# Task-agnostic Temporally Consistent Facial Video Editing

arXiv: https://arxiv.org/abs/2007.01466 · HTML: https://mlsanity.com/paper/2007.01466/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Jul 2020.

## Built on by (most cited first, 4 of 4)

- [Deep Face Video Inpainting via UV Mapping](https://mlsanity.com/paper/2109.00681/) (2021)
- [Video Referring Expression Comprehension via Transformer with Content-aware Query](https://mlsanity.com/paper/2210.02953/) (2022)
- [Migrating Face Swap to Mobile Devices: A lightweight Framework and A Supervised Training Solution](https://mlsanity.com/paper/2204.08339/) (2022)
- [Deep Learning Technology for Face Forgery Detection: A Survey](https://mlsanity.com/paper/2409.14289/) (2024)

## Abstract (arXiv)

Recent research has witnessed the advances in facial image editing tasks. For video editing, however, previous methods either simply apply transformations frame by frame or utilize multiple frames in a concatenated or iterative fashion, which leads to noticeable visual flickers. In addition, these methods are confined to dealing with one specific task at a time without any extensibility. In this paper, we propose a task-agnostic temporally consistent facial video editing framework. Based on a 3D reconstruction model, our framework is designed to handle several editing tasks in a more unified and disentangled manner. The core design includes a dynamic training sample selection mechanism and a novel 3D temporal loss constraint that fully exploits both image and video datasets and enforces temporal consistency. Compared with the state-of-the-art facial image editing methods, our framework generates video portraits that are more photo-realistic and temporally smooth.