3 papers
cs.CV2026
FaceCam: Portrait Video Camera Control via Scale-Aware Conditioning
Weijie Lyu, Ming-Hsuan Yang, Zhixin Shu
We introduce FaceCam, a system that generates video under customizable camera trajectories for monocular human portrait video input. Recent camera control approaches based on large…
cs.SD2024
Learning Frame-Wise Emotion Intensity for Audio-Driven Talking-Head Generation
Jingyi Xu, Hieu Le, Zhixin Shu +3
Human emotional expression is inherently dynamic, complex, and fluid, characterized by smooth transitions in intensity throughout verbal communication. However, the modeling of suc…
cs.CV2024
In-N-Out: Faithful 3D GAN Inversion with Volumetric Decomposition for Face Editing
Yiran Xu, Zhixin Shu, Cameron Smith +2
3D-aware GANs offer new capabilities for view synthesis while preserving the editing functionalities of their 2D counterparts. GAN inversion is a crucial step that seeks the latent…