{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,12]],"date-time":"2025-10-12T04:13:19Z","timestamp":1760242399202,"version":"build-2065373602"},"reference-count":32,"publisher":"MDPI AG","issue":"3","license":[{"start":{"date-parts":[[2017,6,29]],"date-time":"2017-06-29T00:00:00Z","timestamp":1498694400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Robotics"],"abstract":"<jats:p>In order to deal with the scaling problem of volumetric map representations, we propose spatially local methods for high-ratio compression of 3D maps, represented as truncated signed distance fields. We show that these compressed maps can be used as meaningful descriptors for selective decompression in scenarios relevant to robotic applications. As compression methods, we compare using PCA-derived low-dimensional bases to nonlinear auto-encoder networks. Selecting two application-oriented performance metrics, we evaluate the impact of different compression rates on reconstruction fidelity as well as to the task of map-aided ego-motion estimation. It is demonstrated that lossily reconstructed distance fields used as cost functions for ego-motion estimation can outperform the original maps in challenging scenarios from standard RGB-D (color plus depth) data sets due to the rejection of high-frequency noise content.<\/jats:p>","DOI":"10.3390\/robotics6030015","type":"journal-article","created":{"date-parts":[[2017,6,29]],"date-time":"2017-06-29T10:40:04Z","timestamp":1498732804000},"page":"15","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Compressed Voxel-Based Mapping Using Unsupervised Learning"],"prefix":"10.3390","volume":"6","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7035-5710","authenticated-orcid":false,"given":"Daniel","family":"Ricao Canelhas","sequence":"first","affiliation":[{"name":"Center of Applied Autonomous Sensor Systems (AASS), \u00d6rebro University, \u00d6rebro 701 82, Sweden"}]},{"given":"Erik","family":"Schaffernicht","sequence":"additional","affiliation":[{"name":"Center of Applied Autonomous Sensor Systems (AASS), \u00d6rebro University, \u00d6rebro 701 82, Sweden"}]},{"given":"Todor","family":"Stoyanov","sequence":"additional","affiliation":[{"name":"Center of Applied Autonomous Sensor Systems (AASS), \u00d6rebro University, \u00d6rebro 701 82, Sweden"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0217-9326","authenticated-orcid":false,"given":"Achim","family":"Lilienthal","sequence":"additional","affiliation":[{"name":"Center of Applied Autonomous Sensor Systems (AASS), \u00d6rebro University, \u00d6rebro 701 82, Sweden"}]},{"given":"Andrew","family":"Davison","sequence":"additional","affiliation":[{"name":"Department of Computing, Imperial College London, London SW7 2AZ, UK"}]}],"member":"1968","published-online":{"date-parts":[[2017,6,29]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"1145","DOI":"10.1016\/j.imavis.2003.09.004","article-title":"Robust Registration of 2D and 3D Point Sets","volume":"21","author":"Fitzgibbon","year":"2003","journal-title":"Image Vis. Comput."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"527","DOI":"10.1007\/s003710050084","article-title":"Sphere tracing: A geometric method for the antialiased ray tracing of implicit surfaces","volume":"12","author":"Hart","year":"1996","journal-title":"Vis. Comput."},{"key":"ref_3","unstructured":"Fuhrmann, A., Sobotka, G., and Gro\u00df, C. (2003, January 5\u201310). Distance fields for rapid collision detection in physically based modeling. Proceedings of the 2003 International Conference Graphicon, Moscow, Russia."},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Hoff, K.E., Keyser, J., Lin, M., Manocha, D., and Culver, T. (1999, January 8\u201313). Fast computation of generalized voronoi diagrams using graphics hardware. Proceedings of the 26th Annual Conference on Computer Graphics and Interactive Techniques, Los Angeles, CA, USA.","DOI":"10.1145\/311535.311567"},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Schmidt, T., Newcombe, R., and Fox, D. (2014, January 12\u201316). DART: Dense articulated real-time tracking. Proceedings of the Robotics: Science and Systems, Berkeley, CA, USA.","DOI":"10.15607\/RSS.2014.X.030"},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Curless, B., and Levoy, M. (1996, January 4\u20139). A volumetric method for building complex models from range images. Proceedings of the 23rd Annual Conference on Computer Graphics and Interactive Techniques, New Orleans, LA, USA.","DOI":"10.1145\/237170.237269"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Newcombe, R.A., Davison, A.J., Izadi, S., Kohli, P., Hilliges, O., Shotton, J., Molyneaux, D., Hodges, S., Kim, D., and Fitzgibbon, A. (2011, January 26\u201329). KinectFusion: Real-time dense surface mapping and tracking. Proceedings of the 2011 10th IEEE International Symposium on Mixed and Augmented Reality (ISMAR), Basel, Switzerland.","DOI":"10.1109\/ISMAR.2011.6162880"},{"key":"ref_8","unstructured":"Whelan, T., Kaess, M., Fallon, M., Johannsson, H., Leonard, J., and McDonald, J. (2012, January 9\u201313). Kintinuous: Spatially extended KinectFusion. Proceedings of the RSS Workshop on RGB-D: Advanced Reasoning with Depth Cameras, Sydney, Australia."