Heliang Zheng

Heliang Zheng

Auto-generated profile, based on publicly available information

Heliang Zheng

University of Science and Technology of China, Hefei, Anhui, China

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
26 October 2023
Verified
Conference Paper
Open access
JZJing Zhao
Jing Zhao
HZHeliang Zheng
Heliang Zheng
CWChaoyue Wang
Chaoyue Wang
LLLong Lan
Long Lan
WHWanrong Huang
Wanrong Huang
WYWenjing Yang
Wenjing Yang

28 October 2024
Verified
Conference Paper
Open access
ZFZhongyi Fan
Zhongyi Fan
ZYZixin Yin
Zixin Yin
GLGang Li
Gang Li
YZYibing Zhan
Yibing Zhan
HZHeliang Zheng
Heliang Zheng
DreamBooth has demonstrated significant potential in subject-driven text-to-image generation, especially in scenarios requiring precise preservation of a subject's appearance. However, it still suffers from inefficiency and requires extensive iterative training to customize concepts using a small set of reference images. To address these issues, we introduce DreamBooth++, a region-level training strategy designed to significantly improve the efficiency and effectiveness of learning specific subjects. In particular, our approach employs a region-level data re-formulation technique that packs a set of reference images into a single sample, significantly reducing computational costs. Moreover, we adapt convolution and self-attention layers to ensure their processings are restricted within individual regions. Thus their operational scope (i.e., receptive field) can be preserved within a single subject, avoiding generating multiple sub-images within a single image. Last but not least, we design a text-guided prior regularization between our model and the pretrained one to preserve the original semantic generation ability. Comprehensive experiments demonstrate that our training strategy not only accelerates the subject-learning process but also significantly boosts fidelity to both subject and prompts in subject-driven generation.