Generative Video Bi-flow

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Liu, Chen, Ritschel, Tobias
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918119438548992
author Liu, Chen
Ritschel, Tobias
author_facet Liu, Chen
Ritschel, Tobias
contents We propose a novel generative video model to robustly learn temporal change as a neural Ordinary Differential Equation (ODE) flow with a bilinear objective which combines two aspects: The first is to map from the past into future video frames directly. Previous work has mapped the noise to new frames, a more computationally expensive process. Unfortunately, starting from the previous frame, instead of noise, is more prone to drifting errors. Hence, second, we additionally learn how to remove the accumulated errors as the joint objective by adding noise during training. We demonstrate unconditional video generation in a streaming manner for various video datasets, all at competitive quality compared to a conditional diffusion baseline but with higher speed, i.e., fewer ODE solver steps.
format Preprint
id arxiv_https___arxiv_org_abs_2503_06364
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Generative Video Bi-flow
Liu, Chen
Ritschel, Tobias
Computer Vision and Pattern Recognition
Graphics
We propose a novel generative video model to robustly learn temporal change as a neural Ordinary Differential Equation (ODE) flow with a bilinear objective which combines two aspects: The first is to map from the past into future video frames directly. Previous work has mapped the noise to new frames, a more computationally expensive process. Unfortunately, starting from the previous frame, instead of noise, is more prone to drifting errors. Hence, second, we additionally learn how to remove the accumulated errors as the joint objective by adding noise during training. We demonstrate unconditional video generation in a streaming manner for various video datasets, all at competitive quality compared to a conditional diffusion baseline but with higher speed, i.e., fewer ODE solver steps.
title Generative Video Bi-flow
topic Computer Vision and Pattern Recognition
Graphics
url https://arxiv.org/abs/2503.06364