Corpus ID: 28328610

AI2-THOR: An Interactive 3D Environment for Visual AI

@article{Kolve2017AI2THORAI,
  title={AI2-THOR: An Interactive 3D Environment for Visual AI},
  author={Eric Kolve and Roozbeh Mottaghi and Daniel Gordon and Yuke Zhu and Abhinav Gupta and Ali Farhadi},
  journal={ArXiv},
  year={2017},
  volume={abs/1712.05474}
}
  • Eric Kolve, Roozbeh Mottaghi, +3 authors Ali Farhadi
  • Published 2017
  • Computer Science
  • ArXiv
  • We introduce The House Of inteRactions (THOR), a framework for visual AI research, available at this http URL AI2-THOR consists of near photo-realistic 3D indoor scenes, where AI agents can navigate in the scenes and interact with objects to perform tasks. AI2-THOR enables research in many different domains including but not limited to deep reinforcement learning, imitation learning, learning by interaction, planning, visual question answering, unsupervised representation learning, object… CONTINUE READING

    Figures, Tables, and Topics from this paper.

    Citations

    Publications citing this paper.
    SHOWING 1-10 OF 164 CITATIONS

    Visual Semantic Navigation using Scene Priors

    VIEW 7 EXCERPTS
    CITES METHODS

    SplitNet: Sim2Sim and Task2Task Transfer for Embodied Visual Navigation

    VIEW 1 EXCERPT
    CITES BACKGROUND

    Embodied Amodal Recognition: Learning to Move to Perceive Objects

    VIEW 2 EXCERPTS
    CITES METHODS & BACKGROUND

    EARLY FUSION for Goal Directed Robotic Vision

    VIEW 1 EXCERPT
    CITES BACKGROUND

    Embodied Question Answering

    VIEW 1 EXCERPT
    CITES BACKGROUND

    Embodied Question Answering

    VIEW 1 EXCERPT
    CITES BACKGROUND

    FILTER CITATIONS BY YEAR

    2016
    2020

    CITATION STATISTICS

    • 25 Highly Influenced Citations

    • Averaged 53 Citations per year from 2018 through 2020

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 29 REFERENCES

    Target-driven visual navigation in indoor scenes using deep reinforcement learning

    VIEW 1 EXCERPT

    Visual Semantic Planning Using Deep Successor Representations

    IQA: Visual Question Answering in Interactive Environments

    VIEW 1 EXCERPT

    ViZDoom: A Doom-based AI research platform for visual reinforcement learning

    VIEW 2 EXCERPTS

    HoME: a Household Multimodal Environment

    VIEW 2 EXCERPTS

    SceneNet: An annotated model generator for indoor scene understanding

    SeGAN: Segmenting and Generating the Invisible

    VIEW 1 EXCERPT