# DirectSwap: Paired, Mask-Free Video Head Swapping with Full-Reference Evaluation

arXiv: https://arxiv.org/abs/2512.09417 · HTML: https://mlsanity.com/paper/2512.09417/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 29 of its 48 references that are in the map.
- First posted on arXiv 10 Dec 2025.

## Builds on (most cited first, 29 of 29)

- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Wan: Open and Advanced Large-Scale Video Generative Models](https://mlsanity.com/paper/2503.20314/) (2025)
- [IP-Adapter: Text Compatible Image Prompt Adapter for Text-to-Image Diffusion Models](https://mlsanity.com/paper/2308.06721/) (2023)
- [FaceForensics++: Learning to Detect Manipulated Facial Images](https://mlsanity.com/paper/1901.08971/) (2019)
- [First Order Motion Model for Image Animation](https://mlsanity.com/paper/2003.00196/) (2020)
- [DiffEdit: Diffusion-based semantic image editing with mask guidance](https://mlsanity.com/paper/2210.11427/) (2022)
- [MediaPipe: A Framework for Building Perception Pipelines](https://mlsanity.com/paper/1906.08172/) (2019)
- [VACE: All-in-One Video Creation and Editing](https://mlsanity.com/paper/2503.07598/) (2025)
- [AdaFace: Quality Adaptive Margin for Face Recognition](https://mlsanity.com/paper/2204.00964/) (2022)
- [SimSwap: An Efficient Framework For High Fidelity Face Swapping](https://mlsanity.com/paper/2106.06340/) (2021)
- [LivePortrait: Efficient Portrait Animation with Stitching and Retargeting Control](https://mlsanity.com/paper/2407.03168/) (2024)
- [General Facial Representation Learning in a Visual-Linguistic Manner](https://mlsanity.com/paper/2112.03109/) (2021)
- [Self-Correction for Human Parsing](https://mlsanity.com/paper/1910.09777/) (2019)
- [VFHQ: A High-Quality Dataset and Benchmark for Video Face Super-Resolution](https://mlsanity.com/paper/2205.03409/) (2022)
- [DeepfakeBench: A Comprehensive Benchmark of Deepfake Detection](https://mlsanity.com/paper/2307.01426/) (2023)
- [DiffFace: Diffusion-based Face Swapping with Facial Guidance](https://mlsanity.com/paper/2212.13344/) (2022)
- [Fine-Grained Face Swapping via Regional GAN Inversion](https://mlsanity.com/paper/2211.14068/) (2022)
- [EMOPortraits: Emotion-enhanced Multimodal One-shot Head Avatars](https://mlsanity.com/paper/2404.19110/) (2024)
- [KV-Edit: Training-Free Image Editing for Precise Background Preservation](https://mlsanity.com/paper/2502.17363/) (2025)
- [Realistic and Efficient Face Swapping: A Unified Approach with Diffusion Models](https://mlsanity.com/paper/2409.07269/) (2024)
- [Few-Shot Head Swapping in the Wild](https://mlsanity.com/paper/2204.13100/) (2022)
- [Towards Efficient Diffusion-Based Image Editing with Instant Attention Masks](https://mlsanity.com/paper/2401.07709/) (2024)
- [HS-Diffusion: Semantic-Mixing Diffusion for Head Swapping](https://mlsanity.com/paper/2212.06458/) (2022)
- [DreamID: High-Fidelity and Fast diffusion-based Face Swapping via Triplet ID Group Learning](https://mlsanity.com/paper/2504.14509/) (2025)
- [ReliableSwap: Boosting General Face Swapping Via Reliable Supervision](https://mlsanity.com/paper/2306.05356/) (2023)
- [GHOST 2.0: generative high-fidelity one shot transfer of heads](https://mlsanity.com/paper/2502.18417/) (2025)
- [Zero-Shot Head Swapping in Real-World Scenarios](https://mlsanity.com/paper/2503.00861/) (2025)
- [Controllable and Expressive One-Shot Video Head Swapping](https://mlsanity.com/paper/2506.16852/) (2025)
- [Preserving Source Video Realism: High-Fidelity Face Swapping for Cinematic Quality](https://mlsanity.com/paper/2512.07951/) (2025)

## Abstract (arXiv)

Head swapping replaces an entire head while preserving pose, expression, body motion, and scene. Progress is limited by the lack of cross-identity paired videos: real footage cannot provide different identities performing exactly the same motion, leaving the task without paired supervision or frame-aligned ground truth. Existing methods therefore rely on same-identity masked reconstruction, which restricts supervision to predefined editable regions. To address this, we introduce an identity-expression decoupled synthesis pipeline that constructs expression-synchronized cross-identity video pairs from real footage. Expression-bearing facial regions are retained under small clip-consistent geometric perturbations, while the surrounding head is regenerated with a new identity as synthesized swapping input. These pairs form a cross-identity benchmark with frame-aligned real-world video as ground-truth targets, enabling full-reference evaluation of identity, expression, pose, reconstruction fidelity, and temporal stability. This yields HeadSwapBench, the first cross-identity paired dataset for video head swapping, supporting both training (20,278 videos) and benchmarking (1,040 videos). With the cross-identity supervision enabled by this paired dataset, we propose DirectSwap, a mask-free video head swapping training paradigm. Under otherwise identical settings, this formulation outperforms head- and rectangle-masked same-identity reconstruction, particularly for bidirectional head-silhouette changes. At inference, driving-output divergence and emergent reference attention estimate the edit support, allowing unchanged non-head content to be restored from the driving video without external segmentation or additional training. On 1,040 clips from 104 unseen subjects, the resulting model demonstrates that the proposed paired supervision supports effective whole-head swapping.