Papers › Facial Landmark Predictions with Applications to Metaverse

Facial Landmark Predictions with Applications to Metaverse

29 Sep 2022arXiv:2209.14698archive 2025-07-28

Qiao Han, Jun Zhao, Kwok-Yan Lam

This research aims to make metaverse characters more realistic by adding lip animations learnt from videos in the wild. To achieve this, our approach is to extend Tacotron 2 text-to-speech synthesizer to generate lip movements together with mel spectrogram in one pass. The encoder and gate layer weights are pre-trained on LJ Speech 1.1 data set while the decoder is retrained on 93 clips of TED talk videos extracted from LRS 3 data set. Our novel decoder predicts displacement in 20 lip landmark positions across time, using labels automatically extracted by OpenFace 2.0 landmark predictor. Training converged in 7 hours using less than 5 minutes of video. We conducted ablation study for Pre/Post-Net and pre-trained encoder weights to demonstrate the effectiveness of transfer learning between audio and visual speech data.

PaperPDFCode

Code

sweatybridge/text-to-anime officialmentioned in paperpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

DecoderText to SpeechTransfer Learningtext-to-speech

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Batch NormalizationBiGRUBiLSTMCBHGConvolutionDense ConnectionsDilated Causal ConvolutionDropoutGRUGriffin-Lim AlgorithmHighway LayerHighway NetworkLSTMLinear LayerLocation Sensitive AttentionMax PoolingMixture of Logistic DistributionsReLUResidual ConnectionResidual GRUSigmoid ActivationTacotronTacotron 2Tanh ActivationWaveNetZoneout

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections