CONTACT INFORMATION

EDUCATION

• MS in Computer Science and Eng.
  UNC - Chapel Hill (Aug 2008)
• MS by Research (Thesis) in Computer Science and Eng. [Computer Graphics]
  IIIT - Hyderabad (2005)
• B. Tech. in Computer Science and Eng. [Honors in Visual Informatics]
  IIIT - Hyderabad (2003)

OBJECTIVE

ACHIEVEMENTS

• Ranked 10 in the graduating batch of 2003 at IIIT, Hyderabad.
  
• Dean's List (Spring 2001, Fall 2001, Spring 2002 and Spring 2003) - Scholarship given for outstanding academic performance at IIIT, Hyderabad.
  
• Secured 40th position in Google India Code Jam 2005.

REFEREED JOURNAL PUBLICATIONS

• "Compression of Multiple Depth-Maps for IBR"
  Sashi Kumar Penta and P. J. Narayanan
  The Visual Computer, Volume 21, Numbers 8-10 / September, 2005
  Presented at the Thirteenth Pacific Conference on Computer Graphics and Applications, October, 2005
  

REFEREED CONFERENCE PUBLICATIONS

• "Fluid in Video: Augmenting Real Video with Simulated Fluids"
  Vivek Kwatra, Philippos Mordohai, Sashi Kumar Penta , Rahul Narain, Mark Carlson, Marc Pollefeys, and Ming Lin
  To appear in Eurographics 2008.
• "Depth Images: Representations and Real-time Rendering"
  Pooja Verlani, Aditi Goswami, P. J. Narayanan, Shekhar Dwivedi and Sashi Kumar Penta
  Proc. Of Third International Symposium on 3D Data Processing, Visualization and Transmission (3DPVT), June 14-16, 2006
  
• "Depth+Texture Representation for Image Based Rendering"
  P. J. Narayanan, Sashi Kumar P and Sireesh Reddy K
  Proc. Fourth Indian Conference on Computer Vision, Graphics and Image Processing (ICVGIP), pp. 113-118, 2004
  

POSTERS/SKETCHES

• "Background Replacement"
  Sashi Kumar Penta
  Presented at Siggraph 2008, Los Angelos
  

RESEARCH INTERESTS

WORK EXPERIENCE

• Software Engineer, Dx driver development team for Larrabee, Visual Computing Group, Intel (Sept 2008 - Present)
• Research Intern, Integrated Data Systems, Siemens Corporate Research (Summer 2008)
• Research Assistant, CS Dept, UNC at chapel hill (AUG, 2006 - May, 2008)
• Research Intern, Interactive Visual Media group, Microsoft Research, Redmond, USA (Summer 2007)
• Software Engineer, OpenG-ES driver devlopment team, NVIDIA Graphics Private Ltd, Bangalore, India (Aug, 2005-July, 2006)
• Research Student/Associate, Center for Visual Information Technology (CVIT) at IIIT, Hyderabad (2001 - 2005)
• Research Intern, Imaging Technologies group, GE John F Welch Technology Center, Bangalore, India (Summer 2003)
• Instructor for the course, Software Technologies for the Mtech computer science students of IIIT-Hyd (as a junior lecturer) in Spring 2005

MAJOR PROJECTS

• Large scale location recognition [On going]
  

  [       ...        ]
  [More details later]
  [       ...        ]
  

• Realistic image compositions using web [On going]
  

  [       ...        ]
  [More details later]
  [       ...        ]
  

• Image enhancement techniques on the GPU
  In this project, we implemented two enhancement techniques, automatic computation of the angle to correct the horizon of an image, and automatic computation of bi-lateral filter parameters to remove the noise in an image. Parts of these techniques are implemented on the GPU using Direct 3D (DirectX 9) and HLSL in shader model 3.0. This work is done while I was interning at the Interactive visual group, Microsoft Research, under the mentorship and colloboration with Dr. Sing Bing Kang, Dr. Denis demandolx and Bryan Ressler.
  
  
• Sparse matrix computations on the multi cores and GPU [On going]
  In this project we are working on developing efficient algorithms for computing sparse matrix operations on the GPU.
  [.. More details later ..]
  
  
• Fluid in Video: Augmenting Real Video with Simulated Fluids
  In this project, we present a technique for coupling simulated fluid phenomena that interact with real dynamic scenes captured as a binocular video sequence. We first process the binocular video sequence to obtain a complete 3D reconstruction of the scene, including velocity information. We then perform fluid simulation within a 3D domain that contains the object, enabling one-way coupling from the video to the fluid. Our method, not only generates smoothly varying geometry across time, but also simultaneously provides the necessary boundary conditions for one-way coupling between the dynamic geometry and the simulated fluid. Finally, we employ a GPU based scheme for rendering the synthetic fluid in the real video, taking refraction and scene texture into account. This work will appear in Eurographics 2008.
  
