# Learned Spatial Representations for Few-shot Talking-Head Synthesis

arXiv: https://arxiv.org/abs/2104.14557 · HTML: https://mlsanity.com/paper/2104.14557/

## Key facts

- Cited by 32 papers in the map (data through 14 Oct 2026).
- Builds on 43 of its 53 references that are in the map.
- First posted on arXiv 29 Apr 2021.

## Builds on (most cited first, 30 of 43)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [Analyzing and Improving the Image Quality of StyleGAN](https://mlsanity.com/paper/1912.04958/) (2019)
- [Progressive Growing of GANs for Improved Quality, Stability, and Variation](https://mlsanity.com/paper/1710.10196/) (2017)
- [Perceptual Losses for Real-Time Style Transfer and Super-Resolution](https://mlsanity.com/paper/1603.08155/) (2016)
- [Large Scale GAN Training for High Fidelity Natural Image Synthesis](https://mlsanity.com/paper/1809.11096/) (2018)
- [Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization](https://mlsanity.com/paper/1703.06868/) (2017)
- [Semantic Image Synthesis with Spatially-Adaptive Normalization](https://mlsanity.com/paper/1903.07291/) (2019)
- [VoxCeleb2: Deep Speaker Recognition](https://mlsanity.com/paper/1806.05622/) (2018)
- [CNN-generated images are surprisingly easy to spot... for now](https://mlsanity.com/paper/1912.11035/) (2019)
- [Multimodal Unsupervised Image-to-Image Translation](https://mlsanity.com/paper/1804.04732/) (2018)
- [First Order Motion Model for Image Animation](https://mlsanity.com/paper/2003.00196/) (2020)
- [Which Training Methods for GANs do actually Converge?](https://mlsanity.com/paper/1801.04406/) (2018)
- [Face2Face: Real-time Face Capture and Reenactment of RGB Videos](https://mlsanity.com/paper/2007.14808/) (2020)
- [MaskGAN: Towards Diverse and Interactive Facial Image Manipulation](https://mlsanity.com/paper/1907.11922/) (2019)
- [How far are we from solving the 2D & 3D Face Alignment problem? (and a dataset of 230,000 3D facial landmarks)](https://mlsanity.com/paper/1703.07332/) (2017)
- [Dynamic Neural Radiance Fields for Monocular 4D Facial Avatar Reconstruction](https://mlsanity.com/paper/2012.03065/) (2020)
- [One-Shot Free-View Neural Talking-Head Synthesis for Video Conferencing](https://mlsanity.com/paper/2011.15126/) (2020)
- [FSGAN: Subject Agnostic Face Swapping and Reenactment](https://mlsanity.com/paper/1908.05932/) (2019)
- [Toward Multimodal Image-to-Image Translation](https://mlsanity.com/paper/1711.11586/) (2017)
- [Detecting and Simulating Artifacts in GAN Fake Images](https://mlsanity.com/paper/1907.06515/) (2019)
- [Few-Shot Adversarial Learning of Realistic Neural Talking Head Models](https://mlsanity.com/paper/1905.08233/) (2019)
- [Deep Video Portraits](https://mlsanity.com/paper/1805.11714/) (2018)
- [SEAN: Image Synthesis with Semantic Region-Adaptive Normalization](https://mlsanity.com/paper/1911.12861/) (2019)
- [Hierarchical Cross-Modal Talking Face Generationwith Dynamic Pixel-Wise Loss](https://mlsanity.com/paper/1905.03820/) (2019)
- [The Creation and Detection of Deepfakes: A Survey](https://mlsanity.com/paper/2004.11138/) (2020)
- [DeepFakes and Beyond: A Survey of Face Manipulation and Fake Detection](https://mlsanity.com/paper/2001.00179/) (2020)

