ADOBI: Adaptive Diffusion Bridge For Blind Inverse Problems with Application to MRI Reconstruction
On the map: Diffusion models → Inverse problems and image restoration
Abstract (arXiv)
Diffusion bridges (DB) have emerged as a promising alternative to diffusion models for imaging inverse problems, achieving faster sampling by directly bridging low- and high-quality image distributions. While incorporating measurement consistency has been shown to improve performance, existing DB methods fail to maintain this consistency in blind inverse problems, where the forward model is unknown. To address this limitation, we introduce ADOBI (Adaptive Diffusion Bridge for Inverse Problems), a novel framework that adaptively calibrates the unknown forward model to enforce measurement consistency throughout sampling iterations. Our adaptation strategy allows ADOBI to achieve high-quality parallel magnetic resonance imaging (PMRI) reconstruction in only 5-10 steps. Our numerical results show that ADOBI consistently delivers state-of-the-art performance, and further advances the Pareto frontier for the perception-distortion trade-off.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Placed in Inverse problems and image restoration, one of 14 directions in Diffusion models. Builds on 42 of its 62 references that are in the map. First posted on arXiv 25 Nov 2024.
Builds on
42 of 62 references.
Closest ancestors · 13
Same direction, newest first
- 2024Blind Inversion using Latent Diffusion Priors1 Jul
- 2024Principled Probabilistic Imaging using Diffusion Models as Plug-and-Play Priors29 May
- 2023Solving Inverse Problems with Latent Diffusion Models via Hard Data Consistency16 Jul
- 2023Direct Diffusion Bridge using Data Consistency for Inverse Problems31 May
- 2023Denoising Diffusion Models for Plug-and-Play Image Restoration15 May
- 2023Score-Based Diffusion Models as Principled Priors for Inverse Imaging23 Apr
- 2023Decomposed Diffusion Sampler for Accelerating Large-Scale Inverse Problems10 Mar
- 2023GibbsDDRM: A Partially Collapsed Gibbs Sampler for Solving Blind Inverse Problems with Denoising Diffusion Restoration30 Jan
- 2022Multiscale Structure Guided Diffusion for Image Deblurring4 Dec
- 2022Parallel Diffusion Models of Operator and Image for Blind Inverse Problems19 Nov
- 2022Diffusion Posterior Sampling for General Noisy Inverse Problems29 Sep
- 2021Come-Closer-Diffuse-Faster: Accelerating Conditional Diffusion Models for Inverse Problems through Stochastic Contraction9 Dec
1 more
- 2021Deblurring via Stochastic Refinement5 Dec
Other references · 29
- 2020Denoising Diffusion Probabilistic Modelscited by 21,076
- 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
- 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 9,122
- 2021SwinIR: Image Restoration Using Swin Transformercited by 1,887
- 2022Diffusion Models in Vision: A Surveycited by 1,015
- 2018fastMRI: An Open Dataset and Benchmarks for Accelerated MRIcited by 470
- 2016Deep Convolutional Neural Network for Inverse Problems in Imagingcited by 433
- 2019Algorithm Unrolling: Interpretable, Efficient Deep Learning for Signal and Image Processingcited by 421
- 2017MoDL: Model Based Deep Learning Architecture for Inverse Problemscited by 387
- 2016The Little Engine that Could: Regularization by Denoising (RED)cited by 307
- 2020Deep Learning Techniques for Inverse Problems in Imagingcited by 291
- 2017Low-Dose CT with a Residual Encoder-Decoder Convolutional Neural Network (RED-CNN)cited by 224
17 more
- 2023I2SB: Image-to-Image Schr"odinger Bridgecited by 218
- 2020End-to-End Variational Networks for Accelerated MRI Reconstructioncited by 202
- 2023Diffusion Schr"odinger Bridge Matchingcited by 153
- 2021Deep Equilibrium Architectures for Inverse Problems in Imagingcited by 127
- 2022Adaptive Diffusion Priors for Accelerated MRI Reconstructioncited by 118
- 2016A deep convolutional neural network using directional wavelets for low-dose X-ray CT reconstructioncited by 87
- 2017A Review of Convolutional Neural Networks for Inverse Problems in Imagingcited by 81
- 2022Measurement-conditioned Denoising Diffusion Probabilistic Model for Under-sampled Medical Image Reconstructioncited by 65
- 2017Model based learning for accelerated, limited-view 3D photoacoustic tomographycited by 45
- 2020Projected Distribution Loss for Image Enhancementcited by 29
- 2024Similarity and Quality Metrics for MR Image-To-Image Translationcited by 20
- 2021Deep J-Sense: Accelerated MRI Reconstruction via Unrolled Alternating Optimizationcited by 19
- 2023Learning Fourier-Constrained Diffusion Bridges for MRI Reconstructioncited by 14
- 2023A Restoration Network as an Implicit Priorcited by 13
- 2023Kernel Diffusion: An Alternate Approach to Blind Deconvolutioncited by 13
- 2022SPICER: Self-Supervised Learning for MRI with Automatic Coil Sensitivity Estimation and Reconstructioncited by 10
- 2023Block Coordinate Plug-and-Play Methods for Blind Inverse Problemscited by 8
Built on by
Citing papers per year: 2026: 1.
1 paper.
Similar, not cited
Close in wording, no citation either way
- 2025Plug-and-Play Posterior Sampling for Blind Inverse Problems
- 2025Diffusion models for inverse problems
- 2025Automated Tuning for Diffusion Inverse Problem Solvers without Generative Prior Retraining
- 2025A Self-supervised Diffusion Bridge for MRI Reconstruction
- 2025Inference-Time Search Using Side Information for Diffusion-Based Image Reconstruction
- 2026Likelihood-Separable Diffusion Inference for Multi-Image MRI Super-Resolution
- 2024Enhancing and Accelerating Diffusion-Based Inverse Problem Solving through Measurements Optimization
- 2025Patch-Based Diffusion for Data-Efficient, Radiologist-Preferred MRI Reconstruction