Colorizing Monochromatic Radiance Fields

Authors

  • Yean Cheng National Key Laboratory for Multimedia Information Processing, School of Computer Science, Peking University National Engineering Research Center of Visual Technology, School of Computer Science, Peking University AI Innovation Center, School of Computer Science, Peking University
  • Renjie Wan Department of Computer Science, Hong Kong Baptist University
  • Shuchen Weng National Key Laboratory for Multimedia Information Processing, School of Computer Science, Peking University National Engineering Research Center of Visual Technology, School of Computer Science, Peking University
  • Chengxuan Zhu National Key Laboratory of General AI, School of Intelligence Science and Technology, Peking University
  • Yakun Chang National Key Laboratory for Multimedia Information Processing, School of Computer Science, Peking University National Engineering Research Center of Visual Technology, School of Computer Science, Peking University
  • Boxin Shi National Key Laboratory for Multimedia Information Processing, School of Computer Science, Peking University National Engineering Research Center of Visual Technology, School of Computer Science, Peking University AI Innovation Center, School of Computer Science, Peking University

DOI:

https://doi.org/10.1609/aaai.v38i2.27895

Keywords:

CV: Low Level & Physics-based Vision, CV: Computational Photography, Image & Video Synthesis

Abstract

Though Neural Radiance Fields (NeRF) can produce colorful 3D representations of the world by using a set of 2D images, such ability becomes non-existent when only monochromatic images are provided. Since color is necessary in representing the world, reproducing color from monochromatic radiance fields becomes crucial. To achieve this goal, instead of manipulating the monochromatic radiance fields directly, we consider it as a representation-prediction task in the Lab color space. By first constructing the luminance and density representation using monochromatic images, our prediction stage can recreate color representation on the basis of an image colorization module. We then reproduce a colorful implicit model through the representation of luminance, density, and color. Extensive experiments have been conducted to validate the effectiveness of our approaches. Our project page: https://liquidammonia.github.io/color-nerf.

Downloads

Published

2024-03-24

How to Cite

Cheng, Y., Wan, R., Weng, S., Zhu, C., Chang, Y., & Shi, B. (2024). Colorizing Monochromatic Radiance Fields. Proceedings of the AAAI Conference on Artificial Intelligence, 38(2), 1317-1325. https://doi.org/10.1609/aaai.v38i2.27895

Issue

Section

AAAI Technical Track on Computer Vision I