# Generative Fields: Uncovering Hierarchical Feature Control for StyleGAN via Inverted Receptive Fields

arXiv: https://arxiv.org/abs/2504.17712 · HTML: https://mlsanity.com/paper/2504.17712/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 26 of its 41 references that are in the map.
- First posted on arXiv 24 Apr 2025.

## Builds on (most cited first, 26 of 26)

- [A Style-Based Generator Architecture for Generative Adversarial Networks](https://mlsanity.com/paper/1812.04948/) (2018)
- [Analyzing and Improving the Image Quality of StyleGAN](https://mlsanity.com/paper/1912.04958/) (2019)
- [Fast R-CNN](https://mlsanity.com/paper/1504.08083/) (2015)
- [YOLOv3: An Incremental Improvement](https://mlsanity.com/paper/1804.02767/) (2018)
- [Visualizing and Understanding Convolutional Networks](https://mlsanity.com/paper/1311.2901/) (2013)
- [Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks](https://mlsanity.com/paper/1511.06434/) (2015)
- [Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization](https://mlsanity.com/paper/1703.06868/) (2017)
- [Normalizing Flows for Probabilistic Modeling and Inference](https://mlsanity.com/paper/1912.02762/) (2019)
- [Training Generative Adversarial Networks with Limited Data](https://mlsanity.com/paper/2006.06676/) (2020)
- [Multi-Scale Context Aggregation by Dilated Convolutions](https://mlsanity.com/paper/1511.07122/) (2015)
- [Conditional Image Generation with PixelCNN Decoders](https://mlsanity.com/paper/1606.05328/) (2016)
- [InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets](https://mlsanity.com/paper/1606.03657/) (2016)
- [StackGAN: Text to Photo-realistic Image Synthesis with Stacked Generative Adversarial Networks](https://mlsanity.com/paper/1612.03242/) (2016)
- [Towards Principled Methods for Training Generative Adversarial Networks](https://mlsanity.com/paper/1701.04862/) (2017)
- [StyleSpace Analysis: Disentangled Controls for StyleGAN Image Generation](https://mlsanity.com/paper/2011.12799/) (2020)
- [On the "steerability" of generative adversarial networks](https://mlsanity.com/paper/1907.07171/) (2019)
- [Disentangled and Controllable Face Image Generation via 3D Imitative-Contrastive Learning](https://mlsanity.com/paper/2004.11660/) (2020)
- [Controllable Text-to-Image Generation](https://mlsanity.com/paper/1909.07083/) (2019)
- [Face Alignment in Full Pose Range: A 3D Total Solution](https://mlsanity.com/paper/1804.01005/) (2018)
- [S3FD: Single Shot Scale-invariant Face Detector](https://mlsanity.com/paper/1708.05237/) (2017)
- [FaceBoxes: A CPU Real-time Face Detector with High Accuracy](https://mlsanity.com/paper/1708.05234/) (2017)
- [EigenGAN: Layer-Wise Eigen-Learning for GANs](https://mlsanity.com/paper/2104.12476/) (2021)
- [Demystifying Inter-Class Disentanglement](https://mlsanity.com/paper/1906.11796/) (2019)
- [A Spectral Regularizer for Unsupervised Disentanglement](https://mlsanity.com/paper/1812.01161/) (2018)
- [What are the Receptive, Effective Receptive, and Projective Fields of Neurons in Convolutional Neural Networks?](https://mlsanity.com/paper/1705.07049/) (2017)
- [On the Role of Receptive Field in Unsupervised Sim-to-Real Image Translation](https://mlsanity.com/paper/2001.09257/) (2020)

## Abstract (arXiv)

StyleGAN has demonstrated the ability of GANs to synthesize highly-realistic faces of imaginary people from random noise. One limitation of GAN-based image generation is the difficulty of controlling the features of the generated image, due to the strong entanglement of the low-dimensional latent space. Previous work that aimed to control StyleGAN with image or text prompts modulated sampling in W latent space, which is more expressive than Z latent space. However, W space still has restricted expressivity since it does not control the feature synthesis directly; also the feature embedding in W space requires a pre-training process to reconstruct the style signal, limiting its application. This paper introduces the concept of "generative fields" to explain the hierarchical feature synthesis in StyleGAN, inspired by the receptive fields of convolution neural networks (CNNs). Additionally, we propose a new image editing pipeline for StyleGAN using generative field theory and the channel-wise style latent space S, utilizing the intrinsic structural feature of CNNs to achieve disentangled control of feature synthesis at synthesis time.