242 citations · 342 across the 14 of their papers we have counts for
8 papers · 1 filter
Accelerating Text-to-Video Generation with Calibrated Sparse Attention
Shai Yehezkel, Shahar Yadin, Noam Elata +2
Recent diffusion models enable high-quality video generation, but suffer from slow runtimes. The large transformer-based backbones used in these models are bottlenecked by spatiote…
Novel View Synthesis with Pixel-Space Diffusion Models
Noam Elata, Bahjat Kawar, Yaron Ostrovsky-Berman +2
Synthesizing a novel view from a single input image is a challenging task. Traditionally, this task was approached by estimating scene depth, warping, and inpainting, with machine…
Nested Diffusion Processes for Anytime Image Generation
Noam Elata, Bahjat Kawar, Tomer Michaeli +1
Diffusion models are the current state-of-the-art in image generation, synthesizing high-quality images by breaking down the generation process into many fine-grained denoising ste…
Editing Implicit Assumptions in Text-to-Image Diffusion Models
Hadas Orgad, Bahjat Kawar, Yonatan Belinkov
Text-to-image diffusion models often make implicit assumptions about the world when generating images. While some assumptions are useful (e.g., the sky is blue), they can also be o…
Imagic: Text-Based Real Image Editing with Diffusion Models
Bahjat Kawar, Shiran Zada, Oran Lang +5
Text-conditioned image editing has recently attracted considerable interest. However, most methods are currently either limited to specific editing types (e.g., object overlay, sty…
Enhancing Diffusion-Based Image Synthesis with Robust Classifier Guidance
Bahjat Kawar, Roy Ganz, Michael Elad
Denoising diffusion probabilistic models (DDPMs) are a recent family of generative models that achieve state-of-the-art results. In order to obtain class-conditional generation, it…
Threat Model-Agnostic Adversarial Defense using Diffusion Models
Tsachi Blau, Roy Ganz, Bahjat Kawar +2
Deep Neural Networks (DNNs) are highly sensitive to imperceptible malicious perturbations, known as adversarial attacks. Following the discovery of this vulnerability in real-world…
Do Perceptually Aligned Gradients Imply Adversarial Robustness?
Roy Ganz, Bahjat Kawar, Michael Elad
Adversarially robust classifiers possess a trait that non-robust models do not -- Perceptually Aligned Gradients (PAG). Their gradients with respect to the input align well with hu…