Generative Neural Scene Representations for 3D-Aware Image Synthesis

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.

Intro
Generative Models
Representations
Model
Giraffe
Scene Composition
Campari