# TBDub: Production-Oriented Visual Dubbing

arXiv: https://arxiv.org/abs/2609.06144 · HTML: https://mlsanity.com/paper/2609.06144/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 30 references that are in the map.
- First posted on arXiv 5 Sep 2026.

## Builds on (most cited first, 21 of 21)

- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Flow Matching for Generative Modeling](https://mlsanity.com/paper/2210.02747/) (2022)
- [wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations](https://mlsanity.com/paper/2006.11477/) (2020)
- [Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow](https://mlsanity.com/paper/2209.03003/) (2022)
- [HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units](https://mlsanity.com/paper/2106.07447/) (2021)
- [One-step Diffusion with Distribution Matching Distillation](https://mlsanity.com/paper/2311.18828/) (2023)
- [Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inference](https://mlsanity.com/paper/2310.04378/) (2023)
- [On Distillation of Guided Diffusion Models](https://mlsanity.com/paper/2210.03142/) (2022)
- [Improved Distribution Matching Distillation for Fast Image Synthesis](https://mlsanity.com/paper/2405.14867/) (2024)
- [A Lip Sync Expert Is All You Need for Speech to Lip Generation In The Wild](https://mlsanity.com/paper/2008.10010/) (2020)
- [Effective Whole-body Pose Estimation with Two-stages Distillation](https://mlsanity.com/paper/2307.15880/) (2023)
- [VideoReTalking: Audio-based Lip Synchronization for Talking Head Video Editing In the Wild](https://mlsanity.com/paper/2211.14758/) (2022)
- [Identity-Preserving Talking Face Generation with Landmark and Appearance Priors](https://mlsanity.com/paper/2305.08293/) (2023)
- [DINet: Deformation Inpainting Network for Realistic Face Visually Dubbing on High Resolution Video](https://mlsanity.com/paper/2303.03988/) (2023)
- [Motion Consistency Model: Accelerating Video Diffusion with Disentangled Motion-Appearance Distillation](https://mlsanity.com/paper/2406.06890/) (2024)
- [Audio-Visual Speech Representation Expert for Enhanced Talking Face Video Generation and Evaluation](https://mlsanity.com/paper/2405.04327/) (2024)
- [Accelerating Video Diffusion Models via Distribution Matching](https://mlsanity.com/paper/2412.05899/) (2024)
- [KeySync: A Robust Approach for Leakage-free Lip Synchronization in High Resolution](https://mlsanity.com/paper/2505.00497/) (2025)
- [DiffDub: Person-generic Visual Dubbing Using Inpainting Renderer with Diffusion Auto-encoder](https://mlsanity.com/paper/2311.01811/) (2023)
- [From Inpainting to Editing: Unlocking Robust Mask-Free Visual Dubbing via Generative Bootstrapping](https://mlsanity.com/paper/2512.25066/) (2025)
- [Lip Forcing: Few-Step Autoregressive Diffusion for Real-time Lip Synchronization](https://mlsanity.com/paper/2606.11180/) (2026)

## Built on by (most cited first, 1 of 1)

- [Beyond Lip Sync: Reference-Grounded Oral Refinement for Audio-Driven Portrait Animation](https://mlsanity.com/paper/2609.38019/) (2026)

## Abstract (arXiv)

Visual dubbing must synchronize mouth motion with replacement speech while preserving identity, appearance, and temporal consistency. Although X-Dub provides a strong mask-free video-editing baseline, its application to livestream and generated-video content reveals limitations in production-domain robustness, temporal and motion stability, identity and oral-detail preservation, and inference efficiency. We present TBDub, a production-oriented extension of X-Dub that combines task-adaptive post-training with task-aware few-step distillation. Post-training adapts the video DiT using production-domain data, production-specific conditioning and filtering, and enhanced audio features to obtain a 30-step Teacher. Distillation adapts DMD/DMD2 to conditional video editing and compresses the Teacher into a two-step Student. On 38 TalkVid clips, the Teacher improves all eight reported reconstruction, perceptual, identity, and synchronization metrics over X-Dub. In the MOS evaluation, it improves lip-sync consistency, identity consistency, and visual quality over X-Dub by 0.14, 0.95, and 0.90 points, while the Student achieves the highest lip-sync and visual-quality scores and remains close to the Teacher in identity consistency. In paired end-to-end generation timing from the first VAE encode through the final VAE decode on a single NVIDIA H20 GPU at 512×512, the Student reaches 7.13 effective FPS and reduces total latency by 13.93×; the DiT stage alone is accelerated by 42.49×. The Student largely retains the Teacher's generation quality and audiovisual synchronization. The code is available on GitHub at https://github.com/TaoLiveAIGC/TBDub, and the 30-step Teacher and two-step Student weights are available on Hugging Face at https://huggingface.co/TaoLiveAIGC/TBDub.