mlsanityData to 14 Oct 2026

Efficient Coarse-to-Fine Diffusion Models with Time Step Sequence Redistribution

arXiv 2603.21348 ↗First posted 22 Mar 2026cs.CVcited by 0

On the map: Diffusion models → Diffusion foundations and sampling

Abstract (arXiv)

Recently, diffusion models (DMs) have made significant strides in high-quality image generation. However, the multi-step denoising process often results in considerable computational overhead, impeding deployment on resource-constrained edge devices. Existing methods mitigate this issue by compressing models and adjusting the time step sequence. However, they overlook input redundancy and require lengthy search times. In this paper, we propose Coarse-to-Fine Diffusion Models with Time Step Sequence Redistribution. Recognizing indistinguishable early-stage generated images, we introduce Coarse-to-Fine Denoising (C2F) to reduce computation during coarse feature generation. Furthermore, we design Time Step Sequence Redistribution (TRD) for efficient sampling trajectory adjustment, requiring less than 10 minutes for search. Experimental results demonstrate that the proposed methods achieve near-lossless performance with an 80% to 90% reduction in computation on CIFAR10 and LSUN-Church.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Diffusion foundations and sampling, one of 14 directions in Diffusion models. Builds on 23 of its 27 references that are in the map. First posted on arXiv 22 Mar 2026.

Builds on

23 of 27 references.

Closest ancestors · 9

Same direction, newest first

  1. 2023AutoDiffusion: Training-Free Optimization of Time Steps and Architectures for Automated Diffusion Model Acceleration19 Sep
  2. 2023Structural Pruning for Diffusion Models18 May
  3. 2023Q-Diffusion: Quantizing Diffusion Models8 Feb
  4. 2022Post-training Quantization on Diffusion Models28 Nov
  5. 2022DPM-Solver++: Fast Solver for Guided Sampling of Diffusion Probabilistic Models2 Nov
  6. 2021High-Resolution Image Synthesis with Latent Diffusion Models20 Dec
  7. 2021Improved Denoising Diffusion Probabilistic Models18 Feb
  8. 2020Denoising Diffusion Implicit Models6 Oct
  9. 2020Denoising Diffusion Probabilistic Models19 Jun

Other references · 14

  1. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  2. 2022Generative Adversarial Networkscited by 5,627
  3. 2022Video Diffusion Modelscited by 2,305
  4. 2022Imagen Video: High Definition Video Generation with Diffusion Modelscited by 1,778
  5. 2022Make-A-Video: Text-to-Video Generation without Text-Video Datacited by 1,742
  6. 2022RePaint: Inpainting using Denoising Diffusion Probabilistic Modelscited by 1,430
  7. 2015LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loopcited by 1,355
  8. 2022Denoising Diffusion Restoration Modelscited by 963
  9. 2021Diffusion Probabilistic Models for 3D Point Cloud Generationcited by 735
  10. 2021SRDiff: Single Image Super-Resolution with Diffusion Probabilistic Modelscited by 415
  11. 2021Deblurring via Stochastic Refinementcited by 249
  12. 2023HoloDiffusion: Training a 3D Diffusion Model using 2D Imagescited by 106
2 more
  1. 2021A Conditional Point Diffusion-Refinement Paradigm for 3D Point Cloud Completioncited by 100
  2. 2023DiffFacto: Controllable Part-Based 3D Point Cloud Generation with Cross Diffusioncited by 32

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2023Fast Inference in Denoising Diffusion Models via MMD Finetuning
  2. 2025Generalized Denoising Diffusion Codebook Models (gDDCM): Tokenizing images using a pre-trained diffusion model
  3. 2025Optimal Stepsize for Diffusion Sampling
  4. 2022Progressive Deblurring of Diffusion Models for Coarse-to-Fine Image Synthesis
  5. 2023Parallel Sampling of Diffusion Models
  6. 2023ShiftDDPMs: Exploring Conditional Diffusion Models by Shifting Diffusion Trajectories
  7. 2024Beta Sampling is All You Need: Efficient Image Generation Strategy for Diffusion Models using Stepwise Spectral Analysis
  8. 2024Unified Directly Denoising for Both Variance Preserving and Variance Exploding Diffusion Models