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

logo-detection icon logo-detection

One-shot logo detection on images. Implementation of the paper "A Deep One-Shot Network for Query-based LogoRetrieval" (Bhunia et al. 2019).

mat icon mat

MAT: Mask-Aware Transformer for Large Hole Image Inpainting

maxvit icon maxvit

PyTorch reimplementation of the paper "MaxViT: Multi-Axis Vision Transformer" [arXiv 2022].

meta-interpolation icon meta-interpolation

Source code for CVPR 2020 paper "Scene-Adaptive Video Frame Interpolation via Meta-Learning"

mitsuba3 icon mitsuba3

Mitsuba 3: A Retargetable Forward and Inverse Renderer

ml-gmpi icon ml-gmpi

Official PyTorch implementation of GMPI (ECCV 2022, Oral Presentation)

ml-neuman icon ml-neuman

Official repository of NeuMan: Neural Human Radiance Field from a Single Video (ECCV 2022)

monce icon monce

Modulated Contrast for Versatile Image Synthesis [CVPR 2022]

neurmips icon neurmips

Pytorch implementation of paper: "NeurMiPs: Neural Mixture of Planar Experts for View Synthesis"

nice_pytorch icon nice_pytorch

Nonlinear Independent Components Estimation (Dinh et al, 2014) in PyTorch.

noisetolerant-sbir icon noisetolerant-sbir

[CVPR 2022] "Sketching without Worrying: Noise-Tolerant Sketch-Based Image Retrieval”, IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), 2022.

o-cnn icon o-cnn

O-CNN: Octree-based Convolutional Neural Networks for 3D Shape Analysis

oisr-pytorch icon oisr-pytorch

PyTorch implementation of "ODE-inspired Network Design for Single Image Super-Resolution"(CVPR2019)

on-the-fly-fgsbir icon on-the-fly-fgsbir

[CVPR 2020, Oral] "Sketch Less for More: On-the-Fly Fine-Grained Sketch Based Image Retrieval”, IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), 2020. .

paddlegan icon paddlegan

PaddlePaddle GAN library, including lots of interesting applications like First-Order motion transfer, Wav2Lip, picture repair, image editing, photo2cartoon, image style transfer, GPEN, and so on.

partglot icon partglot

Official Implementation of PartGlot (CVPR 2022 Oral)

pix2pix_colorization icon pix2pix_colorization

This is a small project on image colorzation. I did this while I started learning about Deep Learning back in 2018.

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.