# Towards Disentangling Latent Space for Unsupervised Semantic Face Editing

arXiv: https://arxiv.org/abs/2011.02638 · HTML: https://mlsanity.com/paper/2011.02638/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Nov 2020.

## Built on by (most cited first, 9 of 9)

- [A Review of the Role of Causality in Developing Trustworthy AI Systems](https://mlsanity.com/paper/2302.06975/) (2023)
- [IA-FaceS: A Bidirectional Method for Semantic Face Editing](https://mlsanity.com/paper/2203.13097/) (2022)
- [LoRA of Change: Learning to Generate LoRA for the Editing Instruction from A Single Before-After Image Pair](https://mlsanity.com/paper/2411.19156/) (2024)
- [GlassesGAN: Eyewear Personalization using Synthetic Appearance Discovery and Targeted Subspace Modeling](https://mlsanity.com/paper/2210.14145/) (2022)
- [LaTo: Landmark-tokenized Diffusion Transformer for Fine-grained Human Face Editing](https://mlsanity.com/paper/2509.25731/) (2025)
- [Explaining Image Classifiers Using Contrastive Counterfactuals in Generative Latent Spaces](https://mlsanity.com/paper/2206.05257/) (2022)
- [Disentangled Generation Network for Enlarged License Plate Recognition and A Unified Dataset](https://mlsanity.com/paper/2206.00859/) (2022)
- [Disentangling Genotype and Environment Specific Latent Features for Improved Trait Prediction using a Compositional Autoencoder](https://mlsanity.com/paper/2410.19922/) (2024)
- [U-Face: An Efficient and Generalizable Framework for Unsupervised Facial Attribute Editing via Subspace Learning](https://mlsanity.com/paper/2603.14004/) (2026)

## Abstract (arXiv)

Facial attributes in StyleGAN generated images are entangled in the latent space which makes it very difficult to independently control a specific attribute without affecting the others. Supervised attribute editing requires annotated training data which is difficult to obtain and limits the editable attributes to those with labels. Therefore, unsupervised attribute editing in an disentangled latent space is key to performing neat and versatile semantic face editing. In this paper, we present a new technique termed Structure-Texture Independent Architecture with Weight Decomposition and Orthogonal Regularization (STIA-WO) to disentangle the latent space for unsupervised semantic face editing. By applying STIA-WO to GAN, we have developed a StyleGAN termed STGAN-WO which performs weight decomposition through utilizing the style vector to construct a fully controllable weight matrix to regulate image synthesis, and employs orthogonal regularization to ensure each entry of the style vector only controls one independent feature matrix. To further disentangle the facial attributes, STGAN-WO introduces a structure-texture independent architecture which utilizes two independently and identically distributed (i.i.d.) latent vectors to control the synthesis of the texture and structure components in a disentangled way. Unsupervised semantic editing is achieved by moving the latent code in the coarse layers along its orthogonal directions to change texture related attributes or changing the latent code in the fine layers to manipulate structure related ones. We present experimental results which show that our new STGAN-WO can achieve better attribute editing than state of the art methods.