## Built on by (most cited first, 30 of 32)

- [Semantic-Aware Implicit Neural Audio-Driven Video Portrait Generation](https://mlsanity.com/paper/2201.07786/) (2022)
- [Learning Dynamic Facial Radiance Fields for Few-Shot Talking Head Synthesis](https://mlsanity.com/paper/2207.11770/) (2022)
- [SyncTalk: The Devil is in the Synchronization for Talking Head Synthesis](https://mlsanity.com/paper/2311.17590/) (2023)
- [Real-time Neural Radiance Talking Portrait Synthesis via Audio-spatial Decomposition](https://mlsanity.com/paper/2211.12368/) (2022)
- [Talking Head Generation with Probabilistic Audio-to-Visual Diffusion Priors](https://mlsanity.com/paper/2212.04248/) (2022)
- [HyperReenact: One-Shot Reenactment via Jointly Learning to Refine and Retarget Faces](https://mlsanity.com/paper/2307.10797/) (2023)
- [FDNeRF: Few-shot Dynamic Neural Radiance Fields for Face Reconstruction and Expression Editing](https://mlsanity.com/paper/2208.05751/) (2022)
- [MuseTalk: Real-Time High-Fidelity Video Dubbing via Spatio-Temporal Sampling](https://mlsanity.com/paper/2410.10122/) (2024)
- [Finding Directions in GAN's Latent Space for Neural Face Reenactment](https://mlsanity.com/paper/2202.00046/) (2022)
- [DREAM-Talk: Diffusion-based Realistic Emotional Audio-driven Method for Single Image Talking Face Generation](https://mlsanity.com/paper/2312.13578/) (2023)
- [NeRFInvertor: High Fidelity NeRF-GAN Inversion for Single-shot Real Image Animation](https://mlsanity.com/paper/2211.17235/) (2022)
- [Memories are One-to-Many Mapping Alleviators in Talking Face Generation](https://mlsanity.com/paper/2212.05005/) (2022)
- [StyleMask: Disentangling the Style Space of StyleGAN2 for Neural Face Reenactment](https://mlsanity.com/paper/2209.13375/) (2022)
- [Talking Head from Speech Audio using a Pre-trained Image Generator](https://mlsanity.com/paper/2209.04252/) (2022)
- [Quark: Real-time, High-resolution, and General Neural View Synthesis](https://mlsanity.com/paper/2411.16680/) (2024)
- [Implicit Neural Head Synthesis via Controllable Local Deformation Fields](https://mlsanity.com/paper/2304.11113/) (2023)
- [DiffusionAct: Controllable Diffusion Autoencoder for One-shot Face Reenactment](https://mlsanity.com/paper/2403.17217/) (2024)
- [HQ3DAvatar: High Quality Controllable 3D Head Avatar](https://mlsanity.com/paper/2303.14471/) (2023)
- [SyncTalk++: High-Fidelity and Efficient Synchronized Talking Heads Synthesis Using Gaussian Splatting](https://mlsanity.com/paper/2506.14742/) (2025)
- [One-shot Neural Face Reenactment via Finding Directions in GAN's Latent Space](https://mlsanity.com/paper/2402.03553/) (2024)
- [A Comprehensive Taxonomy and Analysis of Talking Head Synthesis: Techniques for Portrait Generation, Driving Mechanisms, and Editing](https://mlsanity.com/paper/2406.10553/) (2024)
- [SegTalker: Segmentation-based Talking Face Generation with Mask-guided Local Editing](https://mlsanity.com/paper/2409.03605/) (2024)
- [GGTalker: Talking Head Systhesis with Generalizable Gaussian Priors and Identity-Specific Adaptation](https://mlsanity.com/paper/2506.21513/) (2025)
- [R2-Talker: Realistic Real-Time Talking Head Synthesis with Hash Grid Landmarks Encoding and Progressive Multilayer Conditioning](https://mlsanity.com/paper/2312.05572/) (2023)
- [Geometry Driven Progressive Warping for One-Shot Face Animation](https://mlsanity.com/paper/2210.02391/) (2022)
- [Cross-Modal Few-Shot Learning: a Generative Transfer Learning Framework](https://mlsanity.com/paper/2410.10663/) (2024)
- [Autoregressive GAN for Semantic Unconditional Head Motion Generation](https://mlsanity.com/paper/2211.00987/) (2022)
- [Controllable One-Shot Face Video Synthesis With Semantic Aware Prior](https://mlsanity.com/paper/2304.14471/) (2023)
- [FluentAvatar: Flicker-Free Talking-Head Animation via Phoneme-Guided Autoregressive Modeling](https://mlsanity.com/paper/2509.12052/) (2025)
- [A Comprehensive Multi-scale Approach for Speech and Dynamics Synchrony in Talking Head Generation](https://mlsanity.com/paper/2307.03270/) (2023)

## Abstract (arXiv)

We propose a novel approach for few-shot talking-head synthesis. While recent works in neural talking heads have produced promising results, they can still produce images that do not preserve the identity of the subject in source images. We posit this is a result of the entangled representation of each subject in a single latent code that models 3D shape information, identity cues, colors, lighting and even background details. In contrast, we propose to factorize the representation of a subject into its spatial and style components. Our method generates a target frame in two steps. First, it predicts a dense spatial layout for the target image. Second, an image generator utilizes the predicted layout for spatial denormalization and synthesizes the target frame. We experimentally show that this disentangled representation leads to a significant improvement over previous methods, both quantitatively and qualitatively.