Qiang Wang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Qiang Wang has a total of 3 co-authors. Here are the top co-authors by number of shared publications:
- Di Kong
Beijing University of Posts and Telecommunications
2 shared publications - Yonggang Qi
Beijing University of Posts and Telecommunications, China
2 shared publications - Fengyin Lin
Beijing University of Posts and Telecommunications Beijing China
1 shared publication
Latest Publications
- Open Access
DiffSketching: Sketch Control Image Synthesis with Diffusion Models
Creative sketch is a universal way of visual expression, but translating images from an abstract sketch is very challenging. Traditionally, creating a deep learning model for sketch-to-image synthesis needs to overcome the distorted input sketch without visual details, and requires to collect large-scale sketch-image datasets. We first study this task by using diffusion models. Our model matches sketches through the cross domain constraints, and uses a classifier to guide the image synthesis more accurately. Extensive experiments confirmed that our method can not only be faithful to user's input sketches, but also maintain the diversity and imagination of synthetic image results. Our model can beat GAN-based method in terms of generation quality and human evaluation, and does not rely on massive sketch-image datasets. Additionally, we present applications of our method in image editing and interpolation.
Open AccessDiffSketching: Sketch Control Image Synthesis with Diffusion Models
Creative sketch is a universal way of visual expression, but translating images from an abstract sketch is very challenging. Traditionally, creating a deep learning model for sketch-to-image synthesis needs to overcome the distorted input sketch without visual details, and requires to collect large-scale sketch-image datasets. We first study this task by using diffusion models. Our model matches sketches through the cross domain constraints, and uses a classifier to guide the image synthesis more accurately. Extensive experiments confirmed that our method can not only be faithful to user's input sketches, but also maintain the diversity and imagination of synthetic image results. Our model can beat GAN-based method in terms of generation quality and human evaluation, and does not rely on massive sketch-image datasets. Additionally, we present applications of our method in image editing and interpolation.
- 11 March 2023
- Published by Springer Nature
- p. 54-70
A Diffusion-ReFinement Model for Sketch-to-Point Modeling
- 11 March 2023
- Published by Springer Nature
- p. 54-70
A Diffusion-ReFinement Model for Sketch-to-Point Modeling