Zobrazeno 1 - 10
of 18
pro vyhledávání: '"Nenglun Chen"'
Autor:
Congyi Zhang, Lei Yang, Nenglun Chen, Nicholas Vining, Alla Sheffer, Francis C.M. Lau, Guoping Wang, Wenping Wang
Publikováno v:
IEEE Transactions on Visualization and Computer Graphics. :1-18
Creating 3D shapes from 2D drawings is an important problem with applications in content creation for computer animation and virtual reality. We introduce a new sketch-based system, CreatureShop, that enables amateurs to create high-quality textured
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::20b4aa36db4869ebf414550b22f38992
https://doi.org/10.1109/tvcg.2022.3197560
https://doi.org/10.1109/tvcg.2022.3197560
Publikováno v:
Recent Advances in Computer Science and Communications. 14:2489-2494
Introduction:: Computing salient feature points (SFP) of 3D models has important application value in the field of computer graphics. In order to extract more effectively, a novel SFP computing algorithm based on geodesic distance and decision graph
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::8ec23a2d24f79fad6af9a3fdfc6c3ab3
https://doi.org/10.2174/2666255813999200928215032
https://doi.org/10.2174/2666255813999200928215032
We propose a method for self-supervised image representation learning under the guidance of 3D geometric consistency. Our intuition is that 3D geometric consistency priors such as smooth regions and surface discontinuities may imply consistent semant
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::c3a8da0fbcb7c0d8940d32614412de8f
http://arxiv.org/abs/2203.15361
http://arxiv.org/abs/2203.15361
Detecting 3D landmarks on cone-beam computed tomography (CBCT) is crucial to assessing and quantifying the anatomical abnormalities in 3D cephalometric analysis. However, the current methods are time-consuming and suffer from large biases in landmark
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::1de7ecd9ccc62e955fec869d9f87879d
http://arxiv.org/abs/2107.09899
http://arxiv.org/abs/2107.09899
Autor:
Nenglun Chen, Runnan Chena, Zhixu Du, Dinggang Shen, Changjian Li, Lei Yang, Zhiming Cui, Wenping Wang, Guodong Wei
Publikováno v:
IEEE transactions on medical imaging. 40(12)
Performance degradation due to domain shift remains a major challenge in medical image analysis. Unsupervised domain adaptation that transfers knowledge learned from the source domain with ground truth labels to the target domain without any annotati
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::9cf3360486c687e42a11ee19cc8e6804
https://pubmed.ncbi.nlm.nih.gov/34161240
https://pubmed.ncbi.nlm.nih.gov/34161240
Publikováno v:
CVPR
We introduce Point2Skeleton, an unsupervised method to learn skeletal representations from point clouds. Existing skeletonization methods are limited to tubular shapes and the stringent requirement of watertight input, while our method aims to produc
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::2f33b57685c66cb8a5633fad0631a486
https://doi.org/10.1109/cvpr46437.2021.00426
https://doi.org/10.1109/cvpr46437.2021.00426
Well-annotated medical images are costly and sometimes even impossible to acquire, hindering landmark detection accuracy to some extent. Semi-supervised learning alleviates the reliance on large-scale annotated data by exploiting the unlabeled data t
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::7c13d6d60f7348fd2e0fa9f650b7360c
Autor:
Zhiwen Lin, Xingjia Pan, Runnan Chen, Ren Yuqiang, Feiyue Huang, Haolei Yuan, Lei Yang, Xiaowei Guo, Nenglun Chen, Wenping Wang
Publikováno v:
ACM Multimedia
We study the problem of weakly supervised grounded image captioning. That is, given an image, the goal is to automatically generate a sentence describing the context of the image with each noun word grounded to the corresponding region in the image.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::d2ec53bc176c91d676106a70368c9bad
Publikováno v:
ACM Multimedia
Facial skin texture synthesis is a fundamental problem in high-quality facial image generation and enhancement. The key behind is how to effectively synthesize plausible textured noise for the faces. With the development of CNNs and GANs, most works
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::f0362d00ceccc3bae6aeed2875c7f50c
https://doi.org/10.1145/3394171.3413637
https://doi.org/10.1145/3394171.3413637
Vid2Curve: Simultaneous Camera Motion Estimation and Thin Structure Reconstruction from an RGB Video
Publikováno v:
ACM Transactions on Graphics
Proceedings of ACM SIGGRAPH 2020
Proceedings of ACM SIGGRAPH 2020
Thin structures, such as wire-frame sculptures, fences, cables, power lines, and tree branches, are common in the real world. It is extremely challenging to acquire their 3D digital models using traditional image-based or depth-based reconstruction m
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::82d9f67018acf32741139a79473c9c11
http://arxiv.org/abs/2005.03372
http://arxiv.org/abs/2005.03372