mlsanityData to 14 Oct 2026

The Diffusion Duet: Harmonizing Dual Channels with Wavelet Suppression for Image Separation

arXiv 2602.13361 ↗First posted 13 Feb 2026cs.CVcited by 0

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

Abstract (arXiv)

Blind image separation (BIS) refers to the inverse problem of simultaneously estimating and restoring multiple independent source images from a single observation image under conditions of unknown mixing mode and without prior knowledge of the source images. Traditional methods relying on statistical independence assumptions or CNN/GAN variants struggle to characterize complex feature distributions in real scenes, leading to estimation bias, texture distortion, and artifact residue under strong noise and nonlinear mixing. This paper innovatively introduces diffusion models into dual-channel BIS, proposing an efficient Dual-Channel Diffusion Separation Model (DCDSM). DCDSM leverages diffusion models' powerful generative capability to learn source image feature distributions and reconstruct feature structures effectively. A novel Wavelet Suppression Module (WSM) is designed within the dual-branch reverse denoising process, forming an interactive separation network that enhances detail separation by exploiting the mutual coupling noise characteristic between source images. Extensive experiments on synthetic datasets containing rain/snow and complex mixtures demonstrate that DCDSM achieves state-of-the-art performance: 1) In image restoration tasks, it obtains PSNR/SSIM values of 35.0023 dB/0.9549 and 29.8108 dB/0.9243 for rain and snow removal respectively, outperforming Histoformer and LDRCNet by 1.2570 dB/0.9272 dB (PSNR) and 0.0262/0.0289 (SSIM) on average; 2) For complex mixture separation, the restored dual-source images achieve average PSNR and SSIM of 25.0049 dB and 0.7997, surpassing comparative methods by 4.1249 dB and 0.0926. Both subjective and objective evaluations confirm DCDSM's superiority in addressing rain/snow residue removal and detail preservation challenges.

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 56 of its 79 references that are in the map. First posted on arXiv 13 Feb 2026.

Builds on

56 of 79 references.

