# InfinityGAN: Towards Infinite-Pixel Image Synthesis

arXiv: https://arxiv.org/abs/2104.03963 · HTML: https://mlsanity.com/paper/2104.03963/

## Key facts

- Cited by 61 papers in the map (data through 14 Oct 2026).
- Builds on 41 of its 53 references that are in the map.
- First posted on arXiv 8 Apr 2021.

## Builds on (most cited first, 30 of 41)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [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)
- [Progressive Growing of GANs for Improved Quality, Stability, and Variation](https://mlsanity.com/paper/1710.10196/) (2017)
- [DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation](https://mlsanity.com/paper/1901.05103/) (2019)
- [Implicit Neural Representations with Periodic Activation Functions](https://mlsanity.com/paper/2006.09661/) (2020)
- [Improved Training of Wasserstein GANs](https://mlsanity.com/paper/1704.00028/) (2017)
- [Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domains](https://mlsanity.com/paper/2006.10739/) (2020)
- [Occupancy Networks: Learning 3D Reconstruction in Function Space](https://mlsanity.com/paper/1812.03828/) (2018)
- [Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization](https://mlsanity.com/paper/1703.06868/) (2017)
- [Generating Diverse High-Fidelity Images with VQ-VAE-2](https://mlsanity.com/paper/1906.00446/) (2019)
- [Pixel Recurrent Neural Networks](https://mlsanity.com/paper/1601.06759/) (2016)
- [GIRAFFE: Representing Scenes as Compositional Generative Neural Feature Fields](https://mlsanity.com/paper/2011.12100/) (2020)
- [pi-GAN: Periodic Implicit Generative Adversarial Networks for 3D-Aware Image Synthesis](https://mlsanity.com/paper/2012.00926/) (2020)
- [Which Training Methods for GANs do actually Converge?](https://mlsanity.com/paper/1801.04406/) (2018)
- [Free-Form Image Inpainting with Gated Convolution](https://mlsanity.com/paper/1806.03589/) (2018)
- [Conditional Image Synthesis With Auxiliary Classifier GANs](https://mlsanity.com/paper/1610.09585/) (2016)
- [Learning Continuous Image Representation with Local Implicit Image Function](https://mlsanity.com/paper/2012.09161/) (2020)
- [Image Inpainting for Irregular Holes Using Partial Convolutions](https://mlsanity.com/paper/1804.07723/) (2018)
- [Image2StyleGAN++: How to Edit the Embedded Images?](https://mlsanity.com/paper/1911.11544/) (2019)
- [SinGAN: Learning a Generative Model from a Single Natural Image](https://mlsanity.com/paper/1905.01164/) (2019)
- [An Intriguing Failing of Convolutional Neural Networks and the CoordConv Solution](https://mlsanity.com/paper/1807.03247/) (2018)
- [DRIT++: Diverse Image-to-Image Translation via Disentangled Representations](https://mlsanity.com/paper/1905.01270/) (2019)
- [Infinite Nature: Perpetual View Generation of Natural Scenes from a Single Image](https://mlsanity.com/paper/2012.09855/) (2020)
- [Mode Seeking Generative Adversarial Networks for Diverse Image Synthesis](https://mlsanity.com/paper/1903.05628/) (2019)
- [Unconstrained Scene Generation with Locally Conditioned Radiance Fields](https://mlsanity.com/paper/2104.00670/) (2021)
- [Improved Techniques for Training Single-Image GANs](https://mlsanity.com/paper/2003.11512/) (2020)

