6 accepted papers
This paper presents SceneCut, a novel approach to jointly discover previously unseen objects and non-object surfaces using a single RGB-D image. SceneCut's joint reasoning over scene semantics and geometry allows a robot to detect and segment object instances in complex scenes where modern deep lear…
For intelligent robots to interact in meaningful ways with their environment, they must understand both the geometric and semantic properties of the scene surrounding them. The majority of research to date has addressed these mapping challenges separately, focusing on either geometric or semantic ma…
In most state-of-the-art hashing-based visual search systems, local image descriptors of an image are first aggregated as a single feature vector. This feature vector is then subjected to a hashing function that produces a binary hash code. In previous work, the aggregating and the hashing processes…
We tackle the problem of large-scale object detection in images, where the number of objects can be arbitrarily large, and can exhibit significant overlap/occlusion. A successful approach to modelling the large-scale nature of this problem has been via point process density functions which jointly…
Modern SLAM systems with a depth sensor are able to reliably reconstruct dense 3D geometric maps of indoor scenes. Representing these maps in terms of meaningful entities is a step towards building semantic maps for autonomous robots. One approach is to segment the 3D maps into semantic objects usin…
This paper addresses the problem of semantic segmentation of 3D indoor scenes reconstructed from RGB-D images.Traditionally label prediction for 3D points is tackled by employing graphical models that capture scene features and complex relations between different class labels. However, the existing…