-
SPI-GAN: DENOISING DIFFUSION GANS WITH STRAIGHT-PATH INTERPOLATIONS
Score-based generative models (SGMs) show the state-of-the-art sampling quality and diversity. However, their training/sampling complexity is notoriously high due to the highly... -
Mirror Diffusion Models
Diffusion models have successfully been applied to generative tasks in various continuous domains. However, applying diffusion to discrete categorical data remains a non-trivial... -
Bespoke Non-Stationary Solvers for Fast Sampling of Diffusion and Flow Models
The dataset used in the paper for Bespoke Non-Stationary (BNS) solvers for fast sampling of diffusion and flow models. -
SynthBuster dataset
The SynthBuster dataset is a collection of images generated by various diffusion models. -
One-dimensional Adapter to Rule Them All: Concepts, Diffusion Models and Eras...
The dataset used in the paper is a text-to-image diffusion model, which is a type of generative model that can generate images from text prompts. -
Single Motion Diffusion Model
Single Motion Diffusion Model, a model designed to learn the internal motifs of a single motion sequence with arbitrary topology and synthesize motions of arbitrary length that... -
FastDiff: A Fast Conditional Diffusion Model for High-Quality Speech Synthesis
FastDiff is a fast conditional diffusion model for high-quality speech synthesis. It employs a stack of time-aware location-variable convolutions with diverse receptive field... -
ControlNet dataset
ControlNet dataset for image generation -
MotionDiffuser: Controllable Multi-Agent Motion Prediction using Diffusion
MotionDiffuser is a learned representation for the joint distribution of future trajectories over multiple agents using diffusion models. -
Accelerating Convergence of Score-Based Diffusion Models, Provably
Diffusion models, while achieving remarkable empirical performance, often suffer from low sampling speed, due to extensive function evaluations needed during the sampling phase. -
CIFAR-10, CIFAR-100, and MNIST
The dataset used in the paper is a benchmark dataset for diffusion models, specifically denoising diffusion probabilistic models (DDPM). The dataset consists of images from... -
Diffusion-based Conditional ECG Generation with Structured State Space Models
Synthetic data generation is a promising solution to address privacy issues with the distribution of sensitive health data. Recently, diffusion models have set new standards for... -
Towards performant and reliable undersampled MR reconstruction via diffusion ...
Towards performant and reliable undersampled MR reconstruction via diffusion model sampling. -
High-frequency space diffusion models for accelerated MRI
High-frequency space diffusion models for accelerated MRI. -
Adding Conditional Control to Diffusion Models with Reinforcement Learning
Diffusion models are powerful generative models that allow for precise control over the characteristics of the generated samples. While these diffusion models trained on large... -
Particle Denoising Diffusion Sampler
Denoising diffusion models have become ubiquitous for generative modeling. The core idea is to transport the data distribution to a Gaussian by using a diffusion. Approximate... -
Spatio-temporal Diffusion Point Processes
Spatio-temporal point process (STPP) is a stochastic collection of points, where each point denotes an event x = (t, s) associated with time t and location s. STPP is a... -
GaussianDreamer: Fast Generation from Text to 3D Gaussians
The dataset used in the paper is not explicitly described, but it is mentioned that the authors used a 3D Gaussian Splatting representation to bridge the 3D and 2D diffusion...
