Search Results for author:
Found 4 papers, 1 papers with code
V-LASIK: Consistent Glasses-Removal from Videos Using Synthetic Data
We show that despite data imperfection, by learning from our generated data and leveraging the prior of pretrained diffusion models, our model is able to perform the desired edit consistently while preserving the original video content.
Diffusing Colors: Image Colorization with Text Guided Diffusion
To tackle these issues, we present a novel image colorization framework that utilizes image diffusion techniques with granular text prompts.
Temporally stable video segmentation without video annotations
Temporally consistent dense video annotations are scarce and hard to collect.
Why do deep convolutional networks generalize so poorly to small image transformations?
Convolutional Neural Networks (CNNs) are commonly assumed to be invariant to small image transformations: either because of the convolutional architecture or because they were trained using data augmentation.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
