SceneNet RGB-D: Can 5M Synthetic Images Beat Generic ImageNet Pre-training on Indoor Segmentation?
Abstract
We introduce SceneNet RGB-D, a dataset providing pixel-perfect ground truth for scene understanding problems such as semantic segmentation, instance segmentation, and object detection. It also provides perfect camera poses and depth data, allowing investigation into geometric computer vision problems such as optical flow, camera pose estimation, and 3D scene labelling tasks. Random sampling permits virtually unlimited scene configurations, and here we provide 5M rendered RGB-D images from 16K randomly generated 3D trajectories in synthetic layouts, with random but physically simulated object configurations. We compare the semantic segmentation performance of network weights produced from pretraining on RGB images from our dataset against generic VGG-16 ImageNet weights. After fine-tuning on the SUN RGB-D and NYUv2 real-world datasets we find in both cases that the synthetically pre-trained network outperforms the VGG-16 weights. When synthetic pre-training includes a depth channel (something ImageNet cannot natively provide) the performance is greater still. This suggests that large-scale high-quality synthetic RGB datasets with task-specific labels can be more useful for pretraining than real-world generic pre-training such as ImageNet. We host the dataset at http://robotvault. bitbucket.io/scenenet-rgbd.html.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
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?
Most existing robotics datasets only have a handful of fixed artist-designed scene layouts which limits the types of relations that can be generated.
“Most existing robotics datasets [47, 48, 49, 50] only have a handful of fixed artist-designed scene layouts which limits the types of relations that can be generated.”
From RoboPoint: A Vision-Language Model for Spatial Affordance Prediction for Robotics (2024) · cites this paper as [47]
Cites
ImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155 · see citing works
U-Net: Convolutional Networks for Biomedical Image Segmentation
Ronneberger, O., Fischer, P., & Brox, T. (2015) · Lecture notes in computer science · doi:10.1007/978-3-319-24574-4_28 · Cited by 99,404 · see citing works
Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification
He, K., Zhang, X., Ren, S., & Sun, J. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.123 · Cited by 19,741 · see citing works
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 · see citing works
Flownet: 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 · see citing works
Ros, 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 · see citing works
SUN RGB-D: A RGB-D scene understanding benchmark suite
Song, S., Lichtenberg, S. P., & Xiao, J. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298655 · Cited by 1,943 · see citing works
VirtualWorlds 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 · see citing works
Flagged first, then by citations
Cited by
Sorted by citations
SemanticKITTI: A Dataset for Semantic Scene Understanding of LiDAR Sequences
Behley, J., Garbade, M., Milioto, A., Quenzel, J., Behnke, S., Stachniss, C., & Gall, J. (2019) · 2019 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00939 · Cited by 2,294 · see citing works
Data augmentation: A comprehensive survey of modern approaches
Mumuni, A., & Mumuni, F. (2022) · Array · doi:10.1016/j.array.2022.100258 · Cited by 891 · see citing works
TartanAir: A Dataset to Push the Limits of Visual SLAM
Wang, W., Zhu, D., Wang, X., Hu, Y., Qiu, Y., Wang, C., Hu, Y., Kapoor, A., & Scherer, S. (2020) · 2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros45743.2020.9341801 · Cited by 456 · see citing works
Hypersim: 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 · see citing works
Efficient RGB-D Semantic Segmentation for Indoor Scene Analysis
Seichter, D., Kohler, M., Lewandowski, B., Wengefeld, T., & Gross, H.-M. (2021) · 2021 IEEE International Conference on Robotics and Automation (ICRA) · doi:10.1109/icra48506.2021.9561675 · Cited by 330 · see citing works
3D-FRONT: 3D Furnished Rooms with layOuts and semaNTics
Fu, H., Cai, B., Gao, L., Zhang, L.-X., Wang, J., Li, C., Zeng, Q., Sun, C., Jia, R., Zhao, B., et al. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.01075 · Cited by 267 · see citing works
What Makes Good Synthetic Training Data for Learning Disparity and Optical Flow Estimation?
Mayer, N., Ilg, E., Fischer, P., Hazirbas, C., Cremers, D., Dosovitskiy, A., & Brox, T. (2018) · International Journal of Computer Vision · doi:10.1007/s11263-018-1082-6 · Cited by 191 · see citing works
RoboPoint: A Vision-Language Model for Spatial Affordance Prediction for Robotics
Yuan, W., Duan, J., Blukis, V., Pumacay, W., Krishna, R., Murali, A., Mousavian, A., & Fox, D. (2024) · arXiv · doi:10.48550/arxiv.2406.10721 · Cited by 7 · see citing works
- Authors
- McCormac, J., Handa, A., Leutenegger, S., & Davison, A. J.
- Affiliations
- Imperial College London (GB)
- Venue
- 2017 IEEE International Conference on Computer Vision (ICCV)
- Publisher
- IEEE
- Published
- 2017-10
- Pages
- 2697-2706
- OpenAlex
- W2780351918
- Cited by
- 291
- References
- 8
- Citations by year
- 2026: 8 · 2025: 19 · 2024: 26 · 2023: 38 · 2022: 31 · 2021: 52 · 2020: 43 · 2019: 43 · 2018: 30 · 2017: 1
- FWCI
- 9.29
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- IEEE/CVF International Conference on Computer Vision (ICCV) (publishedVersion)
- Spiral (Imperial College London) (submittedVersion)
- Topics
- 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
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Vision and Imaging
- Keywords
- scene understanding, instance segmentation, object detection, camera pose estimation, optical flow, fine-tuning, SUN RGB-D, NYUv2
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
