Learning Where to Look: Data-Driven Viewpoint Set Selection for 3D Scenes

By Kyle Genova, Manolis Savva, Angel X. Chang, Thomas A. Funkhouser. 2017

13 citations recorded by the source corpus.

The use of rendered images, whether from completely synthetic datasets or from 3D reconstructions, is increasingly prevalent in vision tasks. However, little attention has been given to how the selection of viewpoints affects the performance of rendered training sets. In this paper, we propose a data-driven approach to view set selection. Given a set of example images, we extract statistics describing their contents and generate a set of views matching the distribution of those statistics. Motivated by semantic segmentation tasks, we model the spatial distribution of each semantic object category within an image view volume. We provide a search algorithm that generates a sampling of likely candidate views according to the example distribution, and a set selection algorithm that chooses a subset of the candidates that jointly cover the example distribution. Results of experiments with these algorithms on SUNCG indicate that they are indeed able to produce view distributions similar to an example set from NYUDv2 according to the earth mover's distance. Furthermore, the selected views improve performance on semantic segmentation compared to alternative view selection algorithms.

Subfields: Aerospace Engineering, Computer Vision and Pattern Recognition, Reinforcement Learning, 3D Vision & Pose

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Aerospace Engineering

  1. Nathan Paczan
  2. Mike Roberts

In Computer Vision and Pattern Recognition

  1. Nathan Paczan
  2. Mike Roberts
  3. Amir Zamir
  4. Roman Bachmann
  5. Jitendra Malik

In Reinforcement Learning

  1. Nathan Paczan
  2. Mike Roberts

In 3D Vision & Pose

  1. Nathan Paczan
  2. Mike Roberts

Citations in the corpus