Configurable 3D Scene Synthesis and 2D Image Rendering with Per-pixel Ground Truth Using Stochastic Grammars
Open accessThe DOI matches its Crossref record; 29 of the 29 references it cites were found in a registry or an index.
Abstract
We propose a systematic learning-based approach to the generation of massive quantities of synthetic 3D scenes and arbitrary numbers of photorealistic 2D images thereof, with associated ground truth information, for the purposes of training, benchmarking, and diagnosing learning-based computer vision and robotics algorithms. In particular, we devise a learning-based pipeline of algorithms capable of automatically generating and rendering a potentially infinite variety of indoor scenes by using a stochastic grammar, represented as an attributed Spatial And-Or Graph, in conjunction with state-of-the-art physics-based rendering. Our pipeline is capable of synthesizing scene layouts with high diversity, and it is configurable inasmuch as it enables the precise customization and control of important attributes of the generated scenes. It renders photorealistic RGB images of the generated scenes while automatically synthesizing detailed, per-pixel ground truth data, including visible surface depth and normal, object identity, and material information (detailed to object parts), as well as environments (e.g., illuminations and camera viewpoints). We demonstrate the value of our synthesized dataset, by improving performance in certain machine-learning-based scene understanding tasks—depth and surface normal prediction, semantic segmentation, reconstruction, etc.—and by providing benchmarks for and diagnostics of trained models by modifying object attributes and scene properties in a controllable manner.
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.
Integrity signals
Registry
Cites
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.
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
ImageNet: A large-scale hierarchical image database
Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., & Fei-Fei, L. (2009) · 2009 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2009.5206848 · Cited by 65,333
The Pascal Visual Object Classes Challenge: A Retrospective
Everingham, M., Eslami, S. M. A., Van Gool, L., Williams, C. K. I., Winn, J., & Zisserman, A. (2015) · International Journal of Computer Vision · doi:10.1007/s11263-014-0733-5 · Cited by 7,139
Indoor segmentation and support inference from rgbd images
Silberman, N., Hoiem, D., Kohli, P., & Fergus, R. (2012) · Lecture Notes in Computer Science · doi:10.1007/978-3-642-33715-4_54 · Cited by 5,760
Training Products of Experts by Minimizing Contrastive Divergence
Hinton, G. E. (2002) · Neural Computation · doi:10.1162/089976602760128018 · Cited by 4,879 · cited 2×
“…for the Markov chain to converge, we adopt the contrastive divergence (CD) learning that follows the gradient of the difference of two divergences (Hinton 2002): where KL ( p 0 || p ∞ ) is the Kullback–Leibler divergence between the data distribution p 0 and the model distribution p ∞ , and p…”
BackgroundMethodLearning Deconvolution Network for Semantic Segmentation
Noh, H., Hong, S., & Han, B. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.178 · Cited by 4,422 · cited 2×
“…Laina et al. 2016), surface normal estimation (Wang et al. 2015; Eigen and Fergus 2015; Bansal et al. 2016), semantic segmentation (Long et al. 2015; Noh et al. 2015; Chen et al. 2016), reasoning about object-supporting relations (Fisher et al. 2011; Silberman et al. 2012; Zheng et al. 2015; Liang…”
BackgroundFlownet: Learning optical flow with convolutional networks
Dosovitskiy, A., Fischer, P., Ilg, E., Hausser, P., Hazirbas, C., Golkov, V., Smagt, P. V. D., Cremers, D., & Brox, T. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.316 · Cited by 4,313
Depth Map Prediction from a Single Image using a Multi-Scale Deep Network
Eigen, D., Puhrsch, C., & Fergus, R. (2014) · arXiv · doi:10.48550/arxiv.1406.2283 · Cited by 3,442
Eigen, D., & Fergus, R. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.304 · Cited by 2,862 · cited 11×
“We see that both Eigen et al. (2014) and Eigen and Fergus (2015) are very sensitive to illumination conditions, whereas Liu et al. (2015) is robust to illumination intensity, but sensitive to illumination color.”
