# Toward Spatially Unbiased Generative Models

arXiv: https://arxiv.org/abs/2108.01285 · HTML: https://mlsanity.com/paper/2108.01285/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- Builds on 41 of its 46 references that are in the map.
- First posted on arXiv 3 Aug 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)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [Deep Unsupervised Learning using Nonequilibrium Thermodynamics](https://mlsanity.com/paper/1503.03585/) (2015)
- [A Style-Based Generator Architecture for Generative Adversarial Networks](https://mlsanity.com/paper/1812.04948/) (2018)
- [Improved Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2102.09672/) (2021)
- [Analyzing and Improving the Image Quality of StyleGAN](https://mlsanity.com/paper/1912.04958/) (2019)
- [Progressive Growing of GANs for Improved Quality, Stability, and Variation](https://mlsanity.com/paper/1710.10196/) (2017)
- [Large Scale GAN Training for High Fidelity Natural Image Synthesis](https://mlsanity.com/paper/1809.11096/) (2018)
- [Group Normalization](https://mlsanity.com/paper/1803.08494/) (2018)
- [LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loop](https://mlsanity.com/paper/1506.03365/) (2015)
- [DiffWave: A Versatile Diffusion Model for Audio Synthesis](https://mlsanity.com/paper/2009.09761/) (2020)
- [Alias-Free Generative Adversarial Networks](https://mlsanity.com/paper/2106.12423/) (2021)
- [Interpreting the Latent Space of GANs for Semantic Face Editing](https://mlsanity.com/paper/1907.10786/) (2019)
- [Which Training Methods for GANs do actually Converge?](https://mlsanity.com/paper/1801.04406/) (2018)
- [Image2StyleGAN: How to Embed Images Into the StyleGAN Latent Space?](https://mlsanity.com/paper/1904.03189/) (2019)
- [WaveGrad: Estimating Gradients for Waveform Generation](https://mlsanity.com/paper/2009.00713/) (2020)
- [Closed-Form Factorization of Latent Semantics in GANs](https://mlsanity.com/paper/2007.06600/) (2020)
- [Assessing Generative Models via Precision and Recall](https://mlsanity.com/paper/1806.00035/) (2018)
- [Making Convolutional Networks Shift-Invariant Again](https://mlsanity.com/paper/1904.11486/) (2019)
- [PULSE: Self-Supervised Photo Upsampling via Latent Space Exploration of Generative Models](https://mlsanity.com/paper/2003.03808/) (2020)
- [Generative Visual Manipulation on the Natural Image Manifold](https://mlsanity.com/paper/1609.03552/) (2016)
- [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)
- [Learning De-biased Representations with Biased Representations](https://mlsanity.com/paper/1910.02806/) (2019)
- [Why do deep convolutional networks generalize so poorly to small image transformations?](https://mlsanity.com/paper/1805.12177/) (2018)
- [Image Processing Using Multi-Code GAN Prior](https://mlsanity.com/paper/1912.07116/) (2019)

## Built on by (most cited first, 17 of 17)

- [ILVR: Conditioning Method for Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2108.02938/) (2021)
- [StyleSwin: Transformer-based GAN for High-resolution Image Generation](https://mlsanity.com/paper/2112.10762/) (2021)
- [Any-resolution Training for High-resolution Image Synthesis](https://mlsanity.com/paper/2204.07156/) (2022)
- [LiDAR Data Synthesis with Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2309.09256/) (2023)
- [Learning to Generate 3D Shapes from a Single Example](https://mlsanity.com/paper/2208.02946/) (2022)
- [Arbitrary-Scale Image Generation and Upsampling using Latent Diffusion Model and Implicit Neural Decoder](https://mlsanity.com/paper/2403.10255/) (2024)
- [LTT-GAN: Looking Through Turbulence by Inverting GANs](https://mlsanity.com/paper/2112.02379/) (2021)
- [Arbitrary-Scale Image Synthesis](https://mlsanity.com/paper/2204.02273/) (2022)
- [The Crystal Ball Hypothesis in diffusion models: Anticipating object positions from initial noise](https://mlsanity.com/paper/2406.01970/) (2024)
- [OPE-SR: Orthogonal Position Encoding for Designing a Parameter-free Upsampling Module in Arbitrary-scale Image Super-Resolution](https://mlsanity.com/paper/2303.01091/) (2023)
- [UnitedHuman: Harnessing Multi-Source Data for High-Resolution Human Generation](https://mlsanity.com/paper/2309.14335/) (2023)
- [Zone Evaluation: Revealing Spatial Bias in Object Detection](https://mlsanity.com/paper/2310.13215/) (2023)
- [Towards Universal Texture Synthesis by Combining Texton Broadcasting with Noise Injection in StyleGAN-2](https://mlsanity.com/paper/2203.04221/) (2022)
- [Unveiling The Mask of Position-Information Pattern Through the Mist of Image Features](https://mlsanity.com/paper/2206.01202/) (2022)
- [DARTS: Double Attention Reference-based Transformer for Super-resolution](https://mlsanity.com/paper/2307.08837/) (2023)
- [HiTSR: A Hierarchical Transformer for Reference-based Super-Resolution](https://mlsanity.com/paper/2408.16959/) (2024)
- [Improving Translation Invariance in Convolutional Neural Networks with Peripheral Prediction Padding](https://mlsanity.com/paper/2307.07725/) (2023)

## Abstract (arXiv)

Recent image generation models show remarkable generation performance. However, they mirror strong location preference in datasets, which we call spatial bias. Therefore, generators render poor samples at unseen locations and scales. We argue that the generators rely on their implicit positional encoding to render spatial content. From our observations, the generator's implicit positional encoding is translation-variant, making the generator spatially biased. To address this issue, we propose injecting explicit positional encoding at each scale of the generator. By learning the spatially unbiased generator, we facilitate the robust use of generators in multiple tasks, such as GAN inversion, multi-scale generation, generation of arbitrary sizes and aspect ratios. Furthermore, we show that our method can also be applied to denoising diffusion probabilistic models.