Improving 3D Imaging with Pre-Trained Perpendicular 2D Diffusion Models

Diffusion models have become a popular approach for image generation and reconstruction due to their numerous advantages. However, most diffusion-based inverse problem-solving methods only deal with 2D images, and even recently published 3D methods do not fully exploit the 3D distribution prior. To address this, we propose a novel approach using two perpendicular pre-trained 2D diffusion models to solve the 3D inverse problem. By modeling the 3D data distribution as a product of 2D distributions sliced in different directions, our method effectively addresses the curse of dimensionality. Our experimental results demonstrate that our method is highly effective for 3D medical image reconstruction tasks, including MRI Z-axis super-resolution, compressed sensing MRI, and sparse-view CT. Our method can generate high-quality voxel volumes suitable for medical applications.

[1]  Seung Wook Kim,et al.  Align Your Latents: High-Resolution Video Synthesis with Latent Diffusion Models , 2023, 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[2]  Yu Takagi,et al.  High-resolution image reconstruction with latent diffusion models from human brain activity , 2023, bioRxiv.

[3]  Y. Matias,et al.  Dreamix: Video Diffusion Models are General Video Editors , 2023, ArXiv.

[4]  M. Nießner,et al.  DiffRF: Rendering-Guided 3D Radiance Field Diffusion , 2022, 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[5]  Yinhuai Wang,et al.  Zero-Shot Image Restoration Using Denoising Diffusion Null-Space Model , 2022, ICLR.

[6]  Jiajun Wu,et al.  3D Neural Field Generation Using Triplane Diffusion , 2022, 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[7]  J. C. Ye,et al.  Parallel Diffusion Models of Operator and Image for Blind Inverse Problems , 2022, 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[8]  Michael T. McCann,et al.  Solving 3D Inverse Problems Using Pre-Trained 2D Diffusion Models , 2022, 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[9]  J. Zhou,et al.  Seeing Beyond the Brain: Conditional Diffusion Model with Sparse Masked Modeling for Vision Decoding , 2022, 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[10]  Weifeng Lv,et al.  GraphGDP: Generative Diffusion Processes for Permutation Invariant Graph Generation , 2022, 2022 IEEE International Conference on Data Mining (ICDM).

[11]  Michael T. McCann,et al.  Diffusion Posterior Sampling for General Noisy Inverse Problems , 2022, ICLR.

[12]  V. Cevher,et al.  DiGress: Discrete Denoising diffusion for graph generation , 2022, ICLR.

[13]  Yaniv Taigman,et al.  Make-A-Video: Text-to-Video Generation without Text-Video Data , 2022, ICLR.

[14]  Jonathan Ho Classifier-Free Diffusion Guidance , 2022, ArXiv.

[15]  J. C. Ye,et al.  Improving Diffusion Models for Inverse Problems using Manifold Constraints , 2022, Neural Information Processing Systems.

[16]  Xiang Lisa Li,et al.  Diffusion-LM Improves Controllable Text Generation , 2022, NeurIPS.

[17]  David J. Fleet,et al.  Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding , 2022, NeurIPS.

[18]  Max W. Y. Lam,et al.  FastDiff: A Fast Conditional Diffusion Model for High-Quality Speech Synthesis , 2022, IJCAI.

[19]  Prafulla Dhariwal,et al.  Hierarchical Text-Conditional Image Generation with CLIP Latents , 2022, ArXiv.

[20]  Timothy S. Coalson,et al.  Surface Vision Transformers: Attention-Based Modelling applied to Cortical Analysis , 2022, MIDL.

[21]  Michael Elad,et al.  Denoising Diffusion Restoration Models , 2022, NeurIPS.

[22]  Jeffrey A. Fessler,et al.  Sparse-View Cone Beam CT Reconstruction Using Data-Consistent Supervised and Adversarial Learning From Scarce Training Data , 2022, IEEE Transactions on Computational Imaging.

