swMATH ID: 43938
Software Authors: Mingyu Ding; Zhe Wang; Jiankai Sun; Jianping Shi; Ping Luo
Description: CamNet: Coarse-to-Fine Retrieval for Camera Re-Localization. Camera re-localization is an important but challenging task in applications like robotics and autonomous driving. Recently, retrieval-based methods have been considered as a promising direction as they can be easily generalized to novel scenes. Despite significant progress has been made, we observe that the performance bottleneck of previous methods actually lies in the retrieval module. These methods use the same features for both retrieval and relative pose regression tasks which have potential conflicts in learning. To this end, here we present a coarse-to-fine retrieval-based deep learning framework, which includes three steps, i.e., image-based coarse retrieval, pose-based fine retrieval and precise relative pose regression. With our carefully designed retrieval module, the relative pose regression task can be surprisingly simpler. We design novel retrieval losses with batch hard sampling criterion and two-stage retrieval to locate samples that adapt to the relative pose regression task. Extensive experiments show that our model (CamNet) outperforms the state-of-the-art methods by a large margin on both indoor and outdoor datasets.
Homepage: https://openaccess.thecvf.com/content_ICCV_2019/papers/Ding_CamNet_Coarse-to-Fine_Retrieval_for_Camera_Re-Localization_ICCV_2019_paper.pdf
Source Code:  https://github.com/dingmyu/CamNet
Dependencies: pytorch
Keywords: Cameras; Three-dimensional displays; Solid modeling; Task analysis; Predictive models; Training; Artificial neural networks
Related Software: ClusterFit; PWC-Net; Flickr30K; MeshLab; Face2Face; PoseCNN; NIMA; Make3D; EfficientNet; WSABIE; CIDEr; DISN; DVDnet; FaceNet; PointNet; MNIST; MVSNet; Fashion-MNIST; SynSin; PIFuHD
Cited in: 1 Publication

Cited by 1 Author

1 Szeliski, Richard

Citations by Year