Proceedings of the 14th European Conference on Visual Media Production (CVMP 2017)最新文献

Cloud-based collaborative 3D reconstruction using smartphones 使用智能手机进行基于云的协同3D重建

Proceedings of the 14th European Conference on Visual Media Production (CVMP 2017) Pub Date : 2017-12-11 DOI: 10.1145/3150165.3150166

F. Poiesi, Alex Locher, P. Chippendale, E. Nocerino, Fabio Remondino, L. Gool

引用次数: 30

User Interaction for Image Recolouring using £2 用户交互图像重新着色使用£2

Proceedings of the 14th European Conference on Visual Media Production (CVMP 2017) Pub Date : 2017-12-11 DOI: 10.1145/3150165.3150171

M. Grogan, Rozenn Dahyot, A. Smolic

引用次数: 20

CRF-net: Single Image Radiometric Calibration using CNNs CRF-net:使用cnn的单图像辐射校准

Proceedings of the 14th European Conference on Visual Media Production (CVMP 2017) Pub Date : 2017-12-11 DOI: 10.1145/3150165.3150170

Han Li, P. Peers

引用次数: 13

Real-time rendering of realistic surface diffraction with low rank factorisation 低秩分解的真实表面衍射实时绘制

Proceedings of the 14th European Conference on Visual Media Production (CVMP 2017) Pub Date : 2017-12-11 DOI: 10.1145/3150165.3150167

Antoine Toisoul, A. Ghosh

引用次数: 5

ThirdLight: Low-cost and High-speed 3D Interaction Using Photosensor Markers ThirdLight:使用光敏传感器标记的低成本和高速3D交互

Proceedings of the 14th European Conference on Visual Media Production (CVMP 2017) Pub Date : 2017-12-11 DOI: 10.1145/3150165.3150169

Jaewon Kim, Gyuchull Han, Hwasup Lim, S. Izadi, A. Ghosh

{"title":"ThirdLight: Low-cost and High-speed 3D Interaction Using Photosensor Markers","authors":"Jaewon Kim, Gyuchull Han, Hwasup Lim, S. Izadi, A. Ghosh","doi":"10.1145/3150165.3150169","DOIUrl":"https://doi.org/10.1145/3150165.3150169","url":null,"abstract":"We present a low-cost 3D tracking system for virtual reality, gesture modeling, and robot manipulation applications which require fast and precise localization of headsets, data gloves, props, or controllers. Our system removes the need for cameras or projectors for sensing, and instead uses cheap LEDs and printed masks for illumination, and low-cost photosensitive markers. The illumination device transmits a spatiotemporal pattern as a series of binary Gray-code patterns. Multiple illumination devices can be combined to localize each marker in 3D at high speed (333Hz). Our method has strengths in accuracy, speed, cost, ambient performance, large working space (1m-5m) and robustness to noise compared with conventional techniques. We compare with a state-of-the-art instrumented glove and vision-based systems to demonstrate the accuracy, scalability, and robustness of our approach. We propose a fast and accurate method for hand gesture modeling using an inverse kinematics approach with the six photosensitive markers. We additionally propose a passive markers system and demonstrate various interaction scenarios as practical applications.","PeriodicalId":412591,"journal":{"name":"Proceedings of the 14th European Conference on Visual Media Production (CVMP 2017)","volume":"85 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-12-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131932079","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 2

Laplacian Pyramid of Conditional Variational Autoencoders 条件变分自编码器的拉普拉斯金字塔

Proceedings of the 14th European Conference on Visual Media Production (CVMP 2017) Pub Date : 2017-12-11 DOI: 10.1145/3150165.3150172

Garoe Dorta, S. Vicente, L. Agapito, N. Campbell, S. Prince, Ivor J. A. Simpson

引用次数: 11

Saliency-Based Sharpness Mismatch Detection For Stereoscopic Omnidirectional Images 基于显著性的立体全向图像清晰度失配检测

