StyleMesh: Style Transfer for Indoor 3D Scene Reconstructions

CVPR 2022

1Technical University of Munich, 2University of Michigan
StyleMesh Teaser

StyleMesh optimizes a stylized texture for an indoor scene reconstruction.

Abstract

We apply style transfer on mesh reconstructions of indoor scenes. This enables VR applications like experiencing 3D environments painted in the style of a favorite artist. Style transfer typically operates on 2D images, making stylization of a mesh challenging. When optimized over a variety of poses, stylization patterns become stretched out and inconsistent in size. On the other hand, model-based 3D style transfer methods exist that allow stylization from a sparse set of images, but they require a network at inference time. To this end, we optimize an explicit texture for the reconstructed mesh of a scene and stylize it jointly from all available input images. Our depth- and angle-aware optimization leverages surface normal and depth data of the underlying mesh to create a uniform and consistent stylization for the whole scene. Our experiments show that our method creates sharp and detailed results for the complete scene without view-dependent artifacts. Through extensive ablation studies, we show that the proposed 3D awareness enables style transfer to be applied to the 3D domain of a mesh. Our method can be used to render a stylized mesh in real-time with traditional rendering pipelines.

Video

Interactive 3D Mesh Viewer - Use Your Mouse to Navigate the Scene

BibTeX

@inproceedings{hollein2022stylemesh,
  title={StyleMesh: Style Transfer for Indoor 3D Scene Reconstructions},
  author={H{\"o}llein, Lukas and Johnson, Justin and Nie{\ss}ner, Matthias},
  booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  pages={6198--6208},
  year={2022}
}