[23]  B. Ommer,et al.  High-Resolution Image Synthesis with Latent Diffusion Models , 2021, 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[24]  S. Ermon,et al.  Solving Inverse Problems in Medical Imaging with Score-Based Generative Models , 2021, ICLR.

[25]  Jong-Chul Ye,et al.  Score-based diffusion models for accelerated MRI , 2021, Medical Image Anal..

[26]  Kwanyoung Kim,et al.  Noise2Score: Tweedie's Approach to Self-Supervised Image Denoising without Clean Images , 2021, NeurIPS.

[27]  Tasnima Sadekova,et al.  Grad-TTS: A Diffusion Probabilistic Model for Text-to-Speech , 2021, ICML.

[28]  Prafulla Dhariwal,et al.  Diffusion Models Beat GANs on Image Synthesis , 2021, NeurIPS.

[29]  Stephan J. Garbin,et al.  FastNeRF: High-Fidelity Neural Rendering at 200FPS , 2021, 2021 IEEE/CVF International Conference on Computer Vision (ICCV).

[30]  Abhishek Kumar,et al.  Score-Based Generative Modeling through Stochastic Differential Equations , 2020, ICLR.

[31]  Bryan Catanzaro,et al.  DiffWave: A Versatile Diffusion Model for Audio Synthesis , 2020, ICLR.

[32]  Pieter Abbeel,et al.  Denoising Diffusion Probabilistic Models , 2020, NeurIPS.

[33]  Bo Zhou,et al.  DuDoRNet: Learning a Dual-Domain Recurrent Network for Fast MRI Reconstruction With Deep T1 Prior , 2020, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[34]  Yang Song,et al.  Generative Modeling by Estimating Gradients of the Data Distribution , 2019, NeurIPS.

[35]  Baiyu Chen,et al.  Low‐dose CT for the detection and classification of metastatic liver lesions: Results of the 2016 Low Dose CT Grand Challenge , 2017, Medical physics.

[36]  Yunming Ye,et al.  DeepFM: A Factorization-Machine based Neural Network for CTR Prediction , 2017, IJCAI.

[37]  Michael Unser,et al.  Deep Convolutional Neural Network for Inverse Problems in Imaging , 2016, IEEE Transactions on Image Processing.

[38]  Thomas Brox,et al.  U-Net: Convolutional Networks for Biomedical Image Segmentation , 2015, MICCAI.

[39]  Nick C Fox,et al.  Using visual rating to diagnose dementia: a critical evaluation of MRI atrophy scales , 2015, Journal of Neurology, Neurosurgery & Psychiatry.

[40]  Surya Ganguli,et al.  Deep Unsupervised Learning using Nonequilibrium Thermodynamics , 2015, ICML.

[41]  Arno Klein,et al.  Large-scale evaluation of ANTs and FreeSurfer cortical thickness measurements , 2014, NeuroImage.

[42]  Ebru Arisoy,et al.  Low-rank matrix factorization for Deep Neural Network training with high-dimensional output targets , 2013, 2013 IEEE International Conference on Acoustics, Speech and Signal Processing.

[43]  B. Efron Tweedie’s Formula and Selection Bias , 2011, Journal of the American Statistical Association.

[44]  Pascal Vincent,et al.  A Connection Between Score Matching and Denoising Autoencoders , 2011, Neural Computation.

[45]  D. Donoho,et al.  Sparse MRI: The application of compressed sensing for rapid MR imaging , 2007, Magnetic resonance in medicine.

[46]  Eero P. Simoncelli,et al.  Image quality assessment: from error visibility to structural similarity , 2004, IEEE Transactions on Image Processing.

[47]  Frederik Barkhof,et al.  White Matter Changes on CT and MRI: An Overview of Visual Rating Scales , 1998, European Neurology.

[48]  B. Anderson Reverse-time diffusion equation models , 1982 .