997 citations · 2.4k across the 65 of their papers we have counts for
8 papers · 2 filters
Uncertainty Visualization via Low-Dimensional Posterior Projections
Omer Yair, Elias Nehme, Tomer Michaeli
In ill-posed inverse problems, it is commonly desirable to obtain insight into the full spectrum of plausible solutions, rather than extracting only a single reconstruction. Inform…
From Posterior Sampling to Meaningful Diversity in Image Restoration
Noa Cohen, Hila Manor, Yuval Bahat +1
Image restoration problems are typically ill-posed in the sense that each degraded image can be restored in infinitely many valid ways. To accommodate this, many works generate a d…
Uncertainty Quantification via Neural Posterior Principal Components
Elias Nehme, Omer Yair, Tomer Michaeli
Uncertainty quantification is crucial for the deployment of image restoration models in safety-critical domains, like autonomous driving and biological imaging. To date, methods fo…
On the Posterior Distribution in Denoising: Application to Uncertainty Quantification
Hila Manor, Tomer Michaeli
Denoisers play a central role in many applications, from noise suppression in low-grade imaging sensors, to empowering score-based generative models. The latter category of methods…
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…
An Edit Friendly DDPM Noise Space: Inversion and Manipulations
Inbar Huberman-Spiegelglas, Vladimir Kulikov, Tomer Michaeli
Denoising diffusion probabilistic models (DDPMs) employ a sequence of white Gaussian noise samples to generate an image. In analogy with GANs, those noise maps could be considered…
Alias-Free Convnets: Fractional Shift Invariance via Polynomial Activations
Hagay Michaeli, Tomer Michaeli, Daniel Soudry
Although CNNs are believed to be invariant to translations, recent works have shown this is not the case, due to aliasing effects that stem from downsampling layers. The existing a…
Discovering Interpretable Directions in the Semantic Latent Space of Diffusion Models
René Haas, Inbar Huberman-Spiegelglas, Rotem Mulayoff +3
Denoising Diffusion Models (DDMs) have emerged as a strong competitor to Generative Adversarial Networks (GANs). However, despite their widespread use in image synthesis and editin…