Meanwhile, the fast-growing generative AI techniques aggravate artists' concerns about releas
Externí odkaz:
http://arxiv.org/abs/2404.16336
Reaching-and-grasping is a fundamental skill for robotic manipulation, but existing methods usually train models on a specific gripper and cannot be reused on another gripper. In this paper, we propose a novel method that can learn a unified policy m
Externí odkaz:
http://arxiv.org/abs/2404.09150
Limited by the encoder-decoder architecture, learning-based edge detectors usually have difficulty predicting edge maps that satisfy both correctness and crispness. With the recent success of the diffusion probabilistic model (DPM), we found it is es
Externí odkaz:
http://arxiv.org/abs/2401.02032
Learning-based edge detection usually suffers from predicting thick edges. Through extensive quantitative study with a new edge crispness measure, we find that noisy human-labeled edges are the main cause of thick predictions. Based on this observati
Externí odkaz:
http://arxiv.org/abs/2306.15172
Publikováno v:
Computational Visual Media 2024
Template matching is a fundamental task in computer vision and has been studied for decades. It plays an essential role in manufacturing industry for estimating the poses of different parts, facilitating downstream tasks such as robotic grasping. Exi
Externí odkaz:
http://arxiv.org/abs/2303.08438
We study the problem of reconstructing 3D feature curves of an object from a set of calibrated multi-view images. To do so, we learn a neural implicit field representing the density distribution of 3D edges which we refer to as Neural Edge Field (NEF
Externí odkaz:
http://arxiv.org/abs/2303.07653
Learning-based edge detection has hereunto been strongly supervised with pixel-wise annotations which are tedious to obtain manually. We study the problem of self-training edge detection, leveraging the untapped wealth of large-scale unlabeled image
Externí odkaz:
http://arxiv.org/abs/2201.05121
Publikováno v:
In Expert Systems With Applications 1 April 2025 267
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.