NeRFReN: Neural Radiance Fields with Reflections

TL;DR

NeRFReN extends Neural Radiance Fields to accurately model and synthesize scenes with complex reflections by decomposing scenes into transmitted and reflected components, improving view synthesis and depth estimation.

Contribution

We introduce a scene decomposition approach within NeRF to handle complex reflections, utilizing geometric priors and specialized training strategies for effective separation.

Findings

Achieves high-quality novel view synthesis in reflective scenes.

Produces physically consistent depth estimations.

Enables scene editing applications with reflections.

Abstract

Neural Radiance Fields (NeRF) has achieved unprecedented view synthesis quality using coordinate-based neural scene representations. However, NeRF's view dependency can only handle simple reflections like highlights but cannot deal with complex reflections such as those from glass and mirrors. In these scenarios, NeRF models the virtual image as real geometries which leads to inaccurate depth estimation, and produces blurry renderings when the multi-view consistency is violated as the reflected objects may only be seen under some of the viewpoints. To overcome these issues, we introduce NeRFReN, which is built upon NeRF to model scenes with reflections. Specifically, we propose to split a scene into transmitted and reflected components, and model the two components with separate neural radiance fields. Considering that this decomposition is highly under-constrained, we exploit geometric priors and apply carefully-designed training strategies to achieve reasonable decomposition results. Experiments on various self-captured scenes show that our method achieves high-quality novel view synthesis and physically sound depth estimation results while enabling scene editing applications.