IEEE

AMT-Net: Adversarial Motion Transfer Network With Disentangled Shape and Pose for Realistic Image Animation

Abstract: Computer vision advancements allow motion transfer for animating static objects in images. However, current methods rely on manually collected motion labels and struggle with accurate shape ...
GitHub

[TIP2024] MWFormer: Multi-Weather Image Restoration Using Degradation-Aware Transformers

This is a PyTorch implementation of the paper MWFormer: Multi-Weather Image Restoration Using Degradation-Aware Transformers published in IEEE TIP 2024. Arxiv link. Notice: This repo is still working ...
IEEE

Consistent and Controllable Image Animation with Motion Diffusion Models

Abstract: Diffusion models have achieved significant progress in the task of image animation due to their powerful generative capabilities. However, preserving appearance consistency to the static ...
GitHub

Fine-Controllable and Expressive Freestyle Portrait Animation

We present Follow-Your-Emoji, a diffusion-based framework for portrait animation, which animates a reference portrait with target landmark sequences. [FollowYourEmoji ...