CoChat

SceneFormer: Indoor Scene Generation with Transformers

Wang, Xinpeng, Yeshwanth, Chandan, Niesner, Matthias · 2021 · 2021 International Conference on 3D Vision (3DV)
Cited by 114

The DOI matches its Crossref record; 11 of the 11 references it cites were found in a registry or an index.

Abstract

We address the task of indoor scene generation by generating a sequence of objects, along with their locations and orientations conditioned on a room layout. Large-scale indoor scene datasets allow us to extract patterns from user-designed indoor scenes, and generate new scenes based on these patterns. Existing methods rely on the 2D or 3D appearance of these scenes in addition to object positions, and make assumptions about the possible relations between objects. In contrast, we do not use any appearance information, and implicitly learn object relations using the self-attention mechanism of transformers. We show that our model design leads to faster scene generation with similar or improved levels of realism compared to previous methods. Our method is also flexible, as it can be conditioned not only on the room layout but also on text descriptions of the room, using only the cross-attention mechanism of transformers. Our user study shows that our generated scenes are preferred to the state-of-the-art FastSynth scenes 53.9% and 56.7% of the time for bedroom and living room scenes, respectively. At the same time, we generate a scene in 1.48 seconds on average, 20% faster than FastSynth.

Overview

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1109/3dv53792.2021.00021

Cites

11 of 11 references verified0 citation errors · 0 not checkable

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Show all 11 references

Research works printed but not linked: 28

  1. 10.1145/3197517.3201362 · DOI · Paper page
  2. wang, 2019, Planit: Planning and instantiating indoor scenes with relation graph and spatial prior networks, ACM Transactions on Graphics (TOG), 38, 1
  3. vaswani, 2017, Attention is all you need, Advances in neural information processing systems, 5998
  4. 10.1109/CVPR.2019.00687 · DOI · Paper page
  5. 10.1109/ICCV.2019.00748 · DOI · Paper page
  6. 10.1145/3381866 · DOI
  7. wu, 2015, 3d shapenets: A deep representation for volumetric shapes, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 1912
  8. 10.1145/2366145.2366154 · DOI · Paper page
  9. henderson, 2017, Automatic generation of constrained furniture layouts, arXiv preprint arXiv 1711 11585
  10. 10.1111/cgf.12976 · DOI
  11. kipf, 2017, Semi-supervised classification with graph convolutional networks, International Conference on Learning Representations (ICLR)
  12. 10.1145/3303766 · DOI · Paper page
  13. 10.1007/978-3-319-69487-0_10 · DOI
  14. savva, 2017, Scenesuggest: Context-driven 3d scene design, arXiv preprint arXiv 1703 00410
  15. 10.3115/v1/W14-3102 · DOI
  16. 10.1109/CVPR.2019.00634 · DOI · Paper page
  17. 10.3115/v1/P15-1006 · DOI
  18. 10.3115/v1/W14-2404 · DOI
  19. 10.1109/CVPR.2017.28 · DOI · Paper page
  20. 10.3115/v1/D14-1217 · DOI · Paper page
  21. chang, 2017, Sceneseer: 3d scene design with natural language, arXiv preprint arXiv 1703 00410
  22. 10.1109/CVPR42600.2020.01264 · DOI
  23. akbik, 2018, Contextual string embeddings for sequence labeling, COLING 2018 27th International Conference on Computational Linguistics, 1638
  24. 10.1109/CVPR42600.2020.00381 · DOI
  25. 10.1145/2010324.1964982 · DOI · Paper page
  26. pennington, 2014, Glove: Global vectors for word representation, Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), 1532, 10.3115/v1/D14-1162 · DOI · Paper page
  27. nash, 2020, Polygen: An autoregressive generative model of 3d meshes, arXiv preprint arXiv 2002 10381
  28. purkait, 2019, Learning to generate new indoor scenes, arXiv preprint arXiv 1912 04554

Cited by

See all 114

Metadata

Authors
Wang, X., Yeshwanth, C., & Niesner, M.
Venue
2021 International Conference on 3D Vision (3DV)
Publisher
IEEE
Published
2021-12
Pages
106-115
OpenAlex
W4205481600
Cited by
114
References
11
FWCI
12.03
Type
conference paper
Language
en
Open access
closed

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

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: SceneFormer: Indoor Scene Generation with Transformers. https://app.cochat.ai/papers/10.1109/3dv53792.2021.00021
The paper
Wang, X., Yeshwanth, C., & Niesner, M. (2021). SceneFormer: Indoor Scene Generation with Transformers. 2021 International Conference on 3D Vision (3DV). https://doi.org/10.1109/3dv53792.2021.00021

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.