Matches in SemOpenAlex for { <https://semopenalex.org/work/W4317233920> ?p ?o ?g. }
Showing items 1 to 99 of
99
with 100 items per page.
- W4317233920 endingPage "47" @default.
- W4317233920 startingPage "35" @default.
- W4317233920 abstract "The goal of Multi-View Stereo is to reconstruct the 3D point cloud model from multiple views. With the development of deep learning, more and more learning-based research has achieved remarkable results. However, existing methods ignore the fine-grained features of the bottom layer, which leads to the poor quality of model reconstruction, especially in terms of completeness. Besides, current methods still rely on a large amount of consumed memory resources because of the application of 3D convolution. To this end, this paper proposes a Multiple Granularities Feature Fusion Network for Multi-View Stereo, an end-to-end depth estimation network combining global and local features, which is characterized by fine-granularity multi-feature fusion. Firstly, we propose a dense feature adaptive connection module, which can adaptively fuse the global and local features in the scene, provide a more complete and effective feature map for inferring a more detailed depth map, and make the ultimate model more complete. Secondly, in order to further improve the accuracy and completeness of the reconstructed point cloud, we introduce normal and edge loss futead of only using depth loss functions as in the existing methods, which makes the network more sensitive to small depth structures. Finally, we propose distributed 3D convolution instead of traditional 3D convolution, which reduces memory consumption. The experimental results on the DTU and Tanks & Temples datasets demonstrate that the proposed method in this papaer achieves the state-of-the-art performance, which proves the accuracy and effectiveness of the MG-MVSNet proposed in this paper." @default.
- W4317233920 created "2023-01-18" @default.
- W4317233920 creator A5014264919 @default.
- W4317233920 creator A5035265607 @default.
- W4317233920 creator A5040932912 @default.
- W4317233920 creator A5078482949 @default.
- W4317233920 date "2023-04-01" @default.
- W4317233920 modified "2023-10-01" @default.
- W4317233920 title "MG-MVSNet: Multiple granularities feature fusion network for multi-view stereo" @default.
- W4317233920 cites W1536680647 @default.
- W4317233920 cites W1903029394 @default.
- W4317233920 cites W2085905957 @default.
- W4317233920 cites W2128052895 @default.
- W4317233920 cites W2129404737 @default.
- W4317233920 cites W2205172244 @default.
- W4317233920 cites W2463669990 @default.
- W4317233920 cites W2471962767 @default.
- W4317233920 cites W2565639579 @default.
- W4317233920 cites W2604231069 @default.
- W4317233920 cites W2738551266 @default.
- W4317233920 cites W2798727000 @default.
- W4317233920 cites W2799018616 @default.
- W4317233920 cites W2887568100 @default.
- W4317233920 cites W2897840891 @default.
- W4317233920 cites W2926429807 @default.
- W4317233920 cites W2962793285 @default.
- W4317233920 cites W2962957359 @default.
- W4317233920 cites W2963488291 @default.
- W4317233920 cites W2963591054 @default.
- W4317233920 cites W2963619659 @default.
- W4317233920 cites W2963820951 @default.
- W4317233920 cites W2964153986 @default.
- W4317233920 cites W2968004941 @default.
- W4317233920 cites W2982169158 @default.
- W4317233920 cites W2985066174 @default.
- W4317233920 cites W2990654629 @default.
- W4317233920 cites W2992718396 @default.
- W4317233920 cites W3034530552 @default.
- W4317233920 cites W3034564916 @default.
- W4317233920 cites W3034600477 @default.
- W4317233920 cites W3086800256 @default.
- W4317233920 cites W3102132650 @default.
- W4317233920 cites W3118982599 @default.
- W4317233920 cites W3120248555 @default.
- W4317233920 cites W3176815366 @default.
- W4317233920 cites W3195174048 @default.
- W4317233920 cites W3214287966 @default.
- W4317233920 cites W4200621093 @default.
- W4317233920 cites W4226456596 @default.
- W4317233920 cites W4238100585 @default.
- W4317233920 cites W832925222 @default.
- W4317233920 doi "https://doi.org/10.1016/j.neucom.2023.01.062" @default.
- W4317233920 hasPublicationYear "2023" @default.
- W4317233920 type Work @default.
- W4317233920 citedByCount "3" @default.
- W4317233920 countsByYear W43172339202023 @default.
- W4317233920 crossrefType "journal-article" @default.
- W4317233920 hasAuthorship W4317233920A5014264919 @default.
- W4317233920 hasAuthorship W4317233920A5035265607 @default.
- W4317233920 hasAuthorship W4317233920A5040932912 @default.
- W4317233920 hasAuthorship W4317233920A5078482949 @default.
- W4317233920 hasBestOaLocation W43172339201 @default.
- W4317233920 hasConcept C138885662 @default.
- W4317233920 hasConcept C153180895 @default.
- W4317233920 hasConcept C154945302 @default.
- W4317233920 hasConcept C158525013 @default.
- W4317233920 hasConcept C2776401178 @default.
- W4317233920 hasConcept C31972630 @default.
- W4317233920 hasConcept C41008148 @default.
- W4317233920 hasConcept C41895202 @default.
- W4317233920 hasConceptScore W4317233920C138885662 @default.
- W4317233920 hasConceptScore W4317233920C153180895 @default.
- W4317233920 hasConceptScore W4317233920C154945302 @default.
- W4317233920 hasConceptScore W4317233920C158525013 @default.
- W4317233920 hasConceptScore W4317233920C2776401178 @default.
- W4317233920 hasConceptScore W4317233920C31972630 @default.
- W4317233920 hasConceptScore W4317233920C41008148 @default.
- W4317233920 hasConceptScore W4317233920C41895202 @default.
- W4317233920 hasFunder F4320321540 @default.
- W4317233920 hasFunder F4320335777 @default.
- W4317233920 hasLocation W43172339201 @default.
- W4317233920 hasOpenAccess W4317233920 @default.
- W4317233920 hasPrimaryLocation W43172339201 @default.
- W4317233920 hasRelatedWork W1504288058 @default.
- W4317233920 hasRelatedWork W2017205855 @default.
- W4317233920 hasRelatedWork W2031347084 @default.
- W4317233920 hasRelatedWork W2048505601 @default.
- W4317233920 hasRelatedWork W2167293474 @default.
- W4317233920 hasRelatedWork W2331674254 @default.
- W4317233920 hasRelatedWork W2358403311 @default.
- W4317233920 hasRelatedWork W2922188210 @default.
- W4317233920 hasRelatedWork W2979079341 @default.
- W4317233920 hasRelatedWork W3042897387 @default.
- W4317233920 hasVolume "528" @default.
- W4317233920 isParatext "false" @default.
- W4317233920 isRetracted "false" @default.
- W4317233920 workType "article" @default.