Matches in SemOpenAlex for { <https://semopenalex.org/work/W4310822351> ?p ?o ?g. }
Showing items 1 to 66 of
66
with 100 items per page.
- W4310822351 abstract "Monocular depth estimation is a challenging problem on which deep neural networks have demonstrated great potential. However, depth maps predicted by existing deep models usually lack fine-grained details due to the convolution operations and the down-samplings in networks. We find that increasing input resolution is helpful to preserve more local details while the estimation at low resolution is more accurate globally. Therefore, we propose a novel depth map fusion module to combine the advantages of estimations with multi-resolution inputs. Instead of merging the low- and high-resolution estimations equally, we adopt the core idea of Poisson fusion, trying to implant the gradient domain of high-resolution depth into the low-resolution depth. While classic Poisson fusion requires a fusion mask as supervision, we propose a self-supervised framework based on guided image filtering. We demonstrate that this gradient-based composition performs much better at noisy immunity, compared with the state-of-the-art depth map fusion method. Our lightweight depth fusion is one-shot and runs in real-time, making our method 80X faster than a state-of-the-art depth fusion method. Quantitative evaluations demonstrate that the proposed method can be integrated into many fully convolutional monocular depth estimation backbones with a significant performance boost, leading to state-of-the-art results of detail enhancement on depth maps." @default.
- W4310822351 created "2022-12-18" @default.
- W4310822351 creator A5000248352 @default.
- W4310822351 creator A5024134840 @default.
- W4310822351 creator A5042268563 @default.
- W4310822351 creator A5043683058 @default.
- W4310822351 creator A5082950272 @default.
- W4310822351 date "2022-12-03" @default.
- W4310822351 modified "2023-10-10" @default.
- W4310822351 title "Multi-resolution Monocular Depth Map Fusion by Self-supervised Gradient-based Composition" @default.
- W4310822351 doi "https://doi.org/10.48550/arxiv.2212.01538" @default.
- W4310822351 hasPublicationYear "2022" @default.
- W4310822351 type Work @default.
- W4310822351 citedByCount "0" @default.
- W4310822351 crossrefType "posted-content" @default.
- W4310822351 hasAuthorship W4310822351A5000248352 @default.
- W4310822351 hasAuthorship W4310822351A5024134840 @default.
- W4310822351 hasAuthorship W4310822351A5042268563 @default.
- W4310822351 hasAuthorship W4310822351A5043683058 @default.
- W4310822351 hasAuthorship W4310822351A5082950272 @default.
- W4310822351 hasBestOaLocation W43108223511 @default.
- W4310822351 hasConcept C115961682 @default.
- W4310822351 hasConcept C138885662 @default.
- W4310822351 hasConcept C141268832 @default.
- W4310822351 hasConcept C153180895 @default.
- W4310822351 hasConcept C154945302 @default.
- W4310822351 hasConcept C158525013 @default.
- W4310822351 hasConcept C31972630 @default.
- W4310822351 hasConcept C41008148 @default.
- W4310822351 hasConcept C41895202 @default.
- W4310822351 hasConcept C45347329 @default.
- W4310822351 hasConcept C50644808 @default.
- W4310822351 hasConcept C65909025 @default.
- W4310822351 hasConcept C69744172 @default.
- W4310822351 hasConcept C81363708 @default.
- W4310822351 hasConceptScore W4310822351C115961682 @default.
- W4310822351 hasConceptScore W4310822351C138885662 @default.
- W4310822351 hasConceptScore W4310822351C141268832 @default.
- W4310822351 hasConceptScore W4310822351C153180895 @default.
- W4310822351 hasConceptScore W4310822351C154945302 @default.
- W4310822351 hasConceptScore W4310822351C158525013 @default.
- W4310822351 hasConceptScore W4310822351C31972630 @default.
- W4310822351 hasConceptScore W4310822351C41008148 @default.
- W4310822351 hasConceptScore W4310822351C41895202 @default.
- W4310822351 hasConceptScore W4310822351C45347329 @default.
- W4310822351 hasConceptScore W4310822351C50644808 @default.
- W4310822351 hasConceptScore W4310822351C65909025 @default.
- W4310822351 hasConceptScore W4310822351C69744172 @default.
- W4310822351 hasConceptScore W4310822351C81363708 @default.
- W4310822351 hasLocation W43108223511 @default.
- W4310822351 hasLocation W43108223512 @default.
- W4310822351 hasOpenAccess W4310822351 @default.
- W4310822351 hasPrimaryLocation W43108223511 @default.
- W4310822351 hasRelatedWork W1490651872 @default.
- W4310822351 hasRelatedWork W1750358731 @default.
- W4310822351 hasRelatedWork W2139242969 @default.
- W4310822351 hasRelatedWork W2204403038 @default.
- W4310822351 hasRelatedWork W2350422455 @default.
- W4310822351 hasRelatedWork W2370195708 @default.
- W4310822351 hasRelatedWork W2379054866 @default.
- W4310822351 hasRelatedWork W2549658594 @default.
- W4310822351 hasRelatedWork W2788731446 @default.
- W4310822351 hasRelatedWork W3152170969 @default.
- W4310822351 isParatext "false" @default.
- W4310822351 isRetracted "false" @default.
- W4310822351 workType "article" @default.