CoChat
Sign Up
Cited by 3583D Shape Modeling and AnalysisAdvanced Neural Network ApplicationsDomain Adaptation and Few-Shot Learning

The DOI matches its Crossref record; 88 of the 95 references it cites were found in a registry or an index.

Hypersim: A Photorealistic Synthetic Dataset for Holistic Indoor Scene Understanding

Open access
Roberts, Mike, Ramapuram, Jason, Ranjan, Anurag, Kumar, Atulit, Bautista, Miguel Angel, Paczan, Nathan, Webb, Russ, Susskind, Joshua M.·2021·2021 IEEE/CVF International Conference on Computer Vision (ICCV)
DOI 10.1109/iccv48922.2021.01073
Open this paper in CoChat — free accountOpen PDF

Abstract

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 dataset: (1) relies exclusively on publicly available 3D assets; (2) includes complete scene geometry, material information, and lighting information for every scene; (3) includes dense per-pixel semantic instance segmentations and complete camera information for every image; and (4) factors every image into diffuse reflectance, diffuse illumination, and a non-diffuse residual term that captures view-dependent lighting effects.We analyze our dataset at the level of scenes, objects, and pixels, and we analyze costs in terms of money, computation time, and annotation effort. Remarkably, we find that it is possible to generate our entire dataset from scratch, for roughly half the cost of training a popular open-source natural language processing model. We also evaluate sim-to-real transfer performance on two real-world scene understanding tasks – semantic segmentation and 3D shape prediction – where we find that pre-training on our dataset significantly improves performance on both tasks, and achieves state-of-the-art performance on the most challenging Pix3D test set. All of our rendered image data, as well as all the code we used to generate our dataset and perform our experiments, is available online.

Overview

Integrity signals

Registry

Crossref · 10.1109/iccv48922.2021.01073

Cites

88 of 88 references verified0 citation errors · 0 not checkable

Statistics

Recomputing p-values needs the paper’s full text.

Verification

Claims the paper makes

We couldn’t retrieve this paper’s full text, so its claims and self-check weren’t run. The registry and citation checks still apply.

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

Citations

Cites

Show all 95 references

Research works printed but not linked: 2

  1. jin, 0, Geometric structure based and regularized depth estimation from 360 degree indoor imagery, CVPR 2020
  2. xiang, 0, A large scale database for 3D object recognition, ECC 2016

Cited by

Sorted by citations

Items 101–200 of 358

Related

See all

Metadata

Authors
Roberts, M., Ramapuram, J., Ranjan, A., Kumar, A., Bautista, M. A., Paczan, N., Webb, R., & Susskind, J. M.
Affiliations
  • Apple (United States) (US)
  • Apple
ORCID
Ramapuram, Jason
Venue
2021 IEEE/CVF International Conference on Computer Vision (ICCV)
Publisher
IEEE
Published
2021-10
Pages
10892-10902
DOI
10.1109/iccv48922.2021.01073
OpenAlex
W3097660860
Cited by
358
References
95
Citations by year
2026: 85 · 2025: 88 · 2024: 73 · 2023: 61 · 2022: 31 · 2021: 19
FWCI
33.65
Type
conference paper
Language
en
Open access
Licence
Locations
  • IEEE/CVF International Conference on Computer Vision (ICCV) (publishedVersion)
  • arXiv (Cornell University) (submittedVersion)
  • arXiv (Cornell University)
  • IEEE/CVF International Conference on Computer Vision (ICCV)
Topics
  • Physical Sciences › Computer Science › Computer Graphics and Computer-Aided Design › 3D Shape Modeling and Analysis
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
  • Physical Sciences › Computer Science › Artificial Intelligence › Domain Adaptation and Few-Shot Learning
Keywords
synthetic dataset, indoor scene understanding, photorealistic rendering, instance segmentation, sim-to-real transfer, diffuse reflectance, scene geometry, annotation cost

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review