Recently Communicated Papers

● A Novel Approach for Neuromorphic Vision Data Compression based on Deep Belief Network

   Sally Khaidem, Mansi Sharma, Abhipraay Nevatia

   arXiv Link Project Page

● A Novel Light Field Coding Scheme Based on Deep Belief Network and Weighted Binary Images for Additive Layered Displays

   Sally Khaidem, Mansi Sharma

   arXiv Link Project Page

● A High Resolution Multi-exposure Stereoscopic Image & Video Database of Natural Scenes

   Rohit Choudhary, Mansi Sharma, Aditya Wadaskar, 2022

   arXiv Link Project Page Data 

● An Integrated Representation & Compression Scheme Based on Convolutional Autoencoders with 4D DCT Perceptual 

   Encoding for High Dynamic Range Light Fields

   Sally Khaidem, Mansi Sharma, 2022

   arXiv Link Project Page   

● A Robust and Scalable Attention Guided Deep Learning Framework for Movement Quality Assessment

    Aditya Kanade, Mansi Sharma, Manivannan Muniyandi, 2022

    arXiv Link Project Page  

● Tactile-ViewGCN: Learning Shape Descriptor from Tactile Data using Graph Convolutional Network

    Sachidanand V S and Mansi Sharma, 2022

    arXiv  Link  Project Page

● Tele-EvalNet: A Low-cost, Teleconsultation System for Home based Rehabilitation of Stroke Survivors using Multiscale CNN-LSTM Architecture

   Aditya Kanade, Mansi Sharma, M. Manivannan, 2021

   arXiv  Link  Project Page

●  A Novel Hierarchical Light Field Coding Scheme Based on Hybrid Stacked Multiplicative Layers and Fourier Disparity 

    Layers for Glasses-Free 3D Displays

    Joshitha Ravishankar*, Mansi Sharma*, 2021 (* equal contribution)

    arXiv  Link  Project Page

● A Flexible Lossy Depth Video Coding Scheme Based on Low-rank Tensor Modelling & HEVC Intra Prediction for Free 

   Viewpoint Video

   Mansi Sharma, Santosh Kumar, 2021

   arXiv  Link  Project Page

● A Novel Unified Model for Multi-exposure Stereo Coding Based on Low Rank Tucker-ALS and 3D-HEVC

   Mansi Sharma, Aditya Wadaskar, 2020

   arXiv  Link  Project Page 

Refereed Journal Papers Published

● Efficient representation and coding of dynamic light field: a data-driven approach based on dynamic 

   mode decomposition

   Joshitha Ravishankar, Mansi Sharma

   Journal of Electronic Imaging, 2025 

   Link Project Page   

● Lightweight and high-speed contextual intensity image reconstruction from event-based sensors with 

  adaptive FastDynamicNet

  Sally Khaidem, Raghav Jangid, and Mansi Sharma

  Journal of Electronic Imaging, 2025

  Link Project Page   

● MEStereo-Du2CNN: A Novel Dual Channel CNN for Learning Robust Depth Estimates from Multi-

   exposure Stereo Images for HDR 3D Applications

   Rohit Choudhary, Mansi Sharma, Uma T V, Rithvik Anil

   The Visual Computer, 2023

   arXiv Link Project Page   

● A Novel Hierarchical Light field Coding Scheme Based on Hybrid Stacked Multiplicative Layers and Fourier Disparity 

   Layers for Glasses-free 3D Displays

   Joshitha R, Mansi Sharma (* equal contribution)

   Signal Processing: Image Communication, 2022

   Link  Project Page

● An Integrated Learning and Approximation Scheme for Coding of Static or Dynamic Light fields Based on Hybrid Tucker-

   KLTSVD via Tensor Double-Sketching

   Joshitha R, Mansi Sharma    

   IET Signal Processing, 2022 

   Link  Project Page

● A Hybrid Tucker-VQ Tensor Sketch Decomposition Model for Coding and Streaming Real World Light Fields using Stack of 

   Differently Focused Images

   Joshitha R*, Mansi Sharma*, Sally Khaidem (* equal contribution)

