Neural Rendering with Attention: An Incremental Improvement for Anime Character Animation
2022/08 @transpchan was kicked out from the authors of Live3Dv1 as I refused to continue submittion after seeing the heart-breaking reviews from ECCV22.
Call for Authors/Contributors: Please contact me if you are willing to be the author of the paper of v2 and future versions, or if you are willing to sponsor furher research. Pull requests are also welcome!!
2022/10 Live3Dv2 is released. Changes are (1) dropping the ResNet50 encoder (2) adding self-attention to the U-Net (3) tuning the hyper-parameters of the networks.
2022/11 Weight file for Live3Dv2 is released.
2022/11 Stay tuned for Live3D v3
[Demo1] Generate videos
[Demo2] Colorize your own model
[Demo3] Generate 3D point cloud from drawings
