' stroke-width='2.4'/%3E%3Ccircle cx='16' cy='16' r='2.4' fill='url(%23m)'/%3E%3C/svg%3E){kind=small}
CVIG LabComputational Photography & HDR
Reconstructing high-dynamic-range scenes from ordinary cameras — tone mapping, multi-exposure fusion, and HDR video.
IIT Gandhinagar · Established 2013
Computer Vision,
Imaging & Graphics
We build algorithms that capture, reconstruct, and interpret the visual world — from a single ray of light to a full three-dimensional scene.
Prof. Shanmuganathan Raman · Principal Investigator
Professor & Head, Computer Science & Engineering · Professor, Electrical Engineering
140+
Peer-Reviewed Papers
10
PhD Scholars Graduated
6
Patents & Applications
6
Research Directions
About the lab
The CVIG Lab studies how images are formed, and how to invert that process to recover the scenes behind them. Our work spans the classical toolkit of geometry and light and the modern toolkit of deep learning — often solving the same problem twice to understand where each approach wins.
Based jointly in the Departments of Electrical Engineering and Computer Science & Engineering at IIT Gandhinagar, the group publishes across the leading venues in vision, graphics, and imaging, and holds patents on image fusion and 3D understanding.
What we work on
Six directions, one pipeline
From forming an image to inverting it — our research runs the length of the imaging pipeline, classical methods first, learned methods second.
Photometric Stereo & Inverse Rendering
Recovering shape, reflectance, and lighting from images through photometric stereo, polarization, and inverse scattering.
3D, Point Clouds & Neural Rendering
Learning geometry from points and views — point-cloud completion, mesh processing, and neural radiance fields.
Differentiable Rendering & Visual Art
Turning rendering into an optimization target — shadow art, anamorphic sculpture, and scribble-guided design.
Saliency, Symmetry & Retargeting
Reading image structure — symmetry detection, saliency estimation, and content-aware retargeting.
Learning, Restoration & Generative Vision
Deep models for real tasks — image restoration, inpainting, EEG decoding, and generative image and video.
Selected work
Recent publications
A snapshot of recent papers across the group’s directions. The full record spans 140+ peer-reviewed papers.
All publications & patents
2 U.S. patents · 4 Indian patent applications
The group
People
SR
Prof. Shanmuganathan Raman
Principal Investigator · Professor & Head, CSE · Professor, EE, IIT Gandhinagar
Current Members
AAAkbar Ali
ASAnupam Sharma
ABArjun Badola
DHDikshit Hegde
AGAshutosh Gupta
STSaurabh Tripathi
AGAnkur Garg
PMPramod Mishra
RSRohit Sinha
PTPrateek Takshak
JDJohn Debbarma
DKDeepanjali Kumari
PAPankaj
SKSinngam Khaidem
ADArka Dutta
HMHement Shekhar Mohanty
AMAkhil Maan
AJAnvesh Jadhav
AJArnav Jagtap
KMKancheti Aparna Mala
AVAmisha Vaghela
Latest
News
Jun 2026
Dikshit Hegde is awarded the IndiaAI Fellowship.
May 2026
Prajwal Singh defends his PhD thesis, Scalable Generative Vision and Neural Decoding.
Apr 2026
Seema Kumari defends her PhD thesis on the restoration and analysis of 3D point clouds.
2026
Lab papers accepted at IEEE ICIP 2026, ICASSP 2026, ISBI 2026, and WACV 2026.
Dec 2025
Ashish Tiwari defends his PhD thesis and joins Dolby Laboratories.
Sep 2025
Prof. Raman takes charge as Head of the Department of Computer Science & Engineering, IIT Gandhinagar.
In the classroom
Teaching
ES 666
Course site ↗
Computer Vision
A graduate course spanning classical and learning-based vision — image formation and geometry through CNNs, transformers, and generative models.
Work with us
Join the lab
We look for curious students who like both the mathematics of vision and the craft of building systems. Prospective students can apply through IIT Gandhinagar’s internship and doctoral programmes.
- Lab
- Academic Block 13, Rooms 313 & 318
IIT Gandhinagar, Palaj, Gujarat – 382355 - shanmuga@iitgn.ac.in
- Departments
- Electrical Engineering & Computer Science & Engineering ↗