NeuFG: Neural Fuzzy Geometric Representation for 3-D Reconstruction

Three-dimensional reconstruction from multiview images is considered as a longstanding problem in computer vision and graphics. In order to achieve high-fidelity geometry and appearance of 3-D scenes, this article proposes a novel geometric object learning method for multiview reconstruction with <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">fuzzy set theory</i>. We establish a <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">new neural 3D reconstruction theoretical frame</i> called neural fuzzy geometric representation (NeuFG), which is a special type of implicit representation of geometric scene that only takes value in [0, 1]. NeuFG is essentially a volume image, and thus can be visualized directly with the conventional volume rendering technique. Extensive experiments on two public datasets, i.e., DTU and BlendedMVS, show that our method has the ability of accurately reconstructing complex shapes with vivid geometric details, without the requirement of mask supervision. Both qualitative and quantitative comparisons demonstrate that the proposed method has superior performance over the state-of-the-art neural scene representation methods. The code will be released on GitHub soon.