Home Members Equipment Publications Apply


Image Processing and Computer Vision (IPCV) Laboratory, Department of E&ECE, IIT Kharagpur

This is an active group in the Department of E&ECE, IIT Kharagpur. The main research areas include:

  • Statistical learning
  • Deep learning
  • Computer vision
  • Image processing
  • Imaging inverse problems
  • Optimization
  • Medical image analysis
  • Computational intelligence
  • Eye movement analysis
  • 3D vision

Email: ipcv.iitkgp@gmail.com


Members


Equipment

    Servers and Workstations
  • 6x single L40s GPU servers
  • 2x dual H100 NVL GPU servers
  • Server with A40 GPU card
  • Server with RTX6000 GPU card
  • Server with 6x 2080Ti GPU cards
  • Server with V100 GPU card
  • Multiple standalone workstations with dual /single GPU cards

    • Specialized Systems /Facilties
  • Resin 3D Printer
  • Go3D Peel 3 3D Scanner
  • Eyelink 1000 plus high precision eye tracking system
  • Tobii Pro X3-120 screen-based eye tracker
  • Specim IQ Hyperspectral Camera
  • AGV: TurtleBot 3 Burger (Camera Mounted + 360 degree Laser Distance Sensor)
  • UAV: DJI Phantom 4 Pro Plus (Camera Mounted + Obstacle Sensor)
  • Intel RealSense Depth Camera D435i
  • FLIR C3 Thermal Imaging Camera
  • FLIR T-650-SC Thermal Imaging Camera
  • Hikvision PTZ surveillance cameras
  • Cannon SX-70 HS RGB Camera + DJI Gimbal
  • RMS MAXIMUS-24 EEG system
  • Rasberry Pi & Arduino Kits
  • A light & sound-controlled room for imaging /human visual system experiments

Selected Recent Publications

    2024

  • Zakhar Shumaylov, Jeremy Budd, Subhadip Mukherjee, and Carola-Bibiane Schönlieb, "Weakly convex regularizers for inverse problems: Convergence of critical points and primal-dual optimization," accepted to the International Conference on Machine Learning (ICML), Vienna, Austria, July 2024. (paper)

  • Andreas Hauptmann, Subhadip Mukherjee, Carola-Bibiane Schönlieb, and Ferdia Sherry, "Convergent Regularization in Inverse Problems and Linear Plug-and-Play Denoisers," accepted to Foundations of Computational Mathematics (invited), June 2024. (paper)

  • Hong Ye Tan, Subhadip Mukherjee, Junqi Tang, and Carola-Bibiane Schönlieb, "Boosting data-driven mirror descent with randomization, equivariance, and acceleration," Transactions on Machine Learning Research (TMLR), vol. 5, May 2024. (paper)

  • Ziruo Cai, Junqi Tang, Subhadip Mukherjee, Jinglai Li, Carola-Bibiane Schönlieb, and Xiaoqun Zhang, "NF-ULA: Normalizing Flow-Based Unadjusted Langevin Algorithm for Imaging Inverse Problems," SIAM Journal on Imaging Sciences, vol. 17, issue 2, pp. 820-860, 2024. (paper)

  • Hong Ye Tan, Subhadip Mukherjee, Junqi Tang, and Carola-Bibiane Schönlieb, "Provably Convergent Plug-and-Play Quasi-Newton Methods," SIAM Journal on Imaging Sciences, vol. 17, issue 2, pp. 785-819, 2024. (paper)

  • Stefano van Gogh, Subhadip Mukherjee, MichaƂ Rawlik, Alexandre Pereira, Simon Spindler, Marie-Christine Zdora, Martin Stauber, Zsuzsanna Varga, and Marco Stampanoni, "Data-Driven Gradient Regularization for Quasi-Newton Optimization in Iterative Grating Interferometry CT Reconstruction," IEEE Transactions on Medical Imaging (IEEE TMI), vol. 43, no. 3, pp. 1033-1044, March 2024. (paper)

  • Ashish Verma, Aupendu Kar, Krishnendu Ghosh, Sobhan Kanti Dhara, Debashis Sen and Prabir Kumar Biswas, "Artificially Generated Visual Scanpath Improves Multi-label Thoracic Disease Classification in Chest X-Ray Images", IEEE Transactions on Instrumentation and Measurement (IEEE TIM), Accepted, 2024. (paper)

