3D Computer Vision

3D Computer Vision Video Compression Motion Tracking Biometrics Texture Analysis Remote Sensing Biomedical Image Processing
    Research Interests in 3D CV:

    3D semantic segmentation, 3D adversarial attack & defense, point cloud reconstruction, point cloud classification,
    adversarial knowledge distillation, 3D dynamic human action recognition, 3D dynamic pose estimation, 3D reconstruction
    & graphical element addition in dynamic sports scenes, 3D virtual reality, RGB-D video generation using GANs,
    self-driving cars, 3D dynamic object tracking and re-identificaion, 3D object recognition, 3D dynamic model building,
    3D video mosaicing, & 3D video super-resolution.

    To download the IPL Azadi Soccer Dataset and receive more information, please contact kasaei[at]sharif[dot]edu.


  1. Mohammad Danial Jahanbani (2024-Pr): Domain Adaptation of Point Cloud Data with Contrastive Language-Image Pre-Training Model
  2. Amir Hossein Naghi Razlighi (2024-Pr): Leveraging 3D Gaussian Splatting for Street Scene Reconstruction and Representation
  3. Reza Heidari (2024-Pr): Point Cloud Classification and Sampling by Deep Learning
  4. Erfan Sadraiyeh (2024-Pr): 3D Data Style Transfer
  5. Benyamin Maleki (2024-Pr): 3D Data Style Transfer
  6. Soroush Jahanzad (2023): Self-Supervised Domain Adaptation in Point Cloud Reconstruction
  7. Vida Ramezanian (2022-2024): Supervised Monocular Depth Estimation using Deep Neural Networks
  8. Kimia Dinashi (2021-Pr):
  9. Nima Jamali (2021-2022): Defense Against 3D Adversarial Point Clouds Using Nearest-Neighbor Search
  10. Yeghaneh Gharehdaghi(2021-2022): Multi-Sensor Data Fusion with Deep Learning in Image Processing Applications
  11. Arian Etemadi (2021-2022): Defense Against Adversarial Attacks on Point Cloud by Diminishing High-Frequency Components
  12. Hassan Hamidi (2021-2022): Point Cloud Semantic Segmentation with Limited Supervision using Deep Neural Networks
  13. Parshan Teimouri (2021-2022): Multi-Sensor Data Fusion Effect on Scene Perception using Deep Learning
  14. Kimia Noorbakhsh (2021-2022): Robustness Improvement of 3D Deep Neural Networks Against Adversarial Attacks by Training with Denoised Data
  15. Emad Salehi (2021): Multi-Sensor Data Fusion by Depp Learning in 3D Object Detection
  16. Aryan Mikaeili (2021): Geometric Interpretability of 3D Deep Neural Networks
  17. Aryan Sadeghi (2020-2022): Multi-Sensor Data Fusion with Deep Learning
  18. Atrin Arya (2020-2021): Adversarial Attack and Defense on 3D Point Cloud
  19. Barbod Pajoum (2020-2021): 3D Point Cloud Segmentation using Generative Adversarial Network
  20. Mehran Hosseinzadeh (2020-2021): Adversarial Attack and Defense in Semantic Segmentation of RGB-D Images
  21. Maryam Moradi (2020-2021): Robustness of Deep Neural Networks to Adversarial Examples
  22. Alireza Zohri (2019-2020): Developing an Augmented Reality Software for Navigation Systems
  23. Sahar Zargarzadeh (2019-2020): Semantic Segmentation of 3D Point Cloud Using RGB-D Data
  24. Mobina Mahdavi (2019-2020): Supervised Semantic Segmentation of 3D Point Clouds
  25. Arash Feizy (2018-2019): Image Segmentation with RGB-D Data Using GANs
  26. Hamed Shirzad, Arezou Fatemi, and Erfan SeyedSalehi (2018-2019): RGB-D Video Generation using GANs
  27. Mehrdad Moghimi (2018): Virtual Advertisement Replacement in Soccer Fields
  28. Ahmad Amiri (2016-2018): SLAM-based 3D Object Recognition using RGB-D Camera
  29. Nafiseh Ashkar (2016-2018): Inserting Graphical Elements in Multiview Soccer Videos
  30. Reza Azad (2016-2017): 4D Hand Gesture Recognition on RGB-D Videos
  31. Hanieh Naderi (2016-2022): Adversarial Attacks on Deep Neural Networks
  32. Mohammad Reza Bagheri (2015-2016): Synchronization of Multiple Videos of a Scene with Drop Possibility
  33. Shirin Feiz (2015-2016): Virtual Advertisement Replacement in Multiview Soccer Video
  34. Hossein Rashidi (2014-2015): Visual Simultaneous Localization and Mapping Using an RGB-D Camera
  35. Mostafa Hadian (2014-2015): Calibration of PTZ Cameras from Multiview Soccer Match Videos
  36. Ali Zarean (2014-2015): Free-viewpoint Soccer Match Video from Overlapping Cameras
  37. Maryam Sepehrinour (2013-2018): 3D Reconstruction of Human Body from Single-View Videos
  38. Afshin Bozorgpour (2013-2014): Automatic Homography Extraction and Tracking in Soccer Scenes
  39. Zahra Montazeri (2013-2014): Visual Odometry using RGB-D Cameras
  40. Ali Arab (2013-2014): Camera Calibration Using Field Model for Soccer Match Videos
  41. Ali Osia (2013-2014): Human Body Pose Estimation Using 3D Point Cloud
  42. Sina Lotfian (2013-2014): Calculating Inter-Frame Homography Matrixes for PTZ Cameras in Soccer Matches
  43. Sadjad Fouladi (2013-2014): Real-time Graphical Elements Addition to Live and Instant Replays of Broadcast Soccer Videos
  44. Mahsa Mohammadi Kaji (2013-2014): Visual Odometry using RGB-D Cameras
  45. Bentolhoda Hadavi Moghadam (2012-2018): Porosity Estimation in Electrospun Nanofibers using 3D Image Analysis
  46. Reza Afrouzian (2010-2015): Multiview Reconstruction in Dynamic Sports Scenes
  47. Sadegh Ramezanpour (2012-2013): 3D Human Pose Estimation using Multiview Videos
  48. Mansoureh Karami (2012-2013): 3D Reconstruction of Soccer Player using Multiview Videos
  49. Amir Mazaheri and Shima Salimi (2012-2013): Model-based Human Pose Estimation from Multiview Videos
  50. Sadjad Fouladi (2012): Color Correction in Mosaiced Images of Soccer Matches
  51. Mahdis Mahdieh and Narges Norouzi (2012): Dress Mapping on Query Body from Four Points of View Using 3D Computer Vision
  52. Zohreh Moteshaker Arani (2011-2012): 3D Reconstruction of Soccer Players from an Arbitrary Closeup Viewpoint Using Multiview Videos
  53. Elham Jabalbarezi (2011-2012): 3D Modeling of Soccer Players from an Arbitrary Viewpoint Using Multiview Images
  54. Mohsen Taghaddosi (2011-2012): 3D Mosaicing Using Multiview Videos
  55. Arsalan Dejkam (2010-2011): 3D Reconstruction of Deformable Surfaces
