Hierarchy Denoising Recursive Autoencoders for 3D Scene Layout Prediction
This addresses indoor scene understanding for robotics or AR/VR applications, presenting an incremental hybrid method.
The paper tackles 3D scene layout prediction by developing a variational denoising recursive autoencoder (VDRAE) that generates and refines hierarchical representations of object layouts from point clouds, improving object detection performance on real-world datasets compared to prior baselines.
Indoor scenes exhibit rich hierarchical structure in 3D object layouts. Many tasks in 3D scene understanding can benefit from reasoning jointly about the hierarchical context of a scene, and the identities of objects. We present a variational denoising recursive autoencoder (VDRAE) that generates and iteratively refines a hierarchical representation of 3D object layouts, interleaving bottom-up encoding for context aggregation and top-down decoding for propagation. We train our VDRAE on large-scale 3D scene datasets to predict both instance-level segmentations and a 3D object detections from an over-segmentation of an input point cloud. We show that our VDRAE improves object detection performance on real-world 3D point cloud datasets compared to baselines from prior work.