%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% % COS 598A Spring 2015 Bib File for RGB-D Videos %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% % When Adding Bibtex Items: % - Group them into topics % - Start each topic with "*** Topic Name” % % Required Bibtex format: % - Please follow the citation naming and formatting conventions in Google Scholar % - Or, simply get the bibtex entry from Google Scholar % % Suggested Bibtex Fields to Add: % - Comments about the paper (comment = “text”) % - Project Page Link (project = “”) % - PDF file Link (pdf = “”) % - Video link (video = “”) %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% %%% Online Alignment (SLAM) %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% @InProceedings{newcombe2011kinectfusion, title = "KinectFusion: Real-time dense surface mapping and tracking", author = "Richard A Newcombe and Shahram Izadi and Otmar Hilliges and David Molyneaux and David Kim and Andrew J Davison and Pushmeet Kohi and Jamie Shotton and Steve Hodges and Andrew Fitzgibbon", booktitle = "Mixed and augmented reality (ISMAR), 2011 10th IEEE international symposium on", pages = "127--136", year = "2011", organization = "IEEE", topic = "SLAM", comment = "A seminal paper in online RGB-D video mapping", project = "http://research.microsoft.com/apps/pubs/default.aspx?id=155378", pdf = "http://research.microsoft.com/pubs/155378/ismar2011.pdf", video = "http://research.microsoft.com/jump/152815", } @InProceedings{henry2010rgb, title = "RGB-D mapping: Using depth cameras for dense 3D modeling of indoor environments", author = "Peter Henry and Michael Krainin and Evan Herbst and Xiaofeng Ren and Dieter Fox", booktitle = "In the 12th International Symposium on Experimental Robotics (ISER", year = "2010", organization = "Citeseer", topic = "SLAM", } @Article{whelan2012kintinuous, title = "Kintinuous: Spatially extended kinectfusion", author = "Thomas Whelan and Michael Kaess and Maurice Fallon and Hordur Johannsson and John Leonard and John McDonald", year = "2012", topic = "SLAM", comment = "Use a sliding volumne to reconstruct large environment and use bag of words to detect loop closure online", } @InProceedings{whelan2013robust, title = "Robust real-time visual odometry for dense RGB-D mapping", author = "Thomas Whelan and Hordur Johannsson and Michael Kaess and John J Leonard and John McDonald", booktitle = "Robotics and Automation (ICRA), 2013 IEEE International Conference on", pages = "5724--5731", year = "2013", organization = "IEEE", topic = "SLAM", comment = "Extensions to Kintinuous for large environment with loop closure", video = "http://youtu.be/MEugh12dcYA", } @InProceedings{salas2013slam++, title = "Slam++: Simultaneous localisation and mapping at the level of objects", author = "Renato F Salas-Moreno and Richard A Newcombe and Hauke Strasdat and Paul HJ Kelly and Andrew J Davison", booktitle = "Computer Vision and Pattern Recognition (CVPR), 2013 IEEE Conference on", pages = "1352--1359", year = "2013", organization = "IEEE", pdf = “http://www.cv-foundation.org/openaccess/content_cvpr_2013/papers/Salas-Moreno_SLAM_Simultaneous_Localisation_2013_CVPR_paper.pdf", project = "http://www.doc.ic.ac.uk/~rfs09/slampp.html", topic = "SLAM", comment = "Detect the same object for alignment", } @InProceedings{kerl2013robust, title = "Robust odometry estimation for RGB-D cameras", author = "Christian Kerl and J{\"u}rgen Sturm and Daniel Cremers", booktitle = "Robotics and Automation (ICRA), 2013 IEEE International Conference on", pages = "3748--3754", year = "2013", organization = "IEEE", topic = "SLAM", } @inproceedings{niessner2014combining, title = "Combining Inertial Navigation and ICP for Real-time 3D Surface Reconstruction", author = "Niessner, M and Dai, A and Fisher, M", year = "2014", organization = "Eurographics", project = "http://graphics.stanford.edu/~mdfisher/inertialNavigation.html", pdf = "http://graphics.stanford.edu/~mdfisher/papers/inertialNavigation.pdf", video = "http://graphics.stanford.edu/~mdfisher/papers/inertialNavigationVideo.mp4", } @InProceedings{whelan2013deformation, title = "Deformation-based loop closure for large scale dense RGB-D SLAM", author = "Thomas Whelan and Michael Kaess and John J Leonard and John McDonald", booktitle = "Intelligent Robots and Systems (IROS), 2013 IEEE/RSJ International Conference on", pages = "548--555", year = "2013", organization = "IEEE", topic = "SLAM", } @Article{stuckler2014multi, title = "Multi-resolution surfel maps for efficient dense 3D modeling and tracking", author = "J{\"o}rg St{\"u}ckler and Sven Behnke", journal = "Journal of Visual Communication and Image Representation", volume = "25", number = "1", pages = "137--147", year = "2014", publisher = "Elsevier", topic = "SLAM", } @InProceedings{kerl2013dense, title = "Dense visual SLAM for RGB-D cameras", author = "Christian Kerl and J{\"u}rgen Sturm and Daniel Cremers", booktitle = "Intelligent Robots and Systems (IROS), 2013 IEEE/RSJ International Conference on", pages = "2100--2106", year = "2013", organization = "IEEE", topic = "SLAM", project = "http://vision.in.tum.de/data/software/dvo", code = "https://github.com/tum-vision/dvo_slam", pdf = "http://vision.in.tum.de/_media/spezial/bib/kerl13iros.pdf", video = "https://www.youtube.com/watch?v=jNbYcw_dmcQ", } @InProceedings{bylow2013real, title = "Real-time camera tracking and 3D reconstruction using signed distance functions", author = "Erik Bylow and J{\"u}rgen Sturm and Christian Kerl and Fredrik Kahl and Daniel Cremers", booktitle = "Robotics: Science and Systems (RSS) Conference 2013", volume = "9", year = "2013", topic = "SLAM", } @InProceedings{henry2013patch, title = "Patch volumes: Segmentation-based consistent mapping with RGB-D cameras", author = "Peter Henry and Dieter Fox and Achintya Bhowmik and Rajiv Mongia", booktitle = "3D Vision-3DV 2013, 2013 International Conference on", pages = "398--405", year = "2013", organization = "IEEE", topic = "SLAM", comment = "Break the environment into sub volumes", } @InProceedings{glocker2013real, title={Real-time RGB-D camera relocalization}, author={Glocker, Ben and Izadi, Shahram and Shotton, Jamie and Criminisi, Antonio}, booktitle={Mixed and Augmented Reality (ISMAR), 2013 IEEE International Symposium on}, pages={173--179}, year={2013}, organization={IEEE}, project = "http://research.microsoft.com/apps/pubs/default.aspx?id=196003", pdf = "http://research.microsoft.com/pubs/196003/glocker2013ismar.pdf", } @InProceedings{herbst2014toward, title = "Toward online 3-d object segmentation and mapping", author = "Evan Herbst and Peter Henry and Dieter Fox", booktitle = "IEEE International Conference on Robotics and Automation (ICRA)", year = "2014", topic = "SLAM", } @InProceedings{huang2011visual, title = "Visual odometry and mapping for autonomous flight using an RGB-D camera", author = "Albert S Huang and Abraham Bachrach and Peter Henry and Michael Krainin and Daniel Maturana and Dieter Fox and Nicholas Roy", booktitle = "International Symposium on Robotics Research (ISRR)", pages = "1--16", year = "2011", topic = "SLAM", } @Article{chen2013scalable, title = "Scalable real-time volumetric surface reconstruction", author = "Jiawen Chen and Dennis Bautembach and Shahram Izadi", journal = "ACM Transactions on Graphics (TOG)", volume = "32", number = "4", pages = "113", year = "2013", publisher = "ACM", topic = "SLAM", comment = "experimentally demonstrate that a shallow hierarchy with relatively large branching factors yields the best memory/speed tradeoff, consuming an order of magnitude less memory than a regular grid.", video = "http://youtu.be/NsrmniEvO4s", } @Article{niessner2013real, title = "Real-time 3d reconstruction at scale using voxel hashing", author = "Matthias Nie{\ss}ner and Michael Zollh{\"o}fer and Shahram Izadi and Marc Stamminger", journal = "ACM Transactions on Graphics (TOG)", volume = "32", number = "6", pages = "169", year = "2013", publisher = "ACM", topic = "SLAM", } @Article{henry2012rgb, title = "RGB-D mapping: Using Kinect-style depth cameras for dense 3D modeling of indoor environments", author = "Peter Henry and Michael Krainin and Evan Herbst and Xiaofeng Ren and Dieter Fox", journal = "The International Journal of Robotics Research", volume = "31", number = "5", pages = "647--663", year = "2012", publisher = "SAGE Publications", topic = "SLAM", } @Article{endres20143, title = "3-D mapping with an rgb-d camera", author = "Felix Endres and J{\"u}rgen Hess and J{\"u}rgen Sturm and Daniel Cremers and Wolfram Burgard", journal = "Robotics, IEEE Transactions on", volume = "30", number = "1", pages = "177--187", year = "2014", publisher = "IEEE", topic = "SLAM", } @InProceedings{steinbrucker2013large, title = "Large-scale multi-resolution surface reconstruction from RGB-D sequences", author = "Frank Steinbrucker and Christian Kerl and Daniel Cremers", booktitle = "Computer Vision (ICCV), 2013 IEEE International Conference on", pages = "3264--3271", year = "2013", organization = "IEEE", topic = "SLAM", } @Article{rodola2013efficient, title = "Efficient shape matching using vector extrapolation", author = "Emanuele Rodol{\`a} and Tatsuya Harada and Yasuo Kuniyoshi and Daniel Cremers", journal = "Proc. BMVC", volume = "1", year = "2013", topic = "SLAM", } @article{chen2013scalable, title={Scalable real-time volumetric surface reconstruction}, author={Chen, Jiawen and Bautembach, Dennis and Izadi, Shahram}, journal={ACM Transactions on Graphics (TOG)}, volume={32}, number={4}, pages={113}, year={2013}, publisher={ACM}, project = "http://research.microsoft.com/apps/pubs/default.aspx?id=198579", pdf = "http://research.microsoft.com/pubs/198579/fusionhd.pdf", } %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% %%% Offline Global Alignment %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% @Article{li20133d, title = "3D self-portraits", author = "Hao Li and Etienne Vouga and Anton Gudym and Linjie Luo and Jonathan T Barron and Gleb Gusev", journal = "ACM Trans. Graph.", volume = "32", number = "6", pages = "187", year = "2013", topic = "GLOB", } @Article{zhou2013dense, title = "Dense scene reconstruction with points of interest", author = "Qian-Yi Zhou and Vladlen Koltun", journal = "ACM Transactions on Graphics (TOG)", volume = "32", number = "4", pages = "112", year = "2013", publisher = "ACM", topic = "GLOB", } @InProceedings{zhou2014simultaneous, title = "Simultaneous Localization and Calibration: Self-Calibration of Consumer Depth Cameras", author = "Qian-Yi Zhou and Vladlen Koltun", booktitle = "2014 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)", pages = "454--460", year = "2014", organization = "IEEE", topic = "GLOB", comment = "Distort each frame to better align them together", } @InProceedings{zhou2013elastic, title = "Elastic fragments for dense scene reconstruction", author = "Qian-Yi Zhou and Stephen Miller and Vladlen Koltun", booktitle = "Computer Vision (ICCV), 2013 IEEE International Conference on", pages = "473--480", year = "2013", organization = "IEEE", topic = "GLOB", } @Article{zhou2014color, title = "Color map optimization for 3D reconstruction with consumer depth cameras", author = "Qian-Yi Zhou and Vladlen Koltun", journal = "ACM Transactions on Graphics (TOG)", volume = "33", number = "4", pages = "155", year = "2014", publisher = "ACM", topic = "GLOB", comment = "Optimize texture for the reconstructed models", } @InProceedings{chen2014fast, title = "Fast MRF Optimization with Application to Depth Reconstruction", author = "Qifeng Chen and Vladlen Koltun", booktitle = "Computer Vision and Pattern Recognition (CVPR), 2014 IEEE Conference on", pages = "3914--3921", year = "2014", organization = "IEEE", topic = "GLOB", } %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% %%% Alignment Dataset and Benchmarks %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% @InProceedings{xiao2013sun3d, title = "SUN3D: A database of big spaces reconstructed using SfM and object labels", author = "Jianxiong Xiao and Andrew Owens and Antonio Torralba", booktitle = "Computer Vision (ICCV), 2013 IEEE International Conference on", pages = "1625--1632", year = "2013", organization = "IEEE", topic = "GLOB,DATA", } @InProceedings{sturm2012benchmark, title = "A benchmark for the evaluation of RGB-D SLAM systems", author = "J{\"u}rgen Sturm and Nikolas Engelhard and Felix Endres and Wolfram Burgard and Daniel Cremers", booktitle = "Intelligent Robots and Systems (IROS), 2012 IEEE/RSJ International Conference on", pages = "573--580", year = "2012", organization = "IEEE", topic = "DATA,SLAM", comment = "Use motion capture system to measure the sensor poses", project = "http://vision.in.tum.de/data/datasets/rgbd-dataset" } %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% %%% Point Cloud Registration %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% @InProceedings{gelfand2005robust, title = "Robust global registration", author = "Natasha Gelfand and Niloy J Mitra and Leonidas J Guibas and Helmut Pottmann", booktitle = "Symposium on geometry processing", volume = "2", number = "3", pages = "5", year = "2005", topic = "PCRE", } @InProceedings{mellado2014super, title = "Super 4PCS Fast Global Pointcloud Registration via Smart Indexing", author = "Nicolas Mellado and Dror Aiger and Niloy J Mitra", booktitle = "Computer Graphics Forum", volume = "33", number = "5", pages = "205--215", year = "2014", organization = "Wiley Online Library", topic = "PCRE", } @Article{lu1997globally, title = "Globally consistent range scan alignment for environment mapping", author = "Feng Lu and Evangelos Milios", journal = "Autonomous robots", volume = "4", number = "4", pages = "333--349", year = "1997", publisher = "Springer", topic = "PCRE", } @Article{huber2003fully, title = "Fully automatic registration of multiple 3D data sets", author = "Daniel F Huber and Martial Hebert", journal = "Image and Vision Computing", volume = "21", number = "7", pages = "637--650", year = "2003", publisher = "Elsevier", topic = "PCRE", } @Article{huang2006reassembling, title = "Reassembling fractured objects by geometric matching", author = "Qi-Xing Huang and Simon Fl{\"o}ry and Natasha Gelfand and Michael Hofer and Helmut Pottmann", journal = "ACM Transactions on Graphics (TOG)", volume = "25", number = "3", pages = "569--578", year = "2006", publisher = "ACM", topic = "PCRE", } @Article{black1996unification, title = "On the unification of line processes, outlier rejection, and robust statistics with applications in early vision", author = "Michael J Black and Anand Rangarajan", journal = "International Journal of Computer Vision", volume = "19", number = "1", pages = "57--91", year = "1996", publisher = "Springer", topic = "PCRE", } @InProceedings{rusinkiewicz2002real, title = "Real-time 3D model acquisition", author = "Szymon Rusinkiewicz and Olaf Hall-Holt and Marc Levoy", booktitle = "ACM Transactions on Graphics (TOG)", volume = "21", number = "3", pages = "438--446", year = "2002", organization = "ACM", topic = "PCRE", } @InProceedings{rusinkiewicz2001efficient, title = "Efficient Variants of the ICP Algorithm", author = "Szymon Rusinkiewicz