  56. Mehran Fotouhi (2009-2019): Homography Matrix Extraction for 3D Positioning of Soccer Players
  1. Mohammad Agahian Panahi (2009-2010): Error Resilient Coding of H.264 for Wireless Networks
  2. Ali Araghi (2009-2010): Error Concealment of H.264/AVC for Wireless Networks
  3. Ghazaleh Panahandeh (2007-2008): Video Error Concealment
  4. Hossein Fattahian Peiro (2007-2008): Error Resilient Video Compression Using H.264/AVC
  5. Amir Hossein Firouzmanesh (2007-2008): Using H.264 Scalable Video Compression for Distance Learning
  6. Mani Ranjbar (2006-2007): Spatial Error Concealment in H.264/AVC
  7. Amin PourRostami (2005-2006): A New Context-Based Lossless Grayscale Image Compression Method
  8. Tayebeh Lotfi (2004-2008): Active Object Tracking in Content-Based Video Coding for Distance Learning using H.264/AVC
  9. Alireza Tavakoli (2002-2003): Object-Based Video Compression
  10. Golamreza Amayeh (2002-2003): Trademark Database Retrieval
  11. Nader Safavian (2002-2003): Content-Based Image Retrieval using Texture & Color Features
  12. Simin Bokharaie (2002-2003): Video Compression based on Object Recognition
  13. Leila Esmaeilani (2002-2003): Video Compression using Wavelet Transform
  14. Hadi Gerailu (2001-2002): Shot Change Detection in Image Sequences
  15. Mehdi Jafari Shahbazzadeh (2001-2005): Object-Based Adaptive Streaming of Layered-Encoded Video over the Internet
  1. Mohammad Namdar (2024): Motion Capture from Video
  2. Pooya Esmail Akhondi (2023): Multi-Object Tracking by Person Re-Identification
  3. Navid Eslami (2022): Optical Flow by Deep Learning
  4. Hanieh Ehsani (2022): Optical Flow Approximation by Deep Neural Networks
  5. Amir Mohammad Mansourian (2022-Pr): Deep Multi-Object Tracking by Part-Based Re-Identification in Soccer Matches
  6. S. Mojtaba Marvasti-Zadeh (2015-2019): Robust Target Tracking using Deep Neural Networks
  7. Reza Fahmi (2015-2016): 3D Soccer Ball Tracking with Fixed and PTZ Cameras
  8. Elaheh Vahdani (2013-2014): Ball Detection in Soccer Match Videos
  9. Fatemeh Elyasi (2013-2014): Detection and Tracking of Moving Objects using Multiview Cameras
  10. Nima Najafzadeh (2013-2014): Multi-Target 3D Tracking
  11. Maryam Mohammadi (2012-2013): An Improved GM-PHD Filter for Multiple Target Tracking
  12. Amin Reza Gholami (2011-2012): Multiview Localization and Tracking of Soccer Players and Ball
  13. Hamed Jamalifar (2010-2011): Reference-Free Deformable Surface 3D Tracking
  14. Gholamreza Rahimi (2009-2010): Background Modeling for Tracking Moving Objects
  15. Elham ShabaniNia (2008-2009): Moving Vehicle Tracking Using Multi-Uncalibrated Cameras
  16. Rasoul Mohammadi Nasiri (2007-2008): Object Motion Parameter Estimation in 3D Spaces
  17. Amir Hossein Khalili (2006-2007): Object Tracking across Uncalibrated Camera Networks
  18. Bardia Mohabbati (2004-2005): Object Tracking in Image Sequences
  19. Halimeh Darabi (2001-2002): Motion Tracking with Application to Virtual Studios
  20. Homayoun Mahdavi Nasab (2001-2005): Motion Estimation for Very Low Bitrate Video Compression
  21. Hossein Rabbani (2000-2001): Motion Estimation using Complex Wavelet Transform
  1. Farzad Beizaee (2018-2019): Human Action Recognition from RGB-D Videos using Deep Networks
  2. Safa Ahmadian (2016-2017): Human Action Recognition using Skeleton Data
  3. Ahmad Khatami Nejhad (2015-2016): 4D Human Action Recognition Using a Fixed RGB-D Camera
  4. Maryam Asadi (2012-2019): A Robust and Compressed Descriptor for Action Recognition from 4D Data
  5. Sara Ershadi Nasab (2010-2016): 3D Reconstruction of Human Pose in Multiview Dynamic Scenes
  6. Mehran Khodabandeh(2012): Analyzing Feature Extraction Methods for Gender Detection from Face Images
  7. Vahid Ghadakchi (2011-2012): Human Action Recognition Using 3D Analysis
  8. Reza Moradi (2011-2012): Human Action Recognition Using Expandable Graphical Models
  9. Mohammad Amin Sadeghi (2009-2010): Real-Time Multiview Face Detection
  10. Amir Ghodrati (2008-2009): Human Action Categorization Using Spatiotemporal Features
  11. Hadis Mohseni (2007-2013): Face Recognition in Subspaces based on Nonlinear Dimension Reduction
  12. Ahmad Ali Abin (2007-2008): Multiface Detection and Tracking
  13. Masoud Mazloom (2004-2005): An Efficient Method for Face Recognition
  14. Bardia Mohabbati (2004-2005): Face Tracking in Image Sequences
  15. Ali Mahmoudi (2002-2003): An Efficient Fingerprint Authentication Method
  16. Ali Azarian (2000-2001): Fingerprint Classification
  17. Behnam Attaran Rezaei (2000-2001): Fingerprint Ridge Extraction & Thinning
  18. Mohammad Reza Rahimi (2000-2001): Fingerprint High-Level Classification
  19. Amir Mohammad Tahmasebi (2000-2001): Enhancement & Foreground/Background Segmentation of Fingerprint Images
  20. Ehsan Pakbaznia (2000-2001): Fingerprint High Level Classification
  1. S. Mohammad Yousef Najafi (2024-2025): Improving Weakly Supervised Semantic Segmentation Models Using Multimodal Models
  2. Amir Reza Hosseinymehr (2024-2025): Defense Against Image Query-based Adversarial Attacks
  3. Amir Reza Azari (2024-2025): Efficient Image Super-Resolution using Deep Learning
  4. Amir Ali Miri (2024-2025): Domain Adaptation Using Diffusion Models
  5. Amir Mohammad Babaei (2024-2025): Blind Image Super-Resolution Using Deep Generative Neural Network Architectures
  6. Mohammad Reza Abbasniya (2024-2025): An Efficient Virtual Try-on Method using Generative Architectures
  7. Ainaz Rafiei (2023-2024): Character and Text Recognition in Images
  8. Mahdi Lotfian (2024): Knowledge Distillation in Computer Vision Models for Semantic Segmentation
  9. Reza VahidiMajd (2024): Knowledge Distillation in Computer Vision Models for Semantic Segmentation
  10. Sara Zahedi (2023-2024): FashionFlow: Intelligent Outfit Recommendation
  11. Arya Jalali (2023): Knowledge Distillation in Semantic Segmentation
  12. Sina Elahimanesh and MohammadAli Mohammadkhani (2023): Persian Twitter Analysis: How much are people similar to their virtual character?
