Understanding Indoor Scenes Using 3D Geometric Phrases


Visual scene understanding is a difficult problem, interleaving object detection, geometric reasoning and scene classification. In this paper, we present a hierarchical scene model for learning and reasoning about complex indoor scenes which is computationally tractable, can be learned from a reasonable amount of training data, and avoids oversimplification. At the core of this approach is the 3D Geometric Phrase Model which captures the semantic and geometric relationships between objects which frequently co-occur in the same 3D spatial configuration. Experiments show that this model effectively explains scene semantics, geometry and object groupings from a single image, while also improving individual object detections.

W. Choi, Y. -W. Chao, C. Pantofaru, S. Savarese. "Understanding Indoor Scenes Using 3D Geometric Phrases" in CVPR, 2013 (to appear as an oral presentation).
 [pdf][supplemetal material][bibtex]



Updates

  • [NEW] The code is released (04/17/2013).
  • [NEW] The Indoor-Scene-Object dataset is uploaded (03/25/2013).
  • This page is created. (03/25/2013).

    Source Code

    The source code is available at github (https://github.com/wgchoi/indoorunderstanding_3dgp) or you can download below:

      indoor_3dgp_v0.5.zip

    Current version provide only testing algorithm. Training algorithm will be available soon!

    The code is released under BSD license.

    Dataset Downloads


    Indoor-scene-object dataset is available to download here.
    The furniture dataset and trained dpm object detectors are available to download here and here.
    The data is released under Creative Common license.

    This work is supported by ONR grant N00014111038 and a gift award from HTC.

    Last updated on 06/16/2014