# Decomposing Private Image Generation via Coarse-to-Fine Wavelet Modeling

arXiv: https://arxiv.org/abs/2602.23262 · HTML: https://mlsanity.com/paper/2602.23262/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 31 of its 48 references that are in the map.
- First posted on arXiv 26 Feb 2026.

## Builds on (most cited first, 30 of 31)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding](https://mlsanity.com/paper/2205.11487/) (2022)
- [Improved Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2102.09672/) (2021)
- [GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models](https://mlsanity.com/paper/2112.10741/) (2021)
- [Taming Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2012.09841/) (2020)
- [Deep Learning with Differential Privacy](https://mlsanity.com/paper/1607.00133/) (2016)
- [Scaling Autoregressive Models for Content-Rich Text-to-Image Generation](https://mlsanity.com/paper/2206.10789/) (2022)
- [Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction](https://mlsanity.com/paper/2404.02905/) (2024)
- [Blended Diffusion for Text-driven Editing of Natural Images](https://mlsanity.com/paper/2111.14818/) (2021)
- [Autoregressive Model Beats Diffusion: Llama for Scalable Image Generation](https://mlsanity.com/paper/2406.06525/) (2024)
- [PaLI: A Jointly-Scaled Multilingual Language-Image Model](https://mlsanity.com/paper/2209.06794/) (2022)
- [Extracting Training Data from Diffusion Models](https://mlsanity.com/paper/2301.13188/) (2023)
- [Make-A-Scene: Scene-Based Text-to-Image Generation with Human Priors](https://mlsanity.com/paper/2203.13131/) (2022)
- [Differentially Private Generative Adversarial Network](https://mlsanity.com/paper/1802.06739/) (2018)
- [How to DP-fy ML: A Practical Guide to Machine Learning with Differential Privacy](https://mlsanity.com/paper/2303.00654/) (2023)
- [Differentially Private Diffusion Models](https://mlsanity.com/paper/2210.09929/) (2022)
- [DP-CGAN: Differentially Private Synthetic Data and Label Generation](https://mlsanity.com/paper/2001.09700/) (2020)
- [GS-WGAN: A Gradient-Sanitized Approach for Learning Differentially Private Generators](https://mlsanity.com/paper/2006.08265/) (2020)
- [Differentially Private Diffusion Models Generate Useful Synthetic Images](https://mlsanity.com/paper/2302.13861/) (2023)
- [Differentially Private Synthetic Data via Foundation Model APIs 1: Images](https://mlsanity.com/paper/2305.15560/) (2023)
- [Don't Generate Me: Training Differentially Private Generative Models with Sinkhorn Divergence](https://mlsanity.com/paper/2111.01177/) (2021)
- [Connect the Dots: Tighter Discrete Approximations of Privacy Loss Distributions](https://mlsanity.com/paper/2207.04380/) (2022)
- [DP-LDMs: Differentially Private Latent Diffusion Models](https://mlsanity.com/paper/2305.15759/) (2023)
- [On the Edge of Memorization in Diffusion Models](https://mlsanity.com/paper/2508.17689/) (2025)
- [Private GANs, Revisited](https://mlsanity.com/paper/2302.02936/) (2023)
- [Spectral Image Tokenizer](https://mlsanity.com/paper/2412.09607/) (2024)
- [Synthesize Privacy-Preserving High-Resolution Images via Private Textual Intermediaries](https://mlsanity.com/paper/2506.07555/) (2025)

## Abstract (arXiv)

Generative models trained on sensitive image datasets risk memorizing and reproducing individual training examples, making strong privacy guarantees essential. While differential privacy (DP) provides a principled framework for such guarantees, standard DP finetuning (e.g., with DP-SGD) often results in severe degradation of image quality, particularly in high-frequency textures, due to the indiscriminate addition of noise across all model parameters. In this work, we propose a spectral DP framework based on the hypothesis that the most privacy-sensitive portions of an image are often low-frequency components in the wavelet space (e.g., facial features and object shapes) while high-frequency components are largely generic and public. Based on this hypothesis, we propose the following two-stage framework for DP image generation with coarse image intermediaries: (1) DP finetune an autoregressive spectral image tokenizer model on the low-resolution wavelet coefficients of the sensitive images, and (2) perform high-resolution upsampling using a publicly pretrained super-resolution model. By restricting the privacy budget to the global structures of the image in the first stage, and leveraging the post-processing property of DP for detail refinement, we achieve promising trade-offs between privacy and utility. Experiments on the MS-COCO and MM-CelebA-HQ datasets show that our method generates images with improved quality and style capture relative to other leading DP image frameworks.