Computational
Imaging Lab IITM

Mission

We explore the emerging paradigm of computational imaging. Traditionally, imaging optics and image-based inference have been designed independently. By jointly optimizing optics and algorithms, we significantly improve imaging-system performance.

⚡ NEWS
Loading…
View all news →
⚡ NEWS
NewBest Paper Award (CVPR Workshop — 3D Geometry Generation for Scientific Computing)PRISM3D Preprint ReleasedNOVA-GS Accepted at CVPR Workshop 2026PhD Admissions OpenThree Papers Accepted at WACV 2025 and ICCP 2025GANESH accepted at WACV 2025, TucsonGAURA and DIVA accepted at ECCV 2024, MilanTwo papers accepted at ECCV 2022, Tel Aviv
View all news →
A Note From Our Principal Investigator

Welcome to the Computational Imaging Lab at IIT Madras. Our work sits at the intersection of optics, computer vision, and machine learning building the algorithms and imaging systems that let cameras see further, sharper, and smarter.

Over the past few years, our group has grown into a close-knit community of researchers tackling problems in lensless imaging, low-light photography, neural rendering, and computational photography, with work published at top venues and adopted by collaborators around the world.

We believe the best imaging systems emerge from the joint design of optics and algorithms. This principle guides every project we undertake, from fundamental research to real-world deployment.

Thank you for visiting. I invite you to explore our research, browse our publications, and reach out if you'd like to collaborate or join the lab.

Signature of Prof. Kaushik Mitra
Prof. Kaushik Mitra
Principal Investigator, Computational Imaging Lab

NOVA-GS: Noise-Aware View-Consistent Gaussian Splatting for Low-LightNovel View Synthesis

NOVA-GS enables robust low-light 3D Gaussian Splatting through unified enhancement, self-supervised denoising, and noise-aware optimization, producing accurate geometry and consistent novel views.

DSMD - for extreme low-light image restoration and depth estimation

DSMD is a public benchmark for extreme low-light stereo vision, providing multi-exposure stereo images with well-lit references. It supports joint evaluation of image enhancement and disparity estimation, advancing robust depth perception for autonomous driving, surveillance, AR/VR, and computational photography.

Lab Equipment
Canon EOS R6 Mark II
Canon EOS 70D
Google Pixel 4 Multi-Phone Rig
Rigid Endoscope
FLIR AX8
FLIR Tau2
FLIR One Edge
DAVIS240C Event Camera
Dimensional Display System
CeleX-V Event Camera
DVS128 Event Camera
Lensless Camera
FLIR Blackfly S
Kinect Depth Camera
AnyBeam Projector
Leap Motion Controller
Stereo Vision Camera
GoPro HERO6 Black
Lytro Light-Field Camera
Blackmagic Camera 6K
HTC Vive VR Headset
Loading team details…
Loading publications…
All Projects
NOVA-GS: Noise-Aware View-Consistent Gaussian Splatting for Low-Light Novel View Synthesis
2026

NOVA-GS: Noise-Aware View-Consistent Gaussian Splatting for Low-Light Novel View Synthesis

CVPR workshop 2026
Low-light imaging · 3D Reconstruction · Novel view synthesis
Dark Stereo Multi-Exposure Dataset (DSMD) for Extreme Low-Light Image Restoration and Depth Estimation
2026

Dark Stereo Multi-Exposure Dataset (DSMD) for Extreme Low-Light Image Restoration and Depth Estimation

Computer Vision and Image Understanding (CVIU) 2026
Depth estimation · Low-light imaging · Image restoration
Distilling Auxiliary RGB–T Features for Unsupervised Semantic Segmentation
2026

Distilling Auxiliary RGB–T Features for Unsupervised Semantic Segmentation

Image and Vision Computing 2026
Semantic segmentation · Thermal imaging
SPC to 3D
2025

SPC to 3D

ICIP 2025
Single-photon imaging · 3D Reconstruction · Novel view synthesis
FlatTrack: Eye-tracking with ultra-thin lensless cameras
2025

FlatTrack: Eye-tracking with ultra-thin lensless cameras

WACV 2025
Lensless imaging
IP-FaceDiff: Identity-Preserving Facial Video Editing with Diffusion
2025

IP-FaceDiff: Identity-Preserving Facial Video Editing with Diffusion

WACV workshop 2025
Generative models
PhotonSplat: 3D Scene Reconstruction and Colorization from SPAD Sensors
2025

