Filters








7,842 Hits in 5.4 sec

Structural Plan of Indoor Scenes with Personalized Preferences [article]

Xinhan Di, Pengqian Yu, Hong Zhu, Lei Cai, Qiuyan Sheng, Changyu Sun
2020 arXiv   pre-print
The proposed model is able to automatically produce the layout of objects of a particular indoor scene according to property owners' preferences.  ...  In particular, the model consists of the extraction of abstract graph, conditional graph generation, and conditional scene instantiation.  ...  We focus on the problem of conditional structure generation of the completed indoor scene y.  ... 
arXiv:2008.01323v2 fatcat:3xlw6rw5rndyzedvdxaf6qetta

A Review of Techniques for 3D Reconstruction of Indoor Environments

Zhizhong Kang, Juntao Yang, Zhou Yang, Sai Cheng
2020 ISPRS International Journal of Geo-Information  
Moreover, based on the hierarchical pyramid structures and the learnable parameters of deep-learning architectures, multi-task collaborative schemes to share parameters and to jointly optimize each other  ...  Indoor environment model reconstruction has emerged as a significant and challenging task in terms of the provision of a semantically rich and geometrically accurate indoor model.  ...  [99] defined and found informative edge probability maps using single images through a fully convolutional network, and then used a maximum margin-structured classifier for generating layout estimation  ... 
doi:10.3390/ijgi9050330 fatcat:nahmlugoa5egnji3wrcigfjrre

3D Layout Propagation to Improve Object Recognition in Egocentric Videos [chapter]

Alejandro Rituerto, Ana C. Murillo, José J. Guerrero
2015 Lecture Notes in Computer Science  
Vision sensors provide rich information and are broadly used to obtain these models, for example, indoor scene modeling from monocular images has been widely studied.  ...  While most of the previous approaches obtain the scene layout from a single image, this work presents a novel approach to estimate the initial layout and addresses the problem of how to propagate it on  ...  [17] presented a method to generate interpretations of a scene from a set of line segments extracted from an indoor image. Similarly, Hedau et al.  ... 
doi:10.1007/978-3-319-16199-0_58 fatcat:skj2nuyddvc27gx7jxtcqzz35m

Holistic 3D Scene Parsing and Reconstruction from a Single RGB Image [chapter]

Siyuan Huang, Siyuan Qi, Yixin Zhu, Yinxue Xiao, Yuanlu Xu, Song-Chun Zhu
2018 Lecture Notes in Computer Science  
Specifically, we introduce a Holistic Scene Grammar (HSG) to represent the 3D scene structure, which characterizes a joint distribution over the functional and geometric space of indoor scenes.  ...  We solve this joint parsing and reconstruction problem in an analysis-by-synthesis fashion, seeking to minimize the differences between the input image and the rendered images generated by our 3D representation  ...  and the 3D geometric structure of an indoor scene from a single RGB image.  ... 
doi:10.1007/978-3-030-01234-2_12 fatcat:n2lyd2g6sve6lartrjexgdal3q

Automatic Dense Annotation for Monocular 3D Scene Understanding

Md Alimoor Reza, Kai Chen, Akshay Naik, David J. Crandall, Soon-Heung Jung
2020 IEEE Access  
Second, we propose a semi-automatic technique for dense annotation of 3d geometry, and in particular, the 3d poses of planes in indoor scenes.  ...  The tools are designed to allow rapid annotation of entire videos collected by RGBD cameras, thus generating thousands of ground-truth frames to use for training.  ...  LayoutNet [26] proposes a generic framework for room layout estimation from a single RGB image.  ... 
doi:10.1109/access.2020.2984745 fatcat:b6njvki67bbr7efdglfohyi3gq

Context-based indoor object detection as an aid to blind persons accessing unfamiliar environments

Xiaodong Yang, YingLi Tian, Chucai Yi, Aries Arditi
2010 Proceedings of the international conference on Multimedia - MM '10  
In this paper, we propose a computer visionbased indoor wayfinding system for assisting blind people to independently access unfamiliar buildings.  ...  We first extract text regions from indoor signs with multiple colors. Then text character localization and layout analysis of text strings are applied to filter out background interference.  ...  Generally, text strings on indoor signage have layouts with a dominant horizontal direction respect to the image frame.  ... 
doi:10.1145/1873951.1874156 dblp:conf/mm/YangTYA10 fatcat:rvuxppvv4za4lafqyvxvmv6yii

Holistic 3D Scene Parsing and Reconstruction from a Single RGB Image [article]

Siyuan Huang, Siyuan Qi, Yixin Zhu, Yinxue Xiao, Yuanlu Xu, Song-Chun Zhu
2018 arXiv   pre-print
Specifically, we introduce a Holistic Scene Grammar (HSG) to represent the 3D scene structure, which characterizes a joint distribution over the functional and geometric space of indoor scenes.  ...  We solve this joint parsing and reconstruction problem in an analysis-by-synthesis fashion, seeking to minimize the differences between the input image and the rendered images generated by our 3D representation  ...  and the 3D geometric structure of an indoor scene from a single RGB image.  ... 
arXiv:1808.02201v1 fatcat:ulqbp66cnfbnxmqnu4np6enxji

2D LiDAR and Camera Fusion Using Motion Cues for Indoor Layout Estimation [article]

