New Metrics and Dataset for Biological Development Video Generation

Author:

Celard P.1,Iglesias E. L.1,Sorribes-Fdez J. M.1,Borrajo L.1,Vieira A. Seara1

Affiliation:

1. Computer Science Dept., Universidade de Vigo, Escuela Superior de Ingeniería Informática, Ourense, Spain and CINBIO - Biomedical Research Centre, Universidade de Vigo, Vigo, Spain and SING Research Group, Galicia Sur Health Research Institute (IIS Galicia Sur), Vigo, Spain

Abstract

Image generative models have advanced in many areas to produce synthetic images of high resolution and detail. This success has enabled its use in the biomedical field, paving the way for the generation of videos showing the biological evolution of its content. Despite the power of generative video models, their use has not yet extended to time-based development, focusing almost exclusively on generating motion in space. This situation is largely due to the lack of specific data sets and metrics to measure the individual quality of videos, particularly when there is no ground truth available for comparison. We propose a new dataset, called GoldenDOT, which tracks the evolution of apples cut in parallel over 10 days, allowing to observe their progress over time while remaining static. In addition, four new metrics are proposed that provide different analyses of the generated videos as a whole and individually. In this paper, the proposed dataset and measures are used to study three state of the art video generative models and their feasibility for video generation with biological development: TemporalGAN (TGANv2), Low Dimensional Video Discriminator GAN (LDVDGAN), and Video Diffusion Model (VDM). Among them, the TGANv2 model has managed to obtain the best results in the vast majority of metrics, including those already known in the state of the art, demonstrating the viability of the new proposed metrics and their congruence with these standard measures.

Publisher

Association for Computing Machinery (ACM)

Reference50 articles.

1. Video Generative Adversarial Networks: A Review

2. Gedas Bertasius, Heng Wang, and Lorenzo Torresani. 2021. Is Space-Time Attention All You Need for Video Understanding?. In Proceedings of the 38th International Conference on Machine Learning(Proceedings of Machine Learning Research, Vol.  139), Marina Meila and Tong Zhang (Eds.). PMLR, Virtual conference, 813–824.

3. Global, voxel, and cluster tests, by theory and permutation, for a difference between two groups of structural MR images of the brain

4. A survey on deep learning applied to medical images: from simple artificial neural networks to generative models

5. P. Celard A Seara Vieira E. L. Iglesias and L. Borrajo. 2023. GoldenDOT: Biological Development Time-Lapse Video Dataset. Universidade de Vigo. https://doi.org/10.5281/zenodo.7778821

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3