Search Results for author:
Found 17 papers, 11 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.
Structure and Content-Guided Video Synthesis with Diffusion Models
Text-guided generative diffusion models unlock powerful image creation and editing tools.
Towards Unified Keyframe Propagation Models
We evaluate our two-stream approach for inpainting tasks, where experiments show that it improves both the propagation of features within a single frame as required for image inpainting, as well as their propagation from keyframes to target frames.
High-Resolution Image Synthesis with Latent Diffusion Models
By decomposing the image formation process into a sequential application of denoising autoencoders, diffusion models (DMs) achieve state-of-the-art synthesis results on image data and beyond.
Ranked #2 on
Layout-to-Image Generation
on COCO-Stuff 256x256
ImageBART: Bidirectional Context with Multinomial Diffusion for Autoregressive Image Synthesis
Thus, in contrast to pure autoregressive models, it can solve free-form image inpainting and, in the case of conditional models, local, text-guided image modification without requiring mask-specific training.
Ranked #4 on
Text-to-Image Generation
on Conceptual Captions
Geometry-Free View Synthesis: Transformers and no 3D Priors
Is a geometric model required to synthesize novel views from a single image?
Ranked #1 on
Novel View Synthesis
on RealEstate10K
Shape or Texture: Understanding Discriminative Features in CNNs
Contrasting the previous evidence that neurons in the later layers of a Convolutional Neural Network (CNN) respond to complex object shapes, recent studies have shown that CNNs actually exhibit a `texture bias': given an image with both texture and shape cues (e. g., a stylized image), a CNN is biased towards predicting the category corresponding to the texture.
Shape or Texture: Disentangling Discriminative Features in CNNs
Contrasting the previous evidence that neurons in the later layers of a Convolutional Neural Network (CNN) respond to complex object shapes, recent studies have shown that CNNs actually exhibit a 'texture bias': given an image with both texture and shape cues (e. g., a stylized image), a CNN is biased towards predicting the category corresponding to the texture.
Taming Transformers for High-Resolution Image Synthesis
We demonstrate how combining the effectiveness of the inductive bias of CNNs with the expressivity of transformers enables them to model and thereby synthesize high-resolution images.
Ranked #3 on
Text-to-Image Generation
on LHQC
A Note on Data Biases in Generative Models
It is tempting to think that machines are less prone to unfairness and prejudice.
Unsupervised Part Discovery by Unsupervised Disentanglement
Our approach leverages a generative model consisting of two disentangled representations for an object's shape and appearance and a latent variable for the part segmentation.
Making Sense of CNNs: Interpreting Deep Representations & Their Invariances with INNs
To open such a black box, it is, therefore, crucial to uncover the different semantic concepts a model has learned as well as those that it has learned to be invariant to.
Network-to-Network Translation with Conditional Invertible Neural Networks
Given the ever-increasing computational costs of modern machine learning models, we need to find new ways to reuse such expert models and thus tap into the resources that have been invested in their creation.
A Disentangling Invertible Interpretation Network for Explaining Latent Representations
We formulate interpretation as a translation of hidden representations onto semantic concepts that are comprehensible to the user.
Unsupervised Robust Disentangling of Latent Characteristics for Image Synthesis
In experiments on diverse object categories, the approach successfully recombines pose and appearance to reconstruct and retarget novel synthesized images.
A Variational U-Net for Conditional Appearance and Shape Generation
Experiments show that the model enables conditional image generation and transfer.
