Shubham Gupta

Final Year Undergraduate Student
Department of Computer Science and Engineering
International Institute of Information Technology, Hyderabad

Office: 40, New Boys Hostel
Email: shubham at students.iiit.ac.in
Phone Number: +919963908773

Research

My broad research interests are specifically Computer Vision, Computer Graphics and GPU programming.

But specifically I worked in geometric problems in computer vision, like large-scale structure-from-motion and robust estimation techniques. At IIIT-Hyderabad, I work with Dr.P.J.Narayanan.

For an update -- I would be joining Credit-Suisse, Mumbai from july.

Projects

Undergraduate Thesis

3D Reconstruction: Large scale structure from motion by reducing the computational bottleneck of the process.
Shubham Gupta, Siddharth Choudhary and P.J.Narayanan.
Ongoing undergraduate thesis, Under this project, the main stress is to reconstruct 3D models from 2 dimensional data (Photos) on the GPU.

Publication Title: Practical Time Bundle Adjustment for 3D Reconstruction on GPU

Abstract: Large-scale 3D reconstruction has received a lot of attention from the computer vision community recently. Bundle adjustment is a key component of the reconstruction pipeline. The bundle adjustment step requires a considerable amount of computational resources and is usually the slowest step in the pipeline. This step hasn't been parallelized effectively either. In this paper, we present a hybrid implementation of sparse bundle adjustment on the GPUs using the CUDA programming model, with the CPU working in parallel. The overall algorithm is decomposed into smaller steps. Each of which is scheduled on the GPU or the CPU. We develop efficient kernels most of the steps and exploit existing libraries for data parallel operations and matrix inverse. Our implementation outperforms the CPU implementation significantly, achieving a speedup of 8-10 times over the standard CPU implementation for datasets with upto 500 images on one quarter of an Nvidia Tesla S1070 GPU.

In the Proc. of ECCV 2010 Workshop on Computer Vision on GPUs pdf

Other Major Projects

Nvidia CUDA Implementation of SIFT Detector [link]
Under guidance of Dr.C.V.Jawahar
Scale-invariant Feature Transform algorithm is a powerful algorithm to extract information from a real-world image. This is an implementation of the detector part of this algorithm, which works on Single/Multi-GPU machine.






Electronic Museum Guide [link]
Under guidance of Dr. Jayanthy Siwaswamy
In this project, I implemented SIFT algorithm on CPU to match an image from the image database of the museum.






Weather Prediction of next three days using improved Nearest Neighbour method [link]
Under guidace of Dr. Anoop Namboodri
In this project, I implemented an algorithm to predict weather of the following three days by using the weather data of the last one/two years. In this, the weather of the next three days are predicted by using the answer of Nearest Neighbour and also the data of the last day's weather. That means a certain special weightage is given to the last days weather also.


Showing any cut-plane of a 4-D data using Oct-tree in real time [link]
Under guidance of Dr. P.J.Narayanan.
This project deals with the visualisation of 3-D data by any cut plane. By using this project one can view the 3D volume data (4D if data is changing in time) by any cut plane, which can be rotated/translated according to the requirements.

Own Grpahics APIs [link]
Under guidance of Dr. P.J.Narayanan.
The objective of this project was to design our very own OpenGL-like Graphics API. The first part developed the complete graphics pipeline starting from Object Reference Coordinates to Screen coordinates through the steps of modelling, viewing , projection and view-port .The second part involved clipping and scan conversion.

Released Software

multi-GPU approach to find SIFT features (on Nvidia GPUs). [link]
Software calculates SIFT features using multi/single GPU(s).

Teaching Experience

• I was a teaching assistant for the course Computer Programming twice. [One in my 5th semester and another in my 7th semester.]
• I was a teaching assistant for the course Computer Systems during my 6th semester.
• I am now enjoying the teaching assistantship for the course Computer Graphics.



Education

 Senior Secondary: St. John's School, India 

 Secondary: Don and Dona convent, India