RGB-D Neural Radiance Fields: Local Sampling for Faster Training
Arnab Dey, Andrew I. Comport. RGB-D Neural Radiance Fields: Local Sampling for Faster Training
CV
Download CV
Detailed CV
Education
- PhD in Computer Science (Marie Curie fellowship) - 09/2020 - Present
I3S/CNRS Laboratory, University Cote d’Azur, Nice, France.
BiomechanicsCapture: Deep learning based biomechanics capture.- The aim of this project is to address the problem of acquiring the pose, shape, appearance, motion and dynamics of humans in 3D using multi-camera environment in real-time, which is fundamental to a wide range of applications including e-health, sport performance analysis, human-robot interaction, augmented reality and many more.
- Industry partner: Youdome, Monaco
- Academic partners: Brown University, United States
- MSc in Computer Science & Engineering - 09/2017 - 04/2020
Politecnico di Milano, Milan, Italy.- Specialized in Artificial Intelligence and Computer vision.
- Theoretical knowledge focused on AI, Machine learning, IoT, computer vision, and robotics.
- Practical projects like: ”Art with computer vision”, ”Dancing robot”, ”Robotics with ROS and Gazebo”, and ”smart led net- work”.
- B.Tech in Computer Science & Engineering - 08/2013 - 08/2017
West Bengal University of Technology, Kolkata, India- With practical experience in software engineering and Image processing.
Work experience
- Visiting Research Fellow - 10/2022 - Current
Brown University, Providence, RI, USA.- Canonical Human: Canonicalization of 3D human model using Tensor Field Networks
- Teaching Assistant - 05/2021 - 06/2021
University Cote d’Azur, Sophia Antipolis, France.- 3D Machine vision course for Master’s students.
- Machine Learning Engineer - 06/2020 - 09/2020
Next Industries, Milan, Italy.- Machine learning applications for wearable gesture & motion controllers.
- Data Scientist Intern - 09/2019 - 03/2020
Unicredit Services, Milan, Italy. - Design and implementation of end-to-end applications to automate manual processes.
- Implemented an OCR web service with pre and post-processing modules to improve OCR quality.
- Worked on object detection, document classification, and entity recognition/extraction-related projects.
Skills
- Python, C++ , C , C# , .NET , Java , JavaScript , Matlab , Octave , Node.js , React / React Native , SQL , MongoDB , ROS , Git , Docker
- PyTorch , Tensorflow , Keras , Matplotlib , Scikit-learn , OpenCV , Pandas , MLflow , AWS , Cloud Computing , NLTK , Spacy , Jupyter
- Computer Vision , Deep Learning , Machine Learning , Data Science
- Languages - English, Bengali, Hindi, Italian, French
Publications
Mip-NeRF RGB-D: Depth Assisted Fast Neural Radiance Fields
Dey, A. and Ahmine, Y. and Comport, A.I., Mip-NeRF RGB-D: Depth Assisted Fast Neural Radiance Fields, Journal of WSCG, Volume 30 pages 34-43. DOI:10.24132/JWSCG.2022.5.
PNeRF: Probabilistic Neural Scene Representations for Uncertain 3D Visual Mapping
PNeRF: Probabilistic Neural Scene Representations for Uncertain 3D Visual Mapping. Y Ahmine, A Dey, AI Comport - arXiv preprint arXiv:2209.11677, 2022
Thesis
- A. Dey, Human activity and emotion recognition from RGB videos using deep learning. Politecnico di Milano, a Deep learning-based approach to recognize human activities and emotions from real-time RGB videos for robotics applications, Implemented using PyTorch.
- A. Dey, Automated region selection in images based on visual saliency. West Bengal University of Technology, Achieved automated region selection without prior knowledge and user interaction, Implemented using MatLab.
Teaching
Awards
- Best Poster Award in Eurographics 2022 for RGB-D Neural Radiance Fields.
- Winner of E-Health Creathon by Innovation Center for Entrepreneurship of the University Cote d’Azur.