English

REFRAME: Reflective Surface Real-Time Rendering for Mobile Devices

Computer Vision and Pattern Recognition 2024-08-16 v2

Abstract

This work tackles the challenging task of achieving real-time novel view synthesis for reflective surfaces across various scenes. Existing real-time rendering methods, especially those based on meshes, often have subpar performance in modeling surfaces with rich view-dependent appearances. Our key idea lies in leveraging meshes for rendering acceleration while incorporating a novel approach to parameterize view-dependent information. We decompose the color into diffuse and specular, and model the specular color in the reflected direction based on a neural environment map. Our experiments demonstrate that our method achieves comparable reconstruction quality for highly reflective surfaces compared to state-of-the-art offline methods, while also efficiently enabling real-time rendering on edge devices such as smartphones.

Keywords

Cite

@article{arxiv.2403.16481,
  title  = {REFRAME: Reflective Surface Real-Time Rendering for Mobile Devices},
  author = {Chaojie Ji and Yufeng Li and Yiyi Liao},
  journal= {arXiv preprint arXiv:2403.16481},
  year   = {2024}
}

Comments

ECCV 2024 accepted. Project Page: https://xdimlab.github.io/REFRAME/

R2 v1 2026-06-28T15:32:16.418Z