Abstract
We address the problem of recovering the shape and spatially-varying reflectance of an object from multi-view images (and their camera poses) of an object illuminated by one unknown lighting condition. This enables the rendering of novel views of the object under arbitrary environment lighting and editing of the object's material properties. The key to our approach, which we call Neural Radiance Factorization (NeRFactor), is to distill the volumetric geometry of a Neural Radiance Field (NeRF) [Mildenhall et al. 2020] representation of the object into a surface representation and then jointly refine the geometry while solving for the spatially-varying reflectance and environment lighting. Specifically, NeRFactor recovers 3D neural fields of surface normals, light visibility, albedo, and Bidirectional Reflectance Distribution Functions (BRDFs) without any supervision, using only a re-rendering loss, simple smoothness priors, and a data-driven BRDF prior learned from real-world BRDF measurements. By explicitly modeling light visibility, NeRFactor is able to separate shadows from albedo and synthesize realistic soft or hard shadows under arbitrary lighting conditions. NeRFactor is able to recover convincing 3D models for free-viewpoint relighting in this challenging and underconstrained capture setup for both synthetic and real scenes. Qualitative and quantitative experiments show that NeRFactor outperforms classic and deep learning-based state of the art across various tasks. Our videos, code, and data are available at people.csail.mit.edu/xiuming/projects/nerfactor/.
Highlights
Recovering an object’s geometry and material properties from captured images, such that it can be rendered from arbitrary viewpoints under novel lighting conditions, is a longstanding problem within computer vision and graphics
Our key insight is that we can first optimize a Neural Radiance Field (NeRF) [Mildenhall et al 2020] from the input images to initialize our model’s surface normals and light visibility, and jointly optimize these initial estimates along with the spatiallyvarying reflectance and the lighting condition to best explain the observed images
We address the second issue by representing the surface normal and light visibility at any 3D location on this surface as continuous functions parameterized by Multi-Layer Perceptrons (MLPs), and encourage these functions to be close to the values derived from the pretrained NeRF and be spatially smooth
Summary
Recovering an object’s geometry and material properties from captured images, such that it can be rendered from arbitrary viewpoints under novel lighting conditions, is a longstanding problem within computer vision and graphics. The difficulty of this problem stems from its fundamentally underconstrained nature, and prior work has typically addressed this either by using additional observations such as scanned geometry, known lighting conditions, or images of the object under multiple different lighting conditions, or by making restrictive assumptions such as assuming a single material. Because NeRFactor models light visibility explicitly and efficiently, it is capable of removing shadows from albedo estimation and synthesizing realistic soft or hard shadows under arbitrary novel lighting conditions
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.