In conjunction with ICCV 2015, Santiago, Chile


Developing autonomous systems able to help humans in their daily activities requires understanding different kind of environments depending on the specific application, e.g., self-driving cars, unmanned aerial vehicles and service or underwater robots.

For computer vision researchers understanding the world from visual data has been a main challenge since the beginning of the community. Research in this area has recently become (again) a focus in the community, leveraging advances in a wide range of topics that include scene parsing, mapping, detection and reconstruction, among others. Nevertheless, there is still a long path until we have more complex approaches capable of a detailed understanding of the environments that surround us.

This workshop aims to summarize the advances in this area through invited talks of experienced researchers and invited poster presentations of young active researchers. Also, the objective of this event is to have the opportunity to discuss and debate about the advantages and drawbacks of current visual scene understanding approaches and possible future paths for research in this field.

Particularly, the workshop will cover the following topics:

  • 2D/3D Object Detection and Recognition 
  • 2D/3D Semantic Segmentation
  • 3D Reconstruction and Reasoning
  • Learning and Inference Techniques for 3D Scene Understanding
  • Scene Flow
  • Scene Recognition 
  • Semantic Mapping
  • Visual SLAM

Invited Speakers

              Sanja Fidler                                                           Abhinav Gupta                                                      Bernt Schiele                                                         Rene Vidal
          Univ. of Toronto                                                    Carnegie Mellon Univ.                                            MPI for Informatics                                               Johns Hopkins Univ.

Sponsored by