mlsanityData to 14 Oct 2026

QuantFace: Efficient Quantization for Face Restoration

arXiv 2506.00820 ↗First posted 1 Jun 2025cs.CVcited by 0

On the map: Diffusion models → Inverse problems and image restoration

Abstract (arXiv)

Diffusion models have been achieving remarkable performance in face restoration. However, the heavy computations hamper the widespread adoption of these models. In this work, we propose QuantFace, a novel low-bit quantization framework for face restoration models, where the full-precision (i.e., 32-bit) weights and activations are quantized to 4~6-bit. We first analyze the data distribution within activations and find that it is highly variant. To preserve the original data information, we employ rotation-scaling channel balancing. Furthermore, we propose Quantization-Distillation Low-Rank Adaptation (QD-LoRA), which jointly optimizes for quantization and distillation performance. Finally, we propose an adaptive bit-width allocation strategy. We formulate such a strategy as an integer programming problem that combines quantization error and perceptual metrics to find a satisfactory resource allocation. Extensive experiments on the synthetic and real-world datasets demonstrate the effectiveness of QuantFace under 6-bit and 4-bit. QuantFace achieves significant advantages over recent leading low-bit quantization methods for face restoration. The code is available at https://github.com/jiatongli2024/QuantFace.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Inverse problems and image restoration, one of 14 directions in Diffusion models. Builds on 53 of its 66 references that are in the map. First posted on arXiv 1 Jun 2025.

Builds on

53 of 66 references.

Closest ancestors · 7

Same direction, newest first

  1. 2024OSDFace: One-Step Diffusion Model for Face Restoration26 Nov
  2. 2024PassionSR: Post-Training Quantization with Adaptive Scale in One-Step Diffusion based Image Super-Resolution26 Nov
  3. 2024WaveFace: Authentic Face Restoration with Efficient Frequency Recovery19 Mar
  4. 2023PGDiff: Guiding Diffusion Models for Versatile Face Restoration via Partial Guidance19 Sep
  5. 2023Generative Diffusion Prior for Unified Image Restoration and Enhancement3 Apr
  6. 2022Zero-Shot Image Restoration Using Denoising Diffusion Null-Space Model1 Dec
  7. 2022Denoising Diffusion Restoration Models27 Jan

Other references · 46

  1. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  3. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  4. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
  5. 2020Denoising Diffusion Implicit Modelscited by 9,781
  6. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 9,122
  7. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 6,013
  8. 2017Progressive Growing of GANs for Improved Quality, Stability, and Variationcited by 2,988
  9. 2023Consistency Modelscited by 1,822
  10. 2017Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inferencecited by 1,593
  11. 2022SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Modelscited by 1,386
  12. 2021MUSIQ: Multi-scale Image Quality Transformercited by 1,081
34 more
  1. 2023One-step Diffusion with Distribution Matching Distillationcited by 1,019
  2. 2022Exploring CLIP for Assessing the Look and Feel of Imagescited by 991
  3. 2020Image Quality Assessment: Unifying Structure and Texture Similaritycited by 811
  4. 2024QuaRot: Outlier-Free 4-Bit Inference in Rotated LLMscited by 634
  5. 2022ZeroQuant: Efficient and Affordable Post-Training Quantization for Large-Scale Transformerscited by 526
  6. 2022MANIQA: Multi-dimension Attention Network for No-Reference Image Quality Assessmentcited by 522
  7. 2021BRECQ: Pushing the Limit of Post-Training Quantization by Block Reconstructioncited by 479
  8. 2021A White Paper on Neural Network Quantizationcited by 472
  9. 2024SpinQuant: LLM quantization with learned rotationscited by 471
  10. 2024QuIP#: Even Better LLM Quantization with Hadamard Incoherence and Lattice Codebookscited by 378
  11. 2021Towards Real-World Blind Face Restoration with Generative Facial Priorcited by 349
  12. 2023LLM-QAT: Data-Free Quantization Aware Training for Large Language Modelscited by 324
  13. 2023Q-Diffusion: Quantizing Diffusion Modelscited by 273
  14. 2022Post-training Quantization on Diffusion Modelscited by 267
  15. 2022Towards Robust Blind Face Restoration with Codebook Lookup Transformercited by 231
  16. 2023LoftQ: LoRA-Fine-Tuning-Aware Quantization for Large Language Modelscited by 196
  17. 2020LSQ+: Improving low-bit quantization through learnable offsets and better initializationcited by 189
  18. 2023PTQD: Accurate Post-Training Quantization for Diffusion Modelscited by 170
  19. 2024EfficientQAT: Efficient Quantization-Aware Training for Large Language Modelscited by 127
  20. 2022VQFR: Blind Face Restoration with Vector-Quantized Dictionary and Parallel Decodercited by 116
  21. 2024ViDiT-Q: Efficient and Accurate Quantization of Diffusion Transformers for Image and Video Generationcited by 115
  22. 2023LQ-LoRA: Low-rank Plus Quantized Matrix Decomposition for Efficient Language Model Finetuningcited by 92
  23. 2021Nonuniform-to-Uniform Quantization: Towards Accurate Quantization via Generalized Straight-Through Estimationcited by 79
  24. 2023EfficientDM: Efficient Quantization-Aware Fine-Tuning of Low-Bit Diffusion Modelscited by 78
  25. 2024MixDQ: Memory-Efficient Few-Step Text-to-Image Diffusion Models with Metric-Decoupled Mixed Precision Quantizationcited by 43
  26. 2024Low-Rank Quantization-Aware Training for LLMscited by 43
  27. 2021OMPQ: Orthogonal Mixed Precision Quantizationcited by 39
  28. 2024BitsFusion: 1.99 bits Weight Quantization of Diffusion Modelcited by 37
  29. 2023RestoreFormer++: Towards Real-World Blind Face Restoration from Undegraded Key-Value Pairscited by 33
  30. 2025MambaQuant: Quantizing the Mamba Family with Variance Aligned Rotation Methodscited by 29
  31. 2023Dual Associated Encoder for Face Restorationcited by 23
  32. 2024QERA: an Analytical Framework for Quantization Error Reconstructioncited by 22
  33. 2024Improving Quantization-aware Training of Low-Precision Network via Block Replacement on Full-Precision Counterpartcited by 6
  34. 2025FBQuant: FeedBack Quantization for Large Language Modelscited by 5

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025LAFR: Efficient Diffusion-based Blind Face Restoration via Latent Codebook Alignment Adapter
  2. 2024AdaBM: On-the-Fly Adaptive Bit Mapping for Image Super-Resolution
  3. 2026Decoder-Free Distillation for Quantized Image Restoration
  4. 2025Post-Training Quantization via Residual Truncation and Zero Suppression for Diffusion Models
  5. 2025DicFace: Dirichlet-Constrained Variational Codebook Learning for Temporally Coherent Video Face Restoration
  6. 2023Towards Real-World Blind Face Restoration with Generative Diffusion Prior
  7. 2024Ef-QuantFace: Streamlined Face Recognition with Small Data and Low-Bit Precision
  8. 2026HDRFace: Rethinking Face Restoration with High-Dimensional Representation