Recent News
[02/2024]: 1 paper at CVPR 2024
[10/2023]: 1 US patent granted (link)
[07/2023]: 1 paper at ICCV 2023
[06/2023]: 1 paper at MICCAI 2023
[02/2023]: 1 paper at CVPR 2023
[07/2022]: 1 paper at ECCV 2022
[07/2021]: 1 paper at ICCV 2021
[10/2019]: 1 paper at Information Fusion
[07/2019]: 1 paper at Pattern Recognition
[03/2019]: 1 paper at CVPR 2019
[05/2019]: 1 paper at ICIP 2019
[08/2018]: 1 paper at Pattern Recognition
[04/2018]: 3 papers at ICPR 2018
Education
| | | | | | University of Edinburgh, UK
PhD at School of Informatics
May 2023 - Present
|
| | | | | | Jadavpur University, India
B.E. in Electrical Engineering
July 2016 - May 2020
|
Research Experiences
| | | | | | MBZUAI, Abu Dhabi
Research Assistant.
Nov 2020 - Apr 2023
|
| | | | | | University of Manitoba, Winnipeg, Canada
MITACS Internship, 2019.
May 2019 - August 2019
|
| | | | | | Robert Bosch, Bangalore
Computer Vision Lab
June 2018 - July 2018 |
| | | | | | IIT Roorkee, India
Under Prof. Partha Pratim Roy
June 2017 - May 2020
|
I'm a 1st year PhD student in the School of Informatics at the University of Edinburgh. I work with Dr. Hakan Bilen in the Visual Computing Group (VICO).
My secondary supervisor is Dr. Changjian Li from GraphVix lab. Previously, I was a full-time research assistant at MBZUAI, Abu Dhabi, where I worked on computer vision and machine learning with Dr Fahad Shahbaz Khan, Dr Salman Khan and Dr Hisham Cholakkal. During my undergrad, I have worked with Dr Yang Wang at the University of Manitoba, Canada and Dr Partha Roy at IIT Roorkee, India. I did my bachalors from Jadavpur University, Kolkata in Electrical Engineering.
- Publications
- Research
- Contact
-
|
Looking 3D: Anomaly Detection with 2D-3D Alignment
- [paper] / [dataset] / [code] (all coming soon!)
Ankan Bhunia, Changjian Li, Hakan Bilen,
CVPR, 2024
|
|
Generative Multiplane Neural Radiance for 3D-Aware Image Generation
- [paper] / [code]
Amandeep Kumar,
Ankan Bhunia, Sanath Narayan, Hisham Cholakkal,
Rao Anwer,
Salman Khan, Ming-Hsuan Yang,
Fahad Khan,
ICCV, 2023
|
Person Image Synthesis via Denoising Diffusion Model
- [paper] / [code] / [demo] / [webpage]
Ankan Bhunia,
Salman Khan,
Hisham Cholakkal,
Rao Anwer,
Jorma Laaksonen,
Mubarak Shah,
Fahad Khan,
CVPR, 2023
|
|
DoodleFormer: Creative Sketch Drawing with Transformers
- [paper] / [code] / [webpage]
Ankan Bhunia,
Salman Khan,
Hisham Cholakkal,
Rao Anwer,
Fahad Khan,
Jorma Laaksonen,
Michael Felsberg,
ECCV, 2022
|
|
Handwriting Transformers
- [paper] / [code] / [demo] / [webpage]
Ankan Bhunia,
Salman Khan,
Hisham Cholakkal,
Rao Anwer,
Fahad Khan,
Mubarak Shah,
ICCV, 2021
|
|
Handwriting Recognition in Low-resource Scripts using Adversarial Learning
- [paper]
Ayan Kumar Bhunia,
Abhirup Das,
Ankan Bhunia,
Sairaj Kishore,
Partha Pratim Roy,
CVPR, 2019
|
|
Improving Document Binarization via Adversarial Noise-Texture Augmentation
- [paper]
Ankan Bhunia,
Ayan Kumar Bhunia,
Aneeshan Sain,
Partha Pratim Roy,
ICIP, 2019
|
|
A Deep One-Shot Network for Query-based Logo Retrieval
- [paper]
Ayan Kumar Bhunia,
Ankan Bhunia,
Shuvozit Ghose,
Partha Pratim Roy,
Umapada Pal,
Pattern Recognition, 2019
|
|
Script identification in natural scene image and video frames using an attention based Convolutional-LSTM network
- [paper]
Ankan Bhunia,