Jieyu Li, Robert Stevenson
2022 arXiv   pre-print
This paper presents a novel indoor layout estimation system based on the fusion of 2D LiDAR and intensity camera data.  ...  The ambiguity in images for ground-wall boundary extraction is removed with the assistance of LiDAR observations, which improves the accuracy of semantic segmentation.  ...  For indoor layout estimation, focusing on polygonal structure modeling, fusion of 2D LiDAR and intensity camera can be a more efficient solution.  ... 
arXiv:2204.11202v1 fatcat:z4hwjdtifnaobnzqfji3cypvfa

Modeling the environment with egocentric vision systems

Alejandro Rituerto
2015 ELCVIA Electronic Letters on Computer Vision and Image Analysis  
., 2009] to create layout hypotheses on the first frame. It generates interpretations of the scene structure given a set of straight lines detected in a single image.  ...  ., 2009] generates interpretations of the scene structure given a set of straight lines detected in a single image.  ... 
doi:10.5565/rev/elcvia.739 fatcat:ts63ewdowrat7a2lqvp7h2uzeq

Towards Panoptic 3D Parsing for Single Image in the Wild [article]

Sainan Liu, Vincent Nguyen, Yuan Gao, Subarna Tripathi, Zhuowen Tu
2021 arXiv   pre-print
This paper presents an integrated system that performs dense scene labeling, object detection, instance segmentation, depth estimation, 3D shape reconstruction, and 3D layout estimation for indoor and  ...  outdoor scenes from a single RGB image.  ...  Total3DUnderstanding [38] infers a box layout and has produced 3D reconstruction inference results on natural indoor images.  ... 
arXiv:2111.03039v2 fatcat:r24t5m2kkvdfjn2yr6vcwryrca

A Spatial Layout and Scale Invariant Feature Representation for Indoor Scene Classification

Munawar Hayat, Salman H. Khan, Mohammed Bennamoun, Senjian An
2016 IEEE Transactions on Image Processing  
Unlike standard object classification, where the image to be classified contains one or multiple instances of the same object, indoor scene classification is quite different since the image consists of  ...  For automatic indoor scene categorization, large scale spatial layout deformations and scale variations are therefore two major challenges and the design of rich feature descriptors which are robust to  ...  To achieve spatial layout invariance, we introduce a new method of Fig. 1 : The spatial structure of indoor scenes is loose, irregular and unpredictable which can confuse the classification system.  ... 
doi:10.1109/tip.2016.2599292 fatcat:vms4fwwggnefhamopmsxq2oxwq

SmartAnnotator: An Interactive Tool for Annotating RGBD Indoor Images [article]

Yu-Shiang Wong, Hung-Kuo Chu, Niloy J. Mitra
2014 arXiv   pre-print
RGBD images with high quality annotations in the form of geometric (i.e., segmentation) and structural (i.e., how do the segments are mutually related in 3D) information provide valuable priors to a large  ...  number of scene and image manipulation applications.  ...  In order to generate a baseline training data, we expect minimal user intervention to assist the construction of 3D structures in images where the quality of data is poor or missing due to occlusion.  ... 
arXiv:1403.5718v1 fatcat:vxkmyhm2qzdwnm5ixtit2l5jia

Learning Indoor Layouts from Simple Point-Clouds [article]

Md. Tareq Mahmood, Mohammed Eunus Ali
2021 arXiv   pre-print
Reconstructing a layout of indoor spaces has been a crucial part of growing indoor location based services.  ...  In this paper, we propose a system to automatically generate floor plans that can recognize rooms from the point-clouds obtained through smartphones like Google's Tango.  ...  Dataset Generation To generate synthetic indoor layout, we first analyze a set of real indoor layouts like Figure 7 .  ... 
arXiv:2108.03378v1 fatcat:xvvaam6gwbhzzf4vd6yaxktt2u

Analysis and Modeling of 3D Indoor Scenes [article]

Rui Ma
2017 arXiv   pre-print
Many efforts have been made in different research communities, e.g. computer graphics, vision and robotics, to capture, analyze and generate the 3D indoor data.  ...  This report mainly focuses on the recent research progress in graphics on geometry, structure and semantic analysis of 3D indoor data and different modeling techniques for creating plausible and realistic  ...  Comparing to generating layouts with fixed objects instances, the automatic open world layout synthesis is more appealing as the goal is to generate diverse layouts with unspecified number of objects.  ... 
arXiv:1706.09577v1 fatcat:pdbztyjkezabnj3eaok5wrs7xq

SmartAnnotator An Interactive Tool for Annotating Indoor RGBD Images

Yu-Shiang Wong, Hung-Kuo Chu, Niloy J. Mitra
2015 Computer graphics forum (Print)  
RGBD images with high quality annotations, both in the form of geometric (i.e., segmentation) and structural (i.e., how do the segments mutually relate in 3D) information, provide valuable priors for a  ...  The system performs the tedious tasks of grouping pixels, creating potential abstracted cuboids, inferring object interactions in 3D, and generates an ordered list of hypotheses.  ...  In this work, we present SMARTANNOTATOR, an assisted interactive tool to annotate indoor RGBD images.  ... 
doi:10.1111/cgf.12574 fatcat:eljana6al5fjxc5myljq67vfzi
« Previous Showing results 1 — 15 out of 7,842 results