FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3206941470> ?p ?o ?g. }

• W3206941470 abstract "Scene flow represents the motion of points in the 3D space, which is the counterpart of the optical flow that represents the motion of pixels in the 2D image. However, it is difficult to obtain the ground truth of scene flow in the real scenes, and recent studies are based on synthetic data for training. Therefore, how to train a scene flow network with unsupervised methods based on real-world data shows crucial significance. A novel unsupervised learning method for scene flow is proposed in this paper, which utilizes the images of two consecutive frames taken by monocular camera without the ground truth of scene flow for training. Our method realizes the goal that training scene flow network with real-world data, which bridges the gap between training data and test data and broadens the scope of available data for training. Unsupervised learning of scene flow in this paper mainly consists of two parts: (i) depth estimation and camera pose estimation, and (ii) scene flow estimation based on four different loss functions. Depth estimation and camera pose estimation obtain the depth maps and camera pose between two consecutive frames, which provide further information for the next scene flow estimation. After that, we used depth consistency loss, dynamic-static consistency loss, Chamfer loss, and Laplacian regularization loss to carry out unsupervised training of the scene flow network. To our knowledge, this is the first paper that realizes the unsupervised learning of 3D scene flow from monocular camera. The experiment results on KITTI show that our method for unsupervised learning of scene flow meets great performance compared to traditional methods Iterative Closest Point (ICP) and Fast Global Registration (FGR). The source code is available at: https://github.com/IRMVLab/3DUnMonoFlow." @default.
• W3206941470 created "2021-10-25" @default.
• W3206941470 creator A5012669482 @default.
• W3206941470 creator A5023336774 @default.
• W3206941470 creator A5046939338 @default.
• W3206941470 creator A5054513966 @default.
• W3206941470 date "2021-05-30" @default.
• W3206941470 modified "2023-10-14" @default.
• W3206941470 title "Unsupervised Learning of 3D Scene Flow from Monocular Camera" @default.
• W3206941470 cites W1921093919 @default.
• W3206941470 cites W1993850091 @default.
• W3206941470 cites W2083624955 @default.
• W3206941470 cites W2088692258 @default.
• W3206941470 cites W2098500213 @default.
• W3206941470 cites W2115579991 @default.
• W3206941470 cites W2342511487 @default.
• W3206941470 cites W2493152400 @default.
• W3206941470 cites W2560474170 @default.
• W3206941470 cites W2562619173 @default.
• W3206941470 cites W2563098792 @default.
• W3206941470 cites W2604909019 @default.
• W3206941470 cites W2737996100 @default.
• W3206941470 cites W2770902190 @default.
• W3206941470 cites W2779333428 @default.
• W3206941470 cites W2887479417 @default.
• W3206941470 cites W2894983388 @default.
• W3206941470 cites W2904340070 @default.
• W3206941470 cites W2962771259 @default.
• W3206941470 cites W2962864875 @default.
• W3206941470 cites W2963345294 @default.
• W3206941470 cites W2963583471 @default.
• W3206941470 cites W2963652593 @default.
• W3206941470 cites W2963891416 @default.
• W3206941470 cites W2964968086 @default.
• W3206941470 cites W2971686478 @default.
• W3206941470 cites W2984858187 @default.
• W3206941470 cites W2986519585 @default.
• W3206941470 cites W3004148335 @default.
• W3206941470 cites W3004347365 @default.
• W3206941470 cites W3007774126 @default.
• W3206941470 cites W3013659224 @default.
• W3206941470 cites W3016861202 @default.
• W3206941470 cites W3034642839 @default.
• W3206941470 cites W3100388886 @default.
• W3206941470 cites W3122159272 @default.
• W3206941470 cites W3150327674 @default.
• W3206941470 cites W764651262 @default.
• W3206941470 doi "https://doi.org/10.1109/icra48506.2021.9561572" @default.
• W3206941470 hasPublicationYear "2021" @default.
• W3206941470 type Work @default.
• W3206941470 sameAs 3206941470 @default.
• W3206941470 citedByCount "6" @default.
• W3206941470 countsByYear W32069414702022 @default.
• W3206941470 countsByYear W32069414702023 @default.
• W3206941470 crossrefType "proceedings-article" @default.
• W3206941470 hasAuthorship W3206941470A5012669482 @default.
• W3206941470 hasAuthorship W3206941470A5023336774 @default.
• W3206941470 hasAuthorship W3206941470A5046939338 @default.
• W3206941470 hasAuthorship W3206941470A5054513966 @default.
• W3206941470 hasBestOaLocation W32069414702 @default.
• W3206941470 hasConcept C115961682 @default.
• W3206941470 hasConcept C146849305 @default.
• W3206941470 hasConcept C154945302 @default.
• W3206941470 hasConcept C155542232 @default.
• W3206941470 hasConcept C31972630 @default.
• W3206941470 hasConcept C41008148 @default.
• W3206941470 hasConcept C8038995 @default.
• W3206941470 hasConceptScore W3206941470C115961682 @default.
• W3206941470 hasConceptScore W3206941470C146849305 @default.
• W3206941470 hasConceptScore W3206941470C154945302 @default.
• W3206941470 hasConceptScore W3206941470C155542232 @default.
• W3206941470 hasConceptScore W3206941470C31972630 @default.
• W3206941470 hasConceptScore W3206941470C41008148 @default.
• W3206941470 hasConceptScore W3206941470C8038995 @default.
• W3206941470 hasFunder F4320321881 @default.
• W3206941470 hasLocation W32069414701 @default.
• W3206941470 hasLocation W32069414702 @default.
• W3206941470 hasOpenAccess W3206941470 @default.
• W3206941470 hasPrimaryLocation W32069414701 @default.
• W3206941470 hasRelatedWork W1935875823 @default.
• W3206941470 hasRelatedWork W2097144653 @default.
• W3206941470 hasRelatedWork W2123374136 @default.
• W3206941470 hasRelatedWork W2171116555 @default.
• W3206941470 hasRelatedWork W2900363363 @default.
• W3206941470 hasRelatedWork W2950629728 @default.
• W3206941470 hasRelatedWork W3004355449 @default.
• W3206941470 hasRelatedWork W3098068165 @default.
• W3206941470 hasRelatedWork W4281553171 @default.
• W3206941470 hasRelatedWork W4294975180 @default.
• W3206941470 isParatext "false" @default.
• W3206941470 isRetracted "false" @default.
• W3206941470 magId "3206941470" @default.
• W3206941470 workType "article" @default.