Generative Multiview Relighting for 3D Reconstruction under Extreme Illumination Variation

https://relight-to-reconstruct.github.io/ Input images with varying illumination Novel views under reference illumination Ours Baseline Reference light Ground truth Figure 1. 3D reconstruction under extreme illumination variation. We propose a method for 3D reconstruction from a set of images captured under strongly varying illumination. Our method recovers high-fidelity appearance details including specular highlights that prior state-of-the-art approaches cannot recover (top baseline: NeRF-Casting [47] with appearance embeddings, bottom baseline: NeROIC [25]).