The Geometry Enhanced Deep Implicit Function Based 3D Reconstruction for Objects in a Real-Scene Image

Abstract

AbstractFor the 3D reconstruction of objects in a real scene, the state-of-the-art scheme is to detect and identify the target by a classic deep neural network and reconstruct the 3D object with deep implicit function (DIF) based methods. This scheme can be computationally and memory efficient, representing high-resolution geometry of arbitrary topology for reconstructing the 3D objects in a scene. However, geometry constraints are lacking in these procedures, which may lead to fatal mistaken identification or structural errors in the reconstruction results. In this paper, we propose to enhance the geometry constraint of the DIF-based 3D reconstruction. A geometry retainer module (GRM) ensures the detected target always retains the correct 2D geometry. The chamfer distance (CD) is introduced as a constraint on the 3D geometry for the DIF-based method. Correspondingly, a strategy to extract a point cloud from the signed distance field (SDF) is proposed to complete this 3D geometry constraint. Abundant experiments show that our method improves the quality of 3D reconstruction greatly.Keywords3D reconstructionDeep learningDeep implicit function