DeepMind Flamingo: A Visual Language Model for Few-Shot Learning

Variable Bitrate Neural Fields: Create Fast Approximations of 3D Scenes

Robotic Telekinesis in the Wild

Building Diverse Skillsets for Video Game Characters With Adversarial Skill Embeddings

Digging Into StyleGAN-NADA for CLIP-Guided Domain Adaptation

Human Dynamics From Monocular Video With Dynamic Camera Movements

Modern Evolution Strategies for Creativity

Extracting Triangular 3D Models, Materials, and Lighting From Images

Barbershop: Hair Transfer with GAN-Based Image Compositing Using Segmentation Masks

EditGAN: High-Precision Semantic Image Editing

Block-NeRF: Scalable Large Scene Neural View Synthesis

PoE-GAN: Generating Images from Multi-Modal Inputs

Omnimatte: How to Detect Objects and Their Effects

Generating Digital Painting Lighting Effects via RGB-space Geometry

NeRF – Representing Scenes as Neural Radiance Fields for View Synthesis

Image Generation Based on Abstract Concepts Using CLIP + BigGAN

One-Shot Free-View Neural Talking-Head Synthesis for Video Conferencing

Overview: Neural Scene Flow Fields (NSFF) for Space-Time View Synthesis of Dynamic Scenes

X-Fields: Implicit Neural View-, Light- and Time-Image Interpolation

Paper Summary: One Shot 3D Photography