3 papers
cs.CV2024
TrailBlazer: Trajectory Control for Diffusion-Based Video Generation
Wan-Duo Kurt Ma, J. P. Lewis, W. Bastiaan Kleijn
Within recent approaches to text-to-video (T2V) generation, achieving controllability in the synthesized video is often a challenge. Typically, this issue is addressed by providing…
cs.CV2023
FDLS: A Deep Learning Approach to Production Quality, Controllable, and Retargetable Facial Performances
Wan-Duo Kurt Ma, Muhammad Ghifary, J. P. Lewis +2
Visual effects commonly requires both the creation of realistic synthetic humans as well as retargeting actors' performances to humanoid characters such as aliens and monsters. Ach…
cs.CV2023
Directed Diffusion: Direct Control of Object Placement through Attention Guidance
Wan-Duo Kurt Ma, J. P. Lewis, Avisek Lahiri +2
Text-guided diffusion models such as DALLE-2, Imagen, eDiff-I, and Stable Diffusion are able to generate an effectively endless variety of images given only a short text prompt des…