NeRF in the Wild

https://nerf-w.github.io/

1 Introduction

First, we model per-image appearance variations such as exposure, lighting, weather, and post-processing in a learned low-dimensional latent space. Following the framework of Generative Latent Optimization [3], we optimize an appearance embedding for each input image, thereby granting NeRF-W the flexibility to explain away photometric and environmental variations between images by learning a shared appearance representation across the entire photo collection. The learned latent space provides control of the appearance of output renderings as illustrated in Figure 1,

4.1 Latent Appearance Modeling

Optimizing the Latent Space of Generative Networks

https://arxiv.org/abs/1707.05776