# Learning Dense Correspondence for NeRF-Based Face Reenactment

arXiv: https://arxiv.org/abs/2312.10422 · HTML: https://mlsanity.com/paper/2312.10422/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Builds on 39 of its 45 references that are in the map.
- First posted on arXiv 16 Dec 2023.

## Builds on (most cited first, 30 of 39)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [A Style-Based Generator Architecture for Generative Adversarial Networks](https://mlsanity.com/paper/1812.04948/) (2018)
- [Deep Learning Face Attributes in the Wild](https://mlsanity.com/paper/1411.7766/) (2014)
- [Analyzing and Improving the Image Quality of StyleGAN](https://mlsanity.com/paper/1912.04958/) (2019)
- [VoxCeleb2: Deep Speaker Recognition](https://mlsanity.com/paper/1806.05622/) (2018)
- [VoxCeleb: a large-scale speaker identification dataset](https://mlsanity.com/paper/1706.08612/) (2017)
- [First Order Motion Model for Image Animation](https://mlsanity.com/paper/2003.00196/) (2020)
- [Accurate 3D Face Reconstruction with Weakly-Supervised Learning: From Single Image to Image Set](https://mlsanity.com/paper/1903.08527/) (2019)
- [Learning an Animatable Detailed 3D Face Model from In-The-Wild Images](https://mlsanity.com/paper/2012.04012/) (2020)
- [StyleNeRF: A Style-based 3D-Aware Generator for High-resolution Image Synthesis](https://mlsanity.com/paper/2110.08985/) (2021)
- [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)
- [AD-NeRF: Audio Driven Neural Radiance Fields for Talking Head Synthesis](https://mlsanity.com/paper/2103.11078/) (2021)
- [StyleSDF: High-Resolution 3D-Consistent Image and Geometry Generation](https://mlsanity.com/paper/2112.11427/) (2021)
- [Thin-Plate Spline Motion Model for Image Animation](https://mlsanity.com/paper/2203.14367/) (2022)
- [Depth-Aware Generative Adversarial Network for Talking Head Video Generation](https://mlsanity.com/paper/2203.06605/) (2022)
- [Latent Image Animator: Learning to Animate Images via Latent Space Navigation](https://mlsanity.com/paper/2203.09043/) (2022)
- [Liquid Warping GAN: A Unified Framework for Human Motion Imitation, Appearance Transfer and Novel View Synthesis](https://mlsanity.com/paper/1909.12224/) (2019)
- [MegaPortraits: One-shot Megapixel Neural Head Avatars](https://mlsanity.com/paper/2207.07621/) (2022)
- [RigNeRF: Fully Controllable Neural 3D Portraits](https://mlsanity.com/paper/2206.06481/) (2022)
- [Semantic-Aware Implicit Neural Audio-Driven Video Portrait Generation](https://mlsanity.com/paper/2201.07786/) (2022)
- [Realistic One-shot Mesh-based Head Avatars](https://mlsanity.com/paper/2206.08343/) (2022)
- [Learning Dynamic Facial Radiance Fields for Few-Shot Talking Head Synthesis](https://mlsanity.com/paper/2207.11770/) (2022)
- [MoFaNeRF: Morphable Facial Neural Radiance Field](https://mlsanity.com/paper/2112.02308/) (2021)
- [MarioNETte: Few-shot Face Reenactment Preserving Identity of Unseen Targets](https://mlsanity.com/paper/1911.08139/) (2019)
- [Efficient Region-Aware Neural Radiance Fields for High-Fidelity Talking Portrait Synthesis](https://mlsanity.com/paper/2307.09323/) (2023)
- [One-Shot High-Fidelity Talking-Head Synthesis with Deformable Neural Radiance Field](https://mlsanity.com/paper/2304.05097/) (2023)
- [OTAvatar: One-shot Talking Face Avatar with Controllable Tri-plane Rendering](https://mlsanity.com/paper/2303.14662/) (2023)
- [Soft-Gated Warping-GAN for Pose-Guided Person Image Synthesis](https://mlsanity.com/paper/1810.11610/) (2018)

## Built on by (most cited first, 12 of 12)

- [Generalizable and Animatable Gaussian Head Avatar](https://mlsanity.com/paper/2410.07971/) (2024)
- [Deepfake Generation and Detection: A Benchmark and Survey](https://mlsanity.com/paper/2403.17881/) (2024)
- [FastAvatar: Instant 3D Gaussian Splatting for Faces from Single Unconstrained Poses](https://mlsanity.com/paper/2508.18389/) (2025)
- [Textured 3D Regenerative Morphing with 3D Diffusion Prior](https://mlsanity.com/paper/2502.14316/) (2025)
- [Hiding Faces in Plain Sight: Defending DeepFakes by Disrupting Face Detection](https://mlsanity.com/paper/2412.01101/) (2024)
- [Towards Geometry-Grounded Dense Semantic Matching with VGGT Priors](https://mlsanity.com/paper/2509.21263/) (2025)
- [Beyond Inserting: Learning Identity Embedding for Semantic-Fidelity Personalized Diffusion Generation](https://mlsanity.com/paper/2402.00631/) (2024)
- [OMG-Avatar: One-shot Multi-LOD Gaussian Head Avatar](https://mlsanity.com/paper/2603.01506/) (2026)
- [Counterfactual Explanations for Face Forgery Detection via Adversarial Removal of Artifacts](https://mlsanity.com/paper/2404.08341/) (2024)
- [3DFlowRenderer: One-shot Face Re-enactment via Dense 3D Facial Flow Estimation](https://mlsanity.com/paper/2404.14667/) (2024)
- [OMEGA-Avatar: One-shot Modeling of 360deg Gaussian Avatars](https://mlsanity.com/paper/2602.11693/) (2026)
- [Splatshot: 3D Face Avatar Generation from a Single Unconstrained Photo](https://mlsanity.com/paper/2606.01493/) (2026)

## Abstract (arXiv)

Face reenactment is challenging due to the need to establish dense correspondence between various face representations for motion transfer. Recent studies have utilized Neural Radiance Field (NeRF) as fundamental representation, which further enhanced the performance of multi-view face reenactment in photo-realism and 3D consistency. However, establishing dense correspondence between different face NeRFs is non-trivial, because implicit representations lack ground-truth correspondence annotations like mesh-based 3D parametric models (e.g., 3DMM) with index-aligned vertexes. Although aligning 3DMM space with NeRF-based face representations can realize motion control, it is sub-optimal for their limited face-only modeling and low identity fidelity. Therefore, we are inspired to ask: Can we learn the dense correspondence between different NeRF-based face representations without a 3D parametric model prior? To address this challenge, we propose a novel framework, which adopts tri-planes as fundamental NeRF representation and decomposes face tri-planes into three components: canonical tri-planes, identity deformations, and motion. In terms of motion control, our key contribution is proposing a Plane Dictionary (PlaneDict) module, which efficiently maps the motion conditions to a linear weighted addition of learnable orthogonal plane bases. To the best of our knowledge, our framework is the first method that achieves one-shot multi-view face reenactment without a 3D parametric model prior. Extensive experiments demonstrate that we produce better results in fine-grained motion control and identity preservation than previous methods.