End-to-End Learnable Geometric Vision by Backpropagating PnP Optimization
Open accessThe DOI matches its Crossref record; 17 of the 17 references it cites were found in a registry or an index.
Abstract
Deep networks excel in learning patterns from large amounts of data. On the other hand, many geometric vision tasks are specified as optimization problems. To seamlessly combine deep learning and geometric vision, it is vital to perform learning and geometric optimization end-to-end. Towards this aim, we present BPnP, a novel network module that backpropagates gradients through a Perspective-n-Points (PnP) solver to guide parameter updates of a neural network. Based on implicit differentiation, we show that the gradients of a ``self-contained" PnP solver can be derived accurately and efficiently, as if the optimizer block were a differentiable function. We validate BPnP by incorporating it in a deep model that can learn camera intrinsics, camera extrinsics (poses) and 3D structure from training datasets. Further, we develop an end-to-end trainable pipeline for object pose estimation, which achieves greater accuracy by combining feature-based heatmap losses with 2D-3D reprojection errors. Since our approach can be extended to other optimization problems, our work helps to pave the way to perform learnable geometric vision in a principled manner. Our PyTorch implementation of BPnP is available on http://github.com/BoChenYS/BPnP.
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 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
LeCun, Y., Bengio, Y., & Hinton, G. (2015) · Nature · doi:10.1038/nature14539 · Cited by 84,126
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
Deep High-Resolution Representation Learning for Human Pose Estimation
Sun, K., Xiao, B., Liu, D., & Wang, J. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00584 · Cited by 5,984 · cited 1×
“We use HRNet [44] as the backbone to predict the landmark heatmaps Φ .”
MethodDepth 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
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 · cited 1×
“Some of these works [17, 11, 24] can only impose constraints on pairs of images, while others [57, 49] learn the structure and the motion in different network branches and do not impose explicit geometric constraints.”
BackgroundPoseNet: A Convolutional Network for Real-Time 6-DOF Camera Relocalization
Kendall, A., Grimes, M., & Cipolla, R. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.336 · Cited by 2,489
PoseCNN: A Convolutional Neural Network for 6D Object Pose Estimation in Cluttered Scenes
Xiang, Y., Schmidt, T., Narayanan, V., & Fox, D. (2018) · Robotics: Science and Systems XIV · doi:10.15607/rss.2018.xiv.019 · Cited by 2,139
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
Geometric Loss Functions for Camera Pose Regression with Deep Learning
Kendall, A., & Cipolla, R. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.694 · Cited by 803 · cited 2×
“On the other extreme, end-to-end methods have been devised [23, 21, 22, 8, 32, 50, 52, 9] that bypass geometric optimization, by using fully connected layers to compute the geometric quantity (e.g., 6DOF camera pose) from a feature map derived from previous layers.”
Background
Cited by
GDR-Net: Geometry-Guided Direct Regression Network for Monocular 6D Object Pose Estimation
Wang, G., Manhardt, F., Tombari, F., & Ji, X. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr46437.2021.01634 · Cited by 462
Back to the Feature: Learning Robust Camera Localization from Pixels to Pose
Sarlin, P.-E., Unagar, A., Larsson, M., Germain, H., Toft, C., Larsson, V., Pollefeys, M., Lepetit, V., Hammarstrand, L., Kahl, F., et al. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr46437.2021.00326 · Cited by 297
Occlusion-Aware Self-Supervised Monocular 6D Object Pose Estimation
Wang, G., Manhardt, F., Liu, X., Ji, X., & Tombari, F. (2024) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2021.3136301 · Cited by 69
Pérez-Villar, J. I. B., García-Martín, Á., Bescós, J., & Escudero-Viñolo, M. (2024) · IEEE Transactions on Aerospace and Electronic Systems · doi:10.1109/taes.2023.3306731 · Cited by 22
A Lightweight Model for Satellite Pose Estimation
Carcagnì, P., Leo, M., Spagnolo, P., Mazzeo, P. L., & Distante, C. (2022) · Lecture Notes in Computer Science · doi:10.1007/978-3-031-06427-2_1 · Cited by 6
Metadata
- Authors
- Chen, B., Parra, A., Cao, J., Li, N., & Chin, T.-J.
- Venue
- 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
- Publisher
- IEEE
- Published
- 2020-06
- Pages
- 8097-8106
- ISSN
- 1063-6919 (ISSN-L)
- OpenAlex
- W3035217469
- Cited by
- 104
- References
- 17
- FWCI
- 5.03
- 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: End-to-End Learnable Geometric Vision by Backpropagating PnP Optimization. https://app.cochat.ai/papers/10.1109/cvpr42600.2020.00812
- The paper
- Chen, B., Parra, A., Cao, J., Li, N., & Chin, T.-J. (2020). End-to-End Learnable Geometric Vision by Backpropagating PnP Optimization. 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). https://doi.org/10.1109/cvpr42600.2020.00812
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.