Deep Color-Normal Residual Networks for Geometry Refinement Extracting Color Consistency and Fine Geometry

  • Full Access Full Access
  • Onsite Student Access Onsite Student Access
  • Onsite Experience Onsite Experience
  • Virtual Full Access Virtual Full Access
  • Virtual Basic Access Virtual Basic Access

*All presentations are available in the virtual platform on-demand. The posters will also be exhibited onsite in Hall E, Tokyo International Forum from 15 – 17 December 2021.

Abstract: We refine 3D geometry based on color consistency using a deep neural network. Our method optimizes the location of each vertex maximizing the quality of related textures.

Author(s)/Presenter(s):
MinGeun Park, Kyung Hee University, South Korea
Seungkyu Lee, Kyung Hee University, South Korea

Back

VRST
sq-ad