PixelSynth: Generating a 3D-Consistent Experience from a Single Image
Abstract
Recent advancements in differentiable rendering and 3D reasoning have driven exciting results in novel view synthesis from a single image. Despite realistic results, methods are limited to relatively small view change. In order to synthesize immersive scenes, models must also be able to extrapolate. We present an approach that fuses 3D reasoning with autoregressive modeling to outpaint large view changes in a 3D-consistent manner, which enables scene synthesis. We demonstrate considerable improvement in single-image large-angle view synthesis results compared to a variety of methods and possible variants across simulated and real datasets. In addition, we show increased 3D consistency compared to alternative accumulation methods.
Cite
Text
Rockwell et al. "PixelSynth: Generating a 3D-Consistent Experience from a Single Image." International Conference on Computer Vision, 2021. doi:10.1109/ICCV48922.2021.01384Markdown
[Rockwell et al. "PixelSynth: Generating a 3D-Consistent Experience from a Single Image." International Conference on Computer Vision, 2021.](https://mlanthology.org/iccv/2021/rockwell2021iccv-pixelsynth/) doi:10.1109/ICCV48922.2021.01384BibTeX
@inproceedings{rockwell2021iccv-pixelsynth,
title = {{PixelSynth: Generating a 3D-Consistent Experience from a Single Image}},
author = {Rockwell, Chris and Fouhey, David F. and Johnson, Justin},
booktitle = {International Conference on Computer Vision},
year = {2021},
pages = {14104-14113},
doi = {10.1109/ICCV48922.2021.01384},
url = {https://mlanthology.org/iccv/2021/rockwell2021iccv-pixelsynth/}
}