NeRF and family

Recent research in Artificial Intelligence, Computer Vision and Computer Graphics has made it possible to render new views of a scene using a limited sequence of images and their associated camera poses.

Neural Radiance Fields (NeRF) provide implicit 3D representations of the scene created from sparse viewpoints of the scene and allowing downstream novel view synthesis.

In this masterclass, we will survey the state of the art in this area by reviewing the original NeRF implementation and explore the family of NeRF models that have improved it.

Addressed to:

Professionals in the industrial and ICT sectors who wish to learn more about Neural Radiance Fields (NeRF).

Programa

Introduction to the Generation of New Views and Representation of 3D Surfaces.
NeRF: Implicit Representation Model in 3D.
NeRF Extensions and Advanced Developments.

Masterclass taught by the i2Cat Foundation (CIDAI core partner)

Play video Download Presentation

Taught by:

Ivan Huerta

Deep Learning Research Lead – Distributed Artificial Intelligence Area (DAI) at the i2Cat Foundation

Ivan earned a degree in Computer Science in 2005 and a PhD in 2010 in Computer Vision and AI from the Autonomous University of Barcelona (UAB).

He is a multidisciplinary researcher in Computer Vision, Artificial Intelligence and Machine Learning. His interests include feature extraction, multi-sensor fusion, object detection, human interaction, deep learning, motion capture, 3D avatars, 2D and 3D tracking, soft biometrics, human analytics and virtual, augmented and mixed reality.