# Spatially Controllable Image Synthesis with Internal Representation Collaging

arXiv: https://arxiv.org/abs/1811.10153 · HTML: https://mlsanity.com/paper/1811.10153/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Nov 2018.

## Built on by (most cited first, 23 of 23)

- [Alias-Free Generative Adversarial Networks](https://mlsanity.com/paper/2106.12423/) (2021)
- [Drag Your GAN: Interactive Point-based Manipulation on the Generative Image Manifold](https://mlsanity.com/paper/2305.10973/) (2023)
- [Exploiting Spatial Dimensions of Latent in GAN for Real-time Image Editing](https://mlsanity.com/paper/2104.14754/) (2021)
- [Repurposing GANs for One-shot Semantic Part Segmentation](https://mlsanity.com/paper/2103.04379/) (2021)
- [Using latent space regression to analyze and leverage compositionality in GANs](https://mlsanity.com/paper/2103.10426/) (2021)
- [Low-Rank Subspaces in GANs](https://mlsanity.com/paper/2106.04488/) (2021)
- [Spatially-Adaptive Multilayer Selection for GAN Inversion and Editing](https://mlsanity.com/paper/2206.08357/) (2022)
- [Linear Semantics in Generative Adversarial Networks](https://mlsanity.com/paper/2104.00487/) (2021)
- [Region-Based Semantic Factorization in GANs](https://mlsanity.com/paper/2202.09649/) (2022)
- [PandA: Unsupervised Learning of Parts and Appearances in the Feature Maps of GANs](https://mlsanity.com/paper/2206.00048/) (2022)
- [Retrieve in Style: Unsupervised Facial Feature Transfer and Retrieval](https://mlsanity.com/paper/2107.06256/) (2021)
- [LinkGAN: Linking GAN Latents to Pixels for Controllable Image Synthesis](https://mlsanity.com/paper/2301.04604/) (2023)
- [StyleGAN of All Trades: Image Manipulation with Only Pretrained StyleGAN](https://mlsanity.com/paper/2111.01619/) (2021)
- [3D-aware Blending with Generative NeRFs](https://mlsanity.com/paper/2302.06608/) (2023)
- [Exploring Sparse MoE in GANs for Text-conditioned Image Synthesis](https://mlsanity.com/paper/2309.03904/) (2023)
- [2D GANs Meet Unsupervised Single-view 3D Reconstruction](https://mlsanity.com/paper/2207.10183/) (2022)
- [Decorating Your Own Bedroom: Locally Controlling Image Generation with Generative Adversarial Networks](https://mlsanity.com/paper/2105.08222/) (2021)
- [MixSyn: Learning Composition and Style for Multi-Source Image Synthesis](https://mlsanity.com/paper/2111.12705/) (2021)
- [Perceptually Validated Precise Local Editing for Facial Action Units with StyleGAN](https://mlsanity.com/paper/2107.12143/) (2021)
- [A Survey on Leveraging Pre-trained Generative Adversarial Networks for Image Editing and Restoration](https://mlsanity.com/paper/2207.10309/) (2022)
- [Unsupervised Discovery of Semantic Concepts in Satellite Imagery with Style-based Wavelet-driven Generative Models](https://mlsanity.com/paper/2208.02089/) (2022)
- [Discovering Class-Specific GAN Controls for Semantic Image Synthesis](https://mlsanity.com/paper/2212.01455/) (2022)
- [Grasping the Arrow of Time from the Singularity: Decoding Micromotion in Low-dimensional Latent Spaces from StyleGAN](https://mlsanity.com/paper/2204.12696/) (2022)

## Abstract (arXiv)

We present a novel CNN-based image editing strategy that allows the user to change the semantic information of an image over an arbitrary region by manipulating the feature-space representation of the image in a trained GAN model. We will present two variants of our strategy: (1) spatial conditional batch normalization (sCBN), a type of conditional batch normalization with user-specifiable spatial weight maps, and (2) feature-blending, a method of directly modifying the intermediate features. Our methods can be used to edit both artificial image and real image, and they both can be used together with any GAN with conditional normalization layers. We will demonstrate the power of our method through experiments on various types of GANs trained on different datasets. Code will be available at https://github.com/pfnet-research/neural-collage.