Real-Time Radiance Fields for Single-Image Portrait View Synthesis
Abstract
We present a one-shot method to infer and render a photorealistic 3D representation from a single unposed image (e.g., face portrait) in real-time. Given a single RGB input, our image encoder directly predicts a canonical triplane representation of a neural radiance field for 3D-aware novel view synthesis via volume rendering. Our method is fast (24 fps) on consumer hardware, and produces higher quality results than strong GAN-inversion baselines that require test-time optimization. To train our triplane encoder pipeline, we use only synthetic data, showing how to distill the knowledge from a pretrained 3D GAN into a feedforward encoder. Technical contributions include a Vision Transformer-based triplane encoder, a camera data augmentation strategy, and a well-designed loss function for synthetic data training. We benchmark against the state-of-the-art methods, demonstrating significant improvements in robustness and image quality in challenging real-world settings. We showcase our results on portraits of faces (FFHQ) and cats (AFHQ), but our algorithm can also be applied in the future to other categories with a 3D-aware image generator.
Document Details
- Document Type
- Pub Defense Publication
- Publication Date
- Jul 26, 2023
- Source ID
- 10.1145/3592460
Entities
People
- Alex Trevithick
- Chao Liu
- Eric R. Chan
- Koki Nagano
- Manmohan Chandraker
- Matthew Chan
- Michael Stengel
- Ravi Ramamoorthi
- Sameh Khamis
- Zhiding Yu
Organizations
- Defense Advanced Research Projects Agency
- National Science Foundation
- Nvidia
- Office of Naval Research
- Stanford University
- University of California, San Diego