search

Fictionarry / TalkingGaussian

[ECCV'24] TalkingGaussian: Structure-Persistent 3D Talking Head Synthesis via Gaussian Splatting
https://fictionarry.github.io/TalkingGaussian/
270 stars 33 forks source link

Is this better than synctalk? #44

Open linhcentrio opened 2 months ago

linhcentrio commented 2 months ago

Is this better than synctalk?

Fictionarry commented 2 months ago

Both ours and SyncTalk are good works, while these two aims to solve different problems. SyncTalk solves some "devil" problems and make validations on ER-NeRF. Our work focus on the modeling methodology itself and relatively less on the details, while in the implementation we also use some good design in SyncTalk to provide better performance, on the premise of fairness.

linhcentrio commented 2 months ago

Both ours and SyncTalk are good works, while these two aims to solve different problems. SyncTalk solves some "devil" problems and make validations on ER-NeRF. Our work focus on the modeling methodology itself and relatively less on the details, while in the implementation we also use some good design in SyncTalk to provide better performance, on the premise of fairness.

thank you, it's good new. good job!