Bowen Zhang

Bowen Zhang

Auto-generated profile, based on publicly available information

Bowen Zhang

University of Science and Technology of China

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

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

Representative Publications

View All Publications
5 December 2024
Verified
Book Chapter
Closed access
PDF file
BZBowen Zhang
Bowen Zhang
YCYiji Cheng
Yiji Cheng
CWChunyu Wang
Chunyu Wang
TZTing Zhang
Ting Zhang
JYJiaolong Yang
Jiaolong Yang
BGBaining Guo
Baining Guo

11 July 2024 in arXiv
Verified
Preprint
Open access
PDF file
BZBowen Zhang
Bowen Zhang
YCYiji Cheng
Yiji Cheng
CWChunyu Wang
Chunyu Wang
TZTing Zhang
Ting Zhang
JYJiaolong Yang
Jiaolong Yang
BGBaining Guo
Baining Guo
We present RodinHD, which can generate high-fidelity 3D avatars from a portrait image. Existing methods fail to capture intricate details such as hairstyles which we tackle in this paper. We first identify an overlooked problem of catastrophic forgetting that arises when fitting triplanes sequentially on many avatars, caused by the MLP decoder sharing scheme. To overcome this issue, we raise a novel data scheduling strategy and a weight consolidation regularization term, which improves the decoder's capability of rendering sharper details. Additionally, we optimize the guiding effect of the portrait image by computing a finer-grained hierarchical representation that captures rich 2D texture cues, and injecting them to the 3D diffusion model at multiple layers via cross-attention. When trained on 46K avatars with a noise schedule optimized for triplanes, the resulting model can generate 3D avatars with notably better details than previous methods and can generalize to in-the-wild portrait input.