FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4312460030> ?p ?o ?g. }

• W4312460030 abstract "Monocular depth estimation is vital for scene understanding and downstream tasks. We focus on the supervised setup, in which ground-truth depth is available only at training time. Based on knowledge about the high regularity of real 3D scenes, we propose a method that learns to selectively leverage information from coplanar pixels to improve the predicted depth. In particular, we introduce a piecewise planarity prior which states that for each pixel, there is a seed pixel which shares the same planar 3D surface with the former. Motivated by this prior, we design a network with two heads. The first head outputs pixel-level plane coefficients, while the second one outputs a dense off-set vector field that identifies the positions of seed pixels. The plane coefficients of seed pixels are then used to predict depth at each position. The resulting prediction is adaptively fused with the initial prediction from the first head via a learned confidence to account for potential deviations from precise local planarity. The entire architecture is trained end-to-end thanks to the differentiability of the proposed modules and it learns to predict regular depth maps, with sharp edges at occlusion boundaries. An extensive evaluation of our method shows that we set the new state of the art in supervised monocular depth estimation, surpassing prior methods on NYU Depth-v2 and on the Garg split of KITTI. Our method delivers depth maps that yield plausible 3D reconstructions of the input scenes. Code is available at: https://github.com/SysCV/P3Depth" @default.
• W4312460030 created "2023-01-04" @default.
• W4312460030 creator A5001254143 @default.
• W4312460030 creator A5048742998 @default.
• W4312460030 creator A5058481699 @default.
• W4312460030 creator A5076239754 @default.
• W4312460030 date "2022-06-01" @default.
• W4312460030 modified "2023-09-30" @default.
• W4312460030 title "P3Depth: Monocular Depth Estimation with a Piecewise Planarity Prior" @default.
• W4312460030 cites W1803059841 @default.
• W4312460030 cites W1905829557 @default.
• W4312460030 cites W1923184257 @default.
• W4312460030 cites W1992178727 @default.
• W4312460030 cites W2074254947 @default.
• W4312460030 cites W2083047701 @default.
• W4312460030 cites W2091297047 @default.
• W4312460030 cites W2115579991 @default.
• W4312460030 cites W2117248802 @default.
• W4312460030 cites W2132947399 @default.
• W4312460030 cites W2146814781 @default.
• W4312460030 cites W2148953571 @default.
• W4312460030 cites W2155256157 @default.
• W4312460030 cites W2155830983 @default.
• W4312460030 cites W2194775991 @default.
• W4312460030 cites W2436453945 @default.
• W4312460030 cites W2520707372 @default.
• W4312460030 cites W2593414960 @default.
• W4312460030 cites W2594519801 @default.
• W4312460030 cites W2609883120 @default.
• W4312460030 cites W2741885505 @default.
• W4312460030 cites W2748021867 @default.
• W4312460030 cites W2798373498 @default.
• W4312460030 cites W2798441115 @default.
• W4312460030 cites W2798727000 @default.
• W4312460030 cites W2798927139 @default.
• W4312460030 cites W2895314356 @default.
• W4312460030 cites W2905260191 @default.
• W4312460030 cites W2917562521 @default.
• W4312460030 cites W2962741876 @default.
• W4312460030 cites W2962807621 @default.
• W4312460030 cites W2962816904 @default.
• W4312460030 cites W2963549785 @default.
• W4312460030 cites W2963583471 @default.
• W4312460030 cites W2963591054 @default.
• W4312460030 cites W2963619659 @default.
• W4312460030 cites W2963710007 @default.
• W4312460030 cites W2963760790 @default.
• W4312460030 cites W2963775509 @default.
• W4312460030 cites W2964014680 @default.
• W4312460030 cites W2964254721 @default.
• W4312460030 cites W2985775862 @default.
• W4312460030 cites W2990946490 @default.
• W4312460030 cites W3034275131 @default.
• W4312460030 cites W3034953156 @default.
• W4312460030 cites W3035563424 @default.
• W4312460030 cites W3060975791 @default.
• W4312460030 cites W3100388886 @default.
• W4312460030 cites W3102597561 @default.
• W4312460030 cites W3107156787 @default.
• W4312460030 cites W3174458495 @default.
• W4312460030 cites W3174541782 @default.
• W4312460030 cites W3175682855 @default.
• W4312460030 cites W3181701703 @default.
• W4312460030 cites W3201971426 @default.
• W4312460030 cites W3203439539 @default.
• W4312460030 cites W4214520160 @default.
• W4312460030 cites W4214651109 @default.
• W4312460030 doi "https://doi.org/10.1109/cvpr52688.2022.00166" @default.
• W4312460030 hasPublicationYear "2022" @default.
• W4312460030 type Work @default.
• W4312460030 citedByCount "14" @default.
• W4312460030 countsByYear W43124600302022 @default.
• W4312460030 countsByYear W43124600302023 @default.
• W4312460030 crossrefType "proceedings-article" @default.
• W4312460030 hasAuthorship W4312460030A5001254143 @default.
• W4312460030 hasAuthorship W4312460030A5048742998 @default.
• W4312460030 hasAuthorship W4312460030A5058481699 @default.
• W4312460030 hasAuthorship W4312460030A5076239754 @default.
• W4312460030 hasBestOaLocation W43124600302 @default.
• W4312460030 hasConcept C114614502 @default.
• W4312460030 hasConcept C115961682 @default.
• W4312460030 hasConcept C134306372 @default.
• W4312460030 hasConcept C141268832 @default.
• W4312460030 hasConcept C146849305 @default.
• W4312460030 hasConcept C153083717 @default.
• W4312460030 hasConcept C153180895 @default.
• W4312460030 hasConcept C154945302 @default.
• W4312460030 hasConcept C160633673 @default.
• W4312460030 hasConcept C164660894 @default.
• W4312460030 hasConcept C31972630 @default.
• W4312460030 hasConcept C33923547 @default.
• W4312460030 hasConcept C41008148 @default.
• W4312460030 hasConcept C65909025 @default.
• W4312460030 hasConcept C68260962 @default.
• W4312460030 hasConcept C89600930 @default.
• W4312460030 hasConceptScore W4312460030C114614502 @default.
• W4312460030 hasConceptScore W4312460030C115961682 @default.
• W4312460030 hasConceptScore W4312460030C134306372 @default.
• W4312460030 hasConceptScore W4312460030C141268832 @default.
• W4312460030 hasConceptScore W4312460030C146849305 @default.

• next