# DiffBFR: Bootstrapping Diffusion Model Towards Blind Face Restoration arXiv: https://arxiv.org/abs/2305.04517 ยท HTML: https://mlsanity.com/paper/2305.04517/ ## Key facts - Cited by 17 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 32 of its 39 references that are in the map. - First posted on arXiv 8 May 2023. ## 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 32) - [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021) - [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020) - [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018) - [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (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) - [GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models](https://mlsanity.com/paper/2112.10741/) (2021) - [DreamFusion: Text-to-3D using 2D Diffusion](https://mlsanity.com/paper/2209.14988/) (2022) - [Progressive Growing of GANs for Improved Quality, Stability, and Variation](https://mlsanity.com/paper/1710.10196/) (2017) - [SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equations](https://mlsanity.com/paper/2108.01073/) (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) - [Image Super-Resolution Using Very Deep Residual Channel Attention Networks](https://mlsanity.com/paper/1807.02758/) (2018) - [Cascaded Diffusion Models for High Fidelity Image Generation](https://mlsanity.com/paper/2106.15282/) (2021) - [Score-based Generative Modeling in Latent Space](https://mlsanity.com/paper/2106.05931/) (2021) - [Deep Long-Tailed Learning: A Survey](https://mlsanity.com/paper/2110.04596/) (2021) - [DeblurGAN: Blind Motion Deblurring Using Conditional Adversarial Networks](https://mlsanity.com/paper/1711.07064/) (2017) - [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) - [SegDiff: Image Segmentation with Diffusion Probabilistic Models](https://mlsanity.com/paper/2112.00390/) (2021) - [Learning a Single Convolutional Super-Resolution Network for Multiple Degradations](https://mlsanity.com/paper/1712.06116/) (2017) - [GAN Prior Embedded Network for Blind Face Restoration in the Wild](https://mlsanity.com/paper/2105.06070/) (2021) - [Compression Artifacts Reduction by a Deep Convolutional Network](https://mlsanity.com/paper/1504.06993/) (2015) - [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) - [CARD: Classification and Regression Diffusion Models](https://mlsanity.com/paper/2206.07275/) (2022) - [Progressive Semantic-Aware Style Transformation for Blind Face Restoration](https://mlsanity.com/paper/2009.08709/) (2020) - [DifFace: Blind Face Restoration with Diffused Error Contraction](https://mlsanity.com/paper/2212.06512/) (2022) - [Learning Warped Guidance for Blind Face Restoration](https://mlsanity.com/paper/1804.04829/) (2018) ## Built on by (most cited first, 17 of 17) - [Diffusion Models for Image Restoration and Enhancement: A Comprehensive Survey](https://mlsanity.com/paper/2308.09388/) (2023) - [POSTA: A Go-to Framework for Customized Artistic Poster Generation](https://mlsanity.com/paper/2503.14908/) (2025) - [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) - [Show and Polish: Reference-Guided Identity Preservation in Face Video Restoration](https://mlsanity.com/paper/2507.10293/) (2025) - [NTIRE 2025 Challenge on Real-World Face Restoration: Methods and Results](https://mlsanity.com/paper/2504.14600/) (2025) - [Visual Style Prompt Learning Using Diffusion Models for Blind Face Restoration](https://mlsanity.com/paper/2412.21042/) (2024) - [INDIGO+: A Unified INN-Guided Probabilistic Diffusion Algorithm for Blind and Non-Blind Image Restoration](https://mlsanity.com/paper/2501.14014/) (2025) - [IQPFR: An Image Quality Prior for Blind Face Restoration and Beyond](https://mlsanity.com/paper/2503.09294/) (2025) - [Towards Unsupervised Blind Face Restoration using Diffusion Prior](https://mlsanity.com/paper/2410.04618/) (2024) - [Restoring Gaussian Blurred Face Images for Deanonymization Attacks](https://mlsanity.com/paper/2506.12344/) (2025) - [DynFaceRestore: Balancing Fidelity and Quality in Diffusion-Guided Blind Face Restoration with Dynamic Blur-Level Mapping and Guidance](https://mlsanity.com/paper/2507.13797/) (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) - [CA-Diff: Collaborative Anatomy Diffusion for Brain Tissue Segmentation](https://mlsanity.com/paper/2506.22882/) (2025) - [Degradation-Agnostic Statistical Facial Feature Transformation for Blind Face Restoration in Adverse Weather Conditions](https://mlsanity.com/paper/2507.07464/) (2025) - [Domain-adaptive Zero-Shot Image Enhancement via Locality-Constrained Diffusion Guidance](https://mlsanity.com/paper/2609.35289/) (2026) ## Abstract (arXiv) Blind face restoration (BFR) is important while challenging. Prior works prefer to exploit GAN-based frameworks to tackle this task due to the balance of quality and efficiency. However, these methods suffer from poor stability and adaptability to long-tail distribution, failing to simultaneously retain source identity and restore detail. We propose DiffBFR to introduce Diffusion Probabilistic Model (DPM) for BFR to tackle the above problem, given its superiority over GAN in aspects of avoiding training collapse and generating long-tail distribution. DiffBFR utilizes a two-step design, that first restores identity information from low-quality images and then enhances texture details according to the distribution of real faces. This design is implemented with two key components: 1) Identity Restoration Module (IRM) for preserving the face details in results. Instead of denoising from pure Gaussian random distribution with LQ images as the condition during the reverse process, we propose a novel truncated sampling method which starts from LQ images with part noise added. We theoretically prove that this change shrinks the evidence lower bound of DPM and then restores more original details. With theoretical proof, two cascade conditional DPMs with different input sizes are introduced to strengthen this sampling effect and reduce training difficulty in the high-resolution image generated directly. 2) Texture Enhancement Module (TEM) for polishing the texture of the image. Here an unconditional DPM, a LQ-free model, is introduced to further force the restorations to appear realistic. We theoretically proved that this unconditional DPM trained on pure HQ images contributes to justifying the correct distribution of inference images output from IRM in pixel-level space. Truncated sampling with fractional time step is utilized to polish pixel-level textures while preserving identity information.