Matches in SemOpenAlex for { <https://semopenalex.org/work/W4320001373> ?p ?o ?g. }
Showing items 1 to 70 of
70
with 100 items per page.
- W4320001373 endingPage "10" @default.
- W4320001373 startingPage "6" @default.
- W4320001373 abstract "Image registration is a basic task in computer vision, for its wide potential applications in image stitching, stereo vision, motion estimation, and etc. Most current methods achieve image registration by estimating a global homography matrix between candidate images with point-feature-based matching or direct prediction. However, as real-world 3D scenes have point-variant photograph distances (depth), a unified homography matrix is not sufficient to depict the specific pixel-wise relations between two images. Some researchers try to alleviate this problem by predicting multiple homography matrixes for different patches or segmentation areas in images; in this letter, we tackle this problem with further refinement, i.e. matching images with pixel-wise, depth-aware homography estimation. Firstly, we construct an efficient convolutional network, the <italic xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink>DPH-Net</i> , to predict the essential parameters causing image deviation, the rotation ( <inline-formula xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink><tex-math notation=LaTeX>$R$</tex-math></inline-formula> ) and translation ( <inline-formula xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink><tex-math notation=LaTeX>$T$</tex-math></inline-formula> ) of cameras. Then, we feed-in an image depth map for the calculation of initial pixel-wise homography matrixes, which are refined with an online optimization scheme. Finally, with the estimated pixel-specific homography parameters, pixel correspondences between candidate images can be easily computed for registration. Compared with state-of-the-art image registration algorithms, the proposed <italic xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink>DPH-Net</i> has the highest performance of 0.912 EPE and 0.977 SSIM, demonstrating the effectiveness of adding depth information and estimating pixel-wise homography into the image registration process." @default.
- W4320001373 created "2023-02-11" @default.
- W4320001373 creator A5022699091 @default.
- W4320001373 creator A5029721832 @default.
- W4320001373 creator A5044423422 @default.
- W4320001373 creator A5085717320 @default.
- W4320001373 date "2023-01-01" @default.
- W4320001373 modified "2023-09-23" @default.
- W4320001373 title "Deep Image Registration With Depth-Aware Homography Estimation" @default.
- W4320001373 doi "https://doi.org/10.1109/lsp.2023.3238274" @default.
- W4320001373 hasPublicationYear "2023" @default.
- W4320001373 type Work @default.
- W4320001373 citedByCount "0" @default.
- W4320001373 crossrefType "journal-article" @default.
- W4320001373 hasAuthorship W4320001373A5022699091 @default.
- W4320001373 hasAuthorship W4320001373A5029721832 @default.
- W4320001373 hasAuthorship W4320001373A5044423422 @default.
- W4320001373 hasAuthorship W4320001373A5085717320 @default.
- W4320001373 hasConcept C105795698 @default.
- W4320001373 hasConcept C115961682 @default.
- W4320001373 hasConcept C138885662 @default.
- W4320001373 hasConcept C153180895 @default.
- W4320001373 hasConcept C154945302 @default.
- W4320001373 hasConcept C160633673 @default.
- W4320001373 hasConcept C165064840 @default.
- W4320001373 hasConcept C166704113 @default.
- W4320001373 hasConcept C177846678 @default.
- W4320001373 hasConcept C2776401178 @default.
- W4320001373 hasConcept C28751775 @default.
- W4320001373 hasConcept C31972630 @default.
- W4320001373 hasConcept C33923547 @default.
- W4320001373 hasConcept C41008148 @default.
- W4320001373 hasConcept C41895202 @default.
- W4320001373 hasConcept C75280867 @default.
- W4320001373 hasConceptScore W4320001373C105795698 @default.
- W4320001373 hasConceptScore W4320001373C115961682 @default.
- W4320001373 hasConceptScore W4320001373C138885662 @default.
- W4320001373 hasConceptScore W4320001373C153180895 @default.
- W4320001373 hasConceptScore W4320001373C154945302 @default.
- W4320001373 hasConceptScore W4320001373C160633673 @default.
- W4320001373 hasConceptScore W4320001373C165064840 @default.
- W4320001373 hasConceptScore W4320001373C166704113 @default.
- W4320001373 hasConceptScore W4320001373C177846678 @default.
- W4320001373 hasConceptScore W4320001373C2776401178 @default.
- W4320001373 hasConceptScore W4320001373C28751775 @default.
- W4320001373 hasConceptScore W4320001373C31972630 @default.
- W4320001373 hasConceptScore W4320001373C33923547 @default.
- W4320001373 hasConceptScore W4320001373C41008148 @default.
- W4320001373 hasConceptScore W4320001373C41895202 @default.
- W4320001373 hasConceptScore W4320001373C75280867 @default.
- W4320001373 hasFunder F4320322919 @default.
- W4320001373 hasLocation W43200013731 @default.
- W4320001373 hasOpenAccess W4320001373 @default.
- W4320001373 hasPrimaryLocation W43200013731 @default.
- W4320001373 hasRelatedWork W1868689119 @default.
- W4320001373 hasRelatedWork W2080860377 @default.
- W4320001373 hasRelatedWork W2167361453 @default.
- W4320001373 hasRelatedWork W2554642673 @default.
- W4320001373 hasRelatedWork W2771220351 @default.
- W4320001373 hasRelatedWork W2786306966 @default.
- W4320001373 hasRelatedWork W67284269 @default.
- W4320001373 hasRelatedWork W217329535 @default.
- W4320001373 hasRelatedWork W2187383233 @default.
- W4320001373 hasRelatedWork W2561510925 @default.
- W4320001373 hasVolume "30" @default.
- W4320001373 isParatext "false" @default.
- W4320001373 isRetracted "false" @default.
- W4320001373 workType "article" @default.