PARF: Primitive-Aware Radiance Fusion for Indoor Scene Novel View Synthesis

TL;DR

This paper introduces PARF, a fast and scene-editable radiance field reconstruction method that leverages semantic parsing and primitive extraction to improve novel view synthesis in indoor scenes.

Contribution

It proposes a primitive-aware hybrid rendering strategy and an iterative reconstruction pipeline that fuses semantic, primitive, and radiance information for efficient scene synthesis.

Findings

Fast reconstruction compared to existing methods

High-quality novel view synthesis results

Enhanced scene editing capabilities

Abstract

This paper proposes a method for fast scene radiance field reconstruction with strong novel view synthesis performance and convenient scene editing functionality. The key idea is to fully utilize semantic parsing and primitive extraction for constraining and accelerating the radiance field reconstruction process. To fulfill this goal, a primitive-aware hybrid rendering strategy was proposed to enjoy the best of both volumetric and primitive rendering. We further contribute a reconstruction pipeline conducts primitive parsing and radiance field learning iteratively for each input frame which successfully fuses semantic, primitive, and radiance information into a single framework. Extensive evaluations demonstrate the fast reconstruction ability, high rendering quality, and convenient editing functionality of our method.