  13. Sepehr Amini Afshar (2023): Extracting Class-Specific Attention Maps for Weakly Supervised Semantic Segmentation Using Vision Transformers
  14. Alireza Honarvar (2023): Knowledge Distillation for Real-Time Semantic Segmentation
  15. Rozhan Ahmadi (2022-2023): Weakly Supervised Semantic Segmentation Using Deep Neural Networks
  16. Narges Javid (2022-2023): Weakly Supervised Semantic Segmentation
  17. Masoud Ghafouri (2022-2024): An Efficient Network for Real-Time Semantic Segmentation
  18. Hamed AliMohammadZadeh (2021-2022): Multi-Modal Image Detection by Improving Neural Network Learning
  19. Zeinab Sadat Saghi (2021-2022): Image Classification by Neural Networks under Domain Change
  20. Arash Chaichi (2021-2022): Trainable Loss Weights for Image Super-Resolution
  21. Mahdi Ghayour (2021-2022): Content-based Image Retrieval of Clothing Items with Neural Networks
  22. Fatemeh Hadizadeh (2021): Unpaired Image-to-Image Translation
  23. Mahdi Ghorbani (2020-2021): Adversarial Knowledge Distillation for Image Classification and Semantic Segmentation
  24. Ghazal Ebrahimi (2020-2021): Adversarially Robust Self-Distillation
  25. Leili Goli (2019-2020): Unrestricted Adversarial Attack and Defense on Deep Convolutional Neural Networks based on Geometric Transforms
  26. Zahra Ghelichkhan (2019-2021): Semantic Segmentation Considering Correlation with RGB-D Data using CNNs
  27. Mohamad Mehabadi Mohamadi (2019-2021): Improving Robustness of Deep Neural Networks against Adversarial Examples in Images
  28. Arash Aghababazadeh (2019-2021): Self-Supervised Disentangled Image Representation Learning
  29. Masoud Khairi (2019-2021): Weakly Supervised Semantic Segmentation using Deep Neural Networks
  30. Farzad Beizaee (2018-2019): Human Action Recognition from RGB-D Videos using Deep Learning Networks
  31. Soraya Safarian (2018-2019): Semantic Segmentation of 3D Point Clouds for Indoor Scene Understanding using Deep Convolutional Neural Networks
  32. Nader Karimi (2018-2019): Semantic Segmentation on Fusion of RGB and Depth Channels of Images using Convolutional Neural Networks
  33. Soheil Daliran (2017-2018): Quality Improvement of Anticipated Future Videos by Unsupervised Deep Learning
  34. Hooman Hashemi (2016-2017): Inference of Support Relations on RGB-D Images for Semantic Segmentation
  35. Ainaz Hajimoradi (2016-2017): Feature Extraction from RGB-D Images for Semantic Segmentation
  36. Hassan Hafez Kolahi (2013-2022): Noisy-Channel Model for Feature Extraction
  37. Alireza Samadian (2016): Player Super-resolution in Soccer Videos
  38. Maryam Mohammadi (2015-2016): Link Prediction in Bipartite Networks
  39. Yaser Souri (2014-2015): Fine-Grained Image Classification
  40. Fahimeh Fooladgar (2013-2018): Supervised Semantic Segmentation of RGB-D Images
  41. Mitra Behzadi (2013-2014): A New Image Registration Method in Elastix Toolbox
  42. Hossein Forghani (2013-2014): Vision-Based 3D Object Recognition
  43. Kamyar Allahverdi (2012-2013): Using Computer Vision Methods to Improve Presentation Facilities
  44. Ali Yadollahi (2012): Image Retrieval from Database based on an Arbitrary Query
  45. Raziyeh Salarifard (2012): Robust Features Extraction for Content-based Video Classification
  46. Jamshid Esmaeilnezhad (2011): A General Graph-Embedding-Based Framework for Dimension Reduction
  47. Mostafa Tavassolipour (2010-2011): Extraction of Important Events in Football Videos Using Video Summarization Techniques
  48. Mahmoud Karimian (2010-2011): Video Categorization Using Semi-supervised Learning
  49. S. Mehdi Shariatzadeh (2009-2010): Exemplar-Based Video Completion
  50. Reyhaneh Hosseini (2008-2009): Logo Detection and Removal from Videos