BackgroundMethodInfluentialRevisiting Unreasonable Effectiveness of Data in Deep Learning Era
Sun, C., Shrivastava, A., Singh, S., & Gupta, A. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.97 · Cited by 2,484
Torralba, A., & Efros, A. A. (2011) · CVPR 2011 · doi:10.1109/cvpr.2011.5995347 · Cited by 2,440 · cited 1×
“Finally, domain adaptation has been shown to be important in learning from synthetic data (Ros et al. 2016; López et al. 2017; Torralba and Efros 2011); hence, we plan to apply domain adaptation techniques to our synthetic dataset.”
MethodRos, G., Sellart, L., Materzynska, J., Vazquez, D., & Lopez, A. M. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.352 · Cited by 2,338
ShapeNet: An Information-Rich 3D Model Repository
Chang, A. X., Funkhouser, T., Guibas, L., Hanrahan, P., Huang, Q., Li, Z., Savarese, S., Savva, M., Song, S., Su, H., et al. (2015) · arXiv · doi:10.48550/arxiv.1512.03012 · Cited by 2,330
Analysis of Representations for Domain Adaptation
Ben-David, S., Blitzer, J., Crammer, K., & Pereira, F. (2007) · Advances in Neural Information Processing Systems 19 · doi:10.7551/mitpress/7503.003.0022 · Cited by 2,019
Playing for Data: Ground Truth from Computer Games
Richter, S. R., Vineet, V., Roth, S., & Koltun, V. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-46475-6_7 · Cited by 1,815
Domain adaptation with structural correspondence learning
Blitzer, J., McDonald, R., & Pereira, F. (2006) · Proceedings of the 2006 Conference on Empirical Methods in Natural Language Processing - EMNLP '06 · doi:10.3115/1610075.1610094 · Cited by 1,543
Target-driven visual navigation in indoor scenes using deep reinforcement learning
Zhu, Y., Mottaghi, R., Kolve, E., Lim, J. J., Gupta, A., Fei-Fei, L., & Farhadi, A. (2017) · 2017 IEEE International Conference on Robotics and Automation (ICRA) · doi:10.1109/icra.2017.7989381 · Cited by 1,533 · cited 2×
“urthermore, a congurable pipeline may be used to generate various virtual environment in a controllable manner in order to train virtual agents situated in virtual environments to learn task planning [69, 155] and control policies [53, 130]. The importance of the different energy terms: In our experiments, the learned…”
BackgroundMethodSelf-citationVirtualWorlds as Proxy for Multi-object Tracking Analysis
Gaidon, A., Wang, Q., Cabon, Y., & Vig, E. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.470 · Cited by 1,079 · cited 1×
“…of training data for object detection and correspondence matching (Starketal.2010;SunandSaenko2014;SongandXiao2014; Fanello et al. 2014; Dosovitskiy et al. 2015; Peng et al. 2015; Zhou et al. 2016; Gaidon et al. 2016; Movshovitz-Attias et al. 2016;Qietal.2016),single-viewreconstruction(Huangetal.”
Deep convolutional neural fields for depth estimation from a single image
Liu, F., Shen, C., & Lin, G. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7299152 · Cited by 892
ElasticFusion: Dense SLAM Without A Pose Graph
Whelan, T., Leutenegger, S., Salas Moreno, R., Glocker, B., & Davison, A. (2015) · Robotics: Science and Systems XI · doi:10.15607/rss.2015.xi.001 · Cited by 835
Emergence of Locomotion Behaviours in Rich Environments
Heess, N., TB, D., Sriram, S., Lemmon, J., Merel, J., Wayne, G., Tassa, Y., Erez, T., Wang, Z., Eslami, S. M. A., et al. (2017) · arXiv · doi:10.48550/arxiv.1707.02286 · Cited by 657 · cited 1×
“Furthermore, a configurable pipeline may be used to generate various virtual environment in a controllable manner in order to train virtual agents situated in virtual environments to learn task planning (Lin et al. 2016; Zhu et al. 2017) and control policies (Heess et al. 2017; Wang et al. 2017).”
