no code implementations • 13 Mar 2024 • Jian Lin, Xueting Liu, Chengze Li, Minshan Xie, Tien-Tsin Wong
Unfortunately, there is no existing method that tailors for automatic manga screening, probably due to the difficulty of generating high-quality shaded high-frequency screentones.
no code implementations • 24 Nov 2023 • Minshan Xie, Hanyuan Liu, Chengze Li, Tien-Tsin Wong
However, they struggle to generate videos with both highly detailed appearance and temporal consistency.
no code implementations • 21 Nov 2023 • Yuxin Liu, Minshan Xie, Hanyuan Liu, Tien-Tsin Wong
In this paper, we propose a synchronized multi-view diffusion approach that allows the diffusion processes from different views to reach a consensus of the generated content early in the process, and hence ensures the texture consistency.
no code implementations • 7 Jun 2023 • Minshan Xie, Chengze Li, Tien-Tsin Wong
To overcome these limitations, we propose a novel interpretable representation of screentones that disentangles their intensity and type features, enabling better recognition and synthesis of screentones.
no code implementations • 2 Jun 2023 • Hanyuan Liu, Minshan Xie, Jinbo Xing, Chengze Li, Tien-Tsin Wong
In this paper, we present ColorDiffuser, an adaptation of a pre-trained text-to-image latent diffusion model for video colorization.
1 code implementation • 21 Apr 2023 • Hanyuan Liu, Jinbo Xing, Minshan Xie, Chengze Li, Tien-Tsin Wong
Our key idea is to exploit the color prior knowledge in the pre-trained T2I diffusion model for realistic and diverse colorization.
no code implementations • 7 Mar 2022 • Minshan Xie, Menghan Xia, Xueting Liu, Tien-Tsin Wong
Fortunately, the rescaled manga shares the same region-wise screentone correspondences with the original manga, which enables us to simplify the screentone synthesis problem as an anchor-based proposals selection and rearrangement problem.
1 code implementation • CVPR 2021 • Minshan Xie, Menghan Xia, Tien-Tsin Wong
First, we predict the target resolution from the degraded manga via the Scale Estimation Network (SE-Net) with spatial voting scheme.
no code implementations • 27 Mar 2021 • Zihao Jian, Minshan Xie
3D face reconstruction and face alignment are two fundamental and highly related topics in computer vision.
no code implementations • 21 Mar 2021 • Menghan Xia, Jose Echevarria, Minshan Xie, Tien-Tsin Wong
Light fields are 4D scene representation typically structured as arrays of views, or several directional samples per pixel in a single view.