no code implementations • 27 Mar 2024 • Sicheng Li, Keqiang Sun, Zhixin Lai, Xiaoshi Wu, Feng Qiu, Haoran Xie, Kazunori Miyata, Hongsheng Li
Secondly, to overcome the issue of limited conditional supervision, we introduce Diffusion Consistency Loss (DCL), which applies supervision on the denoised latent code at any given time step.
no code implementations • 13 Jun 2023 • Zhengyu Huang, Haoran Xie, Tsukasa Fukusato, Kazunori Miyata
In the second stage, we simulated the drawing process of the generated images without any additional data (labels) and trained the sketch encoder for incomplete progressive sketches to generate high-quality portrait images with feature alignment to the disentangled representations in the teacher encoder.
no code implementations • 1 Mar 2023 • Yi He, Haoran Xie, Kazunori Miyata
In this study, we propose Sketch2Cloth, a sketch-based 3D garment generation system using the unsigned distance fields from the user's sketch input.
1 code implementation • 14 Feb 2023 • Yichen Peng, Chunqi Zhao, Haoran Xie, Tsukasa Fukusato, Kazunori Miyata
We then introduce a Stochastic Region Abstraction (SRA), an approach to augment our dataset to improve the robustness of SGLDM to handle sketch input with arbitrary abstraction.
no code implementations • 10 Aug 2021 • Ryoma Miyauchi, Tsukasa Fukusato, Haoran Xie, Kazunori Miyata
First, the proposed system separates the closed areas in each keyframe and estimates the correspondences between closed areas by using the characteristics of shape, depth, and closed area connection.
no code implementations • 17 Jun 2021 • Haoran Xie, Yuki Fujita, Kazunori Miyata
To solve the specific issue, we propose the perceptual manifold of fonts to visualize the perceptual adjustment in the latent space of a generative model of fonts.
1 code implementation • 26 Apr 2021 • Zhengyu Huang, Yichen Peng, Tomohiro Hibino, Chunqi Zhao, Haoran Xie, Tsukasa Fukusato, Kazunori Miyata
In the stage of local guidance, we synthesize detailed portrait images with a deep generative model from user-drawn contour lines, but use the synthesized results as detailed drawing guidance.
no code implementations • 23 Apr 2021 • Yi He, Haoran Xie, Chao Zhang, Xi Yang, Kazunori Miyata
This paper proposes a deep generative model for generating normal maps from users sketch with geometric sampling.