209 citations
- Tsinghua UniversityCN14 papers
- University of Science and Technology of ChinaCN11 papers
- OriginWater (China)CN10 papers
- Renmin University of ChinaCN8 papers
- Peking UniversityCN7 papers
- Chinese Academy of SciencesCN6 papers
- City University of Hong KongHK5 papers
- University of Chinese Academy of SciencesCN5 papers
- Beihang UniversityCN4 papers
- National University of SingaporeSG4 papers
- Shandong Institute of AutomationCN4 papers
- University of Electronic Science and Technology of ChinaCN4 papers
4 papers · 2 filters
DeViT: Deformed Vision Transformers in Video Inpainting
Jiayin Cai, Changlin Li, Xin Tao +2
This paper proposes a novel video inpainting method. We make three main contributions: First, we extended previous Transformers with patch alignment by introducing Deformed Patch-b…
Fast Learning Radiance Fields by Shooting Much Fewer Rays
Wenyuan Zhang, Ruofan Xing, Yunfan Zeng +3
Learning radiance fields has shown remarkable results for novel view synthesis. The learning procedure usually costs lots of time, which motivates the latest methods to speed up th…
Domain Enhanced Arbitrary Image Style Transfer via Contrastive Learning
Yuxin Zhang, Fan Tang, Weiming Dong +4
In this work, we tackle the challenging problem of arbitrary image style transfer using a novel style feature representation learning method. A suitable style representation, as a…
Audio-Driven Talking Face Video Generation with Dynamic Convolution Kernels
Zipeng Ye, Mengfei Xia, Ran Yi +5
In this paper, we present a dynamic convolution kernel (DCK) strategy for convolutional neural networks. Using a fully convolutional network with the proposed DCKs, high-quality ta…