从小摄像机运动视频的动态视图合成。

IF 6.5
Huiqiang Sun, Xingyi Li, Juewen Peng, Liao Shen, Zhiguo Cao, Ke Xian, Guosheng Lin
{"title":"从小摄像机运动视频的动态视图合成。","authors":"Huiqiang Sun, Xingyi Li, Juewen Peng, Liao Shen, Zhiguo Cao, Ke Xian, Guosheng Lin","doi":"10.1109/TVCG.2025.3565642","DOIUrl":null,"url":null,"abstract":"<p><p>Novel view synthesis for dynamic 3D scenes poses a significant challenge. Many notable efforts use NeRF-based approaches to address this task and yield impressive results. However, these methods rely heavily on sufficient motion parallax in the input images or videos. When the camera motion range becomes limited or even stationary (i.e., small camera motion), existing methods encounter two primary challenges: incorrect representation of scene geometry and inaccurate estimation of camera parameters. These challenges make prior methods struggle to produce satisfactory results or even become invalid. To address the first challenge, we propose a novel Distribution-based Depth Regularization (DDR) that ensures the rendering weight distribution to align with the true distribution. Specifically, unlike previous methods that use depth loss to calculate the error of the expectation, we calculate the expectation of the error by using Gumbel-softmax to differentiably sample points from discrete rendering weight distribution. Additionally, we introduce constraints that enforce the volume density of spatial points before the object boundary along the ray to be near zero, ensuring that our model learns the correct geometry of the scene. To demystify the DDR, we further propose a visualization tool that enables observing the scene geometry representation at the rendering weight level. For the second challenge, we incorporate camera parameter learning during training to enhance the robustness of our model to camera parameters. We conduct extensive experiments to demonstrate the effectiveness of our approach in representing scenes with small camera motion input, and our results compare favorably to state-of-the-art methods.</p>","PeriodicalId":94035,"journal":{"name":"IEEE transactions on visualization and computer graphics","volume":"PP ","pages":""},"PeriodicalIF":6.5000,"publicationDate":"2025-04-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Dynamic View Synthesis from Small Camera Motion Videos.\",\"authors\":\"Huiqiang Sun, Xingyi Li, Juewen Peng, Liao Shen, Zhiguo Cao, Ke Xian, Guosheng Lin\",\"doi\":\"10.1109/TVCG.2025.3565642\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><p>Novel view synthesis for dynamic 3D scenes poses a significant challenge. Many notable efforts use NeRF-based approaches to address this task and yield impressive results. However, these methods rely heavily on sufficient motion parallax in the input images or videos. When the camera motion range becomes limited or even stationary (i.e., small camera motion), existing methods encounter two primary challenges: incorrect representation of scene geometry and inaccurate estimation of camera parameters. These challenges make prior methods struggle to produce satisfactory results or even become invalid. To address the first challenge, we propose a novel Distribution-based Depth Regularization (DDR) that ensures the rendering weight distribution to align with the true distribution. Specifically, unlike previous methods that use depth loss to calculate the error of the expectation, we calculate the expectation of the error by using Gumbel-softmax to differentiably sample points from discrete rendering weight distribution. Additionally, we introduce constraints that enforce the volume density of spatial points before the object boundary along the ray to be near zero, ensuring that our model learns the correct geometry of the scene. To demystify the DDR, we further propose a visualization tool that enables observing the scene geometry representation at the rendering weight level. For the second challenge, we incorporate camera parameter learning during training to enhance the robustness of our model to camera parameters. We conduct extensive experiments to demonstrate the effectiveness of our approach in representing scenes with small camera motion input, and our results compare favorably to state-of-the-art methods.</p>\",\"PeriodicalId\":94035,\"journal\":{\"name\":\"IEEE transactions on visualization and computer graphics\",\"volume\":\"PP \",\"pages\":\"\"},\"PeriodicalIF\":6.5000,\"publicationDate\":\"2025-04-29\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"IEEE transactions on visualization and computer graphics\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/TVCG.2025.3565642\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"IEEE transactions on visualization and computer graphics","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/TVCG.2025.3565642","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

摘要

动态三维场景的新颖视图合成提出了重大挑战。许多值得注意的工作使用基于nerf的方法来解决这一任务,并产生了令人印象深刻的结果。然而,这些方法在很大程度上依赖于输入图像或视频中足够的运动视差。当摄像机运动范围变得有限甚至静止(即摄像机运动很小)时,现有方法面临两个主要挑战:场景几何形状的不正确表示和相机参数的不准确估计。这些挑战使得先前的方法很难产生令人满意的结果,甚至变得无效。为了解决第一个挑战,我们提出了一种新的基于分布的深度正则化(DDR),以确保渲染权重分布与真实分布保持一致。具体来说,与以前使用深度损失计算期望误差的方法不同,我们通过使用Gumbel-softmax对离散渲染权重分布的可微分样本点计算误差的期望。此外,我们引入约束,强制物体边界前空间点的体积密度沿着光线接近于零,确保我们的模型学习正确的场景几何。为了揭开DDR的神秘面纱,我们进一步提出了一种可视化工具,可以在渲染权重级别上观察场景几何表示。对于第二个挑战,我们在训练过程中加入相机参数学习,以增强我们的模型对相机参数的鲁棒性。我们进行了大量的实验来证明我们的方法在用小摄像机运动输入表示场景时的有效性,我们的结果与最先进的方法相比是有利的。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Dynamic View Synthesis from Small Camera Motion Videos.

Novel view synthesis for dynamic 3D scenes poses a significant challenge. Many notable efforts use NeRF-based approaches to address this task and yield impressive results. However, these methods rely heavily on sufficient motion parallax in the input images or videos. When the camera motion range becomes limited or even stationary (i.e., small camera motion), existing methods encounter two primary challenges: incorrect representation of scene geometry and inaccurate estimation of camera parameters. These challenges make prior methods struggle to produce satisfactory results or even become invalid. To address the first challenge, we propose a novel Distribution-based Depth Regularization (DDR) that ensures the rendering weight distribution to align with the true distribution. Specifically, unlike previous methods that use depth loss to calculate the error of the expectation, we calculate the expectation of the error by using Gumbel-softmax to differentiably sample points from discrete rendering weight distribution. Additionally, we introduce constraints that enforce the volume density of spatial points before the object boundary along the ray to be near zero, ensuring that our model learns the correct geometry of the scene. To demystify the DDR, we further propose a visualization tool that enables observing the scene geometry representation at the rendering weight level. For the second challenge, we incorporate camera parameter learning during training to enhance the robustness of our model to camera parameters. We conduct extensive experiments to demonstrate the effectiveness of our approach in representing scenes with small camera motion input, and our results compare favorably to state-of-the-art methods.

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
×
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:604180095
Book学术官方微信