Removing Adverse Volumetric Effects From Trained Neural Radiance Fields

TL;DR

This paper introduces a method to remove fog from neural radiance field (NeRF) scenes, enabling clear view synthesis in foggy environments, and provides a new dataset for benchmarking such scenarios.

Contribution

The authors propose a novel fog removal technique for NeRFs based on global contrast and density thresholding, along with a new foggy scene dataset for evaluation.

Findings

Effective fog removal in NeRF-based scene rendering

New dataset with foggy environments for benchmarking

Improved clarity of synthesized views in foggy conditions

Abstract

While the use of neural radiance fields (NeRFs) in different challenging settings has been explored, only very recently have there been any contributions that focus on the use of NeRF in foggy environments. We argue that the traditional NeRF models are able to replicate scenes filled with fog and propose a method to remove the fog when synthesizing novel views. By calculating the global contrast of a scene, we can estimate a density threshold that, when applied, removes all visible fog. This makes it possible to use NeRF as a way of rendering clear views of objects of interest located in fog-filled environments. Additionally, to benchmark performance on such scenes, we introduce a new dataset that expands some of the original synthetic NeRF scenes through the addition of fog and natural environments. The code, dataset, and video results can be found on our project page: https://vegardskui.com/fognerf/