Corpus ID: 226254406

Hypersim: A Photorealistic Synthetic Dataset for Holistic Indoor Scene Understanding

  title={Hypersim: A Photorealistic Synthetic Dataset for Holistic Indoor Scene Understanding},
  author={Mike Roberts and N. Paczan},
  • Mike Roberts, N. Paczan
  • Published 2020
  • Computer Science
  • ArXiv
  • For many fundamental scene understanding tasks, it is difficult or impossible to obtain per-pixel ground truth labels from real images. We address this challenge by introducing Hypersim, a photorealistic synthetic dataset for holistic indoor scene understanding. To create our dataset, we leverage a large repository of synthetic scenes created by professional artists, and we generate 77,400 images of 461 indoor scenes with detailed per-pixel labels and corresponding ground truth geometry. Our… CONTINUE READING
    2 Citations

    Figures and Tables from this paper

    3D-FRONT: 3D Furnished Rooms with layOuts and semaNTics
    • 3
    • PDF


    OpenRooms: An End-to-End Open Framework for Photorealistic Indoor Scene Datasets
    • 2
    • PDF
    SceneNet RGB-D: Can 5M Synthetic Images Beat Generic ImageNet Pre-training on Indoor Segmentation?
    • 152
    • Highly Influential
    • PDF
    Physically-Based Rendering for Indoor Scene Understanding Using Convolutional Neural Networks
    • 159
    • PDF
    Understanding RealWorld Indoor Scenes with Synthetic Data
    • 111
    • PDF
    Neural Inverse Rendering of an Indoor Scene From a Single Image
    • 21
    • PDF
    ScanNet: Richly-Annotated 3D Reconstructions of Indoor Scenes
    • 727
    • Highly Influential
    • PDF
    SUN RGB-D: A RGB-D scene understanding benchmark suite
    • 693
    • PDF
    Structured3D: A Large Photo-realistic Dataset for Structured 3D Modeling
    • 20
    • PDF
    Unlimited Road-scene Synthetic Annotation (URSA) Dataset
    • 11
    • Highly Influential
    • PDF
    The SYNTHIA Dataset: A Large Collection of Synthetic Images for Semantic Segmentation of Urban Scenes
    • 899
    • PDF