C-MInDS Logo
Computer Vision Research

Computer Vision & Visual AISeeing Beyond Human Perception

Advancing the frontiers of visual understanding through deep learning, medical imaging, autonomous systems, and multimedia analysis

🏥
Medical Imaging
🚗
Autonomous Systems
📹
Multimedia Analysis
🔮
3D Vision
Research Overview

Advancing Visual Intelligence

Our computer vision research spans from fundamental algorithms to real-world applications, pushing the boundaries of what machines can see and understand.

🏥

Medical Image Analysis

Advanced AI systems for medical diagnosis, including retinal imaging, radiology, and pathology analysis.

Key Applications:

Diabetic Retinopathy Detection
Cancer Screening
Radiology Automation
Surgical Planning
🤖

Autonomous Systems

Computer vision for robotics, autonomous vehicles, and intelligent surveillance systems.

Key Applications:

Self-Driving Cars
Drone Navigation
Robot Vision
Smart Surveillance
📹

Multimedia Understanding

Deep learning for video analysis, content understanding, and multimedia retrieval systems.

Key Applications:

Video Analytics
Content Moderation
Sports Analysis
Entertainment AI
🔮

3D Vision & AR/VR

Three-dimensional scene understanding, augmented reality, and virtual reality applications.

Key Applications:

3D Reconstruction
AR Applications
Virtual Try-On
Spatial Computing

Cutting-Edge Technologies

Our computer vision research leverages the latest advances in deep learning, including transformer architectures, generative models, and self-supervised learning techniques to achieve state-of-the-art performance.

We focus on developing robust, efficient, and interpretable vision systems that can operate in real-world conditions with limited data and computational resources.

Our interdisciplinary approach combines computer vision with domain expertise in healthcare, robotics, and multimedia to create impactful solutions.

👁️

Visual Intelligence

Enabling machines to see and understand the world

Our Technology Stack

We employ a comprehensive range of technologies and methodologies to tackle diverse computer vision challenges.

Deep Learning Architectures

  • Convolutional Neural Networks
  • Vision Transformers
  • Generative Adversarial Networks
  • Diffusion Models

Computer Vision Tasks

  • Object Detection
  • Semantic Segmentation
  • Image Classification
  • Pose Estimation

Advanced Techniques

  • Few-Shot Learning
  • Domain Adaptation
  • Multi-Modal Learning
  • Self-Supervised Learning

Applications

  • Medical Diagnosis
  • Autonomous Navigation
  • Content Analysis
  • Industrial Inspection

Active Research Projects

Our computer vision projects span from healthcare applications to autonomous systems, creating real-world impact through advanced visual AI.

AI for Diabetic Retinopathy Detection

Production

Deep learning system for early detection of diabetic retinopathy from retinal images, deployed in rural clinics.

Funding:₹2.5 Cr
Duration:2020-2024
Partners:
AIIMSL.V. Prasad Eye Institute
100,000+ patients screened

Autonomous Vehicle Perception

Active

Computer vision algorithms for object detection and scene understanding in autonomous driving systems.

Funding:₹3.2 Cr
Duration:2021-2025
Partners:
Tata MotorsMahindra Research
15+ vehicle prototypes

Medical Image Segmentation

Active

Advanced segmentation algorithms for CT and MRI scans to assist radiologists in diagnosis.

Funding:₹1.8 Cr
Duration:2022-2025
Partners:
Apollo HospitalsFortis Healthcare
50+ hospitals using system

Computer Vision Publications

Our computer vision research advances the state-of-the-art in medical imaging, autonomous systems, and multimedia analysis.

Conference

Medical Image Segmentation with Vision Transformers: A Comprehensive Study

52+
citations
Authors: Amit Sethi, Priya Sharma, Ganesh Ramakrishnan
CVPR 2024 2024

We present a comprehensive evaluation of Vision Transformers for medical image segmentation, achieving state-of-the-art performance on multiple medical imaging datasets with 95.2% Dice coefficient.

Medical ImagingVision TransformersImage SegmentationDeep Learning
Impact:Adopted by 25+ hospitals
Conference

Autonomous Vehicle Perception in Complex Indian Traffic Scenarios

38+
citations
Authors: Biplab Banerjee, Rajesh Kumar, Amit Sethi
ICCV 2023 2023

A robust computer vision system designed specifically for autonomous vehicle perception in complex Indian traffic conditions, handling mixed traffic patterns and challenging weather conditions.

Autonomous VehiclesObject DetectionTraffic AnalysisRobust Vision
Impact:15+ vehicle prototypes
Journal

3D Scene Understanding for Augmented Reality Applications

41+
citations
Authors: Subhasis Chaudhuri, Biplab Banerjee, Arjun Sharma
TPAMI 2024

Novel algorithms for real-time 3D scene understanding that enable robust augmented reality applications with accurate object placement and occlusion handling in dynamic environments.

3D VisionAugmented RealityScene UnderstandingReal-time Processing
Impact:10+ AR applications
Journal

Diabetic Retinopathy Detection Using Multi-Scale Deep Learning

89+
citations
Authors: Priya Sharma, Amit Sethi, Ganesh Ramakrishnan
Nature Medicine AI 2023

A multi-scale deep learning approach for automated diabetic retinopathy detection that achieves 96.5% sensitivity and 94.2% specificity on a large-scale Indian patient dataset.

Medical AIDiabetic RetinopathyMulti-scale LearningHealthcare
Impact:100,000+ patients screened

Top Publication Venues

Our computer vision research appears in premier conferences and journals

18+
CVPR
Computer Vision
15+
ICCV
International CV
12+
ECCV
European CV
8+
TPAMI
Top Journal
6+
IJCV
Vision Journal
10+
Medical AI
Healthcare
120+
Total Papers
6,800+
Total Citations
100M+
Lives Impacted

Research Team

Meet our computer vision research team.

Team component coming soon...