# Reconstruct-and-Generate Diffusion Model for Detail-Preserving Image Denoising

arXiv: https://arxiv.org/abs/2309.10714 · HTML: https://mlsanity.com/paper/2309.10714/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Placed in Diffusion foundations and sampling, one of 14 directions in Diffusion models.
- Builds on 29 of its 57 references that are in the map.
- First posted on arXiv 19 Sep 2023.

## Placed in

- Diffusion models / [Diffusion foundations and sampling](https://mlsanity.com/diffusion/diffusion-foundations-and-sampling/)

## Builds on (most cited first, 29 of 29)

- [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)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Score-Based Generative Modeling through Stochastic Differential Equations](https://mlsanity.com/paper/2011.13456/) (2020)
- [Deep Unsupervised Learning using Nonequilibrium Thermodynamics](https://mlsanity.com/paper/1503.03585/) (2015)
- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [Generative Modeling by Estimating Gradients of the Data Distribution](https://mlsanity.com/paper/1907.05600/) (2019)
- [Perceptual Losses for Real-Time Style Transfer and Super-Resolution](https://mlsanity.com/paper/1603.08155/) (2016)
- [SwinIR: Image Restoration Using Swin Transformer](https://mlsanity.com/paper/2108.10257/) (2021)
- [Restormer: Efficient Transformer for High-Resolution Image Restoration](https://mlsanity.com/paper/2111.09881/) (2021)
- [Image Super-Resolution via Iterative Refinement](https://mlsanity.com/paper/2104.07636/) (2021)
- [Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising](https://mlsanity.com/paper/1608.03981/) (2016)
- [On the Spectral Bias of Neural Networks](https://mlsanity.com/paper/1806.08734/) (2018)
- [Palette: Image-to-Image Diffusion Models](https://mlsanity.com/paper/2111.05826/) (2021)
- [Denoising Diffusion Restoration Models](https://mlsanity.com/paper/2201.11793/) (2022)
- [Residual Dense Network for Image Super-Resolution](https://mlsanity.com/paper/1802.08797/) (2018)
- [Simple Baselines for Image Restoration](https://mlsanity.com/paper/2204.04676/) (2022)
- [WaveGrad: Estimating Gradients for Waveform Generation](https://mlsanity.com/paper/2009.00713/) (2020)
- [The Perception-Distortion Tradeoff](https://mlsanity.com/paper/1711.06077/) (2017)
- [Noise2Noise: Learning Image Restoration without Clean Data](https://mlsanity.com/paper/1803.04189/) (2018)
- [Frequency Principle: Fourier Analysis Sheds Light on Deep Neural Networks](https://mlsanity.com/paper/1901.06523/) (2019)
- [Noise2Void - Learning Denoising from Single Noisy Images](https://mlsanity.com/paper/1811.10980/) (2018)
- [MAXIM: Multi-Axis MLP for Image Processing](https://mlsanity.com/paper/2201.02973/) (2022)
- [Noise2Self: Blind Denoising by Self-Supervision](https://mlsanity.com/paper/1901.11365/) (2019)
- [Deblurring via Stochastic Refinement](https://mlsanity.com/paper/2112.02475/) (2021)
- [CycleISP: Real Image Restoration via Improved Data Synthesis](https://mlsanity.com/paper/2003.07761/) (2020)
- [Stochastic Image Denoising by Sampling from the Posterior Distribution](https://mlsanity.com/paper/2101.09552/) (2021)
- [Perception-Distortion Balanced ADMM Optimization for Single-Image Super-Resolution](https://mlsanity.com/paper/2208.03324/) (2022)
- [Image Denoising via CNNs: An Adversarial Approach](https://mlsanity.com/paper/1708.00159/) (2017)

## Built on by (most cited first, 6 of 6)

- [Image is All You Need to Empower Large-scale Diffusion Models for In-Domain Generation](https://mlsanity.com/paper/2312.08195/) (2023)
- [FiDeSR: High-Fidelity and Detail-Preserving One-Step Diffusion Super-Resolution](https://mlsanity.com/paper/2603.02692/) (2026)
- [A Simple Combination of Diffusion Models for Better Quality Trade-Offs in Image Denoising](https://mlsanity.com/paper/2503.14654/) (2025)
- [Computationally Efficient Diffusion Models in Medical Imaging: A Comprehensive Review](https://mlsanity.com/paper/2505.07866/) (2025)
- [Diffusion-corrected Autoregressive Fourier Neural Operator for Droplet Evolution Prediction](https://mlsanity.com/paper/2607.16238/) (2026)
- [TRIG: Toward Measuring Texture Realism in Image Generation](https://mlsanity.com/paper/2610.15164/) (2026)

## Abstract (arXiv)

Image denoising is a fundamental and challenging task in the field of computer vision. Most supervised denoising methods learn to reconstruct clean images from noisy inputs, which have intrinsic spectral bias and tend to produce over-smoothed and blurry images. Recently, researchers have explored diffusion models to generate high-frequency details in image restoration tasks, but these models do not guarantee that the generated texture aligns with real images, leading to undesirable artifacts. To address the trade-off between visual appeal and fidelity of high-frequency details in denoising tasks, we propose a novel approach called the Reconstruct-and-Generate Diffusion Model (RnG). Our method leverages a reconstructive denoising network to recover the majority of the underlying clean signal, which serves as the initial estimation for subsequent steps to maintain fidelity. Additionally, it employs a diffusion algorithm to generate residual high-frequency details, thereby enhancing visual quality. We further introduce a two-stage training scheme to ensure effective collaboration between the reconstructive and generative modules of RnG. To reduce undesirable texture introduced by the diffusion model, we also propose an adaptive step controller that regulates the number of inverse steps applied by the diffusion model, allowing control over the level of high-frequency details added to each patch as well as saving the inference computational cost. Through our proposed RnG, we achieve a better balance between perception and distortion. We conducted extensive experiments on both synthetic and real denoising datasets, validating the superiority of the proposed approach.