Ref-DVGO: Reflection-Aware Direct Voxel Grid Optimization for an Improved Quality-Efficiency Trade-Off in Reflective Scene Reconstruction

TL;DR

Ref-DVGO introduces a reflection-aware voxel grid method that balances reconstruction quality and efficiency in reflective scene modeling, improving upon existing neural radiance field techniques.

Contribution

The paper presents a novel implicit-explicit volume rendering approach with a density-based grid and reflection reparameterization for better efficiency and quality in reflective scene reconstruction.

Findings

Achieves a favorable quality-efficiency trade-off.

Enhances reconstruction quality of reflective objects.

Provides insights into density-based methods for reflective scenes.

Abstract

Neural Radiance Fields (NeRFs) have revolutionized the field of novel view synthesis, demonstrating remarkable performance. However, the modeling and rendering of reflective objects remain challenging problems. Recent methods have shown significant improvements over the baselines in handling reflective scenes, albeit at the expense of efficiency. In this work, we aim to strike a balance between efficiency and quality. To this end, we investigate an implicit-explicit approach based on conventional volume rendering to enhance the reconstruction quality and accelerate the training and rendering processes. We adopt an efficient density-based grid representation and reparameterize the reflected radiance in our pipeline. Our proposed reflection-aware approach achieves a competitive quality efficiency trade-off compared to competing methods. Based on our experimental results, we propose and discuss hypotheses regarding the factors influencing the results of density-based methods for reconstructing reflective objects. The source code is available at https://github.com/gkouros/ref-dvgo.