Removing Adverse Volumetric Effects From Trained Neural Radiance Fields
This work addresses a domain-specific problem for applications in computer vision and graphics where clear visualization in adverse weather conditions is needed, but it is incremental as it builds on existing NeRF models.
The paper tackles the problem of rendering clear views from foggy environments using neural radiance fields (NeRFs) by proposing a method to remove fog through a density threshold based on global contrast, enabling synthesis of fog-free novel views.
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/