   Pattern Recognition Letters, 2022

   Link  Project Page

● A Hierarchical Approach for Lossy Light field Compression with Multiple Bit Rates Based on Tucker Decomposition via 

   Random Sketching

   Joshitha R, Mansi Sharma 

   IEEE Access, 2022

   Link  Project Page

● A Flexible Coding Scheme Based On Block Krylov Subspace Approximation for Light Field Displays With Stacked 

   Multiplicative Layers

   Joshitha R*, Mansi Sharma*, Pradeep Gopalakrishnan (* equal contribution)

   Sensors, 2021

   Link  Project Page    

● A Novel Hybrid Kinect-Variety Based High Quality Multi-View Rendering Scheme for Glasses-Free 3D Displays

   Mansi Sharma, Santanu Chaudhury, and Brejesh Lall

   IEEE Transactions on Circuits and Systems for Video Technology, 2017

   Link  Project Page    

● A Flexible Architecture for Multi-view 3DTV Based on Uncalibrated Cameras

   Mansi Sharma, Santanu Chaudhury,  Brejesh Lall, and M. S. Venkatesh

   Journal of Visual Communication and Image Representation, 2014

   Link  Project Page  YouTube Video1 Video2     

2022

● Tele-EvalNet: A Low-cost, Teleconsultation System for Home based Rehabilitation of Stroke Survivors using Multiscale CNN-ConvLSTM 

   Architecture

   Aditya Sanjiv Kanade, Mansi Sharma, M. Manivannan

   In ECCV proceedings, Tenth International Workshop on Assistive Computer Vision and Robotics, 2022             

   (Oral Presentation)

   arXiv Link Project Page

2021

● SDE-DualENet: A Novel Dual Efficient Convolutional Neural Network for Robust Stereo Depth Estimation

   Rithvik Anil, Mansi Sharma, Rohit Choudhary 

   IEEE Visual Communications and Image Processing (IEEE VCIP 2021), Novotel Munich City, Germany (Poster Presentation)

   Link  Project Page  

● A Hierarchical Coding Scheme for Glasses-free 3D Displays Based On Scalable Hybrid Layered Representation of  

   Real-World Light Fields 

   Joshitha R*, Mansi Sharma* (* These authors contributed equally to this work)

   IEEE International Conference on Systems, Man, and Cybernetics (IEEE SMC 2021), Melbourne, Australia (Oral Presentation)

   arXiv  Link  Project Page  YouTube Video     

● Latent Factor Modeling of Perceived Quality for Stereoscopic 3D Video Recommendation

   Balasubramanyam Appina, Mansi Sharma, Santosh Kumar, Peter A. Kara, Aniko Simon, Mary Guindye

   In Proceedings of 2021 International Conference on 3D Immersion (IC3D 2021), Brussels, Belgium (Oral Presentation)

   arXiv  Link  Project Page YouTube Video

● A Novel Compression Scheme Based on Hybrid Tucker-Vector Quantization via Tensor Sketching for Dynamic Light Fields 

   Acquired Through Coded Aperture Camera

   Joshitha R*, Mansi Sharma*, Sally Khaidem  (* These authors contributed equally to this work)

   In Proceedings of 2021 International Conference on 3D Immersion (IC3D 2021), Brussels, Belgium (Oral Presentation)

   arXiv  Link  Project Page YouTube Video   

● OGGN: A Novel Generalized Oracle Guided Generative Architecture for Modelling Inverse Function of Artificial Neural 

   Networks

   Mohammad Aaftab V, Mansi Sharma

   Sixth IAPR International Conference on Computer Vision & Image Processing (CVIP2021), Indian Institute of Technology Ropar, 

   Punjab, India (Oral Presentation)

   arXiv  Link  Project Page YouTube Video   

2020

● A Unified Deep Learning Approach for Foveated Rendering & Novel View Synthesis from Sparse RGB-D Light Fields

   Vineet Thumuluri, Mansi Sharma

   In Proceedings of 2020 International Conference on 3D Immersion (IC3D 2020),  Brussels, Belgium (Oral Presentation)