and Marc Levoy", booktitle = "3-D Digital Imaging and Modeling", pages = "145--152", year = "2001", organization = "IEEE", topic = "PCRE", } %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% %%% Image Features for Alignment %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% @Article{lowe2004distinctive, title = "Distinctive image features from scale-invariant keypoints", author = "David G Lowe", journal = "International journal of computer vision", volume = "60", number = "2", pages = "91--110", year = "2004", publisher = "Springer", topic = "IFET", } @Article{bay2008speeded, title = "Speeded-up robust features (SURF)", author = "Herbert Bay and Andreas Ess and Tinne Tuytelaars and Luc Van Gool", journal = "Computer vision and image understanding", volume = "110", number = "3", pages = "346--359", year = "2008", publisher = "Elsevier", topic = "IFET", } @InCollection{rosten2006machine, title = "Machine learning for high-speed corner detection", author = "Edward Rosten and Tom Drummond", booktitle = "Computer Vision--ECCV 2006", pages = "430--443", year = "2006", publisher = "Springer", topic = "IFET", comment = "FAST corner detector", } %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% %%% Geometric Features for Alignment %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% @Article{mian2005automatic, title = "Automatic correspondence for 3D modeling: an extensive review", author = "Ajmal S Mian and Mohammed Bennamoun and Robyn A Owens", journal = "International Journal of Shape Modeling", volume = "11", number = "02", pages = "253--291", year = "2005", publisher = "World Scientific", topic = "GFET", } @InProceedings{rusu2009fast, title = "Fast point feature histograms (FPFH) for 3D registration", author = "Radu Bogdan Rusu and Nico Blodow and Michael Beetz", booktitle = "Robotics and Automation, 2009. ICRA'09. IEEE International Conference on", pages = "3212--3217", year = "2009", organization = "IEEE", topic = "GFET", } @InProceedings{steder2011point, title = "Point feature extraction on 3D range scans taking into account object boundaries", author = "Bastian Steder and Radu Bogdan Rusu and Kurt Konolige and Wolfram Burgard", booktitle = "Robotics and automation (icra), 2011 ieee international conference on", pages = "2601--2608", year = "2011", organization = "IEEE", topic = "GFET", } @Article{guo2013rotational, title = "Rotational projection statistics for 3D local surface description and object recognition", author = "Yulan Guo and Ferdous Sohel and Mohammed Bennamoun and Min Lu and Jianwei Wan", journal = "International journal of computer vision", volume = "105", number = "1", pages = "63--86", year = "2013", publisher = "Springer", topic = "GFET", } @inproceedings{lai2014unsupervised, title={Unsupervised feature learning for 3d scene labeling}, author={Lai, Kevin and Bo, Liefeng and Fox, Dieter}, booktitle={Robotics and Automation (ICRA), 2014 IEEE International Conference on}, pages={3050--3057}, year={2014}, organization={IEEE} } %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% %%% Optimization Methods for Alignment %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% @InCollection{triggs2000bundle, title = "Bundle adjustment - a modern synthesis", author = "Bill Triggs and Philip F McLauchlan and Richard I Hartley and Andrew W Fitzgibbon", booktitle = "Vision algorithms: theory and practice", pages = "298--372", year = "2000", publisher = "Springer", topic = "OPTI", } @InCollection{zach2014robust, title = "Robust Bundle Adjustment Revisited", author = "Christopher Zach", booktitle = "ECCV 2014", pages = "772--787", year = "2014", publisher = "Springer", topic = "OPTI", } @InProceedings{kummerle2011g, title = "g2o: A general framework for graph optimization", author = "Rainer Kummerle and Giorgio Grisetti and Hauke Strasdat and Kurt Konolige and Wolfram Burgard", booktitle = "Robotics and Automation (ICRA), IEEE International Conference on", pages = "3607--3613", year = "2011", organization = "IEEE", topic = "OPTI", } @InProceedings{kahl2005multiple, title = "Multiple view geometry and the L-infinity-norm", author = "Fredrik Kahl", booktitle = "Computer Vision, 2005. ICCV 2005. Tenth IEEE International Conference on", volume = "2", pages = "1002--1009", year = "2005", organization = "IEEE", topic = "OPTI", } @InProceedings{aiger20084, title = "4-points congruent sets for robust pairwise surface registration", author = "Dror Aiger and Niloy J Mitra and Daniel Cohen-Or", booktitle = "ACM Transactions on Graphics (TOG)", volume = "27", number = "3", pages = "85", year = "2008", organization = "ACM", topic = "GFET", } @InProceedings{rodola2014dense, title = "Dense non-rigid shape correspondence using random forests", author = "Emanuele Rodola and Samuel Rota Bulo and Thomas Windheuser and Matthias Vestner and Daniel Cremers", booktitle = "Computer Vision and Pattern Recognition (CVPR), 2014 IEEE Conference on", pages = "4177--4184", year = "2014", organization = "IEEE", topic = "GFET", } @InCollection{schmidt2014dense, title = "Dense Elastic 3D