PhotonSplat: 3D Scene Reconstruction and Colorization from SPAD Sensors

ICCP 2025
Single-photon imaging · 3D Reconstruction · Novel view synthesis
RT-X Net: RGB-Thermal Cross Attention Network for Low-Light Image Enhancement
2025

RT-X Net: RGB-Thermal Cross Attention Network for Low-Light Image Enhancement

ICIP 2025
Low-light imaging · Image restoration · Thermal imaging
BeSplat: Gaussian Splatting from a Single Blurry Image and Event Stream
2025

BeSplat: Gaussian Splatting from a Single Blurry Image and Event Stream

IEEE/CVF WACV 2025 Workshops
Event cameras · 3D Reconstruction · Novel view synthesis · Deblurring
HDRSplat: Gaussian Splatting for High Dynamic Range 3D Scene Reconstruction from Raw Images
2024

HDRSplat: Gaussian Splatting for High Dynamic Range 3D Scene Reconstruction from Raw Images

BMVC 2024
HDR Imaging · 3D Reconstruction · Novel view synthesis
Stereo-Knowledge Distillation from dpMV to Dual Pixels for Light Field Video Reconstruction
2024

Stereo-Knowledge Distillation from dpMV to Dual Pixels for Light Field Video Reconstruction

ICCP 2024
Dual pixel sensor · Light-field imaging
Transforming Single Photon Camera Images to Color HDR
2024

Transforming Single Photon Camera Images to Color HDR

CVIP 2024
Single-photon imaging · HDR Imaging
Passive Snapshot Coded Aperture Dual-Pixel RGB-D Imaging
2024

Passive Snapshot Coded Aperture Dual-Pixel RGB-D Imaging

IEEE/CVF CVPR 2024
Dual pixel sensor · Depth estimation
R2SFD: Improving Single Image Reflection Removal Using Semantic Feature Dictionary
2024

R2SFD: Improving Single Image Reflection Removal Using Semantic Feature Dictionary

ACM Multimedia 2024
Reflection removal · Semantic segmentation · Image restoration
Real-Time Restoration of Dark Stereo Images
2023

Real-Time Restoration of Dark Stereo Images

IEEE/CVF WACV 2023
Low-light imaging · Image restoration
Light field video from monocular video
2022

Light field video from monocular video

ECCV 2022
Light-field imaging
LWGNet-Fourier Ptychographic Phase Retrieval
2022

LWGNet-Fourier Ptychographic Phase Retrieval

ECCV 2022
Fourier ptychography · Computational imaging
Restoring Extremely Dark Light Fields
2022

Restoring Extremely Dark Light Fields

WACV 2022
Light-field imaging · Low-light imaging
FlatNet3D: Intensity and Absolute Depth From Single-Shot Lensless Capture
2022

FlatNet3D: Intensity and Absolute Depth From Single-Shot Lensless Capture

Journal of the Optical Society of America A 2022
3D Reconstruction · Depth estimation · Lensless imaging
Towards Realistic Underwater Dataset Generation and Color Restoration
2022

Towards Realistic Underwater Dataset Generation and Color Restoration

ICVGIP 2022
Underwater imaging · Image restoration
Unaligned Guided Thermal Super Resolution
2021

Unaligned Guided Thermal Super Resolution

IEEE TIP 2021
Thermal imaging · Image restoration
Optical flow from event sensors
2021

Optical flow from event sensors

CVIU 2021
Optical flow estimation · Event cameras
Video reconstruction from Coded-2-bucket camera
2021

Video reconstruction from Coded-2-bucket camera

ICPR 2021
Deblurring · Computational imaging
Light-field video from stereo video
2021

Light-field video from stereo video

ICCV 2021
Light-field imaging
Single Image Reflection Removal
2021

Single Image Reflection Removal

ICCV 2021
Reflection removal · Image restoration
Restoring Extremely Dark Images
2021

Restoring Extremely Dark Images

CVPR 2021
Low-light imaging · Image restoration
Unified framework for compressive video recovery
2021

Unified framework for compressive video recovery

WACV 2021
Compressive sensing
Multi-View Light Fields for Low Light Imaging
2020

Multi-View Light Fields for Low Light Imaging

IEEE TIP 2020
Low-light imaging · Image restoration · Light-field imaging
LLPackNet
2020

LLPackNet

BMCV 2020
Low-light imaging
FlatNet
2020

FlatNet

IEEE TPAMI 2020
Inverse problems · Lensless imaging
Image Restoration in Under Display Cameras
2020

