YoVDO

Efficient Geometry-Aware 3D Generative Adversarial Networks - GAN Paper Explained

Offered By: Aleksa Gordić - The AI Epiphany via YouTube

Tags

Generative Adversarial Networks (GAN) Courses Super-Resolution Courses

Course Description

Overview

Dive into a comprehensive video explanation of the "Efficient Geometry-aware 3D Generative Adversarial Networks" paper, exploring a novel explicit-implicit 3D scene representation network and its framework for state-of-the-art 3D GANs. Learn about NeRF, tri-plane 3D scene representation, efficient 3D GANs pipeline, dual discrimination, and super-resolution techniques. Examine the results, ethical considerations, and robustness of intrinsics and extrinsics in this cutting-edge approach to 3D generative models.

Syllabus

Intro
Tri-plane 3D scene representation intro
NeRF in depth
Explicit voxel grid methods
Tri-plane 3D scene representation explained
Tri-plane is as expressive
Efficient 3D GANs pipeline
Pose correlated facial features
Dual discrimination, super-resolution
Results
Ethical considerations, are we going to change anything?
Intrinsics, extrinsics robustness?
Outro


Taught by

Aleksa Gordić - The AI Epiphany

Related Courses

Build Basic Generative Adversarial Networks (GANs)
DeepLearning.AI via Coursera
Build Better Generative Adversarial Networks (GANs)
DeepLearning.AI via Coursera
Apply Generative Adversarial Networks (GANs)
DeepLearning.AI via Coursera
Generative Adversarial Networks (GANs)
DeepLearning.AI via Coursera
TensorFlow: Advanced Techniques
DeepLearning.AI via Coursera