CVMar 25, 2024

REFRAME: Reflective Surface Real-Time Rendering for Mobile Devices

arXiv:2403.16481v21 citationsh-index: 25ECCV
Originality Incremental advance
AI Analysis

This addresses the problem of rendering reflective surfaces in real-time on mobile devices, which is an incremental improvement over existing methods.

The paper tackles real-time novel view synthesis for reflective surfaces by decomposing color into diffuse and specular components and modeling specular color with a neural environment map, achieving comparable reconstruction quality to offline methods while enabling real-time rendering on mobile devices.

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.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes