Coder Social home page Coder Social logo

Hi there πŸ‘‹

πŸ’¬ I completed Doctor of Philosphy (PhD) in 2022 (October), focussing on Computer Vision and Deep Learning, from SketchX Lab, Centre for Vision, Speech and Signal Processing (CVSSP) of the University of Surrey, England, United Kingdom (UK) under the supervision of Prof. Yi-Zhe Song (SonG) and Prof. Tao Xiang (Tony).

πŸ’¬ Currently, I am working as a Senior Research Scientist (Computer Vision) with Prof. Yiannis Andreopoulos at iSIZE , a London-based deep-tech company specializing in deep learning for video delivery. During my ongoing tenure with iSIZE, I have led the project on Video Denoising from ground up that introduces a low-cost neural-solution (BitClear) for compressed-video artifacts removal. πŸ”­News Update from iSIZEπŸ”­.

πŸ’¬ BitClear won NAB product of the Year (2022) under AI/ML category: πŸ”­LinkπŸ”­ NAB show is the largest show for media, entertainment and technology.

πŸ’¬ Before staring my PhD, I worked as a full-time research assistant for nearly 1.5 years at the Institute for Media Innovation (IMI) Lab of Nanyang Technological University, Singapore.

πŸ’¬ In 2017, I completed my B.Tech (Bachelor of Technology) from the Institute of Engineering & Management (IEM), Kolkata (India), under the West Bengal University of Technology, majoring in Electronics and Communication Engineering.

πŸ’¬ DBLP Profile: https://dblp.org/pid/171/5204.html

πŸ’¬ Google Scholar: https://tinyurl.com/yc3kxzem

πŸ’¬ Reviewer: CVPR'20-22; ICCV'21, ECCV'22, BMVC'19-21; ACCV'20, WACV'20-22, Siggraph'22, IEEE TIP, IEEE-TPAMI, IJCV.

⚑ Top Venue Publications: 17xCVPR 4xICCV 3xECCV, 1xSiggraph Asia. (13-first authored Top Venue Papers as of Feb 2023)

βœ‰ [email protected] βœ‰ [email protected] βœ‰ [email protected]

πŸ”­ For more details, please visit my homepage: https://ayankumarbhunia.github.io/ β˜‘

⚑⚑⚑ Recent ⚑⚑⚑
πŸ’¬β˜² One 𝐩𝐚𝐩𝐞𝐫 on Sketch-Based 3D Shape Retrieval got accepted in ICCV-2023.

πŸ’¬β˜² Our paper 'What Can Human Sketches Do for Object Detection?' (CVPR'23) has been selected among 12 award candidates, out of 9155 submissions and 2360 accepted papers in CVPR, 2023.

πŸ’¬β˜² Seven 𝐩𝐚𝐩𝐞𝐫𝐬 got accepted in CVPR-2023.

πŸ’¬β˜² Defended my PhD Thesis before Prof. Stella Yu and Prof. Adrian Hilton β€” with No Correction

Ayan Kumar Bhunia's Projects

splice icon splice

Official Pytorch Implementation for "Splicing ViT Features for Semantic Appearance Transfer" presenting "Splice" (CVPR 2022)

srflow icon srflow

Official SRFlow training code: Super-Resolution using Normalizing Flow in PyTorch

srgan-pytorch icon srgan-pytorch

A simple and complete implementation of super-resolution paper.

stylegan_xl icon stylegan_xl

[SIGGRAPH'22] StyleGAN-XL: Scaling StyleGAN to Large Diverse Datasets

swinir icon swinir

SwinIR: Image Restoration Using Swin Transformer

targetclip icon targetclip

[ECCV 2022] Official PyTorch implementation of the paper Image-Based CLIP-Guided Essence Transfer.

tecogan-pytorch icon tecogan-pytorch

A PyTorch Reimplementation of TecoGAN: Temporally Coherent GAN for Video Super-Resolution

tedigan icon tedigan

[CVPR 2021] Pytorch implementation for TediGAN: Text-Guided Diverse Face Image Generation and Manipulation

textured-3d-gan icon textured-3d-gan

Learning Generative Models of Textured 3D Meshes from Real-World Images, ICCV 2021

tfill icon tfill

CVPR2022:"Bridging Global Context Interactions for High-Fidelity Image Completion"

transgan icon transgan

[Preprint] "TransGAN: Two Transformers Can Make One Strong GAN", Yifan Jiang, Shiyu Chang, Zhangyang Wang

ttsr icon ttsr

[CVPR'20] TTSR: Learning Texture Transformer Network for Image Super-Resolution

ttvsr icon ttvsr

[CVPR'22 Oral] TTVSR: Learning Trajectory-Aware Transformer for Video Super-Resolution

uformer icon uformer

[CVPR 2022] Official repository for the paper "Uformer: A General U-Shaped Transformer for Image Restoration".

umr icon umr

Self-supervised Single-view 3D Reconstruction

vnext icon vnext

Next-generation Video instance recognition framework on top of Detectron2 which supports SeqFormer(ECCV Oral) and IDOL(ECCV Oral))

weakalign icon weakalign

End-to-end weakly-supervised semantic alignment

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    πŸ–– Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. πŸ“ŠπŸ“ˆπŸŽ‰

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❀️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.