NaRCan: Natural Refined Canonical Image with Integration of Diffusion Prior for Video Editing

TL;DR

NaRCan is a novel video editing framework that combines a hybrid deformation model and diffusion prior to generate high-quality, natural canonical images from videos, significantly improving editing quality and efficiency.

Contribution

It introduces a diffusion prior into canonical image generation, integrates homography and MLPs for complex motion modeling, and employs LoRA fine-tuning with a new update schedule for faster training.

Findings

Outperforms existing methods in video editing tasks

Produces coherent, high-quality edited videos

Accelerates training by 14 times

Abstract

We propose a video editing framework, NaRCan, which integrates a hybrid deformation field and diffusion prior to generate high-quality natural canonical images to represent the input video. Our approach utilizes homography to model global motion and employs multi-layer perceptrons (MLPs) to capture local residual deformations, enhancing the model's ability to handle complex video dynamics. By introducing a diffusion prior from the early stages of training, our model ensures that the generated images retain a high-quality natural appearance, making the produced canonical images suitable for various downstream tasks in video editing, a capability not achieved by current canonical-based methods. Furthermore, we incorporate low-rank adaptation (LoRA) fine-tuning and introduce a noise and diffusion prior update scheduling technique that accelerates the training process by 14 times. Extensive experimental results show that our method outperforms existing approaches in various video editing tasks and produces coherent and high-quality edited video sequences. See our project page for video results at https://koi953215.github.io/NaRCan_page/.