# Diffusion Video Autoencoders: Toward Temporally Consistent Face Video Editing via Disentangled Video Encoding

Source: [Diffusion Video Autoencoders: Toward Temporally Consistent Face Video Editing via Disentangled Video Encoding](<https://www.sota2.com/research/paper/68fa6ee81e209131cea42ced>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T01:09:40.360Z

Authors: Gyeongman Kim, Hajin Shim, Hyunsu Kim, Yunjey Choi, Junho Kim, Eunho Yang

Published: 2022-12-06T07:41:51.000Z

## 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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Facial Video Editing on Facial Video Editing](<https://www.sota2.com/research/sota/facial-video-editing-on-facial-video-editing.md>): Facial Video Editing; Facial Video Editing; TL-ID: 0.901.

- [Video Editing on Custom facial video editing dataset](<https://www.sota2.com/research/sota/video-editing-on-custom-facial-video-editing-dataset.md>): Video Editing; Custom facial video editing dataset; Time Cost (s/frame): 103.6842.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2212.02802>)

[PDF](<https://arxiv.org/pdf/2212.02802.pdf>)
