Filters








207 Hits in 5.7 sec

Interactive Annotation of 3D Object Geometry using 2D Scribbles [article]

Tianchang Shen, Jun Gao, Amlan Kar, Sanja Fidler
2020 arXiv   pre-print
In this paper, we propose an interactive framework for annotating 3D object geometry from both point cloud data and RGB imagery.  ...  First, we make an automatic guess of the 3D shape and allow the user to provide feedback about large errors by drawing scribbles in desired 2D views.  ...  Interactive 3D Annotation We now describe our framework for annotating 3D object.  ... 
arXiv:2008.10719v2 fatcat:efmdbwwvq5akjbjrt2ivu7trju

Neural Volumetric Object Selection [article]

Zhongzheng Ren and Aseem Agarwala and Bryan Russell and Alexander G. Schwing and Oliver Wang
2022 arXiv   pre-print
Our approach takes a set of foreground and background 2D user scribbles in one view and automatically estimates a 3D segmentation of the desired object, which can be rendered into novel views.  ...  We show that our approach out-performs strong baselines, including 2D segmentation and 3D segmentation approaches adapted to our task.  ...  Formally, we first project user interactions in the form of 2D scribbles from a reference image to sparse 3D locations using the reconstructed scene.  ... 
arXiv:2205.14929v1 fatcat:mho64cqyzncnvpdxihm7ml32zm

Annotating 3D electronic books

Lichan Hong, Ed H. Chi, Stuart K. Card
2005 CHI '05 extended abstracts on Human factors in computing systems - CHI '05  
But creating and rendering annotations on a 3D book and other objects in a 3D workspace is nontrivial.  ...  In this paper, we present our exploration of how to use 3D graphics techniques to create realistic annotations with acceptable frame rates.  ...  For a highlight, this object will be a 3D polygon, and, for a scribble, a set of 3D polylines.  ... 
doi:10.1145/1056808.1056942 dblp:conf/chi/HongCC05 fatcat:qtqi2cxdcnewhgau7lgo7lwfrm

Interactive Object Segmentation in 3D Point Clouds [article]

Theodora Kontogianni, Ekin Celikkan, Siyu Tang, Konrad Schindler
2022 arXiv   pre-print
Here, we present an interactive 3D object segmentation method in which the user interacts directly with the 3D point cloud.  ...  Surprisingly, interactive segmentation of 3D scenes has not been explored much.  ...  First we asked the annotators to label 10 random objects from the challenging class picture using our interactive segmentation tool and we compared the real Table 5 : 3D clicks compared to 2D scribbles  ... 
arXiv:2204.07183v1 fatcat:wqkqvtbsy5ghbejnxusi3hg3sa

SmartAnnotator An Interactive Tool for Annotating Indoor RGBD Images

Yu-Shiang Wong, Hung-Kuo Chu, Niloy J. Mitra
2015 Computer graphics forum (Print)  
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.  ...  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  ...  Acknowledgements We are grateful to the anonymous reviewers for their comments and suggestions; all the participants of the user study for their time; and Gerardo Figueroa for the video narration.  ... 
doi:10.1111/cgf.12574 fatcat:eljana6al5fjxc5myljq67vfzi

Sketching annotations in a 3D web environment

Thomas Jung, Mark D. Gross, Ellen Yi-Luen Do
2002 CHI '02 extended abstracts on Human factors in computer systems - CHI '02  
The Space Pen system supports annotation and drawing on (and inside) 3D VRML/Java models using a regular Web browser to exchange text and sketched annotations for review.  ...  Collaborative design review is an important part of architectural design work.  ...  The views contained in this material are those of the authors and do not necessarily reflect the views of the National Science Foundation.  ... 
doi:10.1145/506486.506512 fatcat:5qvxfwv5kfb6pikzikg3jrepny

Sketching annotations in a 3D web environment

Thomas Jung, Mark D. Gross, Ellen Yi-Luen Do
2002 CHI '02 extended abstracts on Human factors in computing systems - CHI '02  
The Space Pen system supports annotation and drawing on (and inside) 3D VRML/Java models using a regular Web browser to exchange text and sketched annotations for review.  ...  Collaborative design review is an important part of architectural design work.  ...  The views contained in this material are those of the authors and do not necessarily reflect the views of the National Science Foundation.  ... 
doi:10.1145/506443.506512 dblp:conf/chi/JungGD02 fatcat:lope2egpjngnfcrvhjdn3safpy

A New Sketch Based Interface using the Gray-level Co-occurrence Matrix for Perceptual Simplification of Paper Based Scribbles [article]

Alexandra Bartolo, Kenneth P. Camilleri, Philip J. Farrugia, Jonathan C. Borg
2006 Sketch-Based Interfaces and Modeling  
This paper describes a new sketch-to-3D tool, which uses annotations to aid the interpretation of the drawing.  ...  However, we show that processing scribbles using these techniques result in a large number of vectors which do not provide a faithful representation of the drawing.  ...  Acknowledgements This research is part of the research project 'Innovative Early Stage Design Product Prototyping' (InPro), (http:www. eng.um.edu.mt/~inpro) which is supported by the University of Malta  ... 
doi:10.2312/sbm/sbm06/091-098 fatcat:yri4k6twabbnfibfmtqty3qjre