## Built on by (most cited first, 30 of 61)

- [Versatile Diffusion: Text, Images and Variations All in One Diffusion Model](https://mlsanity.com/paper/2211.08332/) (2022)
- [DiffCollage: Parallel Generation of Large Content with Diffusion Models](https://mlsanity.com/paper/2303.17076/) (2023)
- [Incremental Transformer Structure Enhanced Image Inpainting with Masking Positional Encoding](https://mlsanity.com/paper/2203.00867/) (2022)
- [InfiniteNature-Zero: Learning Perpetual View Generation of Natural Scenes from Single Images](https://mlsanity.com/paper/2207.11148/) (2022)
- [CityDreamer: Compositional Generative Model of Unbounded 3D Cities](https://mlsanity.com/paper/2309.00610/) (2023)
- [NUWA-Infinity: Autoregressive over Autoregressive Generation for Infinite Visual Synthesis](https://mlsanity.com/paper/2207.09814/) (2022)
- [InfiniCity: Infinite-Scale City Synthesis](https://mlsanity.com/paper/2301.09637/) (2023)
- [Single Motion Diffusion](https://mlsanity.com/paper/2302.05905/) (2023)
- [Ctrl-Room: Controllable Text-to-3D Room Meshes Generation with Layout Constraints](https://mlsanity.com/paper/2310.03602/) (2023)
- [360DVD: Controllable Panorama Video Generation with 360-Degree Video Diffusion Model](https://mlsanity.com/paper/2401.06578/) (2024)
- [Smooth Diffusion: Crafting Smooth Latent Spaces in Diffusion Models](https://mlsanity.com/paper/2312.04410/) (2023)
- [An Arbitrary Scale Super-Resolution Approach for 3D MR Images via Implicit Neural Representation](https://mlsanity.com/paper/2110.14476/) (2021)
- [Customizing 360-Degree Panoramas through Text-to-Image Diffusion Models](https://mlsanity.com/paper/2310.18840/) (2023)
- [Patched Denoising Diffusion Models For High-Resolution Image Synthesis](https://mlsanity.com/paper/2308.01316/) (2023)
- [Persistent Nature: A Generative Model of Unbounded 3D Worlds](https://mlsanity.com/paper/2303.13515/) (2023)
- [SinDiffusion: Learning a Diffusion Model from a Single Natural Image](https://mlsanity.com/paper/2211.12445/) (2022)
- [3DAvatarGAN: Bridging Domains for Personalized Editable Avatars](https://mlsanity.com/paper/2301.02700/) (2023)
- [CoordFill: Efficient High-Resolution Image Inpainting via Parameterized Coordinate Querying](https://mlsanity.com/paper/2303.08524/) (2023)
- [Guided Co-Modulated GAN for 360deg Field of View Extrapolation](https://mlsanity.com/paper/2204.07286/) (2022)
- [Scalable Neural Video Representations with Learnable Positional Features](https://mlsanity.com/paper/2210.06823/) (2022)
- [DiffInfinite: Large Mask-Image Synthesis via Parallel Random Patch Diffusion in Histopathology](https://mlsanity.com/paper/2306.13384/) (2023)
- [Musika! Fast Infinite Waveform Music Generation](https://mlsanity.com/paper/2208.08706/) (2022)
- [Text2Light: Zero-Shot Text-Driven HDR Panorama Generation](https://mlsanity.com/paper/2209.09898/) (2022)
- [3D Cinemagraphy from a Single Image](https://mlsanity.com/paper/2303.05724/) (2023)
- [CityGen: Infinite and Controllable City Layout Generation](https://mlsanity.com/paper/2312.01508/) (2023)
- [ZITS++: Image Inpainting by Improving the Incremental Transformer on Structural Priors](https://mlsanity.com/paper/2210.05950/) (2022)
- [Improving GANs with A Dynamic Discriminator](https://mlsanity.com/paper/2209.09897/) (2022)
- [Towards Enhanced Image Inpainting: Mitigating Unwanted Object Insertion and Preserving Color Consistency](https://mlsanity.com/paper/2312.04831/) (2023)
- [Continuous-Multiple Image Outpainting in One-Step via Positional Query and A Diffusion-based Approach](https://mlsanity.com/paper/2401.15652/) (2024)
- [PanoFree: Tuning-Free Holistic Multi-view Image Generation with Cross-view Self-Guidance](https://mlsanity.com/paper/2408.02157/) (2024)

## Abstract (arXiv)

We present a novel framework, InfinityGAN, for arbitrary-sized image generation. The task is associated with several key challenges. First, scaling existing models to an arbitrarily large image size is resource-constrained, in terms of both computation and availability of large-field-of-view training data. InfinityGAN trains and infers in a seamless patch-by-patch manner with low computational resources. Second, large images should be locally and globally consistent, avoid repetitive patterns, and look realistic. To address these, InfinityGAN disentangles global appearances, local structures, and textures. With this formulation, we can generate images with spatial size and level of details not attainable before. Experimental evaluation validates that InfinityGAN generates images with superior realism compared to baselines and features parallelizable inference. Finally, we show several applications unlocked by our approach, such as spatial style fusion, multi-modal outpainting, and image inbetweening. All applications can be operated with arbitrary input and output sizes. Please find the full version of the paper at https://openreview.net/forum?id=ufGMqIM0a4b .