Ref-NPR: Reference-Based Non-Photorealistic Radiance Fields

12/06/2022
by   Yuechen Zhang, et al.
0

Existing 3D scene stylization methods employ an arbitrary style reference to transfer textures and colors as styles without establishing meaningful semantic correspondences. We present Reference-Based Non-Photorealistic Radiance Fields, i.e., Ref-NPR. It is a controllable scene stylization method utilizing radiance fields to stylize a 3D scene, with a single stylized 2D view taken as reference. To achieve decent results, we propose a ray registration process based on the stylized reference view to obtain pseudo-ray supervision in novel views, and exploit the semantic correspondence in content images to fill occluded regions with perceptually similar styles. Combining these operations, Ref-NPR generates non-photorealistic and continuous novel view sequences with a single reference while obtaining reasonable stylization in occluded regions. Experiments show that Ref-NPR significantly outperforms other scene and video stylization methods in terms of both visual quality and semantic correspondence. Code and data will be made publicly available.

READ FULL TEXT

page 1

page 6

page 8

page 9

page 10

page 11

page 12

page 13

research
04/19/2023

Reference-guided Controllable Inpainting of Neural Radiance Fields

The popularity of Neural Radiance Fields (NeRFs) for view synthesis has ...
research
11/25/2020

Reference-Based Video Colorization with Spatiotemporal Correspondence

We propose a novel reference-based video colorization framework with spa...
research
11/25/2022

ShadowNeuS: Neural SDF Reconstruction by Shadow Ray Supervision

By supervising camera rays between a scene and multi-view image planes, ...
research
07/21/2022

Generalizable Patch-Based Neural Rendering

Neural rendering has received tremendous attention since the advent of N...
research
11/14/2022

SVS: Adversarial refinement for sparse novel view synthesis

This paper proposes Sparse View Synthesis. This is a view synthesis prob...
research
04/13/2023

SPColor: Semantic Prior Guided Exemplar-based Image Colorization

Exemplar-based image colorization aims to colorize a target grayscale im...
research
12/02/2021

Semantic-Sparse Colorization Network for Deep Exemplar-based Colorization

Exemplar-based colorization approaches rely on reference image to provid...

Please sign up or login with your details

Forgot password? Click here to reset