Image Restoration in Under Display Cameras

ECCV-W 2020
Image restoration
CAnOPIC
2020

CAnOPIC

ICME 2020
Computational imaging · Computational photography
Mutli Patch Aggregation for Resampling Detection
2020

Mutli Patch Aggregation for Resampling Detection

ICASSP 2020
Image forensics · Image compression · Machine learning
Guided Thermal Super-Resolution
2020

Guided Thermal Super-Resolution

ECCV-W 2020
Thermal imaging · Super-resolution · Image restoration
HDR and Depth from Dual Cameras
2020

HDR and Depth from Dual Cameras

arXiv 2020
Depth estimation · Dual pixel sensor
Photorealistic video from event sensors
2019

Photorealistic video from event sensors

Journal of Electronic Imaging 2019
Event cameras · Image restoration
LF Reconstruction from Coded Projections
2019

LF Reconstruction from Coded Projections

IEEE TCI 2019
Light-field imaging
Unsupervised Underwater Depth Estimation
2019

Unsupervised Underwater Depth Estimation

ICIP 2019
Depth estimation
Monocular Retinal Depth Estimation
2019

Monocular Retinal Depth Estimation

IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS 2019
Medical imaging · Depth estimation · Semantic segmentation · Machine learning
Learning for Separable Lensless Imaging
2019

Learning for Separable Lensless Imaging

ICCV 2019
Lensless imaging · Image restoration
Deep pixel-level image prior for inverse problems in computational imaging
2019

Deep pixel-level image prior for inverse problems in computational imaging

IEEE TCI 2019
Inverse problems · Computational imaging · Compressive sensing · Generative models · Lensless imaging
Unified learning framework for light field reconstruction from coded projections
2018

Unified learning framework for light field reconstruction from coded projections

arXiv 2018
Light-field imaging · Computational imaging · Novel view synthesis · Depth estimation
Deep learning based phase retrieval for Fourier Ptychography
2018

Deep learning based phase retrieval for Fourier Ptychography

BMVC 2018
Fourier ptychography · Computational imaging · Inverse problems · Machine learning · Generative models
Data Driven Coded Aperture Design for Depth Recovery
2017

Data Driven Coded Aperture Design for Depth Recovery

ICIP 2017
Computational imaging · Computational photography · Depth estimation · Machine learning · Inverse problems
Learning Light Field Reconstruction from a Single Coded Image
2017

Learning Light Field Reconstruction from a Single Coded Image

ACPR 2017
Light-field imaging · Compressive sensing · Computational imaging · Computational photography · Novel view synthesis · Depth estimation · Inverse problems · Machine learning
Dynamic Vision Sensors for Human Activity Recognition
2017

Dynamic Vision Sensors for Human Activity Recognition

ACPR 2017
Event cameras · Machine learning
Compressive image recovery using recurrent generative model
2017

Compressive image recovery using recurrent generative model

ICIP 2017, Poster presented at ICCP'17
Compressive sensing · Computational imaging · Generative models · Machine learning · Inverse problems · Image restoration
Focalsweep for large aperture time-of-flight cameras
2016

Focalsweep for large aperture time-of-flight cameras

ICIP 2016
Computational imaging · Computational photography · Time-of-flight imaging · Depth estimation · Deblurring · Image restoration · Inverse problems
Spatial Phase-Sweep: Increasing temporal resolution of transient imaging using a light source array
2016

Spatial Phase-Sweep: Increasing temporal resolution of transient imaging using a light source array

ICIP 2016
Computational imaging · Time-of-flight imaging · Depth estimation · Inverse problems
Saliency guided Wavelet compression for low-bitrate Image and Video coding
2015

Saliency guided Wavelet compression for low-bitrate Image and Video coding

IEEE GlobalSIP 2015
Image compression · Machine learning
Towards compressive camera networks
2014

Towards compressive camera networks

IEEE Computer 2014
Compressive sensing · Computational imaging · Machine learning · 3D Reconstruction · Optical flow estimation
Recognition of motion blurred faces
2014

Recognition of motion blurred faces

Book chapter in Motion Deblurring, CUP, 2014
Deblurring
Framework for analysis of CI systems
2014

Framework for analysis of CI systems

IEEE TPAMI 2014
Computational imaging · Inverse problems · Image restoration · Deblurring · Light-field imaging
Denoise or deblur: Parameter optimization for imaging systems
2014

