Models related to our paper "Covariance Mismatch in Diffusion Models".
AI & ML interests
The Image and Visual Representation Lab (IVRL) performs research that is primarily focused on the capture, analysis, and reproduction of color images. Aiming to improve everyone’s photographic experience, we develop algorithms and systems that help us understand, process, and measure images. Our research areas are computational photography, color image processing, computer vision, and image quality.
Recent Activity
-
Estimating Image Depth in the Comics Domain
Paper • 2110.03575 • Published • 1 -
Exploiting the Signal-Leak Bias in Diffusion Models
Paper • 2309.15842 • Published • 2 -
Vision Transformer Adapters for Generalizable Multitask Learning
Paper • 2308.12372 • Published • 1 -
NEMTO: Neural Environment Matting for Novel View and Relighting Synthesis of Transparent Objects
Paper • 2303.11963 • Published • 2
Models related to our paper "Covariance Mismatch in Diffusion Models".
-
Estimating Image Depth in the Comics Domain
Paper • 2110.03575 • Published • 1 -
Exploiting the Signal-Leak Bias in Diffusion Models
Paper • 2309.15842 • Published • 2 -
Vision Transformer Adapters for Generalizable Multitask Learning
Paper • 2308.12372 • Published • 1 -
NEMTO: Neural Environment Matting for Novel View and Relighting Synthesis of Transparent Objects
Paper • 2303.11963 • Published • 2
models 7
EPFL-IVRL/wsr
Unconditional Image Generation • Updated
EPFL-IVRL/sd3.5-medium-covariance-mismatch
Updated • 2
EPFL-IVRL/sd3.5-medium-colorednoiseDFT
Text-to-Image • Updated • 2
EPFL-IVRL/sd3.5-medium-colorednoiseDCT
Text-to-Image • Updated • 3
EPFL-IVRL/sd2.1-base-covariance-mismatch
Updated • 1
EPFL-IVRL/sd2.1-base-colorednoiseDFT
Text-to-Image • Updated • 1
EPFL-IVRL/sd2.1-base-colorednoiseDCT
Text-to-Image • Updated • 1