SIGGRAPH Asia 2014 Indoor Scene Understanding Where Graphics Meets Vision最新文献

Blind recovery of spatially varying reflectance from a single image 单幅图像空间变化反射率的盲恢复

SIGGRAPH Asia 2014 Indoor Scene Understanding Where Graphics Meets Vision Pub Date : 2014-11-24 DOI: 10.1145/2670291.2670293

Kevin Karsch, D. Forsyth

引用次数: 2

MCGraph: multi-criterion representation for scene understanding MCGraph:场景理解的多准则表示

SIGGRAPH Asia 2014 Indoor Scene Understanding Where Graphics Meets Vision Pub Date : 2014-11-24 DOI: 10.1145/2670291.2670292

M. Hueting, Áron Monszpart, Nicolas Mellado

{"title":"MCGraph: multi-criterion representation for scene understanding","authors":"M. Hueting, Áron Monszpart, Nicolas Mellado","doi":"10.1145/2670291.2670292","DOIUrl":"https://doi.org/10.1145/2670291.2670292","url":null,"abstract":"The field of scene understanding endeavours to extract a broad range of information from 3D scenes. Current approaches exploit one or at most a few different criteria (e.g., spatial, semantic, functional information) simultaneously for analysis. We argue that to take scene understanding to the next level of performance, we need to take into account many different, and possibly previously unconsidered types of knowledge simultaneously. A unified representation for this type of processing is as of yet missing. In this work we propose MCGraph: a unified multi-criterion data representation for understanding and processing of large-scale 3D scenes. Scene abstraction and prior knowledge are kept separated, but highly connected. For this purpose, primitives (i.e., proxies) and their relationships (e.g., contact, support, hierarchical) are stored in an abstraction graph, while the different categories of prior knowledge necessary for processing are stored separately in a knowledge graph. These graphs complement each other bidirectionally, and are processed concurrently. We illustrate our approach by expressing previous techniques using our formulation, and present promising avenues of research opened up by using such a representation. We also distribute a set of MCGraph annotations for a small number of NYU2 scenes, to be used as ground truth multi-criterion abstractions.","PeriodicalId":148310,"journal":{"name":"SIGGRAPH Asia 2014 Indoor Scene Understanding Where Graphics Meets Vision","volume":"35 21","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-11-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"113939259","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: 7

On being the right scale: sizing large collections of 3D models 关于正确的比例:调整大型3D模型集合的大小

SIGGRAPH Asia 2014 Indoor Scene Understanding Where Graphics Meets Vision Pub Date : 2014-11-24 DOI: 10.1145/2670291.2670295

M. Savva, Angel X. Chang, G. Bernstein, Christopher D. Manning, P. Hanrahan

引用次数: 22

Annotating RGBD images of indoor scenes 对室内场景的RGBD图像进行标注

SIGGRAPH Asia 2014 Indoor Scene Understanding Where Graphics Meets Vision Pub Date : 2014-11-24 DOI: 10.1145/2670291.2670294

Yu-Shiang Wong, Hung-Kuo Chu

引用次数: 1

SIGGRAPH Asia 2014 Indoor Scene Understanding Where Graphics Meets Vision 2014年亚洲室内场景:图形与视觉的结合

SIGGRAPH Asia 2014 Indoor Scene Understanding Where Graphics Meets Vision Pub Date : 1900-01-01 DOI: 10.1145/2670291

引用次数: 1