Shape Matching", author = "Frank R Schmidt and Thomas Windheuser and Ulrich Schlickewei and Daniel Cremers", booktitle = "Efficient Algorithms for Global Optimization Methods in Computer Vision", pages = "1--18", year = "2014", publisher = "Springer Berlin Heidelberg", topic = "GFET", } @InProceedings{drost2010model, title = "Model globally, match locally: Efficient and robust 3D object recognition", author = "Bertram Drost and Markus Ulrich and Nassir Navab and Slobodan Ilic", booktitle = "Computer Vision and Pattern Recognition (CVPR), 2010 IEEE Conference on", pages = "998--1005", year = "2010", organization = "IEEE", topic = "GFET", } %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% %%% Surface Reconstruction from points %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% @InProceedings{curless1996volumetric, title = "A volumetric method for building complex models from range images", author = "Brian Curless and Marc Levoy", booktitle = "Proceedings of the 23rd annual conference on Computer graphics and interactive techniques", pages = "303--312", year = "1996", organization = "ACM", topic = "PCRE", comment = "Used in KinectFusion", } @inproceedings{kazhdan2006poisson, title={Poisson surface reconstruction}, author={Kazhdan, Michael and Bolitho, Matthew and Hoppe, Hugues}, booktitle={Proceedings of the fourth Eurographics symposium on Geometry processing}, volume={7}, year={2006} } @article{kazhdan2013screened, title={Screened poisson surface reconstruction}, author={Kazhdan, Michael and Hoppe, Hugues}, journal={ACM Transactions on Graphics (TOG)}, volume={32}, number={3}, pages={29}, year={2013}, publisher={ACM} } %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% %%% Surface Reconstruction from RGB-D in indoor environments %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% @article {nan2012search, author = {Liangliang Nan and Ke Xie and Andrei Sharf}, title = {A Search-Classify Approach for Cluttered Indoor Scene Understanding}, journal = {ACM Trans. Graph. (Proc. SIGGRAPH Asia)}, year = {2012}, volume = {31}, number = {6}, comment = {Region-growing algorithm that tries to improve the confidence of classifying the region as a single object type. A database shape is deformed to fit the final region to yield an approximate reconstruction.}, } @article {minkim2012acquiring, author = {Young Min Kim and Niloy J. Mitra and Dongming Yan and Leonidas Guibas}, title = {Acquiring {3D} Indoor Environments with Variability and Repetition}, journal = {ACM Trans. Graph. (Proc. SIGGRAPH Asia)}, year = {2012}, volume = {31}, number = {6}, comment = {Learn part/patch hierarchies for objects and try to match them to scan segments}, } @article {shao2012interactive, author = {Tianjia Shao and Weiwei Xu and Kun Zhou and Jingdong Wang and Dongping Li and Baining Guo}, title = {An Interactive Approach to Semantic Modeling of Indoor Scenes with an {RGBD} Camera}, journal = {ACM Trans. Graph. (Proc. SIGGRAPH Asia)}, year = {2012}, volume = {31}, number = {6}, comment = {User annotates regions of RGB-D images with labeled strokes to improve graph-cut results}, } %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% %%% Estimating Room Layout from RGB-D %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% @inproceedings{zhang2013estimating, title={Estimating the 3D layout of indoor scenes and its clutter from depth sensors}, author={Zhang, Jian and Kan, Chen and Schwing, Alexander G and Urtasun, Raquel}, booktitle={Computer Vision (ICCV), 2013 IEEE International Conference on}, pages={1273--1280}, year={2013}, organization={IEEE}, project = {http://n.ethz.ch/~jizhang/project/ICCV13DepthLayout/ICCV13DepthLayout.html}, pdf = {http://alexander-schwing.de/papers/ZhangEtAl_ICCV2013.pdf}, data = {http://n.ethz.ch/~jizhang/project/ICCV13DepthLayout/data.zip}, } @incollection{fouhey2014unfolding, title={Unfolding an indoor origami world}, author={Fouhey, David Ford and Gupta, Abhinav and Hebert, Martial}, booktitle={Computer Vision--ECCV 2014}, pages={687--702}, year={2014}, publisher={Springer} } %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% %%% Estimating Room Layout from RGB %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% @inproceedings{hedau2012recovering, title={Recovering free space of indoor scenes from a single image}, author={Hedau, Varsha and Hoiem, Derek and Forsyth, David}, booktitle={Computer Vision and Pattern Recognition (CVPR), 2012 IEEE Conference on}, pages={2807--2814}, year={2012}, organization={IEEE} } @inproceedings{hedau2009recovering, title={Recovering the spatial layout of cluttered rooms}, author={Hedau, Varsha and Hoiem, Derek and Forsyth, David}, booktitle={Computer vision, 2009 IEEE 12th international conference on}, pages={1849--1856}, year={2009}, organization={IEEE} } @inproceedingsS{chao2013layout, author = {Yu-Wei Chao and Wongun Choi and Caroline Pantofaru and Silvio Savarese}, title = {Layout Estimation of Highly Cluttered Indoor Scenes using Geometric and Semantic Cues}, booktitle = {Proceedings of the International Conference on Image