Diffusion Video Autoencoders: Toward Temporally Consistent Face Video Editing via Disentangled Video Encoding
Authors:
Preprint
Abstract
Inspired by the impressive performance of recent face image editing methods, several studies have been naturally proposed to extend these methods to the face video editing task. One of the main challenges here is temporal consistency among edited frames, which is still unresolved. To this end, we propose a novel face video editing framework based on diffusion autoencoders that can successfully extract the decomposed features - for the first time as a face video editing model - of identity and motion from a given video. This modeling allows us to edit the video by simply manipulating the temporally invariant feature to the desired direction for the consistency. Another unique strength of our model is that, since our model is based on diffusion models, it can satisfy both reconstruction and edit capabilities at the same time, and is robust to corner cases in wild face videos (e.g. occluded faces) unlike the existing GAN-based methods.Keywords
All Related Versions
This publication has 7 references indexed in Scilit:
- Third Time’s the Charm? Image and Video Editing with StyleGAN32023
- Stitch it in Time: GAN-Based Facial Editing of Real Videos2022
- StyleGAN-V: A Continuous Video Generator with the Price, Image Quality and Perks of StyleGAN22022
- BiSeNet V2: Bilateral Network with Guided Aggregation for Real-Time Semantic SegmentationInternational Journal of Computer Vision, 2021
- Face identity disentanglement via latent space mappingACM Transactions on Graphics, 2020
- InterFaceGAN: Interpreting the Disentangled Face Representation Learned by GANsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2020
- Image quality assessment: from error visibility to structural similarityIEEE Transactions on Image Processing, 2004