Publications | Media Coverage | Seminar/Invited Talks/Short Papers | Patents
SELECTED PAPERS
Make3D: Learning 3D Scene Structure from a Single Still Image,
Ashutosh Saxena, Min Sun, Andrew Y. Ng. To appear in IEEE Transactions of Pattern Analysis and Machine Intelligence (PAMI), 2008. [pdf, Make3d]-
Robotic Grasping of Novel Objects using Vision,
Ashutosh Saxena, Justin Driemeyer, Andrew Y. Ng. International Journal of Robotics Research (IJRR), vol. 27, no. 2, pp. 157-173, Feb 2008. [pdf]* 3-D Depth Reconstruction from a Single Still Image,
Ashutosh Saxena, Sung H. Chung, Andrew Y. Ng. International Journal of Computer Vision (IJCV), vol. 76, no. 1, pp 53-69, Jan 2008. (Online first: Aug 2007). [pdf, Springer, springerPdf](IJCV had the highest impact factor (ISI 6.085 in 2006) in all computer sciene journals.)Learning Depth from Single Monocular Images,
Ashutosh Saxena, Sung H. Chung, Andrew Y. Ng. In Neural Information Processing Systems (NIPS) 18, 2005. [pdf]High Speed Obstacle Avoidance using Monocular Vision and Reinforcement Learning,
Jeff Michels, Ashutosh Saxena, Andrew Y. Ng. In 22nd Int'l Conf on Machine Learning (ICML), 2005. [ps, pdf, ppt]
ALL PEER REVIEWED PAPERS
2004-till date (PhD, Stanford University)
Learning 3-D Scene Structure from a Single Still Image,
Ashutosh Saxena, Min Sun, Andrew Y. Ng. In ICCV workshop on 3D Representation for Recognition (3dRR-07), 2007. (best paper award) [ps, pdf, Make3d]
Cascaded Classification Models: Combining Models for Holistic Scene Understanding,
Geremy Heitz, Stephen Gould, Ashutosh Saxena, Daphne Koller. To appear in Neural Information Processing Systems (NIPS), 2008. (full oral) [pdf coming soon, More]-
Learning to Open New Doors,
Ellen Klingbeil, Ashutosh Saxena, Andrew Y. Ng. Robotics Science and Systems (RSS) workshop on Robot Manipulation, 2008. [pdf] -
Make3D: Learning 3D Scene Structure from a Single Still Image,
Ashutosh Saxena, Min Sun, Andrew Y. Ng. To appear in IEEE Transactions of Pattern Analysis and Machine Intelligence (PAMI), 2008. [pdf, Make3d] Make3D: Depth Perception from a Single Still Image,
Ashutosh Saxena, Min Sun, Andrew Y. Ng. In AAAI, 2008. (Nectar Track) [pdf]-
Learning grasp strategies with partial shape information,
Ashutosh Saxena, Lawson Wong, Andrew Y. Ng. In AAAI, 2008. [pdf] -
A Fast Data Collection
and Augmentation Procedure for Object Recognition,
Benjaminn Sapp, Ashutosh Saxena, Andrew Y. Ng. In AAAI, 2008. [pdf]First presented at NIPS workshop on Principles of Learning Problem Design 2007. Robotic Grasping of Novel Objects using Vision,
Ashutosh Saxena, Justin Driemeyer, Andrew Y. Ng. International Journal of Robotics Research (IJRR), vol. 27, no. 2, pp. 157-173, Feb 2008. [pdf]*A Vision-based System for Grasping Novel Objects in Cluttered Environments,
Ashutosh Saxena, Lawson Wong, Morgan Quigley, Andrew Y. Ng. In International Symposium of Robotics Research (ISRR), 2007. [pdf]3-D Reconstruction from Sparse Views using Monocular Vision,
Ashutosh Saxena, Min Sun, Andrew Y. Ng. In ICCV workshop on Virtual Representations and Modeling of Large-scale environments (VRML), 2007. [ps, pdf]3-D Depth Reconstruction from a Single Still Image,
Ashutosh Saxena, Sung H. Chung, Andrew Y. Ng. International Journal of Computer Vision (IJCV), vol. 76, no. 1, pp 53-69, Jan 2008. (Online first: Aug 2007). [ps, pdf, Springer, springerPdf](IJCV had the highest impact factor (ISI 6.085 in 2006) in all computer sciene journals.)Robotic Grasping of Novel Objects,
Ashutosh Saxena, Justin Driemeyer, Justin Kearns, Andrew Y. Ng. In Neural Information Processing Systems (NIPS) 19, 2006. (spotlight paper) [pdf]Depth Estimation using Monocular and Stereo Cues,
Ashutosh Saxena, Jamie Schulte, Andrew Y. Ng. In 20th International Joint Conference on Artificial Intelligence (IJCAI), 2007. [pdf]Learning to Grasp Novel Objects using Vision,
Ashutosh Saxena, Justin Driemeyer, Justin Kearns, Chioma Osondu, Andrew Y. Ng. In 10th International Symposium on Experimental Robotics (ISER), 2006. [pdf](Shorter version appeared in RSS Workshop on Manipulation for Human Environments, 2006.)Learning Depth from Single Monocular Images,
