# CLR-Face: Conditional Latent Refinement for Blind Face Restoration Using Score-Based Diffusion Models

arXiv: https://arxiv.org/abs/2402.06106 · HTML: https://mlsanity.com/paper/2402.06106/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Placed in Inverse problems and image restoration, one of 14 directions in Diffusion models.
- Builds on 38 of its 46 references that are in the map.
- First posted on arXiv 8 Feb 2024.

## Placed in

- Diffusion models / [Inverse problems and image restoration](https://mlsanity.com/diffusion/inverse-problems-and-image-restoration/)

## Builds on (most cited first, 30 of 38)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [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)
- [Diffusion Models Beat GANs on Image Synthesis](https://mlsanity.com/paper/2105.05233/) (2021)
- [A Style-Based Generator Architecture for Generative Adversarial Networks](https://mlsanity.com/paper/1812.04948/) (2018)
- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [Generative Modeling by Estimating Gradients of the Data Distribution](https://mlsanity.com/paper/1907.05600/) (2019)
- [Taming Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2012.09841/) (2020)
- [Elucidating the Design Space of Diffusion-Based Generative Models](https://mlsanity.com/paper/2206.00364/) (2022)
- [Progressive Growing of GANs for Improved Quality, Stability, and Variation](https://mlsanity.com/paper/1710.10196/) (2017)
- [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)
- [Consistency Models](https://mlsanity.com/paper/2303.01469/) (2023)
- [Image Super-Resolution via Iterative Refinement](https://mlsanity.com/paper/2104.07636/) (2021)
- [Encoding in Style: a StyleGAN Encoder for Image-to-Image Translation](https://mlsanity.com/paper/2008.00951/) (2020)
- [ILVR: Conditioning Method for Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2108.02938/) (2021)
- [CSDI: Conditional Score-based Diffusion Models for Probabilistic Time Series Imputation](https://mlsanity.com/paper/2107.03502/) (2021)
- [PULSE: Self-Supervised Photo Upsampling via Latent Space Exploration of Generative Models](https://mlsanity.com/paper/2003.03808/) (2020)
- [Towards Real-World Blind Face Restoration with Generative Facial Prior](https://mlsanity.com/paper/2101.04061/) (2021)
- [Come-Closer-Diffuse-Faster: Accelerating Conditional Diffusion Models for Inverse Problems through Stochastic Contraction](https://mlsanity.com/paper/2112.05146/) (2021)
- [WIDER FACE: A Face Detection Benchmark](https://mlsanity.com/paper/1511.06523/) (2015)
- [Deblurring via Stochastic Refinement](https://mlsanity.com/paper/2112.02475/) (2021)
- [Towards Robust Blind Face Restoration with Codebook Lookup Transformer](https://mlsanity.com/paper/2206.11253/) (2022)
- [GAN Prior Embedded Network for Blind Face Restoration in the Wild](https://mlsanity.com/paper/2105.06070/) (2021)
- [Image Processing Using Multi-Code GAN Prior](https://mlsanity.com/paper/1912.07116/) (2019)
- [FSRNet: End-to-End Learning Face Super-Resolution with Facial Priors](https://mlsanity.com/paper/1711.10703/) (2017)
- [VQFR: Blind Face Restoration with Vector-Quantized Dictionary and Parallel Decoder](https://mlsanity.com/paper/2205.06803/) (2022)
- [Blind Face Restoration via Deep Multi-scale Component Dictionaries](https://mlsanity.com/paper/2008.00418/) (2020)
- [Progressive Semantic-Aware Style Transformation for Blind Face Restoration](https://mlsanity.com/paper/2009.08709/) (2020)

## Built on by (most cited first, 5 of 5)

- [OSDFace: One-Step Diffusion Model for Face Restoration](https://mlsanity.com/paper/2411.17163/) (2024)
- [The Second Challenge on Real-World Face Restoration at NTIRE 2026: Methods and Results](https://mlsanity.com/paper/2604.10532/) (2026)
- [NTIRE 2025 Challenge on Real-World Face Restoration: Methods and Results](https://mlsanity.com/paper/2504.14600/) (2025)
- [HonestFace: Towards Honest Face Restoration with One-Step Diffusion Model](https://mlsanity.com/paper/2505.18469/) (2025)
- [LAFR: Efficient Diffusion-based Blind Face Restoration via Latent Codebook Alignment Adapter](https://mlsanity.com/paper/2505.23462/) (2025)

## Abstract (arXiv)

Recent generative-prior-based methods have shown promising blind face restoration performance. They usually project the degraded images to the latent space and then decode high-quality faces either by single-stage latent optimization or directly from the encoding. Generating fine-grained facial details faithful to inputs remains a challenging problem. Most existing methods produce either overly smooth outputs or alter the identity as they attempt to balance between generation and reconstruction. This may be attributed to the typical trade-off between quality and resolution in the latent space. If the latent space is highly compressed, the decoded output is more robust to degradations but shows worse fidelity. On the other hand, a more flexible latent space can capture intricate facial details better, but is extremely difficult to optimize for highly degraded faces using existing techniques. To address these issues, we introduce a diffusion-based-prior inside a VQGAN architecture that focuses on learning the distribution over uncorrupted latent embeddings. With such knowledge, we iteratively recover the clean embedding conditioning on the degraded counterpart. Furthermore, to ensure the reverse diffusion trajectory does not deviate from the underlying identity, we train a separate Identity Recovery Network and use its output to constrain the reverse diffusion process. Specifically, using a learnable latent mask, we add gradients from a face-recognition network to a subset of latent features that correlates with the finer identity-related details in the pixel space, leaving the other features untouched. Disentanglement between perception and fidelity in the latent space allows us to achieve the best of both worlds. We perform extensive evaluations on multiple real and synthetic datasets to validate the superiority of our approach.