Showing cs.CVShow all
2 papers · 1 filter
cs.CV2025
JOLT3D: Joint Learning of Talking Heads and 3DMM Parameters with Application to Lip-Sync
Sungjoon Park, Minsik Park, Haneol Lee +2
In this work, we revisit the effectiveness of 3DMM for talking head synthesis by jointly learning a 3D face reconstruction model and a talking head synthesis model. This enables us…
cs.CV2024
Interpretable Convolutional SyncNet
Sungjoon Park, Jaesub Yun, Donggeon Lee +1
Because videos in the wild can be out of sync for various reasons, a sync-net is used to bring the video back into sync for tasks that require synchronized videos. Previous state-o…