  
• OpenGL-ES driver development
  OpenGL-ES stands for Open Graphics Library for Embedded Systems. The OpenGL-ES driver is a graphics driver. A graphics driver is a library of functions which allow an application to draw things on the screen. Using a standard API (such as OpenGL, OpenGL-ES) allows an application to be written using one set of functions, and then run on a variety of graphics hardware. As part of this team, I am involved in adding the extensions of OpenGL ES to the NVIDIA's OpenGL-ES, such as rendering to texture. I also worked on porting from OpenGL programs to OpenGL-ES for testing the quality of the OpenGL ES driver and fixing the bugs in the OpenGL-ES driver. This work has been done while I worked at NVIDIA from July, 2005 to June, 2006.
  
  
• Depth Images: Representations and Real-time Rendering
  Depth Images (DIs) are viable representations that can be computed from the real worlds using cameras and/or other scanning devices. In this project, we present a discussion on the Depth Image representation and provide a GPU-based algorithm that can render large models represented using DIs in real time. We show the results using a proxy-based compression scheme for Depth Images and provide results for the same. We provide discussion on quality levels in Image Based Rendering (IBR) and show a way to create representations using DIs with different trade-offs between model size and rendering quality. This work was appeared in 3DPVT, June, 2006. [PDF]
  
  
• Compression of Multiple Depth maps for Image based Rendering
  Image Based Rendering techniques include those with geometry and those without. Geometric information in the form of a depth map aligned with the image holds a lot of promise for IBR due to the several methods available to capture it. It can improve the quality of generated views using a limited number of views. Compression of lightfields or multiple images has attracted a lot of attention in the past. Compression of multiple depth maps of the same scene has not been explored much in the literature. We propose a method for compressing multiple depth maps in this paper using geometric proxy. Different quality of rendering and compression ratio can be achieved by varying different parameters. Experiments show the effectiveness of the compression technique on several model data.This work was appeared in the Proc. Of the Thirteenth Pacific Conference on Computer Graphics and Applications, October, 2005. [PDF]
  
  
• Depth Image Representation for Image based Rendering
  Image Based Rendering holds a lot of promise for navigating through a real world scene without modeling it manually. Different representations have been proposed for IBR in literature. Here we argue that a representation using depth maps and texture images from a number of viewpoints is a rich and viable representation for IBR. We have seen different aspects of this representation, including capture, representation, compression and rendering. Our results show how the representation can be used to model and render complex scenes. This work was presented at the Indian Conference on Computer Vision, Graphics and Image Processing (ICVGIP) 2004. [PDF]
  
  
• Laparoscopic Surgery Training Simulator
  Laparoscopic Surgery training is an important component in the medical education and practice. Conventional training methods involve huge costs. We built a virtual reality system for simulating the laparoscopic surgery training procedures. This enables the surgeons to perform a 'virtual surgery' and get evaluated. The system has a huge graphics module built using OpenGL and an evaluation module. This was done in collaboration with the Center for Artificial Intelligence and Robotics (CAIR), Bangalore.
  

SOFTWARE SKILLS

• Programming Languages: C, C++, Java, Lisp, Perl, Prolog
• Operating Systems: GNU/Linux, Windows 98/ME/2000/XP
• Programming Tools & APIs: OpenGL, Cg, Qt, CVS and SVN, Sed and Awk, Lex and Yacc, Visual C++
• Others: Matlab, HTML, MySQL, Gimp, Latex, Microsoft Office

MAIN STREAM COURSES

IMPORTANT REGULAR COURSES

CONFERENCES/WORKSHOPS ATTENDED

• SIGGRAPH 2007, San Diego, CA, USA.
• Asian Conference on Computer Vision 2006 (ACCV 2006), Hyderabad, India
• Pacific Graphics 2005 (PG 2005), Macau, China
• Indian Conference on Computer Vision, Graphics and Image Processing (ICVGIP 2004), Kolkata, India.
• Workshop on Computer Vision, Graphics and Image Processing (WCVGIP 2004), Gwalior, India.
• Indian Conference on Computer Vision, Graphics and Image Processing (ICVGIP 2002), Ahmedabad, India.

MISCELLANIOUS ACTIVITIES

• I am a member of the Association for Computing Machinery [ACM] and the Institute of Electrical and Electronics Engineers [IEEE].
• I was a volunteer for *Muskaan in my life* Foundation, whose primary objective is to provide educational support to children of under-privileged families.
• I like to play basketball and lawn tennis. I was an active member of the team that won the intra-institute basketball tournament in IIIT thrice in a row.

REFERENCES ON REQUEST