# NaturalInversion: Data-Free Image Synthesis Improving Real-World Consistency

arXiv: https://arxiv.org/abs/2306.16661 · HTML: https://mlsanity.com/paper/2306.16661/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 36 references that are in the map.
- First posted on arXiv 29 Jun 2023.

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

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [Rethinking the Inception Architecture for Computer Vision](https://mlsanity.com/paper/1512.00567/) (2015)
- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [Improved Techniques for Training GANs](https://mlsanity.com/paper/1606.03498/) (2016)
- [Visualizing and Understanding Convolutional Networks](https://mlsanity.com/paper/1311.2901/) (2013)
- [Conditional Generative Adversarial Nets](https://mlsanity.com/paper/1411.1784/) (2014)
- [Scaling Vision Transformers](https://mlsanity.com/paper/2106.04560/) (2021)
- [Learning Efficient Convolutional Networks through Network Slimming](https://mlsanity.com/paper/1708.06519/) (2017)
- [Rethinking the Value of Network Pruning](https://mlsanity.com/paper/1810.05270/) (2018)
- [Dreaming to Distill: Data-free Knowledge Transfer via DeepInversion](https://mlsanity.com/paper/1912.08795/) (2019)
- [Assessing Generative Models via Precision and Recall](https://mlsanity.com/paper/1806.00035/) (2018)
- [Understanding Deep Image Representations by Inverting Them](https://mlsanity.com/paper/1412.0035/) (2014)
- [Understanding Neural Networks Through Deep Visualization](https://mlsanity.com/paper/1506.06579/) (2015)
- [Data-Free Learning of Student Networks](https://mlsanity.com/paper/1904.01186/) (2019)
- [How Much Position Information Do Convolutional Neural Networks Encode?](https://mlsanity.com/paper/2001.08248/) (2020)
- [Data-Free Adversarial Distillation](https://mlsanity.com/paper/1912.11006/) (2019)
- [Generative Hierarchical Features from Synthesizing Images](https://mlsanity.com/paper/2007.10379/) (2020)
- [Detection in Crowded Scenes: One Proposal, Multiple Predictions](https://mlsanity.com/paper/2003.09163/) (2020)
- [The Knowledge Within: Methods for Data-Free Model Compression](https://mlsanity.com/paper/1912.01274/) (2019)
- [Drafting and Revision: Laplacian Pyramid Network for Fast High-Quality Artistic Style Transfer](https://mlsanity.com/paper/2104.05376/) (2021)
- [Semantic Pyramid for Image Generation](https://mlsanity.com/paper/2003.06221/) (2020)
- [In the light of feature distributions: moment matching for Neural Style Transfer](https://mlsanity.com/paper/2103.07208/) (2021)
- [IMAGINE: Image Synthesis by Image-Guided Model Inversion](https://mlsanity.com/paper/2104.05895/) (2021)

## Built on by (most cited first, 7 of 7)

- [Constant Acceleration Flow](https://mlsanity.com/paper/2411.00322/) (2024)
- [Sprint: Sparse-Dense Residual Fusion for Efficient Diffusion Transformers](https://mlsanity.com/paper/2510.21986/) (2025)
- [Blockwise Flow Matching: Improving Flow Matching Models For Efficient High-Quality Generation](https://mlsanity.com/paper/2510.21167/) (2025)
- [pSTarC: Pseudo Source Guided Target Clustering for Fully Test-Time Adaptation](https://mlsanity.com/paper/2309.00846/) (2023)
- [Analytic Personalized Federated Meta-Learning](https://mlsanity.com/paper/2502.06915/) (2025)
- [When Model Knowledge meets Diffusion Model: Diffusion-assisted Data-free Image Synthesis with Alignment of Domain and Class](https://mlsanity.com/paper/2506.15381/) (2025)
- [Seeing the Whole Picture: Distribution-Guided Data-Free Distillation for Semantic Segmentation](https://mlsanity.com/paper/2512.13175/) (2025)

## Abstract (arXiv)

We introduce NaturalInversion, a novel model inversion-based method to synthesize images that agrees well with the original data distribution without using real data. In NaturalInversion, we propose: (1) a Feature Transfer Pyramid which uses enhanced image prior of the original data by combining the multi-scale feature maps extracted from the pre-trained classifier, (2) a one-to-one approach generative model where only one batch of images are synthesized by one generator to bring the non-linearity to optimization and to ease the overall optimizing process, (3) learnable Adaptive Channel Scaling parameters which are end-to-end trained to scale the output image channel to utilize the original image prior further. With our NaturalInversion, we synthesize images from classifiers trained on CIFAR-10/100 and show that our images are more consistent with original data distribution than prior works by visualization and additional analysis. Furthermore, our synthesized images outperform prior works on various applications such as knowledge distillation and pruning, demonstrating the effectiveness of our proposed method.