PixelSynth: Generating a 3D-Consistent Experience from a Single Image (ICCV 2021)

Chris Rockwell, David F. Fouhey, and Justin Johnson

[Project Website] [Paper] [Supplemental]

PixelSynth fuses the complementary strengths of 3D reasoning and autoregressive modeling to create an immersive 3D experience from a single image.

Installation and Demo

• Install
• Demo

Training and Evaluation

• RealEstate10K
• Matterport

Citation

If you use this code for your research, please consider citing:

@inProceedings{Rockwell2021,
  author = {Chris Rockwell and David F. Fouhey and Justin Johnson},
  title = {PixelSynth: Generating a 3D-Consistent Experience from a Single Image},
  booktitle = {ICCV},
  year = 2021
}

Special Thanks

Thanks to Angel Chang and Angela Dai, and Richard Tucker and Noah Snavely, for allowing us to share frames from their datasets. Thanks to Olivia Wiles and Ajay Jain for polished model repositories which were so helpful in this work.