SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2304.02777 · CVPR · 2023

MoStGAN-V: Video Generation with Temporal Motion Styles

Mohamed Elhoseiny, Xiang Li, Xiaoqian Shen

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

Video generation remains a challenging task due to spatiotemporal complexity and the requirement of synthesizing diverse motions with temporal consistency. Previous works attempt to generate videos in arbitrary lengths either in an autoregressive manner or regarding time as a continuous signal. However, they struggle to synthesize detailed and diverse motions with temporal coherence and tend to generate repetitive scenes after a few time steps. In this work, we argue that a single time-agnostic latent vector of style-based generator is insufficient to model various and temporallyconsistent motions. Hence, we introduce additional timedependent motion styles to model diverse motion patterns. In addition, a Motion Style Attention modulation mechanism, dubbed as MoStAtt, is proposed to augment frames with vivid dynamics for each specific scale (i.e., layer), which assigns attention score for each motion style w.r.t deconvolution filter weights in the target synthesis layer and softly attends different motion styles for weight modulation. Experimental results show our model achieves stateof-the-art performance on four unconditional 256 2 video synthesis benchmarks trained with only 3 frames per clip and produces better qualitative results with respect to dynamic motions. Code and videos have been made available at https://github.com/xiaoqian-shen/ MoStGAN-V .

For agents

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

get_harvested_code_for_paper("2304.02777")
get_code_for_paper("2304.02777")
have("2304.02777")

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

curl https://syntology.ai/api/ran/2304.02777.json

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

[![Syntology run record](https://syntology.ai/api/ran/2304.02777.svg)](https://syntology.ai/paper/2304.02777)

Connect an agent — have() is free.