# DiffDub: Person-generic Visual Dubbing Using Inpainting Renderer with Diffusion Auto-encoder

arXiv: https://arxiv.org/abs/2311.01811 · HTML: https://mlsanity.com/paper/2311.01811/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 35 references that are in the map.
- First posted on arXiv 3 Nov 2023.

## Builds on (most cited first, 28 of 28)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [Diffusion Models Beat GANs on Image Synthesis](https://mlsanity.com/paper/2105.05233/) (2021)
- [HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units](https://mlsanity.com/paper/2106.07447/) (2021)
- [Conformer: Convolution-augmented Transformer for Speech Recognition](https://mlsanity.com/paper/2005.08100/) (2020)
- [Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context](https://mlsanity.com/paper/1901.02860/) (2019)
- [RePaint: Inpainting using Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2201.09865/) (2022)
- [Blended Diffusion for Text-driven Editing of Natural Images](https://mlsanity.com/paper/2111.14818/) (2021)
- [A Lip Sync Expert Is All You Need for Speech to Lip Generation In The Wild](https://mlsanity.com/paper/2008.10010/) (2020)
- [SUPERB: Speech processing Universal PERformance Benchmark](https://mlsanity.com/paper/2105.01051/) (2021)
- [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)
- [Diffusion Autoencoders: Toward a Meaningful and Decodable Representation](https://mlsanity.com/paper/2111.15640/) (2021)
- [MakeItTalk: Speaker-Aware Talking-Head Animation](https://mlsanity.com/paper/2004.12992/) (2020)
- [Pose-Controllable Talking Face Generation by Implicitly Modularized Audio-Visual Representation](https://mlsanity.com/paper/2104.11116/) (2021)
- [FaceFormer: Speech-Driven 3D Facial Animation with Transformers](https://mlsanity.com/paper/2112.05329/) (2021)
- [Diffused Heads: Diffusion Models Beat GANs on Talking-Face Generation](https://mlsanity.com/paper/2301.03396/) (2023)
- [DiffTalk: Crafting Diffusion Models for Generalized Audio-Driven Portraits Animation](https://mlsanity.com/paper/2301.03786/) (2023)
- [Seeing What You Said: Talking Face Generation Guided by a Lip Reading Expert](https://mlsanity.com/paper/2303.17480/) (2023)
- [Identity-Preserving Talking Face Generation with Landmark and Appearance Priors](https://mlsanity.com/paper/2305.08293/) (2023)
- [Towards Automatic Face-to-Face Translation](https://mlsanity.com/paper/2003.00418/) (2020)
- [DINet: Deformation Inpainting Network for Realistic Face Visually Dubbing on High Resolution Video](https://mlsanity.com/paper/2303.03988/) (2023)
- [DAE-Talker: High Fidelity Speech-Driven Talking Face Generation with Diffusion Autoencoder](https://mlsanity.com/paper/2303.17550/) (2023)
- [Speech Driven Video Editing via an Audio-Conditioned Diffusion Model](https://mlsanity.com/paper/2301.04474/) (2023)
- [Towards Realistic Visual Dubbing with Heterogeneous Sources](https://mlsanity.com/paper/2201.06260/) (2022)
- [Deep Learning for Visual Speech Analysis: A Survey](https://mlsanity.com/paper/2205.10839/) (2022)
- [Improving Few-Shot Learning for Talking Face System with TTS Data Augmentation](https://mlsanity.com/paper/2303.05322/) (2023)

## Built on by (most cited first, 10 of 10)

- [AniTalker: Animate Vivid and Diverse Talking Faces through Identity-Decoupled Facial Motion Encoding](https://mlsanity.com/paper/2405.03121/) (2024)
- [LatentSync: Taming Audio-Conditioned Latent Diffusion Models for Lip Sync with SyncNet Supervision](https://mlsanity.com/paper/2412.09262/) (2024)
- [KeySync: A Robust Approach for Leakage-free Lip Synchronization in High Resolution](https://mlsanity.com/paper/2505.00497/) (2025)
- [SyncAnyone: Implicit Disentanglement via Progressive Self-Correction for Lip-Syncing in the wild](https://mlsanity.com/paper/2512.21736/) (2025)
- [IM-Portrait: Learning 3D-aware Video Diffusion for Photorealistic Talking Heads from Monocular Videos](https://mlsanity.com/paper/2504.19165/) (2025)
- [Video Editing for Audio-Visual Dubbing](https://mlsanity.com/paper/2505.23406/) (2025)
- [TBDub: Production-Oriented Visual Dubbing](https://mlsanity.com/paper/2609.06144/) (2026)
- [Revisiting Diffusion Autoencoder Training for Image Reconstruction Quality](https://mlsanity.com/paper/2504.21368/) (2025)
- [StableDub: Taming Diffusion Prior for Generalized and Efficient Visual Dubbing](https://mlsanity.com/paper/2509.21887/) (2025)
- [FlashLips: 100-FPS Mask-Free Latent Lip-Sync using Reconstruction Instead of Diffusion or GANs](https://mlsanity.com/paper/2512.20033/) (2025)

## Abstract (arXiv)

Generating high-quality and person-generic visual dubbing remains a challenge. Recent innovation has seen the advent of a two-stage paradigm, decoupling the rendering and lip synchronization process facilitated by intermediate representation as a conduit. Still, previous methodologies rely on rough landmarks or are confined to a single speaker, thus limiting their performance. In this paper, we propose DiffDub: Diffusion-based dubbing. We first craft the Diffusion auto-encoder by an inpainting renderer incorporating a mask to delineate editable zones and unaltered regions. This allows for seamless filling of the lower-face region while preserving the remaining parts. Throughout our experiments, we encountered several challenges. Primarily, the semantic encoder lacks robustness, constricting its ability to capture high-level features. Besides, the modeling ignored facial positioning, causing mouth or nose jitters across frames. To tackle these issues, we employ versatile strategies, including data augmentation and supplementary eye guidance. Moreover, we encapsulated a conformer-based reference encoder and motion generator fortified by a cross-attention mechanism. This enables our model to learn person-specific textures with varying references and reduces reliance on paired audio-visual data. Our rigorous experiments comprehensively highlight that our ground-breaking approach outpaces existing methods with considerable margins and delivers seamless, intelligible videos in person-generic and multilingual scenarios.