mlsanityData to 14 Oct 2026

PassionSR: Post-Training Quantization with Adaptive Scale in One-Step Diffusion based Image Super-Resolution

arXiv 2411.17106 ↗First posted 26 Nov 2024cs.CVcited by 9

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

Abstract (arXiv)

Diffusion-based image super-resolution (SR) models have shown superior performance at the cost of multiple denoising steps. However, even though the denoising step has been reduced to one, they require high computational costs and storage requirements, making it difficult for deployment on hardware devices. To address these issues, we propose a novel post-training quantization approach with adaptive scale in one-step diffusion (OSD) image SR, PassionSR. First, we simplify OSD model to two core components, UNet and Variational Autoencoder (VAE) by removing the CLIPEncoder. Secondly, we propose Learnable Boundary Quantizer (LBQ) and Learnable Equivalent Transformation (LET) to optimize the quantization process and manipulate activation distributions for better quantization. Finally, we design a Distributed Quantization Calibration (DQC) strategy that stabilizes the training of quantized parameters for rapid convergence. Comprehensive experiments demonstrate that PassionSR with 8-bit and 6-bit obtains comparable visual results with full-precision model. Moreover, our PassionSR achieves significant advantages over recent leading low-bit quantization methods for image SR. Our code will be at https://github.com/libozhu03/PassionSR.

Key facts. Cited by 9 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 45 of its 56 references that are in the map. First posted on arXiv 26 Nov 2024.

Builds on

45 of 56 references.

Closest ancestors · 5

Same direction, newest first

  1. 2024One-Step Effective Diffusion Network for Real-World Image Super-Resolution12 Jun
  2. 2023SeeSR: Towards Semantics-Aware Real-World Image Super-Resolution27 Nov
  3. 2023SinSR: Diffusion-Based Image Super-Resolution in a Single Step23 Nov
  4. 2023DiffBIR: Towards Blind Image Restoration with Generative Diffusion Prior29 Aug
  5. 2023Exploiting Diffusion Prior for Real-World Image Super-Resolution11 May

Other references · 40

  1. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  2. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
  3. 2020Denoising Diffusion Implicit Modelscited by 9,781
  4. 2021SwinIR: Image Restoration Using Swin Transformercited by 1,887
  5. 2023Consistency Modelscited by 1,822
  6. 2017Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inferencecited by 1,593
  7. 2015LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loopcited by 1,355
  8. 2023AWQ: Activation-aware Weight Quantization for LLM Compression and Accelerationcited by 1,298
  9. 2018Image Super-Resolution Using Very Deep Residual Channel Attention Networkscited by 1,264
  10. 2014Image Super-Resolution Using Deep Convolutional Networkscited by 1,224
  11. 2023ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation with Variational Score Distillationcited by 1,219
  12. 2021MUSIQ: Multi-scale Image Quality Transformercited by 1,081
28 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. 2021Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Datacited by 970
  4. 2015Accurate Image Super-Resolution Using Very Deep Convolutional Networkscited by 903
  5. 2020Image Quality Assessment: Unifying Structure and Texture Similaritycited by 811
  6. 2018Residual Dense Network for Image Super-Resolutioncited by 799
  7. 2019Learned Step Size Quantizationcited by 628
  8. 2021Designing a Practical Degradation Model for Deep Blind Image Super-Resolutioncited by 529
  9. 2022ZeroQuant: Efficient and Affordable Post-Training Quantization for Large-Scale Transformerscited by 526
  10. 2022MANIQA: Multi-dimension Attention Network for No-Reference Image Quality Assessmentcited by 522
  11. 2021BRECQ: Pushing the Limit of Post-Training Quantization by Block Reconstructioncited by 479
  12. 2023UniPC: A Unified Predictor-Corrector Framework for Fast Sampling of Diffusion Modelscited by 450
  13. 2023Q-Diffusion: Quantizing Diffusion Modelscited by 273
  14. 2022Post-training Quantization on Diffusion Modelscited by 267
  15. 2020Component Divide-and-Conquer for Real-World Image Super-Resolutioncited by 246
  16. 2019Low-bit Quantization of Neural Networks for Efficient Inferencecited by 193
  17. 2023PTQD: Accurate Post-Training Quantization for Diffusion Modelscited by 170
  18. 2023QA-LoRA: Quantization-Aware Low-Rank Adaptation of Large Language Modelscited by 155
  19. 2023Dual Aggregation Transformer for Image Super-Resolutioncited by 124
  20. 2022Cross Aggregation Transformer for Image Restorationcited by 92
  21. 2023Temporal Dynamic Quantization for Diffusion Modelscited by 81
  22. 2021Nonuniform-to-Uniform Quantization: Towards Accurate Quantization via Generalized Straight-Through Estimationcited by 79
  23. 2023EfficientDM: Efficient Quantization-Aware Fine-Tuning of Low-Bit Diffusion Modelscited by 78
  24. 2023Towards Accurate Post-Training Quantization for Vision Transformercited by 71
  25. 2024An empirical study of LLaMA3 quantization: from LLMs to MLLMscited by 64
  26. 2024QuEST: Low-bit Diffusion Model Quantization via Efficient Selective Finetuningcited by 49
  27. 2023Towards Accurate Post-training Quantization for Diffusion Modelscited by 47
  28. 2023SmoothQuant+: Accurate and Efficient 4-bit Post-Training WeightQuantization for LLMcited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 5; 2026: 4.

9 papers.

  1. 2025Low-bit Model Quantization for Deep Neural Networks: A Surveycited by 11
  2. 2026OP4KSR: One-Step Patch-Free 4K Super-Resolution with Periodic Artifact Suppressioncited by 2
  3. 2025OmniScaleSR: Unleashing Scale-Controlled Diffusion Prior for Faithful and Realistic Arbitrary-Scale Image Super-Resolutioncited by 1
  4. 2026LSGQuant: Layer-Sensitivity Guided Quantization for One-Step Diffusion Real-World Video Super-Resolutioncited by 1
  5. 2026SR-Ground: Image Quality Grounding for Super-Resolved Contentcited by 1
  6. 2025QArtSR: Quantization via Reverse-Module and Timestep-Retraining in One-Step Diffusion based Image Super-Resolutioncited by 0
  7. 2025QuantFace: Efficient Quantization for Face Restorationcited by 0
  8. 2025Cat: Post-Training Quantization Error Reduction via Cluster-based Affine Transformationcited by 0
  9. 2026LatentQuant: Preserving the Policy-Facing Latent Contract under NVFP4 VAE Quantizationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Q-DiT4SR: Exploration of Detail-Preserving Diffusion Transformer Quantization for Real-World Image Super-Resolution
  2. 2025Q-Sched: Pushing the Boundaries of Few-Step Diffusion Models with Quantization-Aware Scheduling
  3. 2026TEASR: Training-Efficient Any-Step Diffusion Transformer for Real-World Image Super-Resolution
  4. 2023Post-training Quantization for Text-to-Image Diffusion Models with Progressive Calibration and Activation Relaxing
  5. 2025QuantVSR: Low-Bit Post-Training Quantization for Real-World Video Super-Resolution
  6. 2024You Only Need One Step: Fast Super-Resolution with Stable Diffusion via Scale Distillation
  7. 2024PQD: Post-training Quantization for Efficient Diffusion Models
  8. 20242DQuant: Low-bit Post-Training Quantization for Image Super-Resolution