Overview

In computer vision, scene understanding and modeling encapsulate a diverse set of research problems, ranging from low-level geometric modeling (e.g., SLAM algorithms) to 3D room layout estimation. These tasks are often addressed separately, yielding only a constrained understanding and representation of the underlying scene. In parallel, the popularity of 360° cameras has encouraged the digitization of the real world into augmented and virtual realities, enabling new applications such as virtual social interactions and semantically leveraged augmented reality. This workshop aims to promote comprehensive 3D scene understanding and modeling algorithms that create integrated scene representations (with geometry, appearance, semantics, and perceptual qualities), while utilizing 360° imagery to encourage research on its unique challenges.

The First SUMO Challenge Workshop will bring together computer vision researchers working on 3D scene understanding and modeling for a day of keynote speakers and discussions on the topic. The two primary goals of the workshop are:

The 2018 SUMO Challenge, in conjunction with the workshop, provides a dataset and an evaluation platform to assess and compare such scene understanding approaches that generate complete 3D representations with textured 3D models, pose, and semantics. The datasets created and released for this competition may serve as reference benchmarks for future research in 3D scene understanding.