Learning Dense Flow Field for Highly-accurate Cross-view Camera Localization
This paper addresses the problem of estimating the 3-DoF camera pose for a ground-level image with respect to a satellite image that encompasses the local surroundings. We propose a novel end-to-end approach that leverages the learning of dense pixel-wise flow fields in pairs of ground and satellite images to calculate the camera pose. Our approach differs from existing methods by constructing the feature metric at the pixel level, enabling full-image supervision for learning distinctive geometric configurations and visual appearances across views. Specifically, our method employs two distinct convolution networks for ground and satellite feature extraction. Then, we project the ground feature map to the bird's eye view (BEV) using a fixed camera height assumption to achieve preliminary geometric alignment. To further establish content association between the BEV and satellite features, we introduce a residual convolution block to refine the projected BEV feature. Optical flow estimation is performed on the refined BEV feature map and the satellite feature map using flow decoder networks based on RAFT. After obtaining dense flow correspondences, we apply the least square method to filter matching inliers and regress the ground camera pose. Extensive experiments demonstrate significant improvements compared to state-of-the-art methods. Notably, our approach reduces the median localization error by 89%, 19%, 80% and 35% on the KITTI, Ford multi-AV, VIGOR and Oxford RobotCar datasets, respectively.
Code (0)
등록된 구현이 없습니다.
Tasks
Camera LocalizationDecoderOptical Flow EstimationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Flow Fields: Dense Correspondence Fields for Highly Accurate Large Displacement Optical Flow Estimation
Modern large displacement optical flow algorithms usually use an initialization by either sparse descriptor matching techniques or dense approximate nearest neighbor fields. While the latter have the advantage of being d…
Optical Flow EstimationFlow Fields: Dense Correspondence Fields for Highly Accurate Large Displacement Optical Flow Estimation
Modern large displacement optical flow algorithms usually use an initialization by either sparse descriptor matching techniques or dense approximate nearest neighbor fields. While the latter have the advantage of being d…
Optical Flow EstimationPatch MatchingEfficient Sparse-to-Dense Optical Flow Estimation Using a Learned Basis and Layers
We address the elusive goal of estimating optical flow both accurately and efficiently by adopting a sparse-to-dense approach. Given a set of sparse matches, we regress to dense optical flow using a learned set of full-f…
CPUOptical Flow EstimationNeural Multi-Scale Self-Supervised Registration for Echocardiogram Dense Tracking
Echocardiography has become routinely used in the diagnosis of cardiomyopathy and abnormal cardiac blood flow. However, manually measuring myocardial motion and cardiac blood flow from echocardiogram is time-consuming an…
Flow-NeRF: Joint Learning of Geometry, Poses, and Dense Flow within Unified Neural Representations
Learning accurate scene reconstruction without pose priors in neural radiance fields is challenging due to inherent geometric ambiguity. Recent development either relies on correspondence priors for regularization or use…
Depth EstimationNeRFNovel View SynthesisOptical Flow Estimation+1