1. Network Structure

• StyleGan系列：

1. A Style-Based Generator Architecture for Generative Adversarial Networks
   • NVlabs/stylegan: StyleGAN - Official TensorFlow Implementation (github.com)
2. Analyzing and Improving the Image Quality of StyleGAN
   • NVlabs/stylegan2: StyleGAN2 - Official TensorFlow Implementation (github.com)

2. Avatar

2.1. Face

• A Morphable Model For The Synthesis Of 3D Faces

  • https://github.com/MichaelMure/3DMM

• FLAME: Learning a model of facial shape and expression from 4D scans

  • FLAME (mpg.de)

3. 3D Generation

To be done

MVDream: Multi-view Diffusion for 3D Generation https://mv-dream.github.io/

Instant3D: Fast Text-to-3D with Sparse-view Generation and Large Reconstruction Model https://instant-3d.github.io “High quality, diverse and Janus-free Text-to-3D in 20 seconds.”

LRM: Large Reconstruction Model for Single Image to 3D https://scalei3d.github.io/LRM/

DMV3D: Denoising Multi-view Diffusion Using 3D Large Reconstruction Model https://dmv3d.github.io

PF-LRM: Pose-Free Large Reconstruction Model for Joint Pose and Shape Prediction https://pf-lrm.github.io/project

justimyhxu/awesome-3D-generation: A curated list of awesome 3d generation papers (github.com)