Real-Time Depth Refinement for Specular Objects
This addresses the limitation of existing depth refinement methods that fail with specular objects, providing improved 3D scanning accuracy for applications in computer vision.
The paper tackles the problem of inaccurate depth recovery for specular objects using RGB-D scanners, presenting a shape from shading framework that enhances depth profiles for both diffuse and specular objects in real-time, achieving state-of-the-art results in quantitative and visual evaluations.
The introduction of consumer RGB-D scanners set off a major boost in 3D computer vision research. Yet, the precision of existing depth scanners is not accurate enough to recover fine details of a scanned object. While modern shading based depth refinement methods have been proven to work well with Lambertian objects, they break down in the presence of specularities. We present a novel shape from shading framework that addresses this issue and enhances both diffuse and specular objects' depth profiles. We take advantage of the built-in monochromatic IR projector and IR images of the RGB-D scanners and present a lighting model that accounts for the specular regions in the input image. Using this model, we reconstruct the depth map in real-time. Both quantitative tests and visual evaluations prove that the proposed method produces state of the art depth reconstruction results.