Towards Better Generalization: Joint Depth-Pose Learning Without PoseNet
Open accessThe DOI matches its Crossref record; 30 of the 30 references it cites were found in a registry or an index.
Abstract
In this work, we tackle the essential problem of scale inconsistency for self supervised joint depth-pose learning. Most existing methods assume that a consistent scale of depth and pose can be learned across all input samples, which makes the learning problem harder, resulting in degraded performance and limited generalization in indoor environments and long-sequence visual odometry application. To address this issue, we propose a novel system that explicitly disentangles scale from the network estimation. Instead of relying on PoseNet architecture, our method recovers relative pose by directly solving fundamental matrix from dense optical flow correspondence and makes use of a two-view triangulation module to recover an up-to-scale 3D structure. Then, we align the scale of the depth prediction with the triangulated point cloud and use the transformed depth map for depth error computation and dense reprojection check. Our whole system can be jointly trained end-to-end. Extensive experiments show that our system not only reaches state-of-the-art performance on KITTI depth and flow estimation, but also significantly improves the generalization ability of existing self-supervised depth-pose learning methods under a variety of challenging scenarios, and achieves state-of-the-art results among self-supervised learning-based methods on KITTI Odometry and NYUv2 dataset. Furthermore, we present some interesting findings on the limitation of PoseNet-based relative pose estimation methods in terms of generalization ability. Code is available at https://github.com/B1ueber2y/TrianFlow.
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
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474
Adam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946
Image quality assessment: from error visibility to structural similarity
Wang, Z., Bovik, A. C., Sheikh, H. R., & Simoncelli, E. P. (2004) · IEEE Transactions on Image Processing · doi:10.1109/tip.2003.819861 · Cited by 57,892
Fischler, M. A., & Bolles, R. C. (1981) · Communications of the ACM · doi:10.1145/358669.358692 · Cited by 25,893
Object recognition from local scale-invariant features
Lowe, D. G. (1999) · Proceedings of the Seventh IEEE International Conference on Computer Vision · doi:10.1109/iccv.1999.790410 · Cited by 16,472
SURF: Speeded Up Robust Features
Bay, H., Tuytelaars, T., & Van Gool, L. (2006) · Lecture Notes in Computer Science · doi:10.1007/11744023_32 · Cited by 14,955
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 · cited 4×
“We first validate our design on KITTI dataset [13], then conduct extensive experiments on KITTI Odometry, NYUv2 [49] and TUM-RGBD [50] datasets to demonstrate the robustness and generalization ability of our proposed system.”
BackgroundMethodResultInfluentialORB: An efficient alternative to SIFT or SURF
Rublee, E., Rabaud, V., Konolige, K., & Bradski, G. (2011) · 2011 International Conference on Computer Vision · doi:10.1109/iccv.2011.6126544 · Cited by 11,037
Horn, B. K. P., & Schunck, B. G. (1981) · Artificial Intelligence · doi:10.1016/0004-3702(81)90024-2 · Cited by 10,312
ORB-SLAM2: An Open-Source SLAM System for Monocular, Stereo, and RGB-D Cameras
Mur-Artal, R., & Tardos, J. D. (2017) · IEEE Transactions on Robotics · doi:10.1109/tro.2017.2705103 · Cited by 6,898 · cited 5×
“earning systems. Although our dense correspondence is learned in an unsupervised manner and no local BA and mapping are used at inference, we achieve comparable results with conventional SLAM systems [39]. Figure5shows the recovered trajectories on two tested sequences respectively. 4.4. Generalization on Unseen Ego-m…”
MethodInfluential
Cited by
SurroundOcc: Multi-Camera 3D Occupancy Prediction for Autonomous Driving
Wei, Y., Zhao, L., Zheng, W., Zhu, Z., Zhou, J., & Lu, J. (2023) · 2023 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.01986 · Cited by 260
Wang, K., Ma, S., Chen, J., Ren, F., & Lu, J. (2022) · IEEE Transactions on Cognitive and Developmental Systems · doi:10.1109/tcds.2020.3038898 · Cited by 114
“based methods, most of them use depth and optical flow to assist the training process [96], [104]–[106].”
MethodApproaching the Real-World: Supporting Activity Recognition Training with Virtual IMU Data
Kwon, H., Wang, B., Abowd, G. D., & Plötz, T. (2021) · Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies · doi:10.1145/3478096 · Cited by 48
“Similarly to when filtering out erroneous 3D pose calibrations, we measure the changes in translation and orientation from the estimated camera egomotion [116] by using SLERP [87] and Kalman filter and discard frames that violate smooth egomotion transitions.”
MethodSelf-Supervised 3D Keypoint Learning for Ego-motion Estimation
Tang, J., Ambrus, R., Guizilini, V., Pillai, S., Kim, H., Jensfelt, P., & Gaidon, A. (2019) · arXiv · doi:10.48550/arxiv.1912.03426 · Cited by 14
Metadata
- Authors
- Zhao, W., Liu, S., Shu, Y., & Liu, Y.-J.
- Venue
- 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
- Publisher
- IEEE
- Published
- 2020-06
- Pages
- 9148-9158
- ISSN
- 1063-6919 (ISSN-L)
- OpenAlex
- W3034364596
- Cited by
- 179
- References
- 30
- FWCI
- 9.65
- 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: Towards Better Generalization: Joint Depth-Pose Learning Without PoseNet. https://app.cochat.ai/papers/10.1109/cvpr42600.2020.00917
- The paper
- Zhao, W., Liu, S., Shu, Y., & Liu, Y.-J. (2020). Towards Better Generalization: Joint Depth-Pose Learning Without PoseNet. 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). https://doi.org/10.1109/cvpr42600.2020.00917
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.