Zobrazeno 1 - 10
of 128
pro vyhledávání: '"Zhang, Zhanjie"'
Autor:
Zhang, Zhanjie, Sun, Jiakai, Li, Guangyuan, Zhao, Lei, Zhang, Quanwei, Lan, Zehua, Yin, Haolin, Xing, Wei, Lin, Huaizhong, Zuo, Zhiwen
Arbitrary style transfer holds widespread attention in research and boasts numerous practical applications. The existing methods, which either employ cross-attention to incorporate deep style attributes into content attributes or use adaptive normali
Externí odkaz:
http://arxiv.org/abs/2404.13584
Autor:
Zhang, Zhanjie, Zhang, Quanwei, Lin, Huaizhong, Xing, Wei, Mo, Juncheng, Huang, Shuaicheng, Xie, Jinheng, Li, Guangyuan, Luan, Junsheng, Zhao, Lei, Zhang, Dalong, Chen, Lixia
Artistic style transfer aims to transfer the learned artistic style onto an arbitrary content image, generating artistic stylized images. Existing generative adversarial network-based methods fail to generate highly realistic stylized images and alwa
Externí odkaz:
http://arxiv.org/abs/2404.11474
Recently, diffusion models (DM) have been applied in magnetic resonance imaging (MRI) super-resolution (SR) reconstruction, exhibiting impressive performance, especially with regard to detailed reconstruction. However, the current DM-based SR reconst
Externí odkaz:
http://arxiv.org/abs/2404.04785
Constructing photo-realistic Free-Viewpoint Videos (FVVs) of dynamic scenes from multi-view videos remains a challenging endeavor. Despite the remarkable advancements achieved by current neural rendering techniques, these methods generally require co
Externí odkaz:
http://arxiv.org/abs/2403.01444
Autor:
Zhang, Zhanjie, Zhang, Quanwei, Li, Guangyuan, Xing, Wei, Zhao, Lei, Sun, Jiakai, Lan, Zehua, Luan, Junsheng, Huang, Yiling, Lin, Huaizhong
Artistic style transfer aims to repaint the content image with the learned artistic style. Existing artistic style transfer methods can be divided into two categories: small model-based approaches and pre-trained large-scale model-based approaches. S
Externí odkaz:
http://arxiv.org/abs/2312.06135
Traditional inverse rendering techniques are based on textured meshes, which naturally adapts to modern graphics pipelines, but costly differentiable multi-bounce Monte Carlo (MC) ray tracing poses challenges for modeling global illumination. Recentl
Externí odkaz:
http://arxiv.org/abs/2305.16800
Autor:
Sun, Jiakai, Zhang, Zhanjie, Chen, Jiafu, Li, Guangyuan, Ji, Boyan, Zhao, Lei, Xing, Wei, Lin, Huaizhong
Neural Radiance Fields (NeRF) has shown great success in novel view synthesis due to its state-of-the-art quality and flexibility. However, NeRF requires dense input views (tens to hundreds) and a long training time (hours to days) for a single scene
Externí odkaz:
http://arxiv.org/abs/2304.13386
Autor:
Zuo, Zhiwen, Zhao, Lei, Li, Ailin, Wang, Zhizhong, Zhang, Zhanjie, Chen, Jiafu, Xing, Wei, Lu, Dongming
This paper presents a new adversarial training framework for image inpainting with segmentation confusion adversarial training (SCAT) and contrastive learning. SCAT plays an adversarial game between an inpainting generator and a segmentation network,
Externí odkaz:
http://arxiv.org/abs/2303.13133
Autor:
ZHANG Yu, ZHAO Mengyun, PEI Lijian, GONG Yahong, RUAN Xia, ZHANG Yuguan, XIA Di, LU Zhilong, ZHANG Zhanjie, ZHOU Jiong, FU Chenwei, GAO Jinsong, HUANG Yuguang
Publikováno v:
Xiehe Yixue Zazhi, Vol 15, Iss 2, Pp 246-250 (2024)
Epidural labor analgesia aims to provide effective medical services to alleviate labor pain in parturients, while adhering to the principles of voluntary participation and clinical safety. In 2018, Peking Union Medical College Hospital(PUMCH)became o
Externí odkaz:
https://doaj.org/article/b0b4355499d648828c106344ee13d2b6
Recent studies have shown remarkable success in universal style transfer which transfers arbitrary visual styles to content images. However, existing approaches suffer from the aesthetic-unrealistic problem that introduces disharmonious patterns and
Externí odkaz:
http://arxiv.org/abs/2208.13016