7 papers · 1 filter
Complexity-Balanced Diffusion Splitting
Noam Issachar, Dani Lischinski, Raanan Fattal
Standard continuous-time generative models rely on monolithic architectures that must navigate vastly different signal regimes, from isotropic noise to intricate data distributions…
DyPE: Dynamic Position Extrapolation for Ultra High Resolution Diffusion
Noam Issachar, Guy Yariv, Sagie Benaim +3
Diffusion Transformer models can generate images with remarkable fidelity and detail, yet training them at ultra-high resolutions remains extremely costly due to the self-attention…
Generative Lines Matching Models
Ori Matityahu, Raanan Fattal
In this paper we identify the source of a singularity in the training loss of key denoising models, that causes the denoiser's predictions to collapse towards the mean of the sourc…
Single Image Object Counting and Localizing using Active-Learning
Inbar Huberman-Spiegelglas, Raanan Fattal
The need to count and localize repeating objects in an image arises in different scenarios, such as biological microscopy studies, production lines inspection, and surveillance rec…
Deblurring using Analysis-Synthesis Networks Pair
Adam Kaufman, Raanan Fattal
Blind image deblurring remains a challenging problem for modern artificial neural networks. Unlike other image restoration problems, deblurring networks fail behind the performance…
Detecting Repeating Objects using Patch Correlation Analysis
Inbar Huberman, Raanan Fattal
In this paper we describe a new method for detecting and counting a repeating object in an image. While the method relies on a fairly sophisticated deformable part model, unlike ex…
Reducing Lateral Visual Biases in Displays
Inbar Huberman, Raanan Fattal
The human visual system is composed of multiple physiological components that apply multiple mechanisms in order to cope with the rich visual content it encounters. The complexity…