  • Sudipta Bhuyan, Aupendu Kar, Debashis Sen and Sankha Deb, "RGB-D Fusion through Zero-shot Fuzzy Membership Learning for Salient Object Detection", IEEE Transactions on Artificial Intelligence (IEEE TAI), Vol. 5, No. 7, pp. 3638-3652, 2024. (paper)

  • Debashis Sen and Vivekraj V. K., “Multi-reference Evaluation of Dynamic Video Summaries using Granule-aware F-measure”, IEEE Transactions on Emerging Topics in Computational Intelligence (IEEE TETCI), Vol. 8, No. 4, pp. 3040-3054, 2024. (paper)

  • Aupendu Kar, Sobhan K. Dhara, Debashis Sen and Prabir K. Biswas, “Self-supervision via Controlled Transformation and Unpaired Self-conditioning for Low-light Image Enhancement”, IEEE Transactions on Instrumentation and Measurement (IEEE TIM), Accepted, 2024. (paper)

  • Ashish Verma and Debashis Sen, “Generative Augmentation Driven Prediction of Diverse Visual Scanpaths in Images”, IEEE Transactions on Artificial Intelligence (IEEE TAI), Vol. 5, No. 2, pp. 940-955, 2024. (paper)

  • Siladittya Manna, Saumik Bhattacharya and Umapada Pal, “Self-Supervised Representation Learning for Knee Injury Diagnosis From Magnetic Resonance Data”, IEEE Transactions on Artificial Intelligence (IEEE TAI), Vol. 5, No. 4, pp. 1613 - 1623, 2024. (paper)

  • Alloy Das, Sanket Biswas, Ayan Banerjee, Josep LladĂłs, Umapada Pal and Saumik Bhattacharya, “Harnessing the Power of Multi-Lingual Datasets for Pre-training: Towards Enhancing Text Spotting Performance”, IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), pp. 718-728, 2024. (paper)

  • A. Kar, S. Nehra, J. Mukherjee and P. K. Biswas, "Adapting the Learning Models of Single Image Super-Resolution Into Light-Field Imaging," in IEEE Transactions on Computational Imaging (IEEE TCI), vol. 10, pp. 496-509, 2024. (paper)

  • S. Bera and P. K. Biswas, "Axial Consistent Memory GAN With Interslice Consistency Loss for Low Dose Computed Tomography Image Denoising," in IEEE Transactions on Radiation and Plasma Medical Sciences (IEEE TRPMS), vol. 8, no. 2, pp. 173-183, Feb. 2024. (paper)

  • Siladittya Manna, Saumik Bhattacharya and Umapada Pal, "Self-Supervised Visual Representation Learning for Medical Image Analysis: A Comprehensive Survey", Transactions on Machine Learning Research (TMLR). Accepted, 2024. (paper)

    • 2023

  • Sutanu Bera, Vinay Ummadi, Debashis Sen, Subhamoy Mandal and P. K. Biswas, “Memory Replay for Continual Medical Image Segmentation through Atypical Sample Selection”, International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI), pp. 513-522, Vancouver, Canada, 2023. (paper)

  • Sutanu Bera and P. K. Biswas, “Noise Conditioned Weight Modulation for Robust and Generalizable Low Dose CT Denoising”, International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI), pp. 88-97, Vancouver, Canada, 2023. (paper)

  • Hong Ye Tan, Subhadip Mukherjee, Junqi Tang, and Carola-Bibiane Schönlieb, "Data-Driven Mirror Descent with Input-Convex Neural Networks," SIAM Journal on Mathematics of Data Science, vol. 5, issue 2, pp. 558-587, 2023. (paper)

  • Subhadip Mukherjee, Andreas Hauptmann, Ozan Öktem, Marcelo Pereyra, and Carola-Bibiane Schönlieb, "Learned Reconstruction Methods With Convergence Guarantees: A survey of concepts and applications," IEEE Signal Processing Magazine, vol. 40, no. 1, pp. 164-182, Jan. 2023. (paper)

  • Sutanu Bera and Prabir Kumar Biswas, “Harnessing the Power of Multi-Lingual Datasets for Pre-training: Towards Enhancing Text Spotting Performance”, IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), pp. 5614-5623, 2023. (paper)

