Matches in SemOpenAlex for { <https://semopenalex.org/work/W4385989270> ?p ?o ?g. }
- W4385989270 endingPage "392" @default.
- W4385989270 startingPage "383" @default.
- W4385989270 abstract "Recently 3D reconstruction has received extensive attention and deep research due to the continuous development of the field of computer vision. Nonetheless, the learning-based methods for 3D reconstruction are not robust enough, resulting in the reconstruction model having many occlusions and outliers. In this study, we aim to improve feature matching correlation, aggregate global contextual information, and enhance the robustness of depth estimation to improve the quality of the reconstruction. We propose an attention-based deep sparse priori cascade multi-view stereo network, ADS-MVSNet. Firstly, we propose a feature extraction module based on the attention mechanism to obtain the regions of interest in the input scene. Secondly, we propose a depth sparse prior strategy module to estimate the depth map of the input scene more accurately. It is followed by refinement of the initial depth map using a coarse-to-fine method to improve the accuracy of point cloud reconstruction. These two modules are lightweight and effective, improving the robustness of depth map estimation. We conduct experiments on three common datasets (DTU, ETH3D, Tanks & Temples) and a dataset of a real scene created by us. The experimental results show that ADS-MVSNet performs better in reconstruction quality compared to classical methods." @default.
- W4385989270 created "2023-08-19" @default.
- W4385989270 creator A5046214153 @default.
- W4385989270 creator A5046645047 @default.
- W4385989270 creator A5088035307 @default.
- W4385989270 creator A5091604093 @default.
- W4385989270 date "2023-11-01" @default.
- W4385989270 modified "2023-10-14" @default.
- W4385989270 title "An attention-based and deep sparse priori cascade multi-view stereo network for 3D reconstruction" @default.
- W4385989270 cites W2074378519 @default.
- W4385989270 cites W2108417695 @default.
- W4385989270 cites W2112174119 @default.
- W4385989270 cites W2129404737 @default.
- W4385989270 cites W2168545424 @default.
- W4385989270 cites W2205172244 @default.
- W4385989270 cites W2338968644 @default.
- W4385989270 cites W2471962767 @default.
- W4385989270 cites W2565639579 @default.
- W4385989270 cites W2601564443 @default.
- W4385989270 cites W2738551266 @default.
- W4385989270 cites W2741885505 @default.
- W4385989270 cites W2884585870 @default.
- W4385989270 cites W2926429807 @default.
- W4385989270 cites W2962793285 @default.
- W4385989270 cites W2967693513 @default.
- W4385989270 cites W2982169158 @default.
- W4385989270 cites W2985066174 @default.
- W4385989270 cites W2992718396 @default.
- W4385989270 cites W3018603234 @default.
- W4385989270 cites W3034530552 @default.
- W4385989270 cites W3034552520 @default.
- W4385989270 cites W3034564916 @default.
- W4385989270 cites W3034600477 @default.
- W4385989270 cites W3034643157 @default.
- W4385989270 cites W3035525671 @default.
- W4385989270 cites W3102132650 @default.
- W4385989270 cites W3159981575 @default.
- W4385989270 cites W3170262190 @default.
- W4385989270 cites W3204267695 @default.
- W4385989270 cites W4292387186 @default.
- W4385989270 doi "https://doi.org/10.1016/j.cag.2023.08.017" @default.
- W4385989270 hasPublicationYear "2023" @default.
- W4385989270 type Work @default.
- W4385989270 citedByCount "0" @default.
- W4385989270 crossrefType "journal-article" @default.
- W4385989270 hasAuthorship W4385989270A5046214153 @default.
- W4385989270 hasAuthorship W4385989270A5046645047 @default.
- W4385989270 hasAuthorship W4385989270A5088035307 @default.
- W4385989270 hasAuthorship W4385989270A5091604093 @default.
- W4385989270 hasConcept C104317684 @default.
- W4385989270 hasConcept C108583219 @default.
- W4385989270 hasConcept C109950114 @default.
- W4385989270 hasConcept C111472728 @default.
- W4385989270 hasConcept C115961682 @default.
- W4385989270 hasConcept C11727466 @default.
- W4385989270 hasConcept C131979681 @default.
- W4385989270 hasConcept C138885662 @default.
- W4385989270 hasConcept C141268832 @default.
- W4385989270 hasConcept C153180895 @default.
- W4385989270 hasConcept C154945302 @default.
- W4385989270 hasConcept C185592680 @default.
- W4385989270 hasConcept C31972630 @default.
- W4385989270 hasConcept C34146451 @default.
- W4385989270 hasConcept C41008148 @default.
- W4385989270 hasConcept C43617362 @default.
- W4385989270 hasConcept C55493867 @default.
- W4385989270 hasConcept C63479239 @default.
- W4385989270 hasConcept C75553542 @default.
- W4385989270 hasConcept C79337645 @default.
- W4385989270 hasConceptScore W4385989270C104317684 @default.
- W4385989270 hasConceptScore W4385989270C108583219 @default.
- W4385989270 hasConceptScore W4385989270C109950114 @default.
- W4385989270 hasConceptScore W4385989270C111472728 @default.
- W4385989270 hasConceptScore W4385989270C115961682 @default.
- W4385989270 hasConceptScore W4385989270C11727466 @default.
- W4385989270 hasConceptScore W4385989270C131979681 @default.
- W4385989270 hasConceptScore W4385989270C138885662 @default.
- W4385989270 hasConceptScore W4385989270C141268832 @default.
- W4385989270 hasConceptScore W4385989270C153180895 @default.
- W4385989270 hasConceptScore W4385989270C154945302 @default.
- W4385989270 hasConceptScore W4385989270C185592680 @default.
- W4385989270 hasConceptScore W4385989270C31972630 @default.
- W4385989270 hasConceptScore W4385989270C34146451 @default.
- W4385989270 hasConceptScore W4385989270C41008148 @default.
- W4385989270 hasConceptScore W4385989270C43617362 @default.
- W4385989270 hasConceptScore W4385989270C55493867 @default.
- W4385989270 hasConceptScore W4385989270C63479239 @default.
- W4385989270 hasConceptScore W4385989270C75553542 @default.
- W4385989270 hasConceptScore W4385989270C79337645 @default.
- W4385989270 hasFunder F4320311028 @default.
- W4385989270 hasFunder F4320321001 @default.
- W4385989270 hasFunder F4320335787 @default.
- W4385989270 hasLocation W43859892701 @default.
- W4385989270 hasOpenAccess W4385989270 @default.
- W4385989270 hasPrimaryLocation W43859892701 @default.
- W4385989270 hasRelatedWork W1504109132 @default.
- W4385989270 hasRelatedWork W2046654028 @default.
- W4385989270 hasRelatedWork W2105610540 @default.