SAMURAI: Shape And Material from Unconstrained Real-world Arbitrary Image collections
This addresses the challenge of creating relightable 3D models from arbitrary real-world images for applications like AR/VR, representing a significant advance over prior methods that require known poses or fail in unconstrained settings.
The paper tackles the problem of inverse rendering from unconstrained image collections with unknown camera poses, varying backgrounds, and illuminations, achieving a method that jointly estimates shape, BRDF, camera pose, and illumination to produce relightable 3D assets.
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