ABSTRACT
We present a real-time, interactive system for the geometric reconstruction, object-class segmentation and learning of 3D scenes [Valentin et al. 2015]. Using our system, a user can walk into a room wearing a depth camera and a virtual reality headset, and both densely reconstruct the 3D scene [Newcombe et al. 2011; Nießner et al. 2013; Prisacariu et al. 2014]) and interactively segment the environment into object classes such as 'chair', 'floor' and 'table'. The user interacts physically with the real-world scene, touching objects and using voice commands to assign them appropriate labels. These user-generated labels are leveraged by an online random forest-based machine learning algorithm, which is used to predict labels for previously unseen parts of the scene. The predicted labels, together with those provided directly by the user, are incorporated into a dense 3D conditional random field model, over which we perform mean-field inference to filter out label inconsistencies. The entire pipeline runs in real time, and the user stays 'in the loop' throughout the process, receiving immediate feedback about the progress of the labelling and interacting with the scene as necessary to refine the predicted segmentation.
Supplemental Material
Available for Download
Supplemental files
- Newcombe, R. A. et al. 2011. KinectFusion: Real-Time Dense Surface Mapping and Tracking. In ISMAR, IEEE. Google ScholarDigital Library
- Niessner, M. et al. 2013. Real-time 3D Reconstruction at Scale using Voxel Hashing. ACM TOG 32, 6, 169. Google ScholarDigital Library
- Prisacariu, V. A., Kähler, O. et al. 2014. A Framework for the Volumetric Integration of Depth Images. ArXiv e-prints.Google Scholar
- Valentin, J. P. C. et al. 2015. SemanticPaint: Interactive 3D Labeling and Learning at your Fingertips. To appear in ACM TOG.Google Scholar
Index Terms
- SemanticPaint: interactive segmentation and learning of 3D worlds
Recommendations
SemanticPaint: Interactive 3D Labeling and Learning at your Fingertips
We present a new interactive and online approach to 3D scene understanding. Our system, SemanticPaint, allows users to simultaneously scan their environment whilst interactively segmenting the scene simply by reaching out and touching any desired object ...
SemanticPaint: interactive segmentation and learning of 3D world
SIGGRAPH '15: ACM SIGGRAPH 2015 TalksWe present a real-time, interactive system for the geometric reconstruction, object-class segmentation and learning of 3D scenes [Valentin et al. ]. Using our system, a user can walk into a room wearing a consumer depth camera and a virtual reality ...
Transductive Multilabel Learning via Label Set Propagation
The problem of multilabel classification has attracted great interest in the last decade, where each instance can be assigned with a set of multiple class labels simultaneously. It has a wide variety of real-world applications, e.g., automatic image ...
Comments