},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Roth, H., and Vona, M. (2012, January 3\u20137). Moving volume kinectfusion. Proceedings of the British Machine Vision Conference (BMVC) 2012, Surrey, UK.","DOI":"10.5244\/C.26.112"},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Canelhas, D.R., Stoyanov, T., and Lilienthal, A.J. (2013, January 3\u20137). Sdf tracker: A parallel algorithm for on-line pose estimation and scene reconstruction from depth images. Proceedings of the 2013 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), Tokyo, Japan.","DOI":"10.1109\/IROS.2013.6696880"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Bylow, E., Sturm, J., Kerl, C., Kahl, F., and Cremers, D. (2013, January 24\u201328). Real-time camera tracking and 3d reconstruction using signed distance functions. Proceedings of the Robotics: Science and Systems, Berlin, Germany.","DOI":"10.15607\/RSS.2013.IX.035"},{"key":"ref_12","unstructured":"Elfes, A. (1989). Occupancy Grids: A Probabilistic Framework for Robot Perception and Navigation. [Ph.D. Thesis, Carnegie Mellon University]."},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Frisken, S.F., Perry, R.N., Rockwood, A.P., and Jones, T.R. (2000, January 23\u201328). Adaptively sampled distance fields: A general representation of shape for computer graphics. Proceedings of the 27th Annual Conference on Computer Graphics and Interactive Techniques, New Orleans, LA, USA.","DOI":"10.1145\/344779.344899"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Zeng, M., Zhao, F., Zheng, J., and Liu, X. (2012). A memory-efficient kinectfusion using octree. Computational Visual Media, Springer.","DOI":"10.1007\/978-3-642-34263-9_30"},{"key":"ref_15","unstructured":"Newcombe, R.A. (2014). Dense Visual SLAM. [Ph.D. Thesis, Imperial College London]."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"37","DOI":"10.1016\/0169-7439(87)80084-9","article-title":"Principal component analysis","volume":"2","author":"Wold","year":"1987","journal-title":"Chemom. Intell. Lab. Syst."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Ruhnke, M., Bo, L., Fox, D., and Burgard, W. Compact RGBD Surface Models Based on Sparse Coding, Proceedings of the Twenty-Seventh AAAI Conference on Artificial Intelligence, Bellevue, Washington, USA, 14\u201318 July 2013, Association for the Advancement of Artificial Intelligence (AAAI).","DOI":"10.1609\/aaai.v27i1.8549"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"4311","DOI":"10.1109\/TSP.2006.881199","article-title":"rmK-SVD: An algorithm for designing overcomplete dictionaries for sparse representation","volume":"54","author":"Aharon","year":"2006","journal-title":"IEEE Trans. Signal Process."},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Fleet, D., Pajdla, T., Schiele, B., and Tuytelaars, T. (2014). An active patch model for real world texture and appearance classification. Computer Vision\u2014ECCV 2014, Springer International Publishing. Ser. Lecture Notes in Computer Science.","DOI":"10.1007\/978-3-319-10578-9"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"71","DOI":"10.1162\/jocn.1991.3.1.71","article-title":"Eigenfaces for recognition","volume":"3","author":"Turk","year":"1991","journal-title":"J. Cogn. Neurosci."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Richardson, I.E. (2004). H. 264 and MPEG-4 Video Compression: Video Coding for Next-Generation Multimedia, John Wiley & Sons.","DOI":"10.1002\/0470869615"},{"key":"ref_22","unstructured":"Marcellin, M.W. (2002). JPEG2000 Image Compression Fundamentals, Standards and Practice: Image Compression Fundamentals, Standards, and Practice, Springer."},{"key":"ref_23","first-page":"199","article-title":"Distance field compression","volume":"12","author":"Jones","year":"2004","journal-title":"J. WSCG"},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Rumelhart, D.E., Hinton, G.E., and Williams, R.J. (1986). Learning representations by back-propagating errors. Nature, Nature Publishing Group.","DOI":"10.1038\/323533a0"},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Hinton, G.E., and Salakhutdinov, R.R. (2006). Reducing the dimensionality of data with neural networks. Science, Science\/AAAS.","DOI":"10.1126\/science.1127647"},{"key":"ref_26","unstructured":"(2017, June 26). Libsdf. Available online: https:\/\/bitbucket.org\/danielcanelhas\/libsdf."},{"key":"ref_27","unstructured":"Qu\u00eclez, I. (2017, June 26). Modeling with Distance Functions. Available online: https:\/\/www.iquilezles.org\/www\/articles\/distfunctions\/distfunctions.htm."},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Sturm, J., Engelhard, N., Endres, F., Burgard, W., and Cremers, D. (2012, January 7\u201312). A benchmark for the evaluation of rgb-d slam systems. Proceedings of the International Conference on Intelligent Robot Systems (IROS), Vilamoura, Algarve, Portugal.","DOI":"10.1109\/IROS.2012.6385773"},{"key":"ref_29","first-page":"2825","article-title":"Scikit-learn: Machine learning in Python","volume":"12","author":"Pedregosa","year":"2011","journal-title":"J. Mach. Learn. Res."},{"key":"ref_30","unstructured":"Goodfellow, I.J., Warde-Farley, D., Lamblin, D., Dumoulin, V., Mirza, M., Pascanu, M., Bergstra, M., Bastien, F., and Bengio, Y. (2013). Pylearn2: A machine learning research library. arXiv."},{"key":"ref_31","unstructured":"(2017, June 26). Nvidia Cublas library, NVIDIA Corporation, Santa Clara, CA, USA. Available online: https:\/\/developer.nvidia.com\/cuBLAS."},{"key":"ref_32","unstructured":"Jared Hoberock, J., and Bell, N. (2017, June 26). Thrust: A Parallel Template Library. Available online: https:\/\/thrust.github.io."}],"container-title":["Robotics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2218-6581\/6\/3\/15\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T18:40:49Z","timestamp":1760208049000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2218-6581\/6\/3\/15"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,6,29]]},"references-count":32,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2017,9]]}},"alternative-id":["robotics6030015"],"URL":"https:\/\/doi.org\/10.3390\/robotics6030015","relation":{},"ISSN":["2218-6581"],"issn-type":[{"type":"electronic","value":"2218-6581"}],"subject":[],"published":{"date-parts":[[2017,6,29]]}}}