Ziyu Chen

Ziyu Chen

Auto-generated profile, based on publicly available information

Ziyu Chen

Shanghai Jiao Tong University, Shanghai, China

Research Focus & Metrics

Academic Career Length

5Years (2022-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
JWJionghao Wang
Jionghao Wang
ZCZiyu Chen
Ziyu Chen
JLJun Ling
Jun Ling
RXRong Xie
Rong Xie
LSLi Song
Li Song
360° panoramas are extensively utilized as environmental light sources in computer graphics. However, capturing a 360° × 180° panorama poses challenges due to the necessity of specialized and costly equipment, and additional human resources. Prior studies develop various learning-based generative methods to synthesize panoramas from a single Narrow Field-of-View (NFoV) image, but they are limited in alterable input patterns, generation quality, and controllability. To address these issues, we propose a novel pipeline called PanoDiff, which efficiently generates complete 360° panoramas using one or more unregistered NFoV images captured from arbitrary angles. Our approach has two primary components to overcome the limitations. Firstly, a two-stage angle prediction module to handle various numbers of NFoV inputs. Secondly, a novel latent diffusion-based panorama generation model uses incomplete panorama and text prompts as control signals and utilizes several geometric augmentation schemes to ensure geometric properties in generated panoramas. Experiments show that PanoDiff achieves state-of-the-art panoramic generation quality and high controllability, making it suitable for applications such as content editing.

31 October 2022
Verified
Book Chapter
Closed access
PDF file
ZCZiyu Chen
Ziyu Chen
CDChenjing Ding
Chenjing Ding
JGJianfei Guo
Jianfei Guo
DWDongliang Wang
Dongliang Wang
YLYikang Li
Yikang Li
LSLi Song
Li Song