Analysis and Processing}, year = {2013}, } %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% % Using CG models of scenes for scene understanding in images %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% @inproceedings{satkin20133dnn, title={{3DNN}: Viewpoint Invariant {3D} Geometry Matching for Scene Understanding}, author={Satkin, Scott and Hebert, Martial}, booktitle = {ICCV}, year={2013} } @inproceedings{satkin2012data, title={Data-driven scene understanding from {3D} models}, author={Satkin, Scott and Lin, Jason and Hebert, Martial}, booktitle = {BMVC}, year={2012} } %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% %%% Surface Reconstruction and Object Detection using Repositories of CG Models %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% @inproceedings{li2015database, title = "Object detection and classification from large-scale cluttered indoor scans", author = "Li, Yangyan and Dai, Angela and Guibas, Leonidas and Nie{\ss}ner, Matthias", booktitle = "Computer Graphics Forum", volume = "34", number = "2", year = "2015", pdf = "http://www.graphics.stanford.edu/~niessner/papers/2015/1database/li2015database.pdf", video = "http://www.graphics.stanford.edu/~niessner/papers/2015/1database/li2015database.mp4", project = "http://www.graphics.stanford.edu/~niessner/li2015database.html", topic = "RECON", } @article{shen2012structure, author = {Chao-Hui Shen and Hongbo Fu and Kang Chen and Shi-Min Hu}, title = {Structure Recovery by Part Assembly}, journal = {ACM Trans. Graph. (Proc. SIGGRAPH Asia)}, year = {2012}, volume = {31}, number = {6}, comment = {Approximate reconstruction of single objects from RGB-D scans by assembling parts from database shapes}, } @article{kim2012acquiring, title={Acquiring 3D indoor environments with variability and repetition}, author={Kim, Young Min and Mitra, Niloy J and Yan, Dong-Ming and Guibas, Leonidas}, journal={ACM Transactions on Graphics (TOG)}, volume={31}, number={6}, pages={138}, year={2012}, publisher={ACM} } @inproceedings{kim2013guided, title={Guided Real-Time Scanning of Indoor Objects}, author={Kim, Young Min and Mitra, Niloy J and Huang, Qixing and Guibas, Leonidas}, booktitle={Computer Graphics Forum}, volume={32}, number={7}, pages={177--186}, year={2013}, organization={Wiley Online Library}, comment={The proposed system assesses the quality and completeness of the 3D scan data by comparing to a large collection of commonly occurring indoor man-made objects using an efficient, robust, and effective scan descriptor.} } @InProceedings{Liebelt10, author = "J. Liebelt and C. Schmid", title = {Multi-view object class detection with a 3D geometric model}, booktitle = CVPR, year = {2010}, } @InProceedings{Stark10, author = {M. Stark and M. Goesele and B. Schiele}, title = {Back to the future: Learning shape models from 3D CAD data}, booktitle = BMVC, year = {2010}, } %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% %%% Objectness Measurement %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% @article{alexe2012measuring, title={Measuring the objectness of image windows}, author={Alexe, Bogdan and Deselaers, Thomas and Ferrari, Vittorio}, journal={Pattern Analysis and Machine Intelligence, IEEE Transactions on}, volume={34}, number={11}, pages={2189--2202}, year={2012}, publisher={IEEE}, pdf = {http://www.vision.ee.ethz.ch/~calvin/Publications/alexe12pami.pdf}, project = {http://groups.inf.ed.ac.uk/calvin/objectness/}, code = {http://groups.inf.ed.ac.uk/calvin/objectness/objectness-release-v2.2.zip}, } @inproceedings{chang2011fusing, title={Fusing generic objectness and visual saliency for salient object detection}, author={Chang, Kai-Yueh and Liu, Tyng-Luh and Chen, Hwann-Tzong and Lai, Shang-Hong}, booktitle={Computer Vision (ICCV), 2011 IEEE International Conference on}, pages={914--921}, year={2011}, organization={IEEE}, project = {http://www.iis.sinica.edu.tw/~liutyng/Projects/ObjSal/}, pdf = {http://www.iis.sinica.edu.tw/~liutyng/Publication_files/iccv11.pdf}, } @article{wickens1990proximity, title={Proximity compatibility and information display: Effects of color, space, and objectness on information integration}, author={Wickens, Christopher D and Andre, Anthony D}, journal={Human Factors: The Journal of the Human Factors and Ergonomics Society}, volume={32}, number={1}, pages={61--77}, year={1990}, publisher={Sage Publications} } %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% %%% Object Detection from RGB-D %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% @inproceedings{gupta2014learning, author = {Saurabh Gupta and Ross Girshick and Pabli Arbel{\'a}ez and Jitendra Malik}, booktitle = {ECCV}, title = {Learning Rich Features from {RGB-D} Images for Object Detection and Segmentation}, year = {2014}, pdf = {http://www.cs.berkeley.edu/~sgupta/pdf/rcnn-depth.pdf}, talk = {http://www.cs.berkeley.edu/~sgupta/pdf/rgbdTalkPdf.pdf}, supplemental = {http://www.cs.berkeley.edu/~sgupta/pdf/rcnn-depth-supp.pdf}, code = {https://github.com/s-gupta/rcnn-depth}, poster = {http://www.cs.berkeley.edu/~sgupta/pdf/rcnn-depth-poster.pdf}, } @InProceedings{song2014sliding, author = {S. Song and J. Xiao}, title = {Sliding Shapes for 3D Object Detection in Depth Images}, booktitle = {ECCV}, year = {2014}, pdf = {http://slidingshapes.cs.princeton.edu/paper.pdf}, video = {http://slidingshapes.cs.princeton.edu/slidingshape_video_withvoice.mp4}, project = {http://slidingshapes.cs.princeton.edu/}, code = {http://slidingshapes.cs.princeton.edu/Release/slidingShape_release.zip}, supplemental = {http://slidingshapes.cs.princeton.edu/supp.pdf}, poster = {http://slidingshapes.cs.princeton.edu/resize_slidingshape_poster_eccv.pdf}, talk = {http://slidingshapes.cs.princeton.edu/talk/slidingshape_eccvtalk.zip}, } @inproceedings{shrivastava2013building, title={Building part-based object detectors via 3d geometry}, author={Shrivastava, Abhinav and Gupta, Abhinav}, booktitle={Computer Vision (ICCV), 2013 IEEE International Conference on}, pages={1745--1752}, year={2013}, organization={IEEE}, project = {http://graphics.cs.cmu.edu/projects/gdpm/}, pdf = {http://graphics.cs.cmu.edu/projects/gdpm/gDPM.pdf}, poster = {http://graphics.cs.cmu.edu/projects/gdpm/gdpm-poster.pdf}, } @mastersthesis{Ye:EECS-2013-3, author = {Ye, Edmund Shanming}, editor = {Malik, Jitendra}, title = {Object Detection in RGB-D Indoor Scenes}, school = {EECS Department, University of California, Berkeley}, year = {2013}, month = {Jan}, project = {http://www.eecs.berkeley.edu/Pubs/TechRpts/2013/EECS-2013-3.html}, number = {UCB/EECS-2013-3}, pdf = {http://www.eecs.berkeley.edu/Pubs/TechRpts/2013/EECS-2013-3.pdf}, abstract = {Object detection is a well-studied problem in computer vision. One of the basic tasks is to draw tight bounding boxes around instances of various target classes in a set of images. Computer vision literature has primarily focused on intensity, with less emphasis on depth data. In this report we address the challenge of detecting 10 common household items (bed, chair, etc) in RGB-D images obtained using the Kinect. We operate on the recently released NYU-Depth V2 dataset. Our algorithm augments the deformable parts model by adding a set of vector quantized depth features that are, to the best of our knowledge, novel on this dataset.} } %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% %%% Scene Understanding from RGB-D %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% @article{gupta2014indoor, author = {Saurabh Gupta and Pablo Arbel{\'a}ez and Ross Girshick and Jitendra Malik}, journal = {IJCV}, title = {Indoor Scene Understanding with {RGB-D} Images: Bottom-up Segmentation, Object Detection and Semantic Segmentation}, year = {2014}, } @inproceedings{gupta2013perceptual, author = {Saurabh Gupta and Pablo Arbelaez and Jitendra Malik}, title = {Perceptual Organization and Recognition of Indoor Scenes from {RGB-D} Images}, booktitle = {CVPR}, year = {2013}, } @inproceedings{lin2013holistic, title={Holistic scene understanding for 3d object detection with rgbd cameras}, author={Lin, Dahua and Fidler, Sanja and Urtasun, Raquel}, booktitle={Computer Vision (ICCV), 2013 IEEE International Conference on}, pages={1417--1424}, year={2013}, organization={IEEE}, pdf = {http://ttic.uchicago.edu/~fidler/papers/lin_et_al_iccv13.pdf}, code = {https://bitbucket.org/lindahua/indoor3d}, project = {http://www.cs.toronto.edu/~fidler/projects/scenes3D.html}, } @inproceedings{ren2012rgb, title={Rgb-(d) scene labeling: Features and algorithms}, author={Ren, Xiaofeng and Bo, Liefeng and Fox, Dieter}, booktitle={Computer Vision and Pattern Recognition (CVPR), 2012 IEEE Conference on}, pages={2759--2766}, year={2012}, organization={IEEE} } @inproceedings{finman2013toward, title={Toward lifelong object segmentation from change detection in dense rgb-d maps}, author={Finman, Ross and Whelan, Thomas and Kaess, Michael and Leonard, John J}, booktitle={Mobile Robots (ECMR), 2013 European Conference on}, pages={178--185}, year={2013}, organization={IEEE}, pdf = {http://people.csail.mit.edu/kaess/pub/Finman13ecmr.pdf}, } %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% %%% Scene Understanding Based on Support and Physical Properties %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% @article{shao2014imagining, title={Imagining the Unseen: Stability-based Cuboid Arrangements for Scene Understanding}, author={Shao, Tianjia and Monszpart, Aron and Zheng, Youyi and Koo, Bongjin and Xu, Weiwei and Zhou, Kun and Mitra, Niloy J}, journal={ACM Transactions on Graphics (TOG)}, volume={33}, number={6}, pages={209}, year={2014}, publisher={ACM} project = {http://geometry.cs.ucl.ac.uk/projects/2014/imagining-the-unseen/}, pdf = {http://geometry.cs.ucl.ac.uk/projects/2014/imagining-the-unseen/paper_docs/ShaoMonszpart_Imagining_the_Unseen_sigga14.pdf}, talk = {http://geometry.cs.ucl.ac.uk/projects/2014/imagining-the-unseen/paper_docs/ShaoMonszpartEtAl-ImaginingTheUnseen-SiggA2014.zip}, code = {http://geometry.cs.ucl.ac.uk/projects/2014/imagining-the-unseen/paper_docs/imagining-unseen-0-2.zip}, data = {http://geometry.cs.ucl.ac.uk/projects/2014/imagining-the-unseen/paper_docs/imaginingTheUnseen_data.zip}, video = {https://www.youtube.com/watch?v=AhJogZoFwso&feature=player_embedded}, } @article{jia20143D, title={3D reasoning from blocks to stability}, author={Jia, Zhaoyin and Gallagher, AC and Saxena, Ashutosh and Chen, Tsuhan}, year={2014}, journal={Pattern Analysis and Machine Intelligence, IEEE Transactions on}, volume={37}, number={5}, pdf={http://www.cs.cornell.edu/~asaxena/papers/3d_based_reasoning_saxena_pami14.pdf}, } @inproceedings{jia20133D, title={3D-based reasoning with blocks, support, and stability}, author={Jia, Zhaoyin and Gallagher, Andrew and Saxena, Ashutosh and Chen, Tsuhan}, booktitle={Computer Vision and Pattern Recognition (CVPR), 2013 IEEE Conference on}, pages={1--8}, year={2013}, organization={IEEE}, pdf = {http://www.cs.cornell.edu/~asaxena/papers/rgbd-segmentation-3d-reasoning-cvpr13.pdf}, talk = {http://techtalks.tv/talks/3d-based-reasoning-with-blocks-support-and-stability/58612/}, } @InProceedings{silberman2012indoor, author = {Nathan Silberman and Derek Hoiem and Pushmeet Kohli and Rob Fergus}, title = {Indoor Segmentation and Support Inference from RGBD Images}, booktitle = ECCV, year = {2012} } @inproceedings{guo2013support, title={Support surface prediction in indoor scenes}, author={Guo, Ruiqi and Hoiem, Derek}, booktitle={Computer Vision (ICCV), 2013 IEEE International Conference on}, pages={2144--2151}, year={2013}, organization={IEEE} } @article{zheng2015scene, title={Scene Understanding by Reasoning Stability and Safety}, author={Zheng, Bo and Zhao, Yibiao and Yu, Joey and Ikeuchi, Katsushi and Zhu, Song-Chun}, journal=IJCV, volume={112}, number={2}, pages={221-238}, year={2015}, } @incollection{gupta2010blocks, title={Blocks world revisited: Image understanding using qualitative geometry and mechanics}, author={Gupta, Abhinav and Efros, Alexei A and Hebert, Martial}, booktitle={Computer Vision--ECCV 2010}, pages={482--496}, year={2010}, publisher={Springer} } @inproceedings{zheng2013beyond, title={Beyond point clouds: Scene understanding by reasoning geometry and physics}, author={Zheng, Bo and Zhao, Yibiao and Yu, Joey C and Ikeuchi, Katsushi and Zhu, Song-Chun}, booktitle={Computer Vision and Pattern Recognition (CVPR), 2013 IEEE Conference on}, pages={3127--3134}, year={2013}, organization={IEEE} } %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% %%% Scene Understanding Based on Human-Object Interactions %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% @Article{savva2014scenegrok, title={SceneGrok: Inferring Action Maps in 3D Environments}, author={Manolis Savva and Angel X. Chang and Pat Hanrahan and Matthew Fisher and Matthias Nie{\ss}ner}, journal = {ACM Transactions on Graphics (TOG)}, publisher = {ACM}, volume = {33}, number = {6}, year = {2014} project = {http://www.graphics.stanford.edu/~niessner/savva2014scenegrok.html}, pdf = {http://www.graphics.stanford.edu/~niessner/papers/2014/7scenegrok/savva2014scenegrok.pdf}, video = {http://www.graphics.stanford.edu/~niessner/papers/2014/7scenegrok/savva2014scenegrok.mp4}, } @InProceedings{wei2013modeling, title={Modeling 4D Human-Object Interactions for Event and Object Recognition}, author={Wei, Ping and Zhao, Yibiao and Zheng, Nanning and Zhu, Song-Chun}, booktitle=CVPR, year={2013}, } @InProceedings{jiang2013hallucinated, title={Hallucinated humans as the hidden context for labeling {3D} scenes}, author={Jiang, Yun and Koppula, Hema and Saxena, Ashutosh}, booktitle=CVPR, year={2013}, project = {http://pr.cs.cornell.edu/hallucinatinghumans/}, pdf = {http://www.cs.cornell.edu/~asaxena/papers/jiang-hallucinatinghumans-labeling3d-cvpr13.pdf}, video = {https://www.youtube.com/watch?v=lJ7OcpY3GbA&feature=player_embedded} } @InProceedings{jiang2012learning, title={Learning object arrangements in {3D} scenes using human context}, author={Jiang, Yun and Lim, Marcus and Saxena, Ashutosh}, booktitle= ICML, year={2012} } @InProceedings{koppula2013learning, title={Learning human activities and object affordances from {RGB-D} videos}, author={Koppula, Hema Swetha and Gupta, Rudhir and Saxena, Ashutosh}, booktitle=IJRR, year={2013}, } @InProceedings{yao2010modeling, title={Modeling mutual context of object and human pose in human-object interaction activities}, author={Yao, Bangpeng and Fei-Fei, Li}, booktitle=CVPR, year={2010}, } @InCollection{fouhey2012people, title={People watching: Human actions as a cue for single view geometry}, author={Fouhey, David F and Delaitre, Vincent and Gupta, Abhinav and Efros, Alexei A and Laptev, Ivan and Sivic, Josef}, booktitle=ECCV, year={2012}, } @InCollection{delaitre2012scene, title={Scene semantics from long-term observation of people}, author={Delaitre, Vincent and Fouhey, David F and Laptev, Ivan and Sivic, Josef and Gupta, Abhinav and Efros, Alexei A}, booktitle=ECCV, year={2012}, } @InProceedings{gupta2011from, author = {Abhinav Gupta and Scott Satkin and Alexei A. Efros and Martial Hebert}, title = {From Scene Geometry to Human Workspace}, booktitle = CVPR, year = {2011} }