REVIEW 5 cited by
Tutorial on Diffusion Models for Imaging and Vision
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
The astonishing growth of generative tools in recent years has empowered many exciting applications in text-to-image generation and text-to-video generation. The underlying principle behind these generative tools is the concept of diffusion, a particular sampling mechanism that has overcome some shortcomings that were deemed difficult in the previous approaches. The goal of this tutorial is to discuss the essential ideas underlying the diffusion models. The target audience of this tutorial includes undergraduate and graduate students who are interested in doing research on diffusion models or applying these models to solve other problems.
Forward citations
Cited by 5 Pith papers
-
Flow Equivariant World Models: Memory for Partially Observed Dynamic Environments
Flow equivariant world models use a latent memory that shifts with the agent and with inferred object motion, giving stable long-horizon prediction under partial observability.
-
Object-centric Denoising Diffusion Models for Physical Reasoning
An object-centric diffusion model generates multi-object trajectories with conditioning at arbitrary time steps, demonstrated on the PHYRE physics benchmark.
-
Clustering via Self-Supervised Diffusion
CLUDI trains a student to imitate stochastic diffusion-generated cluster assignments on pre-trained DINO image features and averages multiple assignments to cluster images.
-
Unrolling Nonconvex Graph Total Variation for Image Denoising
NC-GTV introduces a graph Huber function and Gershgorin-circle-based convexity parameter selection, then unrolls the ADMM solver into a lightweight feed-forward denoising network that matches larger CNNs with far fewe...
-
Advancing MRI Reconstruction: A Systematic Review of Deep Learning and Compressed Sensing Integration
A systematic review of 130 papers showing that deep learning methods, especially unrolled networks with data consistency layers, dominate modern accelerated MRI reconstruction.
Discussion (0). Continue with ORCID to comment.