   Link  Project Page  YouTube Video       

● A Novel 3D-UNet Deep Learning Framework Based On High-Dimensional Bilateral Grid For Edge Consistent Single 

   Image Depth Estimation

   Mansi Sharma, Abheesht Sharma, Kadvekar Rohit Tushar, Avinash Panneer

   In Proceedings of 2020 International Conference on 3D Immersion (IC3D 2020),  Brussels, Belgium (Oral Presentation)

   Link  Project Page  YouTube Video     

2019

● A Novel Randomize Hierarchical Extension of MV-HEVC for Improved light Field Compression

   Mansi Sharma, Gowtham Ragavan

   In Proceedings of  2019 International Conference on 3D Immersion (IC3D 2019),  Brussels, Belgium, 

   Part of Stereopsia (World Immersion Forum) (Oral Presentation)

   Link  Project Page    

● A Novel Approach for Multi-view 3D HDR Content Generation Based on DIBR & Depth Adaptive Tone Mapping

   Mansi Sharma, M. S. Venkatesh, Rohan Lal

   In Conference Proceedings of European Association for Signal Processing (EURASIP), 

   European Light Field Imaging Workshop, Borovets, Bulgaria (ELFI 2019), 

   European Training Network on Full Parallax Imaging (Leading European Scientific Event) (Oral Presentation)

   Link  Project Page    

● A Rich Stereoscopic 3D High Dynamic Range Image & Video Database of Natural Scenes

   Aditya Wadaskar, Mansi Sharma, Rohan Lal

   In Proceedings of 2019 International Conference on 3D Immersion (IC3D 2019), Brussels, Belgium, 

   Part of Stereopsia (World Immersion Forum) (Oral Presentation)

    Link  Project Page    

● Predicting Forward & Backward Facial Depth Maps from a Single RGB Image for Mobile 3D AR Application

   Avinash P, Mansi Sharma

   In Proceedings of 2019 International Conference on 3D Immersion (IC3D 2019),  Brussels, Belgium, 

   Part of Stereopsia (World Immersion Forum) (Oral Presentation)

    Link  Project Page    

● A Novel Image Fusion Scheme for FTV View Synthesis based on Layered Depth Scene Representation & Scale 

   Periodic Transform

   Mansi Sharma, Gowtham Ragavan

   In Proceedings of 2019 International Conference on 3D Immersion (IC3D 2019),  Brussels, Belgium, 

   Part of Stereopsia (World Immersion Forum) (Oral Presentation)

   Link  Project Page    

● A Novel Algebraic Variety based Model for High Quality Free-viewpoint View Synthesis on a Krylov Subspace

   Mansi Sharma, Gowtham Ragavan, Arathi B

   In Proceedings of 2019 International Conference on 3D Immersion (IC3D 2019),  Brussels, Belgium, 

   Part of Stereopsia (World Immersion Forum) (Oral Presentation)

   Link  Project Page    

● A Novel Approach for Multi-view 3D HDR Content Generation via Depth Adaptive Cross Trilateral Tone Mapping 

   Mansi Sharma, M. S. Venkatesh, Gowtham Ragavan, Rohan Lal

   In Proceedings of 2019 International Conference on 3D Immersion (IC3D 2019),  Brussels, Belgium, 

   Part of Stereopsia (World Immersion Forum) (Oral Presentation)

   Link  Project Page    

● A Novel Convex Autoregressive Model for Light Field Denoising on Riemannian Space

   Mansi Sharma, Rohan Lal

   In Conference Proceedings of European Association for Signal Processing (EURASIP), 

   European Light Field Imaging Workshop, Borovets, Bulgaria (ELFI 2019),

   European Training Network on Full Parallax Imaging (Leading European Scientific Event) (Oral Presentation)  

   Link  Project Page    

2014

● Content-aware Seamless Stereoscopic 3D Compositing

   Mansi Sharma, Santanu Chaudhury, and Brejesh Lall

   In Proceedings of the Indian Conference on Computer Vision, Graphics and Image Processing, 2014 (Oral Presentation)

   Link  Project Page    

● Kinect-Variety Fusion: A Novel Hybrid Approach for Artifacts-Free 3DTV Content Generation

