SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2201.05723 · AAAI · 2022

Learning Temporally and Semantically Consistent Unpaired Video-to-video Translation Through Pseudo-Supervision From Synthetic Optical Flow

Teruhisa Misu, Kaihong Wang, Kumar Akash

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Unpaired video-to-video translation aims to translate videos between a source and a target domain without the need of paired training data, making it more feasible for real applications. Unfortunately, the translated videos generally suffer from temporal and semantic inconsistency. To address this, many existing works adopt spatiotemporal consistency constraints incorporating temporal information based on motion estimation. However, the inaccuracies in the estimation of motion deteriorate the quality of the guidance towards spatiotemporal consistency, which leads to unstable translation. In this work, we propose a novel paradigm that regularizes the spatiotemporal consistency by synthesizing motions in input videos with the generated optical flow instead of estimating them. Therefore, the synthetic motion can be applied in the regularization paradigm to keep motions consistent across domains without the risk of errors in motion estimation. Thereafter, we utilize our unsupervised recycle and unsupervised spatial loss, guided by the pseudo-supervision provided by the synthetic optical flow, to accurately enforce spatiotemporal consistency in both domains. Experiments show that our method is versatile in various scenarios and achieves state-of-the-art performance in generating temporally and semantically consistent videos. Code is available at: https://github.com/wangkaihong/Unsup Recycle GAN/.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2201.05723")
get_code_for_paper("2201.05723")
have("2201.05723")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2201.05723.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2201.05723.svg)](https://syntology.ai/paper/2201.05723)

Connect an agent — have() is free.