# Deep Identity-aware Transfer of Facial Attributes

arXiv: https://arxiv.org/abs/1610.05586 · HTML: https://mlsanity.com/paper/1610.05586/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Oct 2016.

## Built on by (most cited first, 13 of 13)

- [Seeing What You Said: Talking Face Generation Guided by a Lip Reading Expert](https://mlsanity.com/paper/2303.17480/) (2023)
- [A Complete Survey on Generative AI (AIGC): Is ChatGPT from GPT-4 to GPT-5 All You Need?](https://mlsanity.com/paper/2303.11717/) (2023)
- [CMUA-Watermark: A Cross-Model Universal Adversarial Watermark for Combating Deepfakes](https://mlsanity.com/paper/2105.10872/) (2021)
- [GAN-based Facial Attribute Manipulation](https://mlsanity.com/paper/2210.12683/) (2022)
- [EvoGAN: An Evolutionary Computation Assisted GAN](https://mlsanity.com/paper/2110.11583/) (2021)
- [FakeChain: Exposing Shallow Cues in Multi-Step Deepfake Detection](https://mlsanity.com/paper/2509.16602/) (2025)
- [Perceptually Validated Precise Local Editing for Facial Action Units with StyleGAN](https://mlsanity.com/paper/2107.12143/) (2021)
- [Face Age Progression With Attribute Manipulation](https://mlsanity.com/paper/2106.07696/) (2021)
- [Real, fake and synthetic faces -- does the coin have three sides?](https://mlsanity.com/paper/2404.01878/) (2024)
- [Generative Face Parsing Map Guided 3D Face Reconstruction Under Occluded Scenes](https://mlsanity.com/paper/2412.18920/) (2024)
- [RaceGAN: A Framework for Preserving Individuality while Converting Racial Information for Image-to-Image Translation](https://mlsanity.com/paper/2509.15391/) (2025)
- [LatRef-Diff: Latent and Reference-Guided Diffusion for Facial Attribute Editing and Style Manipulation](https://mlsanity.com/paper/2604.21279/) (2026)
- [AttDiff-GAN: A Hybrid Diffusion-GAN Framework for Facial Attribute Editing](https://mlsanity.com/paper/2604.21289/) (2026)

## Abstract (arXiv)

This paper presents a Deep convolutional network model for Identity-Aware Transfer (DIAT) of facial attributes. Given the source input image and the reference attribute, DIAT aims to generate a facial image that owns the reference attribute as well as keeps the same or similar identity to the input image. In general, our model consists of a mask network and an attribute transform network which work in synergy to generate a photo-realistic facial image with the reference attribute. Considering that the reference attribute may be only related to some parts of the image, the mask network is introduced to avoid the incorrect editing on attribute irrelevant region. Then the estimated mask is adopted to combine the input and transformed image for producing the transfer result. For joint training of transform network and mask network, we incorporate the adversarial attribute loss, identity-aware adaptive perceptual loss, and VGG-FACE based identity loss. Furthermore, a denoising network is presented to serve for perceptual regularization to suppress the artifacts in transfer result, while an attribute ratio regularization is introduced to constrain the size of attribute relevant region. Our DIAT can provide a unified solution for several representative facial attribute transfer tasks, e.g., expression transfer, accessory removal, age progression, and gender transfer, and can be extended for other face enhancement tasks such as face hallucination. The experimental results validate the effectiveness of the proposed method. Even for the identity-related attribute (e.g., gender), our DIAT can obtain visually impressive results by changing the attribute while retaining most identity-aware features.