Denoise or deblur: Parameter optimization for imaging systems

SPIE Electronic Imaging, 2014
Computational imaging · Computational photography · Image restoration · Deblurring · Low-light imaging · Inverse problems
Improving resolution of light field using hybrid imaging design
2014

Improving resolution of light field using hybrid imaging design

ICCP 2014
Computational imaging · Computational photography · Novel view synthesis · Image restoration · Inverse problems
Compressive epsilon photography
2014

Compressive epsilon photography

SIGGRAPH 2014
Computational photography · Compressive sensing · Machine learning
Blur and illumination robust face recognition
2013

Blur and illumination robust face recognition

IEEE TIP 2013
Machine learning
Analyzing computational imaging systems
2013

Analyzing computational imaging systems

SPIE Newsroom, 2013
Computational imaging · Image restoration · Deblurring · Low-light imaging · Computational photography
Analysis of sparsity based robust regression algorithms
2013

Analysis of sparsity based robust regression algorithms

IEEE TSP 2013
Machine learning · Robust regression · Sparse representation · Compressive sensing
A common framework for light field processing
2012

A common framework for light field processing

CVPR Workshop 2012
Light-field imaging · Image denoising · Super-resolution · Computational photography · Machine learning
Missing data matrix factorization
2010

Missing data matrix factorization

NIPS 2010
3D Reconstruction · Structure from motion · Machine learning · Matrix completion
Robust regression using sparse learning techniques
2010

Robust regression using sparse learning techniques

ICASSP 2010
Machine learning · Compressive sensing
Robust RVM regression using sparse outlier model
2010

Robust RVM regression using sparse outlier model

CVPR 2010
Machine learning · Image restoration

Awards & Recognition

News Banner

News

Stay informed about the latest news at IITM-CI-Lab

Loading news…

Dataset

Loading datasets…

Code

Filter by category

Open Positions

The Computational Imaging Lab at IIT Madras builds the algorithms, optics, and learning systems behind next‑generation cameras ➙ spanning lensless and light‑field imaging, low‑light restoration, and neural rendering. We welcome postdoctoral researchers, graduate students, and undergraduates who want to push the boundaries of how machines see. Browse the opportunities below and reach out to Prof. Kaushik Mitra to apply.

How to Apply

For every track below, send your materials by email to Prof. Kaushik Mitra ➙ applications are reviewed on a rolling basis.

Postdoctoral Researchers

We are recruiting postdoctoral researchers and research scientists across several funded projects, looking for a PhD in computational imaging, computer vision, computational photography, optics, signal processing, machine learning, or a closely related area.

  • Curriculum vitae, with links to publications and released code
  • A short note on your research interests and the project(s) you'd like to work on

Graduate Students (PhD / MS by Research)

We welcome prospective PhD and MS by Research students interested in computational imaging, computer vision, computational photography, optics, signal processing, machine learning, or a closely related area. Admission and funding decisions for the IIT Madras EE graduate program are made centrally, so prospective students should first apply through the institute admissions office.

  • Curriculum vitae, with links to relevant publications, projects, or code
  • A short note describing your research interests and how they align with the lab

Undergraduate & Dual‑Degree Students

We're always glad to hear from IIT Madras undergraduate and dual‑degree students with strong math, signal processing, or coding skills.

  • Curriculum vitae and a brief statement of interest

Applications are reviewed on a rolling basis ➝ there is no fixed deadline, so reach out whenever you're ready.

Find Us

The Computational Imaging Lab is located in the Electrical Sciences Block (ESB2), IIT Madras.

1st Floor, ESB2‑104, Electrical Sciences Block (ESB2), IIT Madras, Chennai, Tamil Nadu 600036

FAQs

Do I need to have submitted my PhD before starting as a postdoc?
Yes ➙ candidates should have completed their PhD, or be very close to submission, before the position begins.
Can I apply to more than one track at once?
Yes. If you're unsure which one fits best, mention all relevant interests in your email and we'll point you in the right direction.
How does graduate admission actually work?
Admission and funding for the EE graduate program are decided by the IIT Madras admissions office, not the lab directly ➙ see their page for deadlines and requirements.
Additional questions?
Reach out to kmitra@ee.iitm.ac.in ➙ happy to help.

The Computational Imaging Lab welcomes applicants from all academic and personal backgrounds, and evaluates every candidate on the strength of their research interest and preparation.