MethodHoiem, D., Efros, A. A., & Hebert, M. (2005) · ACM Transactions on Graphics · doi:10.1145/1073204.1073232 · Cited by 616
Anticipating Human Activities Using Object Affordances for Reactive Robotic Response
Koppula, H. S., & Saxena, A. (2016) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2015.2430335 · Cited by 596
Material recognition in the wild with the Materials in Context Database
Bell, S., Upchurch, P., Snavely, N., & Bala, K. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298970 · Cited by 516
Domain Adaptation: Learning Bounds and Algorithms
Mansour, Y., Mohri, M., & Rostamizadeh, A. (2009) · arXiv · doi:10.48550/arxiv.0902.3430 · Cited by 504 · cited 2×
“eader to a recent survey [21]. Traditionally, domain adaptation techniques can be divided into four categories:(i)covariateshiftwithsharedsupport[11, 20, 42, 51], (ii) learning shared representations [10, 12, 80], (iii) featurebased learning [22, 31, 131], and (iv) parameter-based learning [16, 23, 138, 141]. Given th…”
BackgroundSample Selection Bias Correction Theory
Cortes, C., Mohri, M., Riley, M., & Rostamizadeh, A. (2008) · Lecture Notes in Computer Science · doi:10.1007/978-3-540-87987-9_8 · Cited by 272
Marr Revisited: 2D-3D Alignment via Surface Normal Prediction
Bansal, A., Russell, B., & Gupta, A. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.642 · Cited by 213
Bell (2013) · doi:10.1145/2461912.2462002 · Cited by 200
Scene Parsing by Integrating Function, Geometry and Appearance Models
Zhao, Y., & Zhu, S.-C. (2013) · 2013 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2013.401 · Cited by 135
Self-citationHow Useful Is Photo-Realistic Rendering for Visual Learning?
Movshovitz-Attias, Y., Kanade, T., & Sheikh, Y. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-49409-8_18 · Cited by 118 · cited 2×
“Synthetic image datasets have recently been a source of training data for object detection and correspondence matching (Stark et al. 2010; Sun andSaenko2014;SongandXiao2014; Fanello et al. 2014; Dosovitskiy et al. 2015; Peng et al. 2015; Zhou et al. 2016; Gaidon et al. 2016;Movshovitz-Attias et al. 2016;Qi et al. 2016…”
Cited by
Gibson Env: Real-World Perception for Embodied Agents
Xia, F., Zamir, A. R., He, Z., Sax, A., Malik, J., & Savarese, S. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00945 · Cited by 763
3D Scene Graph: A Structure for Unified Semantics, 3D Space, and Camera
Armeni, I., He, Z.-Y., Zamir, A., Gwak, J., Malik, J., Fischer, M., & Savarese, S. (2019) · 2019 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00576 · Cited by 350
“Grammars that combine geometry, affordance and appearance have been used toward holistic scene parsing in images, where information about the scene and objects is captured in a hierarchical tree structure [11, 48, 21, 19].”
BackgroundHypersim: A Photorealistic Synthetic Dataset for Holistic Indoor Scene Understanding
Roberts, M., Ramapuram, J., Ranjan, A., Kumar, A., Bautista, M. A., Paczan, N., Webb, R., & Susskind, J. M. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.01073 · Cited by 358
“In response to this challenge, the computer vision community has developed several photorealistic synthetic datasets and interactive simulation environments that have spurred rapid progress towards the goal of holistic indoor scene understanding [5, 6, 8, 9, 13, 14, 17, 20, 22, 29, 31, 34, 35, 37, 41, 42, 43, 44, 47,…”
BackgroundKimera: From SLAM to spatial perception with 3D dynamic scene graphs
Rosinol, A., Violette, A., Abate, M., Hughes, N., Chang, Y., Shi, J., Gupta, A., & Carlone, L. (2021) · The International Journal of Robotics Research · doi:10.1177/02783649211056674 · Cited by 271
Diffusion-based Generation, Optimization, and Planning in 3D Scenes
Huang, S., Wang, Z., Li, P., Jia, B., Liu, T., Zhu, Y., Liang, W., & Zhu, S.-C. (2023) · 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52729.2023.01607 · Cited by 192
Self-citation
Metadata
- Authors
- Jiang, C., Qi, S., Zhu, Y., Huang, S., Lin, J., Yu, L.-F., Terzopoulos, D., & Zhu, S.-C.
- Venue
- International Journal of Computer Vision
- Published
- 2018-06-30
- Volume
- 126
- Issue
- 9
- Pages
- 920-941
- ISSN
- 0920-5691 (ISSN-L)
- 1573-1405
- OpenAlex
- W2808775391
- Cited by
- 79
- References
- 29
- FWCI
- 7.55
- Type
- journal article
- Language
- en
- Open access
- green
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
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.