Leyi Li

2 accepted papers

2024

GAIA: Zero-shot Talking Avatar Generation

Tianyu He, Junliang Guo, Runyi Yu, Yuchi Wang, jialiang zhu, Kaikai An +7

ICLR 2024poster

Zero-shot talking avatar generation aims at synthesizing natural talking videos from speech and a single portrait image. Previous methods have relied on domain-specific heuristics such as warping-based motion representation and 3D Morphable Models, which limit the naturalness and diversity of the ge…

Cited by 21 Source ↗PDF ↗Scholar ↗

2023

Metadata-Based RAW Reconstruction via Implicit Neural Functions

Leyi Li, Huijie Qiao, Qi Ye, Qinmin Yang

CVPR 2023poster

Many low-level computer vision tasks are desirable to utilize the unprocessed RAW image as input, which remains the linear relationship between pixel values and scene radiance. Recent works advocate to embed the RAW image samples into sRGB images at capture time, and reconstruct the RAW from sRGB by…

Cited by 8 Source ↗PDF ↗Scholar ↗