SynthCam3D: Semantic Understanding With Synthetic Indoor Scenes
This addresses scene understanding for robotics or AR applications, but it appears incremental as it builds on existing methods with synthetic data.
The paper tackled semantic segmentation for real-time reconstruction by training a deep autoencoder on synthetic depth data from a new 3D scene library, achieving preliminary results without noise modeling.
We are interested in automatic scene understanding from geometric cues. To this end, we aim to bring semantic segmentation in the loop of real-time reconstruction. Our semantic segmentation is built on a deep autoencoder stack trained exclusively on synthetic depth data generated from our novel 3D scene library, SynthCam3D. Importantly, our network is able to segment real world scenes without any noise modelling. We present encouraging preliminary results.