    • 2022

  • Sobhan Kanti Dhara and Debashis Sen, "Exposedness-based Noise-Suppressing Low-Light Image Enhancement", IEEE Transactions on Circuits and Systems for Video Technology (IEEE TCSVT), Vol. 32, No. 6, pp. 3438-3451, 2022. (paper)

  • Prasun Roy, Subhankar Ghosh, Saumik Bhattacharya, Umapada Pal and Michael Blumenstein, "TIPS: Text-Induced Pose Synthesis", The European Conference on Computer Vision (ECCV), pp. 161-178, 2022. (paper)

  • Siladittya Manna, Soumitri Chattopadhyay, Saumik Bhattacharya and Umapada Pal, "SWIS: Self-Supervised Representation Learning For Writer Independent Offline Signature Verification", IEEE International Conference on Image Processing (ICIP), pp. 1411-1415, 2022. (paper)

  • Bhavya Vasudeva, Puneesh Deora, Saumik Bhattacharya and Pyari Mohan Pradhan, "Compressed sensing mri reconstruction with co-vegan: Complex-valued generative adversarial network", IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), pp. 672-681, 2022. (paper)

  • Siladittya Manna, Dipayan Das, Saumik Bhattacharya, Umapada Pal, and Sukalpa Chanda, "PLSM: A parallelized liquid state machine for unintentional action detection", IEEE Transactions on Emerging Topics in Computing (IEEE TETC), vol. 11, no. 2, pp. 474-484, 2022. (paper)

  • Stefano van Gogh, Zhentian Wang, MichaƂ Rawlik, Christian Etmann, Subhadip Mukherjee, Carola-Bibiane Schönlieb, Florian Angst, Andreas Boss, and Marco Stampanoni, "INSIDEnet: Interpretable NonexpanSIve Data-Efficient network for denoising in grating interferometry breast CT," Medical Physics, vol. 49, issue 6, pp. 3729–3748, Jun. 2022. (paper)

  • Sutanu Bera and P. K. Biswas, “Analyzing and Improving Low Dose CT Denoising Network via HU Level Slicing”, International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI), pp. 593-602, Singapore, 2022. (paper)

  • Aupendu Kar, Suresh Nehra, Jayanta Mukhopadhyay and Prabir Kumar Biswas, "Sub-Aperture Feature Adaptation in Single Image Super-Resolution Model for Light Field Imaging", IEEE International Conference on Image Processing (ICIP), 2022. (paper)

  • K. Ghosh, A. Kar, S. Bhattacharya, D. Sen and P. K. Biswas, "Multi-Latent GAN Inversion for Unsupervised 3D Shape Completion", IEEE International Conference on Image Processing (ICIP), pp. 3460-3464, Bordeaux, France, 2022. (paper)

  • Suman Tewary and Sudipta Mukhopadhyay, "AutoIHCNet: CNN Architecture and Decision Fusion for Automated HER2 Scoring", Applied Soft Computing, Vol. 119, 2022, Art No. 108572. (paper)

  • S. Sahoo, S. K. Panda, D. K. Pratihar and S. Mukhopadhyay, "Locomotion Modes and Environmental Features Recognition Using Laser Distance Sensors," in IEEE Sensors Journal, vol. 22, no. 5, pp. 4625-4633, 2022. (paper)

    • 2021

  • Sobhan Kanti Dhara, Mayukh Roy, Debashis Sen, and Prabir Kumar Biswas, "Color Cast Dependent Image Dehazing via Adaptive Airlight Refinement and Non-linear Color Balancing", IEEE Transactions on Circuits and Systems for Video Technology (IEEE TCSVT), Vol. 31, No. 5, pp. 2076 - 2081, 2021. (paper)

  • Aupendu Kar, Sobhan K. Dhara, Debashis Sen and Prabir Kumar Biswas, "Zero-shot Single Image Restoration through Controlled Perturbation of Koschmieder’s Model", IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 16205-16215, Nashiville, USA, 2021. (paper)

  • Subhadip Mukherjee, Marcello Carioni, Ozan Öktem, and Carola-Bibiane Schönlieb, "End-to-end reconstruction meets data-driven regularization for inverse problems", 35th Conference on Neural Information Processing Systems (NeurIPS), Dec. 2021. (paper)

