References & Further Reading

References

J. Ho, A. Jain, and P. Abbeel, Denoising diffusion probabilistic models, 2020
The paper that made diffusion models practical for image generation. Introduced the noise prediction parameterisation and the simplified training objective used throughout this chapter.
Y. Song and S. Ermon, Generative modeling by estimating gradients of the data distribution, 2019
Introduced score-based generative models via Langevin dynamics with noise-conditional score networks. The foundational paper for the score-matching perspective of diffusion models.
Y. Song, J. Sohl-Dickstein, D. P. Kingma, A. Kumar, S. Ermon, and B. Poole, Score-based generative modeling through stochastic differential equations, 2021
Unified score matching and diffusion models through the SDE framework. Introduced the VP-SDE, VE-SDE, and the probability flow ODE.
H. Chung, J. Kim, M. T. McCann, M. L. Klasky, and J. C. Ye, Diffusion posterior sampling for general noisy inverse problems, 2023
The DPS paper. Proposes modifying the reverse diffusion process with likelihood guidance via the Tweedie estimate. Demonstrates strong results on deblurring, inpainting, and super-resolution.
B. Kawar, M. Elad, S. Ermon, and J. Song, Denoising diffusion restoration models, 2022
DDRM paper introducing SVD-based null-space preservation for diffusion-based inverse problems.
Y. Wang, J. Yu, and J. Zhang, Zero-shot image restoration using denoising diffusion null-space model, 2023
DDNM paper introducing the pseudoinverse-based correction for zero-shot (no fine-tuning) diffusion restoration.
H. Chung, B. Sim, and J. C. Ye, Come-closer-diffuse-faster: accelerating conditional diffusion models for inverse problems through stochastic contraction, 2022
Introduced manifold constrained gradients (MCG) combining gradient guidance with hard projection.
Y. Zhu, K. Zhang, J. Liang, J. Cao, B. Wen, R. Timofte, and L. Van Gool, Denoising diffusion models for plug-and-play image restoration, 2023
DiffPIR paper integrating diffusion models into the HQS/PnP framework. Provides a principled connection between PnP and diffusion-based reconstruction.
J. Song, C. Meng, and S. Ermon, Denoising diffusion implicit models, 2021
DDIM paper enabling deterministic, accelerated sampling. Essential for making diffusion-based reconstruction practical.
C. Lu, Y. Zhou, F. Bao, J. Chen, C. Li, and J. Zhu, DPM-Solver: a fast ODE solver for diffusion probabilistic model sampling in around 10 steps, 2022
Exploited the semi-linear structure of the diffusion ODE for high-quality samples in 10--25 steps.
Y. Song, P. Dhariwal, M. Chen, and I. Sutskever, Consistency models, 2023
Introduced consistency models for one-step generation via distillation from diffusion models.
S. H. Chan, Tutorial on diffusion models for imaging and vision, 2024. [Link]
Comprehensive tutorial covering score matching, DDPM, DDIM, DPS, and applications to computational imaging. Excellent pedagogical resource for the material in this chapter.
L. Shen, L. Xing, and S. Ermon, Solving inverse problems in medical imaging with score-based generative models, 2022
Score-SDE approach to inverse problems applied to MRI and CT reconstruction. Directly relevant to RF imaging applications.
P. Vincent, A connection between score matching and denoising autoencoders, 2011
Foundational paper connecting score matching to denoising, establishing the theoretical basis for denoising score matching.
G. Daras, H. Chung, C.-L. Li, J. C. Ye, and A. G. Dimakis, A survey on diffusion models for inverse problems, 2024
Comprehensive survey of diffusion-based inverse problem methods. Provides unified notation and experimental comparisons across DPS, DDRM, DDNM, MCG, DiffPIR, and many variants.