activity
20192022
most citedVideo2StyleGAN: Disentangling Local and Global Variations in a Video

3 citations · 4 across the 2 of their papers we have counts for

collaborators

6 papers

cs.CV20223 cited

Video2StyleGAN: Disentangling Local and Global Variations in a Video

Rameen Abdal, Peihao Zhu, Niloy J. Mitra +1

Image editing using a pretrained StyleGAN generator has emerged as a powerful paradigm for facial editing, providing disentangled controls over age, expression, illumination, etc.…

cs.CV2021

Flow-Guided Video Inpainting with Scene Templates

Dong Lao, Peihao Zhu, Peter Wonka +1

We consider the problem of filling in missing spatio-temporal regions of a video. We provide a novel flow-based solution by introducing a generative model of images in relation to…

cs.CV2021

Labels4Free: Unsupervised Segmentation using StyleGAN

Rameen Abdal, Peihao Zhu, Niloy Mitra +1

We propose an unsupervised segmentation framework for StyleGAN generated objects. We build on two main observations. First, the features generated by StyleGAN hold valuable informa…

cs.CV2020

Improved StyleGAN Embedding: Where are the Good Latents?

Peihao Zhu, Rameen Abdal, Yipeng Qin +2

StyleGAN is able to produce photorealistic images that are almost indistinguishable from real photos. The reverse problem of finding an embedding for a given image poses a challeng…

cs.LG20201 cited

Channel-Directed Gradients for Optimization of Convolutional Neural Networks

Dong Lao, Peihao Zhu, Peter Wonka +1

We introduce optimization methods for convolutional neural networks that can be used to improve existing gradient-based optimization in terms of generalization error. The method re…

cs.CV2019

SEAN: Image Synthesis with Semantic Region-Adaptive Normalization

Peihao Zhu, Rameen Abdal, Yipeng Qin +1

We propose semantic region-adaptive normalization (SEAN), a simple but effective building block for Generative Adversarial Networks conditioned on segmentation masks that describe…