  • Bhavya Vasudeva, Puneesh Deora, Saumik Bhattacharya, Umapada Pal, Sukalpa Chanda, "Loop: Looking for optimal hard negative embeddings for deep metric learning", IEEE/CVF International Conference on Computer Vision (ICCV), pp. 10634-10643, 2021. (paper)

  • Aupendu Kar and Prabir Kumar Biswas, "Fast Bayesian Uncertainty Estimation and Reduction of Batch Normalized Single Image Super-Resolution Network", IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 13696-13705, Nashiville, USA, 2021. (paper)

  • S. Bera and P. K. Biswas, "Noise Conscious Training of Non Local Neural Network Powered by Self Attentive Spectral Normalized Markovian Patch GAN for Low Dose CT Denoising," in IEEE Transactions on Medical Imaging (IEEE TMI), vol. 40, no. 12, pp. 3663-3673, 2021. (paper)

  • A. Lahiri, S. Bairagya, S. Bera, S. Haldar and P. K. Biswas, "Lightweight Modules for Efficient Deep Learning Based Image Restoration," in IEEE Transactions on Circuits and Systems for Video Technology (IEEE TCVST), vol. 31, no. 4, pp. 1395-1410, 2021. (paper)

  • S. Sahoo, D. K. Pratihar and S. Mukhopadhyay, "A Locomotion Mode Adaptive Strategy for Real-Time Detection of Gait Events During Negotiating Staircases," in IEEE Transactions on Instrumentation and Measurement (IEEE TIM), vol. 70, pp. 1-8, 2021, Art no. 4002508. (paper)

    • 2020

  • Vivekraj V.K., Debashis Sen and Balasubramanian Raman, "Video Skimming: Taxonomy and Comprehensive Survey", ACM Computing Surveys, Vol. 52, No. 5, Article No. 106, 2020. (paper)

  • Prasun Roy, Saumik Bhattacharya, Subhankar Ghosh and Umapada Pal, "STEFANN: scene text editor using font adaptive neural network", IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 13228-13237, 2020. (paper)

  • Avisek Lahiri, Arnav Kumar Jain, Sanskar Agrawal, Pabitra Mitra and Prabir Kumar Biswas, "Prior Guided GAN Based Semantic Inpainting", IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 13696-13705, Seattle, USA, 2020. (paper)

  • S. Sahoo, S. K. Panda, D. K. Pratihar and S. Mukhopadhyay, "Prediction of Step Length Using Neuro-Fuzzy Approach Suitable for Prosthesis Control," in IEEE Transactions on Instrumentation and Measurement (IEEE TIM), vol. 69, no. 8, pp. 5658-5665, Aug. 2020. (paper)

  • S. Sahoo, M. Saboo, D. K. Pratihar and S. Mukhopadhyay, "Real-Time Detection of Actual and Early Gait Events During Level-Ground and Ramp Walking," in IEEE Sensors Journal, vol. 20, no. 14, pp. 8128-8136, 2020. (paper)

Information for Prospective PhD Students and Post-Docs

  • For Ph.D, go here: https://www.iitkgp.ac.in/phd-admission
    Choose Electronics and Electrical Communication Engineering (E&ECE) as the department. Among the PhD options, you can choose:
    (1) The "Ph.D with Institute Assistantship" option. One can apply for the enhanced Prime Minister's research fellowship in the first year. https://www.pmrf.in
    (2) The "Ph.D with Individual Fellowship" option. To avail this option you will have to secure the fellowship first.
    Fellowships examples:
    Prime Minister's research fellowship (direct entry channel) - https://www.pmrf.in/guidelines
    Inspire Fellowship under Assured Opportunity for Research Careers (AORC) - https://online-inspire.gov.in/Account/INSPIREProgramme
    UGC-NET (Junior Research Fellowship) - https://ugcnet.nta.nic.in/information-bulletin
    Qualities we look for: Strong interest & background in pattern recognition and machine learning related math foundations, and familiarity with deep learning frameworks (e.g. Pytorch).

  • For Post-Doc, please go here: https://www.iitkgp.ac.in/pdf and apply for the institute's fellowship.
    Otherwise, you can also consider individual post-doctoral funding from agencies such as SERB (https://serbonline.in/SERB/npdf).
    Qualities we look for: Expert in mathematical foundations of pattern recognition and machine learning, expert in deep learning implementation frameworks, and a few publications in high quality journals /conferences.