# LinkGAN: Linking GAN Latents to Pixels for Controllable Image Synthesis

arXiv: https://arxiv.org/abs/2301.04604 · HTML: https://mlsanity.com/paper/2301.04604/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- Builds on 63 of its 69 references that are in the map.
- First posted on arXiv 11 Jan 2023.

## Builds on (most cited first, 30 of 63)

- [A Style-Based Generator Architecture for Generative Adversarial Networks](https://mlsanity.com/paper/1812.04948/) (2018)
- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [Zero-Shot Text-to-Image Generation](https://mlsanity.com/paper/2102.12092/) (2021)
- [Analyzing and Improving the Image Quality of StyleGAN](https://mlsanity.com/paper/1912.04958/) (2019)
- [Taming Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2012.09841/) (2020)
- [Large Scale GAN Training for High Fidelity Natural Image Synthesis](https://mlsanity.com/paper/1809.11096/) (2018)
- [Improved Training of Wasserstein GANs](https://mlsanity.com/paper/1704.00028/) (2017)
- [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)
- [Spectral Normalization for Generative Adversarial Networks](https://mlsanity.com/paper/1802.05957/) (2018)
- [LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loop](https://mlsanity.com/paper/1506.03365/) (2015)
- [Semantic Image Synthesis with Spatially-Adaptive Normalization](https://mlsanity.com/paper/1903.07291/) (2019)
- [Efficient Geometry-aware 3D Generative Adversarial Networks](https://mlsanity.com/paper/2112.07945/) (2021)
- [Alias-Free Generative Adversarial Networks](https://mlsanity.com/paper/2106.12423/) (2021)
- [High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs](https://mlsanity.com/paper/1711.11585/) (2017)
- [StarGAN v2: Diverse Image Synthesis for Multiple Domains](https://mlsanity.com/paper/1912.01865/) (2019)
- [Semantic Understanding of Scenes through the ADE20K Dataset](https://mlsanity.com/paper/1608.05442/) (2016)
- [StarGAN: Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translation](https://mlsanity.com/paper/1711.09020/) (2017)
- [StyleCLIP: Text-Driven Manipulation of StyleGAN Imagery](https://mlsanity.com/paper/2103.17249/) (2021)
- [GIRAFFE: Representing Scenes as Compositional Generative Neural Feature Fields](https://mlsanity.com/paper/2011.12100/) (2020)
- [Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks](https://mlsanity.com/paper/1703.10593/) (2017)
- [Which Training Methods for GANs do actually Converge?](https://mlsanity.com/paper/1801.04406/) (2018)
- [GANSpace: Discovering Interpretable GAN Controls](https://mlsanity.com/paper/2004.02546/) (2020)
- [Closed-Form Factorization of Latent Semantics in GANs](https://mlsanity.com/paper/2007.06600/) (2020)
- [InterFaceGAN: Interpreting the Disentangled Face Representation Learned by GANs](https://mlsanity.com/paper/2005.09635/) (2020)
- [Generative Visual Manipulation on the Natural Image Manifold](https://mlsanity.com/paper/1609.03552/) (2016)
- [StyleSpace Analysis: Disentangled Controls for StyleGAN Image Generation](https://mlsanity.com/paper/2011.12799/) (2020)
- [Unsupervised Discovery of Interpretable Directions in the GAN Latent Space](https://mlsanity.com/paper/2002.03754/) (2020)
- [DatasetGAN: Efficient Labeled Data Factory with Minimal Human Effort](https://mlsanity.com/paper/2104.06490/) (2021)
- [On the "steerability" of generative adversarial networks](https://mlsanity.com/paper/1907.07171/) (2019)

## Built on by (most cited first, 15 of 15)

- [DragDiffusion: Harnessing Diffusion Models for Interactive Point-based Image Editing](https://mlsanity.com/paper/2306.14435/) (2023)
- [Drag Your GAN: Interactive Point-based Manipulation on the Generative Image Manifold](https://mlsanity.com/paper/2305.10973/) (2023)
- [Control3Diff: Learning Controllable 3D Diffusion Models from Single-view Images](https://mlsanity.com/paper/2304.06700/) (2023)
- [LightningDrag: Lightning Fast and Accurate Drag-based Image Editing Emerging from Videos](https://mlsanity.com/paper/2405.13722/) (2024)
- [Learning 3D-aware Image Synthesis with Unknown Pose Distribution](https://mlsanity.com/paper/2301.07702/) (2023)
- [GeneAvatar: Generic Expression-Aware Volumetric Head Avatar Editing from a Single Image](https://mlsanity.com/paper/2404.02152/) (2024)
- [Generative Artificial Intelligence Meets Synthetic Aperture Radar: A Survey](https://mlsanity.com/paper/2411.05027/) (2024)
- [SMaRt: Improving GANs with Score Matching Regularity](https://mlsanity.com/paper/2311.18208/) (2023)
- [DA-HFNet: Progressive Fine-Grained Forgery Image Detection and Localization Based on Dual Attention](https://mlsanity.com/paper/2406.01489/) (2024)
- [Diverse and Lifespan Facial Age Transformation Synthesis with Identity Variation Rationality Metric](https://mlsanity.com/paper/2401.14036/) (2024)
- [Revealing Directions for Text-guided 3D Face Editing](https://mlsanity.com/paper/2410.04965/) (2024)
- [Learning Modulated Transformation in GANs](https://mlsanity.com/paper/2308.15472/) (2023)
- [Survey on Controlable Image Synthesis with Deep Learning](https://mlsanity.com/paper/2307.10275/) (2023)
- [Multi-task SAR Image Processing via GAN-based Unsupervised Manipulation](https://mlsanity.com/paper/2408.01553/) (2024)
- [UCD: Unconditional Discriminator Promotes Nash Equilibrium in GANs](https://mlsanity.com/paper/2510.00624/) (2025)

## Abstract (arXiv)

This work presents an easy-to-use regularizer for GAN training, which helps explicitly link some axes of the latent space to a set of pixels in the synthesized image. Establishing such a connection facilitates a more convenient local control of GAN generation, where users can alter the image content only within a spatial area simply by partially resampling the latent code. Experimental results confirm four appealing properties of our regularizer, which we call LinkGAN. (1) The latent-pixel linkage is applicable to either a fixed region (textiti.e., same for all instances) or a particular semantic category (i.e., varying across instances), like the sky. (2) Two or multiple regions can be independently linked to different latent axes, which further supports joint control. (3) Our regularizer can improve the spatial controllability of both 2D and 3D-aware GAN models, barely sacrificing the synthesis performance. (4) The models trained with our regularizer are compatible with GAN inversion techniques and maintain editability on real images.