mlsanityData to 7 Oct 2026

TAFG-MAN: Timestep-Adaptive Frequency-Gated Latent Diffusion for Efficient and High-Quality Low-Dose CT Image Denoising

arXiv 2603.20868 ↗First posted 21 Mar 2026cs.CVcited by 0

On the map: Diffusion models → Medical imaging and segmentation

Abstract (arXiv)

Low-dose computed tomography (LDCT) reduces radiation exposure but also introduces substantial noise and structural degradation, making it difficult to suppress noise without erasing subtle anatomical details. In this paper, we present TAFG-MAN, a latent diffusion framework for efficient and high-quality LDCT image denoising. The framework combines a perceptually optimized autoencoder, conditional latent diffusion restoration in a compact latent space, and a lightweight Timestep-Adaptive Frequency-Gated (TAFG) conditioning design. TAFG decomposes condition features into low- and high-frequency components, predicts timestep-adaptive gates from the current denoising feature and timestep embedding, and progressively releases high-frequency guidance in later denoising stages before cross-attention. In this way, the model relies more on stable structural guidance at early reverse steps and introduces fine details more cautiously as denoising proceeds, improving the balance between noise suppression and detail preservation. Experiments show that TAFG-MAN achieves a favorable quality-efficiency trade-off against representative baselines. Compared with its base variant without TAFG, it further improves detail preservation and perceptual quality while maintaining essentially the same inference cost, and ablation results confirm the effectiveness of the proposed conditioning mechanism.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Medical imaging and segmentation, one of 14 directions in Diffusion models. Builds on 19 of its 29 references that are in the map. First posted on arXiv 21 Mar 2026.

Builds on

19 of 29 references.

Closest ancestors · 4

Same direction, newest first

  1. 2025MAN: Latent Diffusion Enhanced Multistage Anti-Noise Network for Efficient and High-Quality Low-Dose CT Image Denoising28 Sep
  2. 2024Fast-DDPM: Fast Denoising Diffusion Probabilistic Models for Medical Image-to-Image Generation23 May
  3. 2023Diffusion Probabilistic Priors for Zero-Shot Low-Dose CT Image Denoising25 May
  4. 2023Zero-shot Medical Image Translation via Frequency-Guided Diffusion Models5 Apr

Other references · 15

  1. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  2. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  3. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  4. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  5. 2020Denoising Diffusion Implicit Modelscited by 9,655
  6. 2017Squeeze-and-Excitation Networkscited by 4,763
  7. 2021Improved Denoising Diffusion Probabilistic Modelscited by 3,736
  8. 2017FiLM: Visual Reasoning with a General Conditioning Layercited by 2,286
  9. 2017Low-Dose CT with a Residual Encoder-Decoder Convolutional Neural Network (RED-CNN)cited by 224
  10. 2017Low Dose CT Image Denoising Using a Generative Adversarial Network with Wasserstein Distance and Perceptual Losscited by 161
  11. 2021DU-GAN: Generative Adversarial Networks with Dual-Domain U-Net Based Discriminators for Low-Dose CT Denoisingcited by 46
  12. 2019Quadratic Autoencoder (Q-AE) for Low-dose CT Denoisingcited by 35
3 more
  1. 2023A Unified Conditional Framework for Diffusion-based Image Restorationcited by 22
  2. 2024WaveFace: Authentic Face Restoration with Efficient Frequency Recoverycited by 20
  3. 2024Frequency-Guided Posterior Sampling for Diffusion-Based Image Restorationcited by 10

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025FoundDiff: Foundational Diffusion Model for Generalizable Low-Dose CT Denoising
  2. 2023CoreDiff: Contextual Error-Modulated Generalized Diffusion Model for Low-Dose CT Denoising and Generalization
  3. 2022Low-Dose CT Using Denoising Diffusion Probabilistic Model for 20× Speedup
  4. 2026ProSAC-CT: Progressive Spectral-Anatomical Co-Guided Multi-Stage Diffusion Model for Low-Dose CT Denoising
  5. 2026RDDM: A Residual-Driven Drifting Model for High-Fidelity Low-Dose CT Denoising
  6. 2025FD-DiT: Frequency Domain-Directed Diffusion Transformer for Low-Dose CT Reconstruction
  7. 2024HC3L-Diff: Hybrid conditional latent diffusion with high frequency enhancement for CBCT-to-CT synthesis
  8. 2025AST-n: A Fast Sampling Approach for Low-Dose CT Reconstruction using Diffusion Models