Aishik Konwer,
Abir Bhowmik,
Ayan Kumar Bhunia,
Partha Pratim Roy,
Pattern Recognition, 2019
|
|
Signature Verification Approach using Fusion of Hybrid Texture Features
- [paper]
Ankan Bhunia,
Alireza Alaei,
Partha Pratim Roy,
Neural computing and Applications, 2019
|
|
Word Level Font-to-Font Image Translation using Convolutional Recurrent Generative Adversarial Networks
- [paper]
Ankan Bhunia,
Ayan Kumar Bhunia,
Prithaj Banerjee,
Aishik Konwer,
Abir Bhowmik,
Partha Pratim Roy,
Umapada Pal,
ICPR, 2018
|
|
Staff line Removal using Generative Adversarial Networks
- [paper]
Aishik Konwer,
Ayan Kumar Bhunia,
Abir Bhowmik,
Ankan Bhunia,
Prithaj Banerjee,
Partha Pratim Roy,
Umapada Pal,
ICPR, 2018
|
|
Handwriting Trajectory Recovery using End-to-End Deep Encoder-Decoder Network
- [paper]
Ayan Kumar Bhunia,
Abir Bhowmik,
Ankan Bhunia,
Aishik Konwer,
Prithaj Banerjee,
Partha Pratim Roy,
Umapada Pal,
ICPR, 2018
|
|
Title: Person Image Synthesis via Denoising Diffusion Model (CVPR'23) [ Paper / GitHub / Project / Demo]
The Pose-guided person image synthesis task aims to render a person’s image with a desired pose and appearance. Specifically, the appearance is defined by a given source image and the pose by a set of keypoints. Having control over the synthesized person images in terms of pose and style is an important requisite for applications such as e-commerce, virtual reality, metaverse and content generation for the entertainment industry. Read our paper here.
Title: Generative Multiplane Neural Radiance for 3D-Aware Image Generation (ICCV'23) [ Paper / GitHub]
We introduced an approach, named GMNR, that focuses at efficiently generating 3D-aware high-resolution images that are view-consistent across multiple camera pose. Qualitative and quantitative experiments on three datasets
demonstrate the merits of our contributions, leading to favorable performance in terms of image generation quality
and computational efficiency, compared to existing works.
Title: Handwriting Transformers (ICCV'21) [ Paper / GitHub / Demo]
Automatic handwritten text generation can be beneficial for people having disabilities or injuries that prevent them from writing, adapting an author's writing style or gathering additional data for training deep learning-based handwritten text recognition models. Here, we investigate the problem of realistic handwritten text generation of text sequences with arbitrary length and diverse calligraphic attributes representing writing styles of a writer. For more visit our project page here.
Title: Doodleformer: Creative sketch drawing with transformers (ECCV'22) [ Paper / GitHub]
Humans have an outstanding ability to easily communicate and express abstract ideas
and emotions through sketch drawings. Creative sketching or doodling is an expressive activity, where imaginative and previously unseen depictions of everyday visual objects are drawn. Creative sketch image generation is a challenging vision problem, where the task is to generate diverse, yet realistic creative sketches possessing the unseen composition of the visual-world objects. Please visit our project page here.
❮
❯
-
The Bayes Centre, Edinburgh EH8 9BT
Email: ankankumarbhunia@gmail.com /
a.k.bhunia@sms.ed.ac.uk
Phone: +44-7770723790
Whatsapp: +91-9038858890
|
|