Autoregressive GAN for Semantic Unconditional Head Motion Generation
Not on the map. Why?
Abstract (arXiv)
In this work, we address the task of unconditional head motion generation to animate still human faces in a low-dimensional semantic space from a single reference pose. Different from traditional audio-conditioned talking head generation that seldom puts emphasis on realistic head motions, we devise a GAN-based architecture that learns to synthesize rich head motion sequences over long duration while maintaining low error accumulation levels.In particular, the autoregressive generation of incremental outputs ensures smooth trajectories, while a multi-scale discriminator on input pairs drives generation toward better handling of high- and low-frequency signals and less mode collapse.We experimentally demonstrate the relevance of the proposed method and show its superiority compared to models that attained state-of-the-art performances on similar tasks.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 41 of its 58 references that are in the map. First posted on arXiv 2 Nov 2022.
Builds on
41 of 58 references.
References · 41
- 2017Attention Is All You Needcited by 59,932
- 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
- 2015Rethinking the Inception Architecture for Computer Visioncited by 5,451
- 2017Neural Discrete Representation Learningcited by 4,650
- 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,510
- 2017Quo Vadis, Action Recognition? A New Model and the Kinetics Datasetcited by 3,259
- 2018Towards Accurate Generative Models of Video: A New Metric & Challengescited by 1,204
- 2017High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANscited by 1,176
- 2018VoxCeleb2: Deep Speaker Recognitioncited by 862
- 2016InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Netscited by 858
- 2018Social GAN: Socially Acceptable Trajectories with Generative Adversarial Networkscited by 687
- 2017MoCoGAN: Decomposing Motion and Content for Video Generationcited by 523
29 more
- 2021Action-Conditioned 3D Human Motion Synthesis with Transformer VAEcited by 497
- 2016Generating Videos with Scene Dynamicscited by 376
- 2019MelGAN: Generative Adversarial Networks for Conditional Waveform Synthesiscited by 351
- 2017On human motion prediction using recurrent neural networkscited by 336
- 2020MakeItTalk: Speaker-Aware Talking-Head Animationcited by 310
- 2021Pose-Controllable Talking Face Generation by Implicitly Modularized Audio-Visual Representationcited by 288
- 2019Few-Shot Adversarial Learning of Realistic Neural Talking Head Modelscited by 284
- 2019Hierarchical Cross-Modal Talking Face Generationwith Dynamic Pixel-Wise Losscited by 252
- 2017Geometric GANcited by 232
- 2018Talking Face Generation by Adversarially Disentangled Audio-Visual Representationcited by 212
- 2021FaceFormer: Speech-Driven 3D Facial Animation with Transformerscited by 208
- 2022EAMM: One-Shot Emotional Talking Face via Audio-Based Emotion-Aware Motion Modelcited by 151
- 2021Audio2Head: Audio-driven One-shot Talking-head Generation with Natural Head Motioncited by 148
- 2019Realistic Speech-Driven Facial Animation with GANscited by 142
- 2016Mode Regularized Generative Adversarial Networkscited by 123
- 2020Fast Bi-layer Neural Synthesis of One-Shot Realistic Head Avatarscited by 116
- 2020Talking-head Generation with Rhythmic Head Motioncited by 112
- 2017PacGAN: The power of two samples in generative adversarial networkscited by 104
- 2020Audio-driven Talking Face Video Generation with Learning-based Personalized Head Posecited by 92
- 2017Learning to Generate Long-term Future via Hierarchical Predictioncited by 88
- 2021One-shot Talking Face Generation from Single-speaker Audio-Visual Correlation Learningcited by 87
- 2018BiHMP-GAN: Bidirectional 3D Human Motion Prediction GANcited by 55
- 2018Human Motion Modeling using DVGANscited by 45
- 2021Chunked Autoregressive GAN for Conditional Waveform Synthesiscited by 38
- 2021Learned Spatial Representations for Few-shot Talking-Head Synthesiscited by 32
- 2021Sparse to Dense Motion Transfer for Face Image Animationcited by 25
- 2019Dynamic Facial Expression Generation on Hilbert Hypersphere with Conditional Wasserstein Generative Adversarial Netscited by 19
- 2022HiT-DVAE: Human Motion Generation via Hierarchical Transformer Dynamical VAEcited by 16
- 2021SocialInteractionGAN: Multi-person Interaction Sequence Generationcited by 4
Built on by
Citing papers per year: 2023: 1.
1 paper.