Motion-from-Blur: 3D Shape and Motion Estimation of Motion-blurred Objects in Videos
Author:
Affiliation:
1. ETH Zurich,Department of Computer Science
2. Google Research
Publisher
IEEE
Link
http://xplorestaging.ieee.org/ielx7/9878378/9878366/09879620.pdf?arnumber=9879620
Reference45 articles.
1. What Do Single-View 3D Reconstruction Networks Learn?
2. Spatially-Attentive Patch-Hierarchical Network for Adaptive Motion Deblurring
3. Pixelwise view selection for un-structured multi-view stereo;schönberger;European Conference on Computer Vision (ECCV),0
4. Structure-from-Motion Revisited
5. Shape from blur: Recovering textured 3d shape and motion of fast moving objects;rozumnyi;NeurIPS,0
Cited by 5 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献
1. Single-Image Deblurring, Trajectory and Shape Recovery of Fast Moving Objects with Denoising Diffusion Probabilistic Models;2024 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV);2024-01-03
2. Human from Blur: Human Pose Tracking from Blurry Images;2023 IEEE/CVF International Conference on Computer Vision (ICCV);2023-10-01
3. Tracking by 3D Model Estimation of Unknown Objects in Videos;2023 IEEE/CVF International Conference on Computer Vision (ICCV);2023-10-01
4. Blur Interpolation Transformer for Real-World Motion from Blur;2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR);2023-06
5. Video frame interpolation for high dynamic range sequences captured with dual‐exposure sensors;Computer Graphics Forum;2023-05
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