Expansive Supervision for Neural Radiance Field

Weixiang Zhang, Shuzhao Xie, Shijia Ge, Wei Yao, Chen Tang, Zhi Wang
{"title":"Expansive Supervision for Neural Radiance Field","authors":"Weixiang Zhang, Shuzhao Xie, Shijia Ge, Wei Yao, Chen Tang, Zhi Wang","doi":"arxiv-2409.08056","DOIUrl":null,"url":null,"abstract":"Neural Radiance Fields have achieved success in creating powerful 3D media\nrepresentations with their exceptional reconstruction capabilities. However,\nthe computational demands of volume rendering pose significant challenges\nduring model training. Existing acceleration techniques often involve\nredesigning the model architecture, leading to limitations in compatibility\nacross different frameworks. Furthermore, these methods tend to overlook the\nsubstantial memory costs incurred. In response to these challenges, we\nintroduce an expansive supervision mechanism that efficiently balances\ncomputational load, rendering quality and flexibility for neural radiance field\ntraining. This mechanism operates by selectively rendering a small but crucial\nsubset of pixels and expanding their values to estimate the error across the\nentire area for each iteration. Compare to conventional supervision, our method\neffectively bypasses redundant rendering processes, resulting in notable\nreductions in both time and memory consumption. Experimental results\ndemonstrate that integrating expansive supervision within existing\nstate-of-the-art acceleration frameworks can achieve 69% memory savings and 42%\ntime savings, with negligible compromise in visual quality.","PeriodicalId":501130,"journal":{"name":"arXiv - CS - Computer Vision and Pattern Recognition","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2024-09-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"arXiv - CS - Computer Vision and Pattern Recognition","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/arxiv-2409.08056","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

Abstract

Neural Radiance Fields have achieved success in creating powerful 3D media representations with their exceptional reconstruction capabilities. However, the computational demands of volume rendering pose significant challenges during model training. Existing acceleration techniques often involve redesigning the model architecture, leading to limitations in compatibility across different frameworks. Furthermore, these methods tend to overlook the substantial memory costs incurred. In response to these challenges, we introduce an expansive supervision mechanism that efficiently balances computational load, rendering quality and flexibility for neural radiance field training. This mechanism operates by selectively rendering a small but crucial subset of pixels and expanding their values to estimate the error across the entire area for each iteration. Compare to conventional supervision, our method effectively bypasses redundant rendering processes, resulting in notable reductions in both time and memory consumption. Experimental results demonstrate that integrating expansive supervision within existing state-of-the-art acceleration frameworks can achieve 69% memory savings and 42% time savings, with negligible compromise in visual quality.
神经辐射场的扩展监督
神经辐射场凭借其卓越的重建能力,在创建强大的三维媒体表现方面取得了成功。然而,体积渲染的计算需求给模型训练带来了巨大挑战。现有的加速技术往往需要设计模型架构,导致不同框架之间的兼容性受到限制。此外,这些方法往往忽略了由此产生的巨大内存成本。为了应对这些挑战,我们引入了一种扩展性监督机制,它能有效地平衡神经辐射场训练的计算负荷、渲染质量和灵活性。该机制通过选择性地渲染一小部分关键像素,并扩展其值来估计每次迭代中整个区域的误差。与传统的监督相比,我们的方法有效地绕过了多余的渲染过程,从而显著减少了时间和内存消耗。实验结果表明,在现有的最先进的加速框架中集成扩展式监督,可以节省 69% 的内存和 42% 的时间,而视觉质量的影响几乎可以忽略不计。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信