# MoCha:End-to-End Video Character Replacement without Structural Guidance

arXiv: https://arxiv.org/abs/2601.08587 · HTML: https://mlsanity.com/paper/2601.08587/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 32 references that are in the map.
- First posted on arXiv 13 Jan 2026.

## Builds on (most cited first, 25 of 25)

- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (2022)
- [Flow Matching for Generative Modeling](https://mlsanity.com/paper/2210.02747/) (2022)
- [RoFormer: Enhanced Transformer with Rotary Position Embedding](https://mlsanity.com/paper/2104.09864/) (2021)
- [Scaling Rectified Flow Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2403.03206/) (2024)
- [SAM 2: Segment Anything in Images and Videos](https://mlsanity.com/paper/2408.00714/) (2024)
- [VBench: Comprehensive Benchmark Suite for Video Generative Models](https://mlsanity.com/paper/2311.17982/) (2023)
- [HunyuanVideo: A Systematic Framework For Large Video Generative Models](https://mlsanity.com/paper/2412.03603/) (2024)
- [Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data](https://mlsanity.com/paper/2401.10891/) (2024)
- [FLUX.1 Kontext: Flow Matching for In-Context Image Generation and Editing in Latent Space](https://mlsanity.com/paper/2506.15742/) (2025)
- [VACE: All-in-One Video Creation and Editing](https://mlsanity.com/paper/2503.07598/) (2025)
- [YOLOv12: Attention-Centric Real-Time Object Detectors](https://mlsanity.com/paper/2502.12524/) (2025)
- [Aligning Text-to-Image Diffusion Models with Reward Backpropagation](https://mlsanity.com/paper/2310.03739/) (2023)
- [ReCamMaster: Camera-Controlled Generative Rendering from A Single Video](https://mlsanity.com/paper/2503.11647/) (2025)
- [Video models are zero-shot learners and reasoners](https://mlsanity.com/paper/2509.20328/) (2025)
- [LivePortrait: Efficient Portrait Animation with Stitching and Retargeting Control](https://mlsanity.com/paper/2407.03168/) (2024)
- [HunyuanCustom: A Multimodal-Driven Architecture for Customized Video Generation](https://mlsanity.com/paper/2505.04512/) (2025)
- [Aesthetic Post-Training Diffusion Models from Generic Preferences with Step-by-step Preference Optimization](https://mlsanity.com/paper/2406.04314/) (2024)
- [VideoPainter: Any-length Video Inpainting and Editing with Plug-and-Play Context Control](https://mlsanity.com/paper/2503.05639/) (2025)
- [Wan-Animate: Unified Character Animation and Replacement with Holistic Replication](https://mlsanity.com/paper/2509.14055/) (2025)
- [FullDiT: Multi-Task Video Generative Foundation Model with Full Attention](https://mlsanity.com/paper/2503.19907/) (2025)
- [Directly Aligning the Full Diffusion Trajectory with Fine-Grained Human Preference](https://mlsanity.com/paper/2509.06942/) (2025)
- [VIVID-10M: A Dataset and Baseline for Versatile and Interactive Video Local Editing](https://mlsanity.com/paper/2411.15260/) (2024)
- [FullDiT2: Efficient In-Context Conditioning for Video Diffusion Transformers](https://mlsanity.com/paper/2506.04213/) (2025)
- [VFXMaster: Unlocking Dynamic Visual Effect Generation via In-Context Learning](https://mlsanity.com/paper/2510.25772/) (2025)

## Built on by (most cited first, 6 of 6)

- [DreamID-Omni: Unified Framework for Controllable Human-Centric Audio-Video Generation](https://mlsanity.com/paper/2602.12160/) (2026)
- [SCAIL-2: Unifying Controlled Character Animation with End-to-End In-Context Conditioning](https://mlsanity.com/paper/2606.10804/) (2026)
- [Soap2Soap: Long Cinematic Video Remaking via Multi-Agent Collaboration](https://mlsanity.com/paper/2605.17423/) (2026)
- [Cinematic Compositing Using Character-Environment-Harmonized Video Generation Models](https://mlsanity.com/paper/2606.20233/) (2026)
- [Vorch-IR: Long-Form Unified Multimodal Identity Replacement Video Generation](https://mlsanity.com/paper/2608.05648/) (2026)
- [UniSwap: Streaming Audio-Visual Identity Swapping for Talking Videos](https://mlsanity.com/paper/2608.11752/) (2026)

## Abstract (arXiv)

Controllable video character replacement with a user-provided identity remains a challenging problem due to the lack of paired video data. Prior works have predominantly relied on a reconstruction-based paradigm that requires per-frame segmentation masks and explicit structural guidance (e.g., skeleton, depth). This reliance, however, severely limits their generalizability in complex scenarios involving occlusions, character-object interactions, unusual poses, or challenging illumination, often leading to visual artifacts and temporal inconsistencies. In this paper, we propose MoCha, a pioneering framework that bypasses these limitations by requiring only a single arbitrary frame mask. To effectively adapt the multi-modal input condition and enhance facial identity, we introduce a condition-aware RoPE and employ an RL-based post-training stage. Furthermore, to overcome the scarcity of qualified paired-training data, we propose a comprehensive data construction pipeline. Specifically, we design three specialized datasets: a high-fidelity rendered dataset built with Unreal Engine 5 (UE5), an expression-driven dataset synthesized by current portrait animation techniques, and an augmented dataset derived from existing video-mask pairs. Extensive experiments demonstrate that our method substantially outperforms existing state-of-the-art approaches. We will release the code to facilitate further research. Please refer to our project page for more details: orange-3dv-team.github.io/MoCha