Hypersim: A Photorealistic Synthetic Dataset for Holistic Indoor Scene Understanding

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 with Hypersim, a photorealistic synthetic dataset for holistic indoor scene understanding.

Released in: Hypersim: A Photorealistic Synthetic Dataset for Holistic Indoor Scene Understanding

Source: Hypersim: A Photorealistic Synthetic Dataset for Holistic Indoor Scene Understanding

Contributor:

by

Homepage

Summary

@inproceedings{hypersim, title = {Hypersim: A Photorealistic Synthetic Dataset for Holistic Indoor Scene Understanding}, author = {Mike Roberts and Jason Ramapuram and Anurag Ranjan and Atulit Kumar and Miguel Angel Bautista and Nathan Paczan and Russ Webb and Joshua M. Susskind}, year = {2021}, URL = {https://arxiv.org/pdf/2011.02523.pdf} }

77,400

Images in dataset

July 2021

Year Released

Key Links & Stats

apple/ml-hypersim

Hypersim

Custom - non-commercial scientific research purposes

@inproceedings{hypersim, title = {Hypersim: A Photorealistic Synthetic Dataset for Holistic Indoor Scene Understanding}, author = {Mike Roberts and Jason Ramapuram and Anurag Ranjan and Atulit Kumar and Miguel Angel Bautista and Nathan Paczan and Russ Webb and Joshua M. Susskind}, year = {2021}, URL = {https://arxiv.org/pdf/2011.02523.pdf} }

scenebox

Modalities

  1. Still Image
  2. Video
  3. RGB-D
  4. 3D Asset
  5. Point Cloud

Verticals

  1. Home/Office

ML Task

  1. Image Classification
  2. Object Detection
  3. Semantic Segmentation
  4. Object Recognition
  5. Scene Understanding

Related organizations

Apple

ICCV