Matches in SemOpenAlex for { <https://semopenalex.org/work/W4380052295> ?p ?o ?g. }
- W4380052295 endingPage "2970" @default.
- W4380052295 startingPage "2970" @default.
- W4380052295 abstract "We propose an enhancement module called depth discontinuity learning (DDL) for learning-based multi-view stereo (MVS) methods. Traditional methods are known for their accuracy but struggle with completeness. While recent learning-based methods have improved completeness at the cost of accuracy, our DDL approach aims to improve accuracy while retaining completeness in the reconstruction process. To achieve this, we introduce the joint estimation of depth and boundary maps, where the boundary maps are explicitly utilized for further refinement of the depth maps. We validate our idea by integrating it into an existing learning-based MVS pipeline where the reconstruction depends on high-quality depth map estimation. Extensive experiments on various datasets, namely DTU, ETH3D, “Tanks and Temples”, and BlendedMVS, show that our method improves reconstruction quality compared to our baseline, Patchmatchnet. Our ablation study demonstrates that incorporating the proposed DDL significantly reduces the depth map error, for instance, by more than 30% on the DTU dataset, and leads to improved depth map quality in both smooth and boundary regions. Additionally, our qualitative analysis has shown that the reconstructed point cloud exhibits enhanced quality without any significant compromise on completeness. Finally, the experiments reveal that our proposed model and strategies exhibit strong generalization capabilities across the various datasets." @default.
- W4380052295 created "2023-06-10" @default.
- W4380052295 creator A5027616562 @default.
- W4380052295 creator A5047673695 @default.
- W4380052295 creator A5051936833 @default.
- W4380052295 creator A5074902093 @default.
- W4380052295 date "2023-06-07" @default.
- W4380052295 modified "2023-09-24" @default.
- W4380052295 title "DDL-MVS: Depth Discontinuity Learning for Multi-View Stereo Networks" @default.
- W4380052295 cites W2009422376 @default.
- W4380052295 cites W2059496137 @default.
- W4380052295 cites W2097261533 @default.
- W4380052295 cites W2128052895 @default.
- W4380052295 cites W2129404737 @default.
- W4380052295 cites W2138821028 @default.
- W4380052295 cites W2143516773 @default.
- W4380052295 cites W2167335287 @default.
- W4380052295 cites W2168545424 @default.
- W4380052295 cites W2205172244 @default.
- W4380052295 cites W2338968644 @default.
- W4380052295 cites W2519683295 @default.
- W4380052295 cites W2520322935 @default.
- W4380052295 cites W2565639579 @default.
- W4380052295 cites W2604231069 @default.
- W4380052295 cites W2738551266 @default.
- W4380052295 cites W2741885505 @default.
- W4380052295 cites W2776796896 @default.
- W4380052295 cites W2889759829 @default.
- W4380052295 cites W2926429807 @default.
- W4380052295 cites W2950496566 @default.
- W4380052295 cites W2962793285 @default.
- W4380052295 cites W2963277791 @default.
- W4380052295 cites W2963619659 @default.
- W4380052295 cites W2992718396 @default.
- W4380052295 cites W3034524082 @default.
- W4380052295 cites W3034530552 @default.
- W4380052295 cites W3034564916 @default.
- W4380052295 cites W3034600477 @default.
- W4380052295 cites W3034953156 @default.
- W4380052295 cites W3035257660 @default.
- W4380052295 cites W3035477536 @default.
- W4380052295 cites W3040318838 @default.
- W4380052295 cites W3102132650 @default.
- W4380052295 cites W3152935628 @default.
- W4380052295 cites W3170204303 @default.
- W4380052295 cites W3170262190 @default.
- W4380052295 cites W3181256344 @default.
- W4380052295 cites W3204267695 @default.
- W4380052295 cites W3204354488 @default.
- W4380052295 cites W4233857083 @default.
- W4380052295 cites W4238307586 @default.
- W4380052295 cites W4312725665 @default.
- W4380052295 cites W4313143504 @default.
- W4380052295 cites W4317233920 @default.
- W4380052295 cites W845365781 @default.
- W4380052295 doi "https://doi.org/10.3390/rs15122970" @default.
- W4380052295 hasPublicationYear "2023" @default.
- W4380052295 type Work @default.
- W4380052295 citedByCount "0" @default.
- W4380052295 crossrefType "journal-article" @default.
- W4380052295 hasAuthorship W4380052295A5027616562 @default.
- W4380052295 hasAuthorship W4380052295A5047673695 @default.
- W4380052295 hasAuthorship W4380052295A5051936833 @default.
- W4380052295 hasAuthorship W4380052295A5074902093 @default.
- W4380052295 hasBestOaLocation W43800522951 @default.
- W4380052295 hasConcept C11413529 @default.
- W4380052295 hasConcept C115961682 @default.
- W4380052295 hasConcept C131979681 @default.
- W4380052295 hasConcept C134306372 @default.
- W4380052295 hasConcept C141268832 @default.
- W4380052295 hasConcept C154945302 @default.
- W4380052295 hasConcept C17231256 @default.
- W4380052295 hasConcept C177148314 @default.
- W4380052295 hasConcept C2777042112 @default.
- W4380052295 hasConcept C33923547 @default.
- W4380052295 hasConcept C41008148 @default.
- W4380052295 hasConcept C62354387 @default.
- W4380052295 hasConceptScore W4380052295C11413529 @default.
- W4380052295 hasConceptScore W4380052295C115961682 @default.
- W4380052295 hasConceptScore W4380052295C131979681 @default.
- W4380052295 hasConceptScore W4380052295C134306372 @default.
- W4380052295 hasConceptScore W4380052295C141268832 @default.
- W4380052295 hasConceptScore W4380052295C154945302 @default.
- W4380052295 hasConceptScore W4380052295C17231256 @default.
- W4380052295 hasConceptScore W4380052295C177148314 @default.
- W4380052295 hasConceptScore W4380052295C2777042112 @default.
- W4380052295 hasConceptScore W4380052295C33923547 @default.
- W4380052295 hasConceptScore W4380052295C41008148 @default.
- W4380052295 hasConceptScore W4380052295C62354387 @default.
- W4380052295 hasIssue "12" @default.
- W4380052295 hasLocation W43800522951 @default.
- W4380052295 hasOpenAccess W4380052295 @default.
- W4380052295 hasPrimaryLocation W43800522951 @default.
- W4380052295 hasRelatedWork W2752490943 @default.
- W4380052295 hasRelatedWork W2766011388 @default.
- W4380052295 hasRelatedWork W3000107993 @default.
- W4380052295 hasRelatedWork W3154650674 @default.
- W4380052295 hasRelatedWork W3173709168 @default.