A Skeleton-bridged Deep Learning Approach for Generating Meshes of Complex Topologies from Single RGB Images
This addresses a challenge in computer vision for applications like robotics and AR/VR, but it appears incremental as it builds on existing geometric representations with a novel integration.
The paper tackles the problem of reconstructing 3D object surfaces from single RGB images, particularly for complex topologies, by proposing a skeleton-bridged, stage-wise deep learning approach that outperforms existing methods in qualitative and quantitative experiments.
This paper focuses on the challenging task of learning 3D object surface reconstructions from single RGB images. Existing methods achieve varying degrees of success by using different geometric representations. However, they all have their own drawbacks, and cannot well reconstruct those surfaces of complex topologies. To this end, we propose in this paper a skeleton-bridged, stage-wise learning approach to address the challenge. Our use of skeleton is due to its nice property of topology preservation, while being of lower complexity to learn. To learn skeleton from an input image, we design a deep architecture whose decoder is based on a novel design of parallel streams respectively for synthesis of curve- and surface-like skeleton points. We use different shape representations of point cloud, volume, and mesh in our stage-wise learning, in order to take their respective advantages. We also propose multi-stage use of the input image to correct prediction errors that are possibly accumulated in each stage. We conduct intensive experiments to investigate the efficacy of our proposed approach. Qualitative and quantitative results on representative object categories of both simple and complex topologies demonstrate the superiority of our approach over existing ones. We will make our ShapeNet-Skeleton dataset publicly available.