Explore three groundbreaking papers on generative neural scene representations for 3D-aware image synthesis in this 26-minute talk by Andreas Geiger. Delve into GRAF (Generative Radiance Fields), GIRAFFE (Compositional Generative Neural Feature Fields), and CAMPARI (Camera-Aware Decomposed Generative Neural Radiance Fields). Learn about advanced techniques in generative models, scene representations, and composition. Gain insights into the latest developments in 3D-aware image synthesis, with access to accompanying slides and GitHub resources for further study.
Generative Neural Scene Representations for 3D-Aware Image Synthesis
Overview
Syllabus
Intro
Generative Models
Representations
Model
Giraffe
Scene Composition
Campari
Taught by
Andreas Geiger
Related Courses
-
Implicit Neural Representations: From Objects to 3D Scenes
-
Towards Unsupervised Learning of Generative Models for 3D Controllable Image Synthesis
-
Neural Radiance Fields for View Synthesis
-
Generative Models for Image Synthesis
-
Efficient Geometry-Aware 3D Generative Adversarial Networks - GAN Paper Explained
-
Constraining 3D Fields for Reconstruction and View Synthesis
