Siddhartha Chaudhuri


Postdoctoral Research Associate
Dept. of Computer Science, Princeton University
35 Olden Street, #409, Princeton, NJ 08540

sidch [AT] cs [DOT] princeton [DOT] edu

My research focuses on richer tools for visual content creation, particularly for novice and casual users, and on problems in 3D reconstruction and synthesis. This research is driven by a more abstract interest in shape understanding at both the structural and semantic levels. (Why is a model of a chair not one of a chicken? What distinguishes a well-designed chair from a badly designed one? How can one build a better chair?) By building computational models of form, attribute and function, we hope to develop new techniques for designing shapes (e.g. for 3D printing or architecture), for recognizing and reconstructing objects (e.g. in scanned cities or indoor environments), and for analysing large collections of three-dimensional data such as the 3D Warehouse.

I also like rendering scenes with many billions of polygons in real time.

I currently work with Tom Funkhouser, and received my PhD from Stanford University in 2011, supervised by Vladlen Koltun.

Here's a CV.

News

Our paper on exploratory design with semantic attributes ("make the animal more scary", "make the airplane more military", "make the webpage more artistic") was accepted to UIST 2013.
Mixamo Inc. released the second beta of the Fuse character modeling tool and demoed it at GDC. With Fuse, you can design, texture and animate a character in a matter of minutes, without any prior artistic training. Fuse grew out of my PhD thesis work, and I was the architect and chief developer. Prasanna Vasudevan and others at Mixamo added support for clothing and Allegorithmic's procedural textures, and more features are in development.

Publications

S. Chaudhuri, E. Kalogerakis, S. Giguere and T. Funkhouser, "AttribIt: Content Creation with Semantic Attributes", Proc. UIST, 2013. [project page] [preprint] [video (50 MB)]
V. G. Kim, W. Li, N. J. Mitra, S. Chaudhuri, S. DiVerdi and T. Funkhouser, "Learning Part-Based Templates from Large Collections of 3D Shapes", ACM Transactions on Graphics 32(4) (Proc. SIGGRAPH), 2013. [project page] [preprint]
E. Kalogerakis, S. Chaudhuri, D. Koller and V. Koltun, "A Probabilistic Model for Component-Based Shape Synthesis", ACM Transactions on Graphics 31(4) (Proc. SIGGRAPH), 2012. [project page] [preprint] [video (112 MB)]
S. Chaudhuri, E. Kalogerakis, L. Guibas and V. Koltun, "Probabilistic Reasoning for Assembly-Based 3D Modeling", ACM Transactions on Graphics 30(4) (Proc. SIGGRAPH), 2011. [project page] [preprint] [video (44 MB)]
S. Chaudhuri and V. Koltun, "Data-Driven Suggestions for Creativity Support in 3D Modeling", ACM Transactions on Graphics 29(6) (Proc. SIGGRAPH Asia), 2010.
[journal] [preprint] [video (58 MB)]
S. Chaudhuri and V. Koltun, "Smoothed Analysis of Probabilistic Roadmaps", Computational Geometry: Theory and Applications 42(8), pp. 731-747, 2009.
[journal] [preprint]
S. Chaudhuri, D. Horn, P. Hanrahan and V. Koltun, "Image-Based Exploration of Massive Online Environments", Stanford University Computer Science Technical Report, CSTR 2009-02, 2009. [pdf]
S. Chaudhuri, R. K. Singh and E. Charbon, "Feature-Based Techniques for Real-Time Morphable Model Facial Image Analysis", Image and Video Communications and Processing Conference, IS&T/SPIE's 17th Annual Symposium on Electronic Imaging Science and Technology, San Jose, 2005.
[pdf] [extended version]
S. Chaudhuri, R. K. Ghosh and S. K. Das, "Towards Optimal Sensor Placement with Hypercube Cutting Planes", IEEE Wireless Communications and Networking Conference, New Orleans, 2005 (invited paper).
[pdf] [extended version]
M. Chhabra et al, "Novel Approaches to Vision and Motion Control for Robot Soccer", National Conference on Advanced Manufacturing and Robotics, CMERI, Durgapur, 2004. [pdf]

Teaching

Utilities (public-domain, unrestricted use)

Links