  51. Mohammad Moghimi (2008-2010): Multiclass Visual Object Recognition based on Cluttered Images
  52. Mehran Fotouhi (2007-2008): Body Skin Detection in Color Images
  53. S.Monireh Pedram (2006-2007): Image Representation Using Tensor Voting
  54. Mojtaba Bagheri (2006-2007): Multiresolution Video Mosaicing
  55. Elyas Khameneh (2005-2006): Multiresolution Image Mosaicing
  56. Ali Reza Ghane (2005-2006): Color Histogram-Based Image Retrieval from Databases under MPEG7 Standard
  57. Arash Abadpour (2004-2005): Color Image Processing using Principle Component Analysis
  58. Mohsen Ghoudarzi (2004-2005): Structural Analysis and Character Recognition for Iranian License Plate Recognition
  59. Majid Lesani (2004-2005): A New Method for Iranian License Plate Localization
  60. Arash Tavakkol (2004-2005): Watermarking of Fingerprint Images
  61. Javad Behrouzi Moghaddam (2003-2004): Wavelet-based Digital Image Watermarking
  62. Mona Ghassemzadeh (2002-2003): Content-Based Image Retrieval using Color & Texture Features
  63. Saeed Milady (2001-2002): Detection & Removal of Line Scratches in Image Sequences
  64. Abulfazl Lakdashti (2001-2002): Design & Implementation of a Search Engine of Image Databases on the Internet
  65. Mohsen Abbas PourSeyyedi (2001-2002): Restoration/Resolution Enhancement of Noisy and Blurred Image Sequences using GCV
  66. Shirin Karimifar (2001-2002): Content-Based Image Retrieval using Shape Features
  67. Elham Shahinfard (2000-2001): Digital Image Watermarking
  68. Mojtaba Ghaderi (2000-2001): Image Sequence Restoration applied on IRIB Archive Resources
  1. Farzad Samie (2007-2008): Radiometric Correction and Normalization of Satellite Images
  2. S. Mohammad Mehdi Ghotbi (2007-2008): Investigating Different Multispectral Image Registration Methods
  3. S. Mohsen Amiri (2005-2006): Texture Change Detection in Multispectral Images
  4. Rouhollah Dianat (2004-2010): Change Detection using Texture Analysis in Hyperspectral Images
  5. Shirin Mahmoodi (2004-2008): Change Detection using Texture Analysis
  6. Zeinab Shariatmadari (2004-2005): Change Detection using Hyperspectral Images
  1. Abolfazl Eshagh (2023-Pr): Teeth Point Cloud Generation after Orthodontic Treatment
  2. Parsa Sharifi (2023-Pr): Contrastive Learning from Medical Image and Text
  3. Mehrab Moradzadeh (2023-Pr): Creating Immunohistochemical Images from Hematoxylin-eosin Images in Pathology using Deep Learning
  4. Alireza Taherian (2023-Pr): Contrastive Learning from Medical Image and Text
  5. Ali Karimi (2023-Pr): Gait Recognition Using Deep Neural Networks
  6. Mahsa Amani (2022): Brain Tumor Segmentation using Deep Neural Networks
  7. Nasim Dadashi (2010-2015): Adaptive Registration of Endoscopic Videos to MDCT Images for Error Reduction in ENT Navigation Systems
  8. Amir Hossein Abdi (2012-2013): Diagnosis of Jaw Lesions in Dental Radiographs
  9. Ali Foroughipour (2012-2013): 3D Reconstruction of Brain from MR Images
  10. Morteza Safaei Pour (2012-2013): Reducing Registration Error between CT and Ultrasound Images
  11. Mahsa Mohammadi Kaji (2012): Glioma Diagnosis and Follow up Using MR Images
  12. Kimia Tajik (2012): 3D Reconstruction of Sinuous Using Endoscopy Images
  13. Arsalan Mohsennia (2012): Reconstruction of Body Tissue Structures from Biomedical Videos using ASKC
  14. Hakimeh Amiri (2011-2012): Intraoperative Registration of Non-rigid Tissue for Image-Guided Surgery
  15. Mahdi Abbaspour Tehrani and Mohammad Naghibi (2011-2012): Detection of Left Ventricular Boundaries in MR Images
  16. Hadis Mohseni (2006-2007): Automatic Localization of Cephalometric Landmarks
  17. Maryam Hasanzadeh (2004-2008): Multispectral Fuzzy Image Segmentation
Copyright 2016 IPL - All Rights Reserved
Developed by: Mohammad Reza Bagheri