The DOI matches its Crossref record; 10 of the 10 references it cites were found in a registry or an index.
MegaDepth: Learning Single-View Depth Prediction from Internet Photos
Open accessAbstract
Single-view depth prediction is a fundamental problem in computer vision. Recently, deep learning methods have led to significant progress, but such methods are limited by the available training data. Current datasets based on 3D sensors have key limitations, including indoor-only images (NYU), small numbers of training examples (Make3D), and sparse sampling (KITTI). We propose to use multi-view Internet photo collections, a virtually unlimited data source, to generate training data via modern structure-from-motion and multi-view stereo (MVS) methods, and present a large depth dataset called MegaDepth based on this idea. Data derived from MVS comes with its own challenges, including noise and unreconstructable objects. We address these challenges with new data cleaning methods, as well as automatically augmenting our data with ordinal depth relations generated using semantic segmentation. We validate the use of large amounts of Internet data by showing that models trained on MegaDepth exhibit strong generalization-not only to novel scenes, but also to other diverse datasets including Make3D, KITTI, and DIW, even when no images from those datasets are seen during training.
Overview
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
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
Adam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946
Are we ready for autonomous driving? The KITTI vision benchmark suite
Geiger, A., Lenz, P., & Urtasun, R. (2012) · 2012 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2012.6248074 · Cited by 14,897
Structure-from-Motion Revisited
Schonberger, J. L., & Frahm, J.-M. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.445 · Cited by 6,433
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
Unsupervised Monocular Depth Estimation with Left-Right Consistency
Godard, C., Aodha, O. M., & Brostow, G. J. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.699 · Cited by 3,270
Unsupervised Learning of Depth and Ego-Motion from Video
Zhou, T., Brown, M., Snavely, N., & Lowe, D. G. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.700 · Cited by 2,910
Self-citationObject scene flow for autonomous vehicles
Menze, M., & Geiger, A. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298925 · Cited by 2,270
Unsupervised CNN for Single View Depth Estimation: Geometry to the Rescue
Garg, R., B.G., V. K., Carneiro, G., & Reid, I. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-46484-8_45 · Cited by 1,632
Unsupervised CNN for Single View Depth Estimation: Geometry to the Rescue
Garg, R., BG, V. K., Carneiro, G., & Reid, I. (2016) · arXiv · doi:10.48550/arxiv.1603.04992 · Cited by 1,632
Discrete-Continuous Depth Estimation from a Single Image
Liu, M., Salzmann, M., & He, X. (2014) · 2014 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2014.97 · Cited by 381
Research works printed but not linked: 35
- xu, 2017, Multiscale continuous CRFs as sequential deep networks for monocular depth estimation, Proc Computer Vision and Pattern Recognition (CVPR)
- xie, 2016, Deep3D: Fully automatic 2D-to-3D video conversion with deep convolutional neural networks, Proc European Conf on Computer Vision (ECCV)
- 10.1109/ICCVW.2011.6130298 · DOI · Paper page
- schönberger, 2016, Pixelwise view selection for unstructured multi-view stereo, Proc European Conf on Computer Vision (ECCV), 501
- 10.1109/CVPR.2015.7299148 · DOI
- 10.1109/3DV.2013.25 · DOI · Paper page
- 10.1109/CVPR.2017.596 · DOI · Paper page
- 10.1145/1141911.1141964 · DOI · Paper page
- zhang, 2014, Personal photograph enhancement using internet photo collections, IEEE Trans Visualization and Computer Graphics
- 10.1145/2231816.2231817 · DOI
- 10.1109/ICCV.2007.4408933 · DOI · Paper page
- 10.1109/ICCV.2005.107 · DOI · Paper page
- 10.1007/978-3-642-33715-4_56 · DOI · Paper page
- knapitsch, 2017, Tanks and temples: Benchmarking large-scale scene reconstruction, ACM Trans Graphics, 36, 10.1145/3072959.3073599 · DOI · Paper page
- 10.1109/3DV.2016.32 · DOI · Paper page
- saxena, 2005, Learning depth from single monocular images, Neural Information Processing Systems, 18, 1
- chen, 2016, Single-image depth perception in the wild, Neural Information Processing Systems, 730
- 10.1109/CVPR.2016.594 · DOI · Paper page
- 10.1109/WACV.2016.7477699 · DOI
- 10.1109/ICCV.2015.304 · DOI · Paper page
- 10.1109/TPAMI.2008.132 · DOI · Paper page
- 10.1109/ICCV.2017.173 · DOI
- frahm, 2010, Building Rome on a cloudless day, Proc European Conf on Computer Vision (ECCV)
- eigen, 2014, Depth map prediction from a single image using a multi -scale deep network, Neural Information Processing Systems, 2366
- 10.1109/ICCV.2009.5459148 · DOI · Paper page
- 10.1109/CVPR.2010.5539802 · DOI · Paper page
- 2016, PyTorch
- li, 2015, Depth and surface normal estimation from monocular images using regression on deep features and hierarchical CRFs, Proc Computer Vision and Pattern Recognition (CVPR), 1119
- liu, 2015, Deep convolutional neural fields for depth estimation from a single image, Proc Computer Vision and Pattern Recognition (CVPR)
- li, 2016, Worldwide pose estimation using 3D point clouds, Large-Scale Visual Geo-Localization, 147, 10.1007/978-3-319-25781-5_8 · DOI
- 10.1109/CVPR.2017.544 · DOI · Paper page
- 10.1109/CVPR.2017.660 · DOI · Paper page
- 10.1109/TPAMI.2015.2505283 · DOI · Paper page
- 10.1109/ICCV.2015.52 · DOI · Paper page
- 10.1109/ICCV.2017.558 · DOI
Cited by
Digging Into Self-Supervised Monocular Depth Estimation
Godard, C., Aodha, O. M., Firman, M., & Brostow, G. (2019) · 2019 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00393 · Cited by 2,561
Vision Transformers for Dense Prediction
Ranftl, R., Bochkovskiy, A., & Koltun, V. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.01196 · Cited by 2,373
LoFTR: Detector-Free Local Feature Matching with Transformers
Sun, J., Shen, Z., Wang, Y., Bao, H., & Zhou, X. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr46437.2021.00881 · Cited by 1,719
Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-Shot Cross-Dataset Transfer
Ranftl, R., Lasinger, K., Hafner, D., Schindler, K., & Koltun, V. (2022) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2020.3019967 · Cited by 1,618
Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data
Yang, L., Kang, B., Huang, Z., Xu, X., Feng, J., & Zhao, H. (2024) · 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52733.2024.00987 · Cited by 1,296
Metadata
- Authors
- Li, Z., & Snavely, N.
- Venue
- 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition
- Publisher
- IEEE
- Published
- 2018-06
- Pages
- 2041-2050
- ISSN
- 1063-6919 (ISSN-L)
- OpenAlex
- W2963760790
- Cited by
- 1,135
- References
- 10
- FWCI
- 25.38
- Type
- conference paper
- 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
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: MegaDepth: Learning Single-View Depth Prediction from Internet Photos. https://app.cochat.ai/papers/10.1109/cvpr.2018.00218
- The paper
- Li, Z., & Snavely, N. (2018). MegaDepth: Learning Single-View Depth Prediction from Internet Photos. 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. https://doi.org/10.1109/cvpr.2018.00218
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.