Ayan Sinha


Ayan is a PhD student in the School of Mechanical Engineering, Purdue University, since Fall 2011. He completed his undergraduate studies (B.Tech) from I.I.T., Kharagpur (Spring 2009) and subsequently received his masters (M.S.) from Georgia Tech (Spring 2011), all in mechanical engineering. His current work focuses on using random walks and spectral graph theory for understanding the multiscale structure and evolution of graphs over time. The applications include 3D shape analysis, retrieval, correspondence for geometric graphs (or manifolds) and clustering, evaluation, hierarchical community structure finding for social network graphs.


SurfNet: Generating 3D shape surfaces using deep residual networks

Sinha, A., Unmesh, A., Huang, Q., and Ramani, K
Continue reading...

Deconvolving Feedback Loops in Recommender Systems

Ayan Sinha, David F. Gleich, Karthik Ramani
In Proceedings of the Thirtieth Annual Conference on Neural Information Processing Systems (NIPS'16) , Barcelona, Spain, 2016

Deep Learning 3D Shape Surfaces using Geometry Images

Ayan SInha, Jing Bai, Karthik Ramani
The 14th European Conference on Computer Vision, October 11-14, 2016, Amsterdam, The Netherlands.
This series of photos shows the use of a new system, called DeepHand, developed by researchers in Purdue University’s C Design Lab. It is capable of “deep learning” to understand the hand’s nearly endless complexity of joint angles and contortions, an advance that will be needed for future systems that allow people to interact with virtual environments in virtual and augmented reality. (Purdue University image/C Design Lab)

New tool for virtual and augmented reality uses ‘deep learning’

WEST LAFAYETTE, Ind. – Future systems that allow people to interact with virtual environments will require computers to interpret the human hand’s nearly endless variety… Continue reading...

DeepHand: Robust Hand Pose Estimation by Completing a Matrix Imputed with Deep Features

Ayan Sinha*, Chiho Choi*, and Karthik Ramani (* denotes equal contribution)
In Proc. IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2016, Las Vegas, USA.

A Collaborative Filtering Approach to Real-Time Hand Pose Estimation

Chiho Choi, Ayan Sinha, Joon Hee Choi, Sujin Jang, and Karthik Ramani
In Proc. IEEE International Conference on Computer Vision (ICCV) 2015, Santiago, Chile.

Multiscale Kernels using Random Walks

Karthik Ramani, Ayan Sinha
11th Symposium on Geometry processing, 3-5 July, Genova, Italy, 2013. Proceedings of the Computer Graphics Forum, Computer Graphics Forum, Volume 33, Issue 1, pages 164–177, 2014.

Ayan’s Publications

Ayan Sinha
Continue reading...