   Mansi Sharma, Santanu Chaudhury, and Brejesh Lall

   In Proceedings of the 22nd International Conference on Pattern Recognition (ICPR), 2014 (Poster Presentation)

   Link  Project Page    

2013

● Space-time Parameterized Variety Manifolds: A Novel Approach for Arbitrary Multi-perspective 3D View Generation

   Mansi Sharma, Santanu Chaudhury, and Brejesh Lall

   In Proceedings of International Conference on 3D Vision, 2013 (Poster Presentation)

    Link  Project Page    

● A Novel Variety-based 3DTV Content Generation Scheme for Casually Captured Sparse Photo Collections

   Mansi Sharma, Santanu Chaudhury, and Brejesh Lall

   3DTV-Conference: The True Vision-Capture, Transmission and Dispaly of 3D Video (3DTV-CON), 2013 (Oral Presentation)

   Link  Project Page    

2012

● Parameterized Variety Based View Synthesis Scheme for Multi-view 3DTV

   Mansi Sharma, Santanu Chaudhury, and Brejesh Lall

   In Proceedings of the 11th Asian conference on Computer Vision, 2012 (Poster Presentation)

   Link  Project Page    

● A Free-viewpoint 3DTV System based on Parameterized Variety Model

   Mansi Sharma, Santanu Chaudhury, and Brejesh Lall

   In Proceedings of the 21st International Conference on Pattern Recognition, 2012 (Oral Presentation)

   Link  Project Page    

● Parameterized Variety for Multi-view Multi-exposure Image Synthesis & High Dynamic Range Stereo Reconstruction 

   Mansi Sharma, Santanu Chaudhury, and Brejesh Lall

   3DTV-Conference: The True Vision - Capture, Transmission and Display of 3D Video (3DTV-CON), 2012 (Oral Presentation)

   Link  Project Page    

● 3DTV View Generation with Virtual Pan/Tilt/Zoom Functionality

   Mansi Sharma, Santanu Chaudhury, and Brejesh Lall

   In Proceedings of the Eighth Indian Conference on Computer Vision, Graphics and Image Processing, 2012 (Poster Presentation)

   Link  Project Page    

Preprints

● Latent Factor Modeling of Users Subjective Perception for Stereoscopic 3D Video Recommendation

   Balasubramanyam Appina, Mansi Sharma, Santosh Kumar

   Accepted at 2021 International Conference on 3D Immersion (IC3D 2021), Brussels, Belgium     

   arXiv  Link  Project Page

● Multi-user Augmented Reality Application for Video Communication in Virtual Space

   Kumar Mridul, M. Ramanathan, Kunal Ahirwar, Mansi Sharma

   Abstract Presented at ELFI 2019, European Light Field Imaging Workshop, Borovets, Bulgaria

   European Training Network on Full Parallax Imaging (Leading European Scientific Event)

   arXiv  Project Page  YouTube Video   

Thesis/Dissertation

●  Uncalibrated Camera Based Content Generation for 3D Multi-view Display

    Mansi Sharma, PhD dissertation, Indian Institute of Technology Delhi, 2017

    Reviewers - Prof. Dinesh Manocha, Department of Computer Science, University of Maryland  

                       Prof. A. N. Rajagopalan, Department of Electrical Engineering, IIT Madras

Books/Book Chapters

Title: “Virtual Reality, Robotics & Artificial Intelligence: An Integrated Technological Interventions in Stroke Rehabilitation"

Authors: Aditya Sanjiv Kanade, Mansi Sharma, Muniyandi Manivannan

Chapter proposal accepted to “The Internet of Medical Things (IoMT) and Telemedicine Frameworks and Applications” 

Published by IGI Global, 2022,  DOI: 10.4018/978-1-6684-3533-5

Patents

Coming Soon

Poster Presentations

● Hybrid Multiplicative and Fourier Disparity Layers based Light Field Coding for Autostereoscopic Displays

 Joshitha R, Mansi Sharma

 Women in Computer Vision (WiCV) at CVPR 2024, Seattle, USA