Computer Vision Research | Applied ML
Hello! I'm Manu Gond from Kolkata, India 🇮🇳. I'm currently a part of EU Project Horizon's Marie Sklodowska-Curie network. Enrolled at Mid Sweden University, Sweden 🇸🇪 & Technical University of Berlin, Germany 🇩🇪 as a dual degree PhD Student. My area of research is mainly focused on novel view synthesis methods.
If you want to contact me, do it with email or twitter. I'm not much active on LinkedIn
You will find me playing CS:GO, scrolling twitter or shitposting random photos on instagram when I am free.
EmailQoMEX 2024
Light field is a promising technology that enables the capture and reproduction of real light rays from the scene. There are still many challenges in transmitting and reproducing light field data. This paper proposes a spherical light field dataset that can be used as a foundation for developing telepresence applications. The Spherical Light Field Database (SLFDB) consists of a light field of 60 views captured with an omnidirectional camera in 20 scenes. To show the usefulness of the proposed database, we provide two use cases: compression and viewpoint estimation.
CVMP 2023
Considering the applications in real-time immersive telepresence, this paper investigates how a single omnidirectional image (ODI) can be used to extend 3DoF to 6DoF. To achieve this, we propose a fully learning-based method for spherical light field reconstruction from a single omnidirectional image.
Languages
Tools & Libraries
Jan 2022
to
Current
My main research work focuses on novel view synthesis methods in real time
The specialization of our research group is in the area of Representation of Light Fields, Compression, and Rendering
June 2024
to
July 2024
Worked at Logitech for 2 months as an research intern
Key areas of focus were novel view synthesis (NVS) and real-time rendering pipeline
Feb 2020
to
Sep 2020
Mainly worked as a ML research engineer in collaboration with researchers for the development and testing of hybrid recommendation system for business.
Database design, and deployment pipelines
Creation of backend APIs with Node.js
Creation of Graph Visualization library which reads Neo4j data. To be used by front end for displaying and traversing the interactive graph.
Hybrid Recommender System
Facial Keypoint Detection
Simultaneous Localization and Mapping (SLAM)
Automatic Image Captioning
Computer Graphics and Image Processing
DCGAN for Face Image Generation
Reinforcement Learning Agents
Basics of CUDA C++
GA (Genetic Algorithm) for optimization problem (TSP & Advt.)
Socket Programming
Lex-Yacc implementation to generate 3 address code
VLSI VHDL Programs to implement basic logical blocks
2017 - 2019
University of Calcutta
2014 - 2017
University of Calcutta
-
3 Bronze and 1 Silver in Competitve Programming on Hacckerrank Hackerrank Profile -
Intel® Edge AI Scholarship Program This scholarship program was hosted on Udacity and it covers optimization and deployment of computer vision models on Edge devices
-
FacebookAI PyTorch Scholarship Program This scholarship program was hosted on Udacity and it covered Deep Learning with help of PyTorch as key library for implementataion of MLPs, CNNs, RNNs and other modified versions of same ANN architecture for time series, image, text analysis.
-
Google India Android Scholarship - 2018 It covered android basics which are required to start with any android project with all implementations done with minimal use of other libraries. It covered lifecycle of activites, implementation of networking and storage services and use of libraries in projects. This is program gives solid foundation so that student can utilize android documentation to create their own applications.