Large-Scale Automatic Reconstruction of Neuronal Processes from Electron Microscopy Images [article]

Verena Kaynig, Amelio Vazquez-Reina, Seymour Knowles-Barley, Mike Roberts, Thouis R. Jones, Narayanan Kasthuri, Eric Miller, Jeff Lichtman, Hanspeter Pfister
2013 arXiv   pre-print
First, we train a random forest classifier on interactive sparse user annotations.  ...  These segmentations are then combined into geometrically consistent 3D objects by segmentation fusion.  ...  Acknowledgment The authors would like to thank Daniel Berger for providing manual segmentation, and Nancy Aulet for interactively annotating the training data.  ... 
arXiv:1303.7186v1 fatcat:hcgsjcvwpndkbo242wga4czuo4

Large-scale automatic reconstruction of neuronal processes from electron microscopy images

Verena Kaynig, Amelio Vazquez-Reina, Seymour Knowles-Barley, Mike Roberts, Thouis R. Jones, Narayanan Kasthuri, Eric Miller, Jeff Lichtman, Hanspeter Pfister
2015 Medical Image Analysis  
First, we train a random forest classifier on interactive sparse user annotations.  ...  These segmentations are then combined into geometrically consistent 3D objects by segmentation fusion.  ...  Acknowledgments The authors would like to thank Daniel Berger for providing manual segmentation, and Nancy Aulet for interactively annotating the training data.  ... 
doi:10.1016/j.media.2015.02.001 pmid:25791436 pmcid:PMC4406409 fatcat:bxrzur7grreulenny45vomncbi

Robust semi-automatic 2D-to-3D image conversion via residual-driven optimization

Hongxing Yuan
2018 EURASIP Journal on Image and Video Processing  
Semi-automatic 2D-to-3D conversion provides a cost-effective solution to the problem of 3D content shortage.  ...  The performance of most methods degrades significantly when cross-boundary scribbles are present due to their inability to remove unwanted input.  ...  Availability of data and materials The author can provide the data and source code.  ... 
doi:10.1186/s13640-018-0310-x fatcat:lbylzpd3ivgrnmcnq4pvmhwck4

A 3D Annotation Interface Using the DIVINE Visual Display

Karim Osman, Francois Malric, Shervin Shirmohammadi
2006 2006 IEEE International Workshop on Haptic Audio Visual Environments and their Applications (HAVE 2006)  
In this paper, we introduce an immersive interface for manipulating 3D objects using the DIVINE system.  ...  While systems such as CAVEs have been experimented with and used for a number of years, their deployment has been slow mainly due to their expense and space requirements.  ...  ACKNOWLEDGEMENTS The authors acknowledge the financial support of the Canada's Natural Sciences and Engineering Research Council (NSERC) for its USRA scholarship.  ... 
doi:10.1109/have.2006.283798 fatcat:h7zdo4ldr5cdreck7gtsuko7fe

Depth annotations: Designing depth of a single image for depth-based effects

Jingtang Liao, Shuheng Shen, Elmar Eisemann
2018 Computers & graphics  
Consequently, our solution centers around user interaction and relies on a scribble-based depth editing.  ...  We demonstrate a variety of artistic 3D results, including wiggle stereoscopy, artistic abstractions, haze, unsharp masking, and depth of field.  ...  11 maps for several key frames and propagating the annotations, similar to rotoscoping (Agarwala et al., 2004) .  ... 
doi:10.1016/j.cag.2017.11.005 fatcat:uoxlzk645rcc3pwec4vthj7ed4

Cross-Modal 3D Shape Generation and Manipulation [article]

Zezhou Cheng, Menglei Chai, Jian Ren, Hsin-Ying Lee, Kyle Olszewski, Zeng Huang, Subhransu Maji, Sergey Tulyakov
2022 arXiv   pre-print
Creating and editing the shape and color of 3D objects require tremendous human effort and expertise.  ...  Compared to direct manipulation in 3D interfaces, 2D interactions such as sketches and scribbles are usually much more natural and intuitive for the users.  ...  Our experiments were partially performed on the University of Massachusetts GPU cluster funded by the Mass. Technology Collaborative.  ... 
arXiv:2207.11795v1 fatcat:tdi22eh3zjgxhamm5fvz5q6ioi

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

Yu-Shiang Wong, Hung-Kuo Chu, Niloy J. Mitra
2014 arXiv   pre-print
The system performs the tedious tasks of grouping pixels, creating potential abstracted cuboids, inferring object interactions in 3D, and comes up with various hypotheses.  ...  We present SmartAnnotator, an interactive system to facilitate annotating RGBD images.  ...  Thus, we model distribution of 3D size of object category using 2D distribution of the bottom face area and height of cuboids from SGs, and then learn the geometric prior using a multi-class probability  ... 
arXiv:1403.5718v1 fatcat:vxkmyhm2qzdwnm5ixtit2l5jia
« Previous Showing results 1 — 15 out of 207 results