Search Results for author:
Found 11 papers, 10 papers with code
Fast High-Resolution Image Synthesis with Latent Adversarial Diffusion Distillation
Distillation methods, like the recently introduced adversarial diffusion distillation (ADD) aim to shift the model from many-shot to single-step inference, albeit at the cost of expensive and difficult optimization due to its reliance on a fixed pretrained DINOv2 discriminator.
Scaling Rectified Flow Transformers for High-Resolution Image Synthesis
Rectified flow is a recent generative model formulation that connects data and noise in a straight line.
Adversarial Diffusion Distillation
We introduce Adversarial Diffusion Distillation (ADD), a novel training approach that efficiently samples large-scale foundational image diffusion models in just 1-4 steps while maintaining high image quality.
StyleGAN-T: Unlocking the Power of GANs for Fast Large-Scale Text-to-Image Synthesis
Text-to-image synthesis has recently seen significant progress thanks to large pretrained language models, large-scale training data, and the introduction of scalable model families such as diffusion and autoregressive models.
Ranked #19 on
Text-to-Image Generation
on MS COCO
VoxGRAF: Fast 3D-Aware Image Synthesis with Sparse Voxel Grids
State-of-the-art 3D-aware generative models rely on coordinate-based MLPs to parameterize 3D radiance fields.
StyleGAN-XL: Scaling StyleGAN to Large Diverse Datasets
StyleGAN in particular sets new standards for generative modeling regarding image quality and controllability.
Ranked #1 on
Image Generation
on CIFAR-10
(NFE metric)
Projected GANs Converge Faster
Generative Adversarial Networks (GANs) produce high-quality images but are challenging to train.
Ranked #1 on
Image Generation
on Stanford Cars
Counterfactual Generative Networks
Prior works on image classification show that instead of learning a connection to object shape, deep classifiers tend to exploit spurious correlations with low-level texture or the background for solving the classification task.
How to Make Deep RL Work in Practice
Additionally, techniques from supervised learning are often used by default but influence the algorithms in a reinforcement learning setting in different and not well-understood ways.
Tracking Holistic Object Representations
The framework leverages the idea of obtaining additional object templates during the tracking process.
Ranked #3 on
Visual Object Tracking
on VOT2017/18
Conditional Affordance Learning for Driving in Urban Environments
Most existing approaches to autonomous driving fall into one of two categories: modular pipelines, that build an extensive model of the environment, and imitation learning approaches, that map images directly to control outputs.
