Adobe & UCL’s Pix2Video: Text-Guided Video Editing via Image Diffusion Without Preprocessing or Finetuning

In the new paper Pix2Video: Video Editing Using Image Diffusion, an Adobe Research and University College London team presents Pix2Video, a framework for realistic text-guided video editing using a pretrained image diffusion model.

adobe ai artificial intelligence college deep-neural-networks diffusion diffusion model editing finetuning framework image image diffusion london machine learning machine learning & data science ml paper research team technology text university university college london video video-editing