no code implementations • 12 Dec 2022 • Qixin Yan, Chunle Guo, Jixin Zhao, Yuekun Dai, Chen Change Loy, Chongyi Li
The key insights of this study are modeling component-specific correspondence for local makeup transfer, capturing long-range dependencies for global makeup transfer, and enabling efficient makeup transfer via a single-path structure.
2 code implementations • CVPR 2022 • Chun-Le Guo, Qixin Yan, Saeed Anwar, Runmin Cong, Wenqi Ren, Chongyi Li
Though Transformer has occupied various computer vision tasks, directly leveraging Transformer for image dehazing is challenging: 1) it tends to result in ambiguous and coarse details that are undesired for image reconstruction; 2) previous position embedding of Transformer is provided in logic or spatial position order that neglects the variational haze densities, which results in the sub-optimal dehazing performance.