Recursive 3D stylization using radiance fields

Home

Discover

Bookmarks

Keep Up With Latest Trending Papers. Computer Science, AI and Machine Learning and more.Subscribe

CC BY

Source arXiv

Computer Vision

Recursive 3D stylization using radiance fields

ARF: Artistic Radiance Fields

We present a method for transferring the artistic features of an arbitrary style image to a 3d scene.

Our extensive evaluation demonstrates that our method outperforms baselines by generating artistic appearance that more closely resembles the style image.

We present a method for transferring the artistic features of an arbitrary style image to a 3d scene.

Previous methods that perform 3d stylization on point clouds or meshes are sensitive to geometric reconstruction errors for complex real-world scenes.

Instead, we propose to stylize the more robustradiance field representation.

We find that the commonly used gram matrix-based loss tends to produce blurry results without faithful brushstrokes, and introduce a nearest neighbor-based loss that is highly effective at capturing style details while maintaining multi-view consistency.

We also propose a novel deferred back-propagation method to enable optimization of memory-intensive radiance fields using style losses defined on full-resolution rendered images.

We present a method for transferring the artistic features of an arbitrary style image to a 3d scene.

Previous methods that perform 3d stylization on point clouds or meshes are sensitive to geometric reconstruction errors for complex real-world scenes.

Instead, we propose to stylize the more robustradiance field representation.

Authors

Kai Zhang, Nick Kolkin, Sai Bi, Fujun Luan, Zexiang Xu, Eli Shechtman, Noah Snavely

Related Topics

Radiance field representation

Deferred back-propagation method

Read the Paper

Read Paper