3D Face Reconstruction With Geometry Details From a Single Color Image Under Occluded Scenes
This addresses the problem of realistic 3D face modeling for applications in computer vision and graphics, but it is incremental as it builds on common reconstruction approaches with added occlusion handling.
The paper tackles 3D face reconstruction from a single color image under occluded scenes, achieving high-quality results with geometry details by introducing bump mapping and a unified framework to handle multiple occlusion types like hair and glasses.
3D face reconstruction technology aims to generate a face stereo model naturally and realistically. Previous deep face reconstruction approaches are typically designed to generate convincing textures and cannot generalize well to multiple occluded scenarios simultaneously. By introducing bump mapping, we successfully added mid-level details to coarse 3D faces. More innovatively, our method takes into account occlusion scenarios. Thus on top of common 3D face reconstruction approaches, we in this paper propose a unified framework to handle multiple types of obstruction simultaneously (e.g., hair, palms and glasses et al.).Extensive experiments and comparisons demonstrate that our method can generate high-quality reconstruction results with geometry details from captured facial images under occluded scenes.