ROSA: Reconstructing Object Shape and Appearance Textures by Adaptive Detail Transfer
This work addresses a domain-specific problem in computer graphics for 3D reconstruction, offering incremental improvements over previous methods by enhancing detail and efficiency.
The paper tackles the ill-posed problem of reconstructing object shape and appearance from limited images by introducing ROSA, an inverse rendering method that optimizes mesh geometry with adaptive resolution and reconstructs fine details via a tile-based approach, achieving improved reconstruction without requiring large meshes or suffering from normal map limitations.
Reconstructing an object's shape and appearance in terms of a mesh textured by a spatially-varying bidirectional reflectance distribution function (SVBRDF) from a limited set of images captured under collocated light is an ill-posed problem. Previous state-of-the-art approaches either aim to reconstruct the appearance directly on the geometry or additionally use texture normals as part of the appearance features. However, this requires detailed but inefficiently large meshes, that would have to be simplified in a post-processing step, or suffers from well-known limitations of normal maps such as missing shadows or incorrect silhouettes. Another limiting factor is the fixed and typically low resolution of the texture estimation resulting in loss of important surface details. To overcome these problems, we present ROSA, an inverse rendering method that directly optimizes mesh geometry with spatially adaptive mesh resolution solely based on the image data. In particular, we refine the mesh and locally condition the surface smoothness based on the estimated normal texture and mesh curvature. In addition, we enable the reconstruction of fine appearance details in high-resolution textures through a pioneering tile-based method that operates on a single pre-trained decoder network but is not limited by the network output resolution.