Ashutosh Saxena, Sung H. Chung, Andrew Y. Ng. In Neural Information Processing Systems (NIPS) 18, 2005. [pdf]High Speed Obstacle Avoidance using Monocular Vision and Reinforcement Learning,
Jeff Michels, Ashutosh Saxena, Andrew Y. Ng. In 22nd Int'l Conf on Machine Learning (ICML), 2005. [ps, pdf, ppt]
2004 (At CSIRO, Sydney, Australia)
In Use Parameter Estimation of Inertial Sensors by Detecting Multilevel Quasi-Static States,
Ashutosh Saxena, Gaurav Gupta, Vadim Gerasimov, Sebastian Ourselin. In Lecture Notes in Computer Science, vol. 3684, KES, 2005. [pdf, Springer]
2000-2004 (During B. Tech., IIT Kanpur, India)
Non-Linear Dimensionality Reduction by Locally Linear Isomaps,
Ashutosh Saxena, Abhinav Gupta and Amitabha Mukerjee. In Lecture Notes in Computer Science, Proc 11th Int'l Conf on Neural Information Processing- ICONIP 2004, vol. 3316, 2004. [pdf, Springer]Robust Facial Expression Recognition using Spatially Localized Geometric Model,
Ashutosh Saxena, Ankit Anand and Amitabha Mukerjee. In proc. Int'l Conf Systemics, Cybernetics and Informatics ICSCI, vol. 1, pp 124-129, 2004. [pdf]
A Microprocessor based Speech Recognizer for Isolated Hindi Digits,
Ashutosh Saxena, and Abhishek Singh.
In IEEE Annual Convention and Exhibition ACE 2002, India, 2002.
Also awarded Best Paper in IEEE India Student Paper contest 2002.
[pdf, More]
Bioinspired Modification of Polystyryl Matrix:
Single-step Chemical Evolution to a Moderately Conducting Polymer,
Ashutosh Saxena, S.G. Srivatsan, Vishal Saxena, Sandeep Verma.
Chemistry Letters, vol. 33, no. 6, pp. 740-741, 2004. [pdf]
A Novel Electric Shock Protection System based on Contact
Currents on Skin Surface,
Ashutosh Saxena, Supratim Ray, and Rajiv K. Varma.
In proc. Twelfth National Power
Systems Conference, India, vol. 2, pp 584-587, 2002.
[pdf, Extended version: pdf]
MEDIA COVERAGE
3-D Modeling Advance: A single photo can be reconstructed into a 3-D scene with Make3D, Technology Review, Mar 7, 2008.. Also Heise Germany
Make3D, 365, Japanese magazine by NTT Group, vol 19, July 2008.
New website advances the science of turning 2-D into 3-D, by David Orenstein, Stanford Report, Jan 23, 2008. For followup releases such as frontpage of Slashdot, Dr. Dobbs, etc., click here.
Getting a Grip: Building the Ultimate Robotic Hand, Wired Magazine, Issue 15.12, Dec 2007. (Also Robot Hands Get a Grip on the Future, Wired, Sep 20, 2008.)
Challenges for Robot Manipulation in Human Environments, Charles C. Kemp, Aaron Edsinger, Eduardo Torres-Jara,
IEEE Robotics and Automation Magazine, vol. 14, issue 1, 2007.Robot learns to grasp everyday chores, Brian D. Lee, Stanford Report, Nov 8, 2006. Also: Artificial Intelligence might keep you from doing the dishes, Jack Hubbard, Nov 8, 2005. Also: A multitasking machine, Stanford Magazine, March 2007.
Brainy Robots Start Stepping Into Daily Life, Frontpage of New York Times, July 18, 2006. Other major newspapers that have given our work prominent coverage include the International Herald Tribune; the Sunday Times (UK); Mercury News; and Apple News (Hong Kong).
(Comments on STAIR, and my project on unloading a dishwasher.)Robots will 'do housework'. In BBC News. 6pm, Feb 16, 2007. Also ABC Channel 4 News, 11pm, April 6, 2007. Also Kron 4 News, 6pm, April 2007.
Robot Car. In John Fowler's Cutting Edge (KTVU News). 5 pm, Dec 13, 2005.
Why a robot is better with one eye than two, New Scientist, Dec 17, 2005.
New algorithm improves Robot Vision, Stanford Report (Dec 7, 2005), Physorg (Dec 7, 2005), Science Daily (Jan 9, 2006). (On Learning Depth from Single Monocular Images work.)
One eye on the world, Stanford Scientific, vol. 4, Issue 3, 2006. (On Learning Depth from Single Monocular Images work.)
Shock Protection Gadget, Business World (India), 2001; and other national (Indian) newspapers. (On Inventing the Novel Electric Shock protection Gadget.)
