# Disentangled Image Generation Through Structured Noise Injection

arXiv: https://arxiv.org/abs/2004.12411 · HTML: https://mlsanity.com/paper/2004.12411/

## Key facts

- Cited by 39 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Apr 2020.

## Built on by (most cited first, 30 of 39)

- [EditGAN: High-Precision Semantic Image Editing](https://mlsanity.com/paper/2111.03186/) (2021)
- [Exploiting Spatial Dimensions of Latent in GAN for Real-time Image Editing](https://mlsanity.com/paper/2104.14754/) (2021)
- [Third Time's the Charm? Image and Video Editing with StyleGAN3](https://mlsanity.com/paper/2201.13433/) (2022)
- [Pose with Style: Detail-Preserving Pose-Guided Image Synthesis with Conditional StyleGAN](https://mlsanity.com/paper/2109.06166/) (2021)
- [TransEditor: Transformer-Based Dual-Space GAN for Highly Controllable Facial Editing](https://mlsanity.com/paper/2203.17266/) (2022)
- [Diagonal Attention and Style-based GAN for Content-Style Disentanglement in Image Generation and Translation](https://mlsanity.com/paper/2103.16146/) (2021)
- [State-of-the-Art in the Architecture, Methods and Applications of StyleGAN](https://mlsanity.com/paper/2202.14020/) (2022)
- [TryOnGAN: Body-Aware Try-On via Layered Interpolation](https://mlsanity.com/paper/2101.02285/) (2021)
- [One-Shot Adaptation of GAN in Just One CLIP](https://mlsanity.com/paper/2203.09301/) (2022)
- [StyleFusion: A Generative Model for Disentangling Spatial Segments](https://mlsanity.com/paper/2107.07437/) (2021)
- [Going the Extra Mile in Face Image Quality Assessment: A Novel Database and Model](https://mlsanity.com/paper/2207.04904/) (2022)
- [DrawingInStyles: Portrait Image Generation and Editing with Spatially Conditioned StyleGAN](https://mlsanity.com/paper/2203.02762/) (2022)
- [CAD: Photorealistic 3D Generation via Adversarial Distillation](https://mlsanity.com/paper/2312.06663/) (2023)
- [CoordGAN: Self-Supervised Dense Correspondences Emerge from GANs](https://mlsanity.com/paper/2203.16521/) (2022)
- [3D-Aware Video Generation](https://mlsanity.com/paper/2206.14797/) (2022)
- [Feature-Style Encoder for Style-Based GAN Inversion](https://mlsanity.com/paper/2202.02183/) (2022)
- [GAN-based Facial Attribute Manipulation](https://mlsanity.com/paper/2210.12683/) (2022)
- [PASTA: Controllable Part-Aware Shape Generation with Autoregressive Transformers](https://mlsanity.com/paper/2407.13677/) (2024)
- [StyleGAN of All Trades: Image Manipulation with Only Pretrained StyleGAN](https://mlsanity.com/paper/2111.01619/) (2021)
- [Controllable cardiac synthesis via disentangled anatomy arithmetic](https://mlsanity.com/paper/2107.01748/) (2021)
- [IA-FaceS: A Bidirectional Method for Semantic Face Editing](https://mlsanity.com/paper/2203.13097/) (2022)
- [Retriever: Learning Content-Style Representation as a Token-Level Bipartite Graph](https://mlsanity.com/paper/2202.12307/) (2022)
- [DisCO: Portrait Distortion Correction with Perspective-Aware 3D GANs](https://mlsanity.com/paper/2302.12253/) (2023)
- [3D Generative Model Latent Disentanglement via Local Eigenprojection](https://mlsanity.com/paper/2302.12798/) (2023)
- [Learning at a Glance: Towards Interpretable Data-limited Continual Semantic Segmentation via Semantic-Invariance Modelling](https://mlsanity.com/paper/2407.15429/) (2024)
- [LatentKeypointGAN: Controlling Images via Latent Keypoints](https://mlsanity.com/paper/2103.15812/) (2021)
- [Controllable Data Augmentation Through Deep Relighting](https://mlsanity.com/paper/2110.13996/) (2021)
- [Restoring Images Captured in Arbitrary Hybrid Adverse Weather Conditions in One Go](https://mlsanity.com/paper/2305.09996/) (2023)
- [Semantic Image Synthesis with Unconditional Generator](https://mlsanity.com/paper/2402.14395/) (2024)
- [Mask-Guided Discovery of Semantic Manifolds in Generative Models](https://mlsanity.com/paper/2105.07273/) (2021)

## Abstract (arXiv)

We explore different design choices for injecting noise into generative adversarial networks (GANs) with the goal of disentangling the latent space. Instead of traditional approaches, we propose feeding multiple noise codes through separate fully-connected layers respectively. The aim is restricting the influence of each noise code to specific parts of the generated image. We show that disentanglement in the first layer of the generator network leads to disentanglement in the generated image. Through a grid-based structure, we achieve several aspects of disentanglement without complicating the network architecture and without requiring labels. We achieve spatial disentanglement, scale-space disentanglement, and disentanglement of the foreground object from the background style allowing fine-grained control over the generated images. Examples include changing facial expressions in face images, changing beak length in bird images, and changing car dimensions in car images. This empirically leads to better disentanglement scores than state-of-the-art methods on the FFHQ dataset.