Proceedings of the 14th European Conference on Visual Media Production (CVMP 2017) Pub Date : 2017-12-11 DOI: 10.1145/3150165.3150168

S. Croci, S. Knorr, A. Smolic

引用次数: 2

Story Version Control and Graphical Visualization for Collaborative Story Authoring 协作故事创作的故事版本控制和图形可视化

Proceedings of the 14th European Conference on Visual Media Production (CVMP 2017) Pub Date : 2017-12-11 DOI: 10.1145/3150165.3150175

Fabio Zünd, Steven Poulakos, Mubbasir Kapadia, R. Sumner

{"title":"Story Version Control and Graphical Visualization for Collaborative Story Authoring","authors":"Fabio Zünd, Steven Poulakos, Mubbasir Kapadia, R. Sumner","doi":"10.1145/3150165.3150175","DOIUrl":"https://doi.org/10.1145/3150165.3150175","url":null,"abstract":"This paper presents a story version control and graphical visualization framework to enhance collaborative story authoring. We propose a media-agnostic story representation based on story beats, events, and participants that describes the flow of events in a storyline. We develop tree edit distance operations for this representation and use them to build the core features for story version control, including visual diff, conflict detection, and conflict resolution using three-way merge. Our system allows authors to work independently on the same story while providing the ability to automatically synchronize their efforts and resolve conflicts that may arise. We further enhance the collaborative authoring process using visualizations derived from the version control database that visually encode relationships between authors, characters, and story elements, during the evolution of the narrative. We demonstrate the efficacy of our system by integrating it within an existing visual storyboarding tool for authoring animated stories, and additionally use it to collaboratively author stories using video and images. We evaluate the usability of our system though two user studies. Our results reveal that untrained users are able to use and benefit from our system. Additionally, users are able to correctly interpret the graphical visualizations and perceive it to benefit collaboration during the story authoring process.","PeriodicalId":412591,"journal":{"name":"Proceedings of the 14th European Conference on Visual Media Production (CVMP 2017)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-12-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117300480","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 4

Seam-hiding for Looping Videos 循环视频的接缝隐藏

Proceedings of the 14th European Conference on Visual Media Production (CVMP 2017) Pub Date : 2017-12-11 DOI: 10.1145/3150165.3152766

James Durrant, G. Brostow

{"title":"Seam-hiding for Looping Videos","authors":"James Durrant, G. Brostow","doi":"10.1145/3150165.3152766","DOIUrl":"https://doi.org/10.1145/3150165.3152766","url":null,"abstract":"The proposed algorithm creates a seamless looping video clip from a real world video of an almost-cyclic motion. For a video that has repeating motion, such as a person on a trampoline, the first and last video frames may not precisely line up, even though the content is very similar. Playing back the video in a looping fashion can cause the re-start transition to jump out and appear discontinuous, both spatially and in terms of object velocity. Most work on video looping has sought to find the best re-set point in a longer video's timeline, but we start there, and modify the frames to hide the jump point. Our approach essentially fits a curve to the (x, y) and RGB coordinates of points in the scene, and then smooths those curves using gradient domain optimisation. We address important qualitative factors, balancing smoothness against preservation of the original trajectories/curves. Our modular system also incorporates video stabilisation and inpainting, to cope with more dynamic videos. For most videos within our scope, we found that automatic seam-hiding is succesful. For the cases in which the proposed system cannot satisfactorily produce a seamless loop, we hope our framework can be modified with improved components to achieve better results in the future.","PeriodicalId":412591,"journal":{"name":"Proceedings of the 14th European Conference on Visual Media Production (CVMP 2017)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-12-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133252125","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Method for Efficient CPU-GPU Streaming for Walkthrough of Full Motion Lightfield Video 全运动光场视频演练的高效CPU-GPU流处理方法

Proceedings of the 14th European Conference on Visual Media Production (CVMP 2017) Pub Date : 2017-12-11 DOI: 10.1145/3150165.3150173

Floyd M. Chitalu, Babis Koniaris, Kenny Mitchell

引用次数: 1