NeROIC: Neural Rendering of Objects from Online Image Collections
This addresses the challenge of creating detailed object models from in-the-wild photos for computer graphics and vision applications, representing an incremental improvement over existing neural rendering methods.
The paper tackles the problem of acquiring high-quality 3D object representations from online image collections with varying conditions, enabling novel-view synthesis, relighting, and background composition. It demonstrates advantages in capturing geometry and appearance properties for rendering applications.
We present a novel method to acquire object representations from online image collections, capturing high-quality geometry and material properties of arbitrary objects from photographs with varying cameras, illumination, and backgrounds. This enables various object-centric rendering applications such as novel-view synthesis, relighting, and harmonized background composition from challenging in-the-wild input. Using a multi-stage approach extending neural radiance fields, we first infer the surface geometry and refine the coarsely estimated initial camera parameters, while leveraging coarse foreground object masks to improve the training efficiency and geometry quality. We also introduce a robust normal estimation technique which eliminates the effect of geometric noise while retaining crucial details. Lastly, we extract surface material properties and ambient illumination, represented in spherical harmonics with extensions that handle transient elements, e.g. sharp shadows. The union of these components results in a highly modular and efficient object acquisition framework. Extensive evaluations and comparisons demonstrate the advantages of our approach in capturing high-quality geometry and appearance properties useful for rendering applications.