Rapid Interactive 3D Reconstruction from a Single Still Image, Ashutosh Saxena, Nuwan Senaratna, Savil Srivastava, Andrew Y. Ng. In SIGGRAPH Late Breaking work (Informal Session), 2008. [1-page pdf, Video]
Learning 3D Models from a Single Still Image, Ashutosh Saxena. Invited talk in Oxford University (July 2008) and MSR Cambridge (July 2008).
Monocular 3D Depth Perception for Navigation, Ashutosh Saxena. In ARO/NSF Workshop on Future Directions in Visual Navigation, May 2008.
Learning to Open New Doors,
Ellen Klingbeil, Ashutosh Saxena, Andrew Y. Ng. In AAAI 17th Annual Robot Workshop and Exhibition, 2008. [pdf]Building a 3-D Model From a Single Still Image,
Ashutosh Saxena, Min Sun and Andrew Y. Ng. Demonstration in Neural Information Processing Systems (NIPS), 2007.
Also presented at NIPS Workshop on The Grammar of Vision: Probabilistic Grammar-Based Models for Visual Scene Understanding and Object Categorization, 2007. [png]
Also in AAAI IS Demonstration, 2008.Learning 3-D Object Orientation from Images,
Ashutosh Saxena, Justin Driemeyer and Andrew Y. Ng. NIPS workshop on Robotic Challenges for Machine Learning, 2007. [abstract, extended full version]Data Manipulation and Creation Techniques for Learning Tasks,
NIPS workshop on Principles of Learning Problem Design, 2007. [ppt]Monocular Vision and its applications,
HomeBrew Robotics Club, Jan 2007; Stanford PAIL, Apr 2007; Bay Area Vision Research Day (BAVRD), Aug 2007; Stanford DAGS, Oct 2007; Smith-Kettlewell Colloquium, Oct 2007; Stanford GRAI, Oct 2007; Nokia-NRC, Nov 2007; MIT, Jan 2008; Google, Jan 2008.STAIR: The STanford Artificial Intelligence Robot project,
Learning Workshop, Snowbird, Apr 2008.Learning to Grasp Novel Objects using Vision,
Ashutosh Saxena, Justin Driemeyer, Justin Kearns, Chioma Osondu, Andrew Y. Ng, RSS Workshop on Manipulation for Human Environments, 2006.STAIR: Robotic Grasping of Novel Objects,
Stanford-KAIST Robotics Workshop, 2007.Learning Depth from Single Still Images: Approximate Inference,
Ashutosh Saxena, Ilya O. Ryzhov, Channing Wong, Jianlin Wang, Project Report, MS&E 211, Stanford University, 2006.Vernier Acuity and Contrast Sensitivity,
Ashutosh Saxena, Brian Wandell, Project Report, Psych221/EE362: Human Vision and Imaging Systems, Stanford University, Mar 2005.Ultrasonic Sensor Network: Realtime Target Localization with Passive Self-Localization,
Ashutosh Saxena, and Andrew Ng, Project Report, CS229: Machine Learning, Stanford University, Dec 2004.A New Embedded Multiresolution Signaling Scheme for CPFSK ,
Ashutosh Saxena, Ajit K. Chaturvedi, B. Tech. research thesis, IIT Kanpur, India , April 2004.Adaptive Multirate CDMA for Uplink ensuring Maximum Proportional Fairness,
Ashutosh Saxena, Ajit K. Chaturvedi, IIT Kanpur tech report, April 2004.Lip Enhancement Transform for Color Face Images Based on Gaussian Modeling of Skin and Lip Color,
Ashutosh Saxena, IIT Kanpur tech report, Nov 2003.SANKET: Hand Gesture Recognition,
Ashutosh Saxena, Aditya Awasthi and Vaibhav Vaish, IEEE CSIDC 2003. (More)Fiber Optic Evanescent Field Refractive Index Sensor using Phase Sensitive Detection: Effect of Radius of Bending on Sensitivity,
Ashutosh Saxena, IIT Kanpur Technical Report, July 2002.Computer Based Automatic Test and Measurement System for a Three-Terminal Device,
Ashutosh Saxena. In Virtual Instrumentation, held by National Instruments at IIT Kanpur, Feb 2002.Ashutosh Saxena, Supratim Ray, and Rajiv K. Varma, A Novel Electric Shock Protection Gadget, Indian Patent pending (application with TIFAC).
Ashutosh Saxena, Jingwei Lu, Nimish Khanolkar, undisclosed title, International patent (US plus many other countries) filed through Microsoft.
Undisclosed, Stanford University, 2007.
Undisclosed-2, Stanford University, 2008.
SEMINARS / INVITED TALKS / TECHNICAL REPORTS / DEMOS / WORKSHOPS
PATENTS
Copyright notice
All papers may be copyrighted by the journals/conferences, therefore, do not download without checking the journals' or conferences' copyright notices!
* The final, definitive version of this paper has been published in IJRR, vol, issue, Feb 2008 by Sage Publications Ltd, All rights reserved. (c) SAGE publications Ltd, 2008. It is available online at http://online.sagepub.com