The DOI matches its Crossref record; 16 of the 16 references it cites were found in a registry or an index.
Structure-Guided Ranking Loss for Single Image Depth Prediction
Abstract
Single image depth prediction is a challenging task due to its ill-posed nature and challenges with capturing ground truth for supervision. Large-scale disparity data generated from stereo photos and 3D videos is a promising source of supervision, however, such disparity data can only approximate the inverse ground truth depth up to an affine transformation. To more effectively learn from such pseudo-depth data, we propose to use a simple pair-wise ranking loss with a novel sampling strategy. Instead of randomly sampling point pairs, we guide the sampling to better characterize structure of important regions based on the low-level edge maps and high-level object instance masks. We show that the pair-wise ranking loss, combined with our structure-guided sampling strategies, can significantly improve the quality of depth map prediction. In addition, we introduce a new relative depth dataset of about 21K diverse high-resolution web stereo photos to enhance the generalization ability of our model. In experiments, we conduct cross-dataset evaluation on six benchmark datasets and show that our method consistently improves over the baselines, leading to superior quantitative and qualitative results.
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
Vision meets robotics: The KITTI dataset
Geiger, A., Lenz, P., Stiller, C., & Urtasun, R. (2013) · The International Journal of Robotics Research · doi:10.1177/0278364913491297 · Cited by 9,913
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 · cited 1×
“The key idea behind these methods [9, 12, 17, 35, 40] is the image reconstruction loss for view synthesis, requiring calibrated stereo pairs or video sequences for training.”
MethodUnsupervised 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
Eigen, D., & Fergus, R. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.304 · Cited by 2,862
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
Deep Ordinal Regression Network for Monocular Depth Estimation
Fu, H., Gong, M., Wang, C., Batmanghelich, K., & Tao, D. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00214 · Cited by 1,991
A Naturalistic Open Source Movie for Optical Flow Evaluation
Butler, D. J., Wulff, J., Stanley, G. B., & Black, M. J. (2012) · Lecture Notes in Computer Science · doi:10.1007/978-3-642-33783-3_44 · Cited by 1,842
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 · cited 1×
“The key idea behind these methods [9, 12, 17, 35, 40] is the image reconstruction loss for view synthesis, requiring calibrated stereo pairs or video sequences for training.”
MethodUnsupervised 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
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
A Multi-view Stereo Benchmark with High-Resolution Images and Multi-camera Videos
Schops, T., Schonberger, J. L., Galliani, S., Sattler, T., Schindler, K., Pollefeys, M., & Geiger, A. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.272 · Cited by 915
Semi-Supervised Deep Learning for Monocular Depth Map Prediction
Kuznietsov, Y., Stuckler, J., & Leibe, B. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.238 · Cited by 680
Self-Supervised Monocular Depth Hints
Watson, J., Firman, M., Brostow, G., & Turmukhambetov, D. (2019) · 2019 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00225 · Cited by 275 · cited 1×
“The key idea behind these methods [9, 12, 17, 35, 40] is the image reconstruction loss for view synthesis, requiring calibrated stereo pairs or video sequences for training.”
MethodMonocular Relative Depth Perception with Web Stereo Data Supervision
Xian, K., Shen, C., Cao, Z., Lu, H., Xiao, Y., Li, R., & Luo, Z. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00040 · Cited by 215
Self-citationWeb Stereo Video Supervision for Depth Prediction from Dynamic Scenes
Wang, C., Lucey, S., Perazzi, F., & Wang, O. (2019) · 2019 International Conference on 3D Vision (3DV) · doi:10.1109/3dv.2019.00046 · Cited by 103 · cited 6×
“Similar to prior work [33, 36], we use FlowNet2.”
BackgroundMethodResultInfluentialSelf-citation
Research works printed but not linked: 26
- 10.1109/ICCV.2019.00578 · DOI · Paper page
- dan xu, 0, Structured attention guided convolutional neural fields for monocular depth estimation, Proc Computer Vision and Pattern Recognition (CVPR)
- igor, 2019, Diode A dense indoor and outdoor depth dataset
- uhrig, 0, Sparsity invariant cnns, Proc IEEE Int Conf 3D Vis (3DV)
- 10.1109/IROS.2012.6385773 · DOI · Paper page
- 10.1109/CVPR.2018.00077 · DOI · Paper page
- 10.1145/3272127.3275013 · DOI
- 10.1109/ICCV.2019.00772 · DOI
- 10.1109/ICCV.2017.322 · DOI · Paper page
- 10.1109/CVPR.2017.179 · DOI · Paper page
- 10.1109/TPAMI.2014.2316835 · DOI · Paper page
- koch, 0, Evaluation of cnn-based single-image depth estimation methods, Proc European Conf on Computer Vision Workshop (ECCV-WS), 331
- 10.1109/3DV.2016.32 · DOI · Paper page
- lasinger, 2019, Towards robust monocular depth estimation Mixing datasets for zero-shot cross-dataset transfer
- 10.1109/CVPR.2019.00575 · DOI
- 10.1109/TPAMI.2008.132 · DOI · Paper page
- chen, 0, Single-image depth perception in the wild, Advances in neural information processing systems, 730
- eigen, 0, Depth map prediction from a single image using a multi-scale deep network, Advances in neural information processing systems
- chakrabarti, 2016, Depth from a single image by harmonizing overcomplete local network predictions, Advances in neural information processing systems
- 10.1109/CVPR.2018.00042 · DOI · Paper page
- 10.1109/CVPR.2018.00218 · DOI · Paper page
- 10.1109/CVPR.2019.00465 · DOI · Paper page
- liu, 2015, Learning depth from single monocular images using deep convolutional neural fields, Trans Pattern Analysis and Machine Intelligence
- 10.1109/ICCV.2015.52 · DOI · Paper page
- 10.1109/CVPR.2010.5539823 · DOI · Paper page
- 10.1109/CVPR.2018.00037 · DOI · Paper page
Cited by
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
“Similar to [32], we first pretrain on a well-curated subset of the data [47, 48, 49] for 60 epochs before training on the full dataset.”
MethodDepth 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
“Following this, many works consistently improve the depth estimation accuracy by carefully designing the regression task as a classification task [3, 34], introducing more priors [32, 53, 75, 82], and better objective functions [67, 77], etc .”
Hu, M., Yin, W., Zhang, C., Cai, Z., Long, X., Chen, H., Wang, K., Yu, G., Shen, C., & Shen, S. (2024) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2024.3444912 · Cited by 260
Single image depth estimation: An overview
Mertan, A., Duff, D. J., & Unal, G. (2022) · Digital Signal Processing · doi:10.1016/j.dsp.2022.103441 · Cited by 121
Metadata
- Authors
- Xian, K., Zhang, J., Wang, O., Mai, L., Lin, Z., & Cao, Z.
- Venue
- 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
- Publisher
- IEEE
- Published
- 2020-06
- Pages
- 608-617
- ISSN
- 1063-6919 (ISSN-L)
- OpenAlex
- W3035563424
- Cited by
- 192
- References
- 16
- FWCI
- 9.65
- 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
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.