面向现实世界的HDRTV重建:一种基于数据综合的方法

Zhen Cheng, Tao Wang, Yong Li, Fenglong Song, C. Chen, Zhiwei Xiong
{"title":"面向现实世界的HDRTV重建:一种基于数据综合的方法","authors":"Zhen Cheng, Tao Wang, Yong Li, Fenglong Song, C. Chen, Zhiwei Xiong","doi":"10.48550/arXiv.2211.03058","DOIUrl":null,"url":null,"abstract":"Existing deep learning based HDRTV reconstruction methods assume one kind of tone mapping operators (TMOs) as the degradation procedure to synthesize SDRTV-HDRTV pairs for supervised training. In this paper, we argue that, although traditional TMOs exploit efficient dynamic range compression priors, they have several drawbacks on modeling the realistic degradation: information over-preservation, color bias and possible artifacts, making the trained reconstruction networks hard to generalize well to real-world cases. To solve this problem, we propose a learning-based data synthesis approach to learn the properties of real-world SDRTVs by integrating several tone mapping priors into both network structures and loss functions. In specific, we design a conditioned two-stream network with prior tone mapping results as a guidance to synthesize SDRTVs by both global and local transformations. To train the data synthesis network, we form a novel self-supervised content loss to constraint different aspects of the synthesized SDRTVs at regions with different brightness distributions and an adversarial loss to emphasize the details to be more realistic. To validate the effectiveness of our approach, we synthesize SDRTV-HDRTV pairs with our method and use them to train several HDRTV reconstruction networks. Then we collect two inference datasets containing both labeled and unlabeled real-world SDRTVs, respectively. Experimental results demonstrate that, the networks trained with our synthesized data generalize significantly better to these two real-world datasets than existing solutions.","PeriodicalId":72676,"journal":{"name":"Computer vision - ECCV ... : ... European Conference on Computer Vision : proceedings. European Conference on Computer Vision","volume":"136 1","pages":"199-216"},"PeriodicalIF":0.0000,"publicationDate":"2022-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"5","resultStr":"{\"title\":\"Towards Real World HDRTV Reconstruction: A Data Synthesis-based Approach\",\"authors\":\"Zhen Cheng, Tao Wang, Yong Li, Fenglong Song, C. Chen, Zhiwei Xiong\",\"doi\":\"10.48550/arXiv.2211.03058\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Existing deep learning based HDRTV reconstruction methods assume one kind of tone mapping operators (TMOs) as the degradation procedure to synthesize SDRTV-HDRTV pairs for supervised training. In this paper, we argue that, although traditional TMOs exploit efficient dynamic range compression priors, they have several drawbacks on modeling the realistic degradation: information over-preservation, color bias and possible artifacts, making the trained reconstruction networks hard to generalize well to real-world cases. To solve this problem, we propose a learning-based data synthesis approach to learn the properties of real-world SDRTVs by integrating several tone mapping priors into both network structures and loss functions. In specific, we design a conditioned two-stream network with prior tone mapping results as a guidance to synthesize SDRTVs by both global and local transformations. To train the data synthesis network, we form a novel self-supervised content loss to constraint different aspects of the synthesized SDRTVs at regions with different brightness distributions and an adversarial loss to emphasize the details to be more realistic. To validate the effectiveness of our approach, we synthesize SDRTV-HDRTV pairs with our method and use them to train several HDRTV reconstruction networks. Then we collect two inference datasets containing both labeled and unlabeled real-world SDRTVs, respectively. Experimental results demonstrate that, the networks trained with our synthesized data generalize significantly better to these two real-world datasets than existing solutions.\",\"PeriodicalId\":72676,\"journal\":{\"name\":\"Computer vision - ECCV ... : ... European Conference on Computer Vision : proceedings. European Conference on Computer Vision\",\"volume\":\"136 1\",\"pages\":\"199-216\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2022-11-06\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"5\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Computer vision - ECCV ... : ... European Conference on Computer Vision : proceedings. European Conference on Computer Vision\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.48550/arXiv.2211.03058\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Computer vision - ECCV ... : ... European Conference on Computer Vision : proceedings. European Conference on Computer Vision","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.48550/arXiv.2211.03058","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 5

摘要

现有的基于深度学习的HDRTV重建方法采用一种音调映射算子(TMOs)作为退化过程,合成SDRTV-HDRTV对进行监督训练。在本文中,我们认为,尽管传统的TMOs利用了有效的动态范围压缩先验,但它们在模拟现实退化方面存在一些缺点:信息过度保存、颜色偏差和可能的伪影,使得训练好的重建网络难以很好地推广到现实世界的情况。为了解决这个问题,我们提出了一种基于学习的数据合成方法,通过将几个音调映射先验值集成到网络结构和损失函数中来学习真实世界sdrtv的属性。具体来说,我们设计了一个有条件的两流网络,以先验的音调映射结果作为指导,通过全局和局部变换合成sdrtv。为了训练数据合成网络,我们形成了一种新的自监督内容损失来约束合成的sdrtv在不同亮度分布区域的不同方面,并形成了一种对抗损失来强调细节,使其更加逼真。为了验证该方法的有效性,我们利用该方法合成了SDRTV-HDRTV对,并用它们训练了多个HDRTV重建网络。然后,我们收集了两个推理数据集,分别包含标记和未标记的真实世界的sdrtv。实验结果表明,与现有的解决方案相比,用我们的合成数据训练的网络对这两个现实世界数据集的泛化能力明显更好。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
Towards Real World HDRTV Reconstruction: A Data Synthesis-based Approach
Existing deep learning based HDRTV reconstruction methods assume one kind of tone mapping operators (TMOs) as the degradation procedure to synthesize SDRTV-HDRTV pairs for supervised training. In this paper, we argue that, although traditional TMOs exploit efficient dynamic range compression priors, they have several drawbacks on modeling the realistic degradation: information over-preservation, color bias and possible artifacts, making the trained reconstruction networks hard to generalize well to real-world cases. To solve this problem, we propose a learning-based data synthesis approach to learn the properties of real-world SDRTVs by integrating several tone mapping priors into both network structures and loss functions. In specific, we design a conditioned two-stream network with prior tone mapping results as a guidance to synthesize SDRTVs by both global and local transformations. To train the data synthesis network, we form a novel self-supervised content loss to constraint different aspects of the synthesized SDRTVs at regions with different brightness distributions and an adversarial loss to emphasize the details to be more realistic. To validate the effectiveness of our approach, we synthesize SDRTV-HDRTV pairs with our method and use them to train several HDRTV reconstruction networks. Then we collect two inference datasets containing both labeled and unlabeled real-world SDRTVs, respectively. Experimental results demonstrate that, the networks trained with our synthesized data generalize significantly better to these two real-world datasets than existing solutions.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
自引率
0.00%
发文量
0
期刊最新文献
Dual-Stream Knowledge-Preserving Hashing for Unsupervised Video Retrieval Spatial and Visual Perspective-Taking via View Rotation and Relation Reasoning for Embodied Reference Understanding Rethinking Confidence Calibration for Failure Prediction PCR-CG: Point Cloud Registration via Deep Explicit Color and Geometry Diverse Human Motion Prediction Guided by Multi-level Spatial-Temporal Anchors
×
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
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 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 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1