Subspace Diffusion Generative Models

Jing, Bowen; Corso, Gabriele; Berlinghieri, Renato; Jaakkola, Tommi S.

doi:10.1007/978-3-031-20050-2_17

Cited by 44 publications

(51 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, the method is currently intended for offline processing only. However, the fast pace of advancements in diffusion models provides a promising outlook on substantial speed-up of the reverse diffusion process [51]. Given the flexibility of the proposed method, improved sampling schemes are easily adopted, potentially enabling real-time implementation in the future.…”

Section: Discussionmentioning

confidence: 99%

Accelerated Intravascular Ultrasound Imaging using Deep Reinforcement Learning

Stevens

Chennakeshava

Bruijn

et al. 2022

ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

Echocardiography has been a prominent tool for the diagnosis of cardiac disease. However, these diagnoses can be heavily impeded by poor image quality. Acoustic clutter emerges due to multipath reflections imposed by layers of skin, subcutaneous fat, and intercostal muscle between the transducer and heart. As a result, haze and other noise artifacts pose a real challenge to cardiac ultrasound imaging. In many cases, especially with difficult-to-image patients such as patients with obesity, a diagnosis from B-Mode ultrasound imaging is effectively rendered unusable, forcing sonographers to resort to contrast-enhanced ultrasound examinations or refer patients to other imaging modalities. Tissue harmonic imaging has been a popular approach to combat haze, but in severe cases is still heavily impacted by haze. Alternatively, denoising algorithms are typically unable to remove highly structured and correlated noise, such as haze. It remains a challenge to accurately describe the statistical properties of structured haze, and develop an inference method to subsequently remove it. Diffusion models have emerged as powerful generative models and have shown their effectiveness in a variety of inverse problems. In this work, we present a joint posterior sampling framework that combines two separate diffusion models to model the distribution of both clean ultrasound and haze in an unsupervised manner. Furthermore, we demonstrate techniques for effectively training diffusion models on radiofrequency ultrasound data and highlight the advantages over image data. Experiments on both in-vitro and in-vivo cardiac datasets show that the proposed dehazing method effectively removes haze while preserving signals from weakly reflected tissue.

show abstract

Section: Discussionmentioning

confidence: 99%

Accelerated Intravascular Ultrasound Imaging using Deep Reinforcement Learning

Stevens

Chennakeshava

Bruijn

et al. 2022

ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

show abstract

“…Subspace diffusion models [Jing et al, 2022] also consider correlated diffusion, with a particular emphasis on focusing the diffusion to most relevant factors of variation for statistical and computational efficiency. Additionally, latent-space diffusion models [Rombach et al, 2022] might be viewed as learning a transformed coordinate system in which the diffusion process can more efficiently model the targer distribution.…”

Section: Supplementary Informationmentioning

confidence: 99%

Illuminating protein space with a programmable generative model

Ingraham

Baranov

Costello

et al. 2022

Preprint

View full text Add to dashboard Cite

Three billion years of evolution have produced a tremendous diversity of protein molecules, and yet the full potential of this molecular class is likely far greater. Accessing this potential has been challenging for computation and experiments because the space of possible protein molecules is much larger than the space of those likely to host function. Here we introduce Chroma, a generative model for proteins and protein complexes that can directly sample novel protein structures and sequences and that can be conditioned to steer the generative process towards desired properties and functions. To enable this, we introduce a diffusion process that respects the conformational statistics of polymer ensembles, an efficient neural architecture for molecular systems based on random graph neural networks that enables long-range reasoning with sub-quadratic scaling, equivariant layers for efficiently synthesizing 3D structures of proteins from predicted inter-residue geometries, and a general low-temperature sampling algorithm for diffusion models. We suggest that Chroma can effectively realize protein design as Bayesian inference under external constraints, which can involve symmetries, substructure, shape, semantics, and even natural language prompts. With this unified approach, we hope to accelerate the prospect of programming protein matter for human health, materials science, and synthetic biology.

show abstract

“…In this work, we leverage the recently popularized class of denoising diffusion models, , which have already shown promising results for protein structure generation, − conformer generation, and docking . In particular, we train a score-based generative model on CG structures sampled from the CG equilibrium distribution.…”

Section: Introductionmentioning

confidence: 99%

Two for One: Diffusion Models and Force Fields for Coarse-Grained Molecular Dynamics

Arts,

Garcia Satorras,

Huang

et al. 2023

J. Chem. Theory Comput.

View full text Add to dashboard Cite

Subspace Diffusion Generative Models

Cited by 44 publications

References 2 publications

Accelerated Intravascular Ultrasound Imaging using Deep Reinforcement Learning

Accelerated Intravascular Ultrasound Imaging using Deep Reinforcement Learning

Illuminating protein space with a programmable generative model

Two for One: Diffusion Models and Force Fields for Coarse-Grained Molecular Dynamics

Contact Info

Product

Resources

About