Matches in SemOpenAlex for { <https://semopenalex.org/work/W4386723894> ?p ?o ?g. }
Showing items 1 to 95 of
95
with 100 items per page.
- W4386723894 abstract "Abstract This paper aims to address the problem of supervised monocular depth estimation. We start with a meticulous pilot study to demonstrate that the long-range correlation is essential for accurate depth estimation. Moreover, the Transformer and convolution are good at long-range and close-range depth estimation, respectively. Therefore, we propose to adopt a parallel encoder architecture consisting of a Transformer branch and a convolution branch. The former can model global context with the effective attention mechanism and the latter aims to preserve the local information as the Transformer lacks the spatial inductive bias in modeling such contents. However, independent branches lead to a shortage of connections between features. To bridge this gap, we design a hierarchical aggregation and heterogeneous interaction module to enhance the Transformer features and model the affinity between the heterogeneous features in a set-to-set translation manner. Due to the unbearable memory cost introduced by the global attention on high-resolution feature maps, we adopt the deformable scheme to reduce the complexity. Extensive experiments on the KITTI, NYU, and SUN RGB-D datasets demonstrate that our proposed model, termed DepthFormer, surpasses state-of-the-art monocular depth estimation methods with prominent margins. The effectiveness of each proposed module is elaborately evaluated through meticulous and intensive ablation studies." @default.
- W4386723894 created "2023-09-14" @default.
- W4386723894 creator A5027059038 @default.
- W4386723894 creator A5038376785 @default.
- W4386723894 creator A5050023810 @default.
- W4386723894 creator A5087165831 @default.
- W4386723894 date "2023-09-13" @default.
- W4386723894 modified "2023-10-10" @default.
- W4386723894 title "DepthFormer: Exploiting Long-range Correlation and Local Information for Accurate Monocular Depth Estimation" @default.
- W4386723894 cites W125693051 @default.
- W4386723894 cites W1901129140 @default.
- W4386723894 cites W1923184257 @default.
- W4386723894 cites W1980302581 @default.
- W4386723894 cites W1985238052 @default.
- W4386723894 cites W2016053056 @default.
- W4386723894 cites W2115579991 @default.
- W4386723894 cites W2194775991 @default.
- W4386723894 cites W2300779272 @default.
- W4386723894 cites W2397854647 @default.
- W4386723894 cites W2412782625 @default.
- W4386723894 cites W2520322935 @default.
- W4386723894 cites W2520707372 @default.
- W4386723894 cites W2560023338 @default.
- W4386723894 cites W2601564443 @default.
- W4386723894 cites W2752782242 @default.
- W4386723894 cites W2884585870 @default.
- W4386723894 cites W2889002172 @default.
- W4386723894 cites W2895314356 @default.
- W4386723894 cites W2963316641 @default.
- W4386723894 cites W2963446712 @default.
- W4386723894 cites W2963488291 @default.
- W4386723894 cites W2963591054 @default.
- W4386723894 cites W2963911235 @default.
- W4386723894 cites W2964912923 @default.
- W4386723894 cites W2990946490 @default.
- W4386723894 cites W3034428934 @default.
- W4386723894 cites W3087588036 @default.
- W4386723894 cites W3096609285 @default.
- W4386723894 cites W3097217077 @default.
- W4386723894 cites W3108179104 @default.
- W4386723894 cites W3112288616 @default.
- W4386723894 cites W3131500599 @default.
- W4386723894 cites W3136416617 @default.
- W4386723894 cites W3138516171 @default.
- W4386723894 cites W3170841864 @default.
- W4386723894 cites W3173727695 @default.
- W4386723894 cites W3174397558 @default.
- W4386723894 cites W3176027594 @default.
- W4386723894 cites W3187276661 @default.
- W4386723894 cites W3202016623 @default.
- W4386723894 cites W3203439539 @default.
- W4386723894 cites W3205856632 @default.
- W4386723894 cites W3207804100 @default.
- W4386723894 cites W4200631318 @default.
- W4386723894 cites W4214520160 @default.
- W4386723894 cites W4214696292 @default.
- W4386723894 cites W4312819733 @default.
- W4386723894 doi "https://doi.org/10.1007/s11633-023-1458-0" @default.
- W4386723894 hasPublicationYear "2023" @default.
- W4386723894 type Work @default.
- W4386723894 citedByCount "1" @default.
- W4386723894 crossrefType "journal-article" @default.
- W4386723894 hasAuthorship W4386723894A5027059038 @default.
- W4386723894 hasAuthorship W4386723894A5038376785 @default.
- W4386723894 hasAuthorship W4386723894A5050023810 @default.
- W4386723894 hasAuthorship W4386723894A5087165831 @default.
- W4386723894 hasBestOaLocation W43867238941 @default.
- W4386723894 hasConcept C111919701 @default.
- W4386723894 hasConcept C118505674 @default.
- W4386723894 hasConcept C154945302 @default.
- W4386723894 hasConcept C31972630 @default.
- W4386723894 hasConcept C41008148 @default.
- W4386723894 hasConcept C65909025 @default.
- W4386723894 hasConceptScore W4386723894C111919701 @default.
- W4386723894 hasConceptScore W4386723894C118505674 @default.
- W4386723894 hasConceptScore W4386723894C154945302 @default.
- W4386723894 hasConceptScore W4386723894C31972630 @default.
- W4386723894 hasConceptScore W4386723894C41008148 @default.
- W4386723894 hasConceptScore W4386723894C65909025 @default.
- W4386723894 hasLocation W43867238941 @default.
- W4386723894 hasOpenAccess W4386723894 @default.
- W4386723894 hasPrimaryLocation W43867238941 @default.
- W4386723894 hasRelatedWork W127013308 @default.
- W4386723894 hasRelatedWork W1628937209 @default.
- W4386723894 hasRelatedWork W2094957557 @default.
- W4386723894 hasRelatedWork W2113039159 @default.
- W4386723894 hasRelatedWork W2144760288 @default.
- W4386723894 hasRelatedWork W2971051170 @default.
- W4386723894 hasRelatedWork W3158344581 @default.
- W4386723894 hasRelatedWork W3185738386 @default.
- W4386723894 hasRelatedWork W4224011692 @default.
- W4386723894 hasRelatedWork W4321512589 @default.
- W4386723894 isParatext "false" @default.
- W4386723894 isRetracted "false" @default.
- W4386723894 workType "article" @default.