SAMURAI: Shape And Material from Unconstrained Real-world Arbitrary Image collections

TL;DR

SAMURAI introduces a novel joint optimization framework that reconstructs relightable 3D objects from unconstrained, real-world image collections without known camera poses, enabling advanced AR/VR applications.

Contribution

It is the first method to jointly optimize shape, material, pose, and illumination from in-the-wild images with minimal user input.

Findings

Successfully reconstructs relightable 3D assets from wild images

Handles unknown camera poses and varying lighting conditions

Enables realistic scene relighting in AR/VR applications

Abstract

Inverse rendering of an object under entirely unknown capture conditions is a fundamental challenge in computer vision and graphics. Neural approaches such as NeRF have achieved photorealistic results on novel view synthesis, but they require known camera poses. Solving this problem with unknown camera poses is highly challenging as it requires joint optimization over shape, radiance, and pose. This problem is exacerbated when the input images are captured in the wild with varying backgrounds and illuminations. Standard pose estimation techniques fail in such image collections in the wild due to very few estimated correspondences across images. Furthermore, NeRF cannot relight a scene under any illumination, as it operates on radiance (the product of reflectance and illumination). We propose a joint optimization framework to estimate the shape, BRDF, and per-image camera pose and illumination. Our method works on in-the-wild online image collections of an object and produces relightable 3D assets for several use-cases such as AR/VR. To our knowledge, our method is the first to tackle this severely unconstrained task with minimal user interaction. Project page: https://markboss.me/publication/2022-samurai/ Video: https://youtu.be/LlYuGDjXp-8