Qingyan Bai

机构：The Hong Kong University of Science and Technology · 主页：https://scholar.google.com/citations?user=xUMjxi4AAAAJ

发表论文 19 篇 · 总被引 630 次 · h-index 10

代表论文

• StyleHEAT: One-Shot High-Resolution Editable Talking Face Generation via Pre-trained StyleGAN (2022 · European Conference on Computer Vision · 被引 249)
• CoDeF: Content Deformation Fields for Temporally Consistent Video Processing (2023 · Computer Vision and Pattern Recognition · 被引 136)
• Advancing Open-source World Models (2026 · arXiv.org · 被引 94)
• Scaling Instruction-Based Video Editing with a High-Quality Synthetic Dataset (2025 · arXiv.org · 被引 68)
• NTIRE 2021 Challenge on Perceptual Image Quality Assessment (2021 · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · 被引 40)
• High-fidelity GAN Inversion with Padding Space (2022 · European Conference on Computer Vision · 被引 34)