X-Section: Cross-Section Prediction for Enhanced RGBD Fusion
This addresses 3D reconstruction for robotics and AR/VR applications, but it is incremental as it extends existing methods like KinectFusion.
The paper tackles the problem of detailed 3D reconstruction in indoor scenes by proposing X-Section, an RGB-D approach that predicts object thicknesses using deep learning, enabling shape completion behind sensed data and integration into volumetric fusion, with qualitative and quantitative evaluations showing accurate predictions.
Detailed 3D reconstruction is an important challenge with application to robotics, augmented and virtual reality, which has seen impressive progress throughout the past years. Advancements were driven by the availability of depth cameras (RGB-D), as well as increased compute power, e.g.\ in the form of GPUs -- but also thanks to inclusion of machine learning in the process. Here, we propose X-Section, an RGB-D 3D reconstruction approach that leverages deep learning to make object-level predictions about thicknesses that can be readily integrated into a volumetric multi-view fusion process, where we propose an extension to the popular KinectFusion approach. In essence, our method allows to complete shape in general indoor scenes behind what is sensed by the RGB-D camera, which may be crucial e.g.\ for robotic manipulation tasks or efficient scene exploration. Predicting object thicknesses rather than volumes allows us to work with comparably high spatial resolution without exploding memory and training data requirements on the employed Convolutional Neural Networks. In a series of qualitative and quantitative evaluations, we demonstrate how we accurately predict object thickness and reconstruct general 3D scenes containing multiple objects.