References · 56

  1. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  2. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  3. 2023GPT-4 Technical Reportcited by 18,396
  4. 2024The Llama 3 Herd of Modelscited by 14,715
  5. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  6. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,626
  7. 2015You Only Look Once: Unified, Real-Time Object Detectioncited by 4,852
  8. 2023Retrieval-Augmented Generation for Large Language Models: A Surveycited by 2,212
  9. 2024From Local to Global: A Graph RAG Approach to Query-Focused Summarizationcited by 1,453
  10. 2023LongLLMLingua: Accelerating and Enhancing LLMs in Long Context Scenarios via Prompt Compressioncited by 453
  11. 2023Is ChatGPT a Good NLG Evaluator? A Preliminary Studycited by 422
  12. 2023Ragas: Automated Evaluation of Retrieval Augmented Generationcited by 418
38 more
  1. 2025Seed1.5-VL Technical Reportcited by 373
  2. 2024LightRAG: Simple and Fast Retrieval-Augmented Generationcited by 315
  3. 2024Long-context LLMs Struggle with Long In-context Learningcited by 286
  4. 2023Blind Image Quality Assessment via Vision-Language Correspondence: A Multitask Learning Perspectivecited by 280
  5. 2024Self-Preference Bias in LLM-as-a-Judgecited by 258
  6. 2024OCRBench v2: An Improved Benchmark for Evaluating Large Multimodal Models on Visual Text Localization and Reasoningcited by 173
  7. 2023DocPedia: Unleashing the Power of Large Multimodal Model in the Frequency Domain for Versatile Document Understandingcited by 106
  8. 2024MTVQA: Benchmarking Multilingual Text-Centric Visual Question Answeringcited by 93
  9. 2024Medical Graph RAG: Towards Safe Medical Large Language Model via Graph Retrieval-Augmented Generationcited by 90
  10. 2024Enhancing Code LLMs with Reinforcement Learning in Code Generation: A Surveycited by 83
  11. 2025Dolphin: Document Image Parsing via Heterogeneous Anchor Promptingcited by 79
  12. 2023UniDoc: A Universal Large Multimodal Model for Simultaneous Text Detection, Recognition, Spotting and Understandingcited by 74
  13. 2024Late Chunking: Contextual Chunk Embeddings Using Long-Context Embedding Modelscited by 73
  14. 2024TabPedia: Towards Comprehensive Visual Table Understanding with Concept Synergycited by 71
  15. 2023SPTS v2: Single-Point Scene Text Spottingcited by 66
  16. 2022Few Could Be Better Than All: Feature Sampling and Grouping for Scene Text Detectioncited by 65
  17. 2024Attentive Eraser: Unleashing Diffusion Model's Object Removal Potential via Self-Attention Redirection Guidancecited by 63
  18. 2024TextSquare: Scaling up Text-Centric Visual Instruction Tuningcited by 62
  19. 2024A Bounding Box is Worth One Token: Interleaving Layout and Text in a Large Language Model for Document Understandingcited by 57
  20. 2024Harmonizing Visual Text Comprehension and Generationcited by 54
  21. 2023Multi-modal In-Context Learning Makes an Ego-evolving Scene Text Recognizercited by 53
  22. 2023Enhancing Knowledge Graph Construction Using Large Language Modelscited by 44
  23. 2024ParGo: Bridging Vision-Language with Partial and Global Viewscited by 40
  24. 2025Vision as LoRAcited by 37
  25. 2025Prolonged Reasoning Is Not All You Need: Certainty-Based Adaptive Routing for Efficient LLM/MLLM Reasoningcited by 35
  26. 2024Hermes 3 Technical Reportcited by 34
  27. 2022Optimal Boxes: Boosting End-to-End Scene Text Recognition by Adjusting Annotated Bounding Boxes via Reinforcement Learningcited by 33
  28. 2024MCTBench: Multimodal Cognition towards Text-Rich Visual Scenes Benchmarkcited by 26
  29. 2025WildDoc: How Far Are We from Achieving Comprehensive and Robust Document Understanding in the Wild?cited by 26
  30. 2025Advancing Sequential Numerical Prediction in Autoregressive Modelscited by 26
  31. 2025Evaluating Supervised Learning Models for Fraud Detection: A Comparative Study of Classical and Deep Architectures on Imbalanced Transaction Datacited by 20
  32. 2025SETransformer: A Hybrid Attention-Based Architecture for Robust Human Activity Recognitioncited by 19
  33. 2025Benchmarking Vision-Language Models on Chinese Ancient Documents: From OCR to Knowledge Reasoningcited by 19
  34. 2025CME-CAD: Heterogeneous Collaborative Multi-Expert Reinforcement Learning for CAD Code Generationcited by 19
  35. 2024Fine-Tuning Vision-Language Model for Automated Engineering Drawing Information Extractioncited by 18
  36. 2025Resolving Evidence Sparsity: Agentic Context Engineering for Long-Document Understandingcited by 18
  37. 2023Real-Time Idling Vehicles Detection using Combined Audio-Visual Deep Learningcited by 17
  38. 2023Translation and Fusion Improves Zero-shot Cross-lingual Information Extractioncited by 15

50 most cited of 56 All 56 (JSON)

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2023Residual Denoising Diffusion Models
  2. 2023WaveDM: Wavelet-Based Diffusion Models for Image Restoration
  3. 2025A Simple Combination of Diffusion Models for Better Quality Trade-Offs in Image Denoising
  4. 2024Frequency-Aware Guidance for Blind Image Restoration via Diffusion Models
  5. 2023Low-Light Image Enhancement with Wavelet-based Diffusion Models
  6. 2024Joint Conditional Diffusion Model for Image Restoration with Mixed Degradations
  7. 2022SinDDM: A Single Image Denoising Diffusion Model
  8. 2024Taming Generative Diffusion Prior for Universal Blind Image Restoration