FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3042778412> ?p ?o ?g. }

• W3042778412 abstract "This paper tackles the unsupervised depth estimation task in indoor environments. The task is extremely challenging because of the vast areas of non-texture regions in these scenes. These areas could overwhelm the optimization process in the commonly used unsupervised depth estimation framework proposed for outdoor environments. However, even when those regions are masked out, the performance is still unsatisfactory. In this paper, we argue that the poor performance suffers from the non-discriminative point-based matching. To this end, we propose P$^2$Net. We first extract points with large local gradients and adopt patches centered at each point as its representation. Multiview consistency loss is then defined over patches. This operation significantly improves the robustness of the network training. Furthermore, because those textureless regions in indoor scenes (e.g., wall, floor, roof, etc) usually correspond to planar regions, we propose to leverage superpixels as a plane prior. We enforce the predicted depth to be well fitted by a plane within each superpixel. Extensive experiments on NYUv2 and ScanNet show that our P$^2$Net outperforms existing approaches by a large margin. Code is available at url{https://github.com/svip-lab/Indoor-SfMLearner}." @default.
• W3042778412 created "2020-07-23" @default.
• W3042778412 creator A5034339267 @default.
• W3042778412 creator A5040658030 @default.
• W3042778412 creator A5086486425 @default.
• W3042778412 date "2020-07-15" @default.
• W3042778412 modified "2023-09-26" @default.
• W3042778412 title "P$^{2}$Net: Patch-match and Plane-regularization for Unsupervised Indoor Depth Estimation" @default.
• W3042778412 cites W125693051 @default.
• W3042778412 cites W1522301498 @default.
• W3042778412 cites W1677409904 @default.
• W3042778412 cites W1803059841 @default.
• W3042778412 cites W1899309388 @default.
• W3042778412 cites W1905829557 @default.
• W3042778412 cites W1992178727 @default.
• W3042778412 cites W1999478155 @default.
• W3042778412 cites W2061637641 @default.
• W3042778412 cites W2083047701 @default.
• W3042778412 cites W2124907686 @default.
• W3042778412 cites W2129404737 @default.
• W3042778412 cites W2132947399 @default.
• W3042778412 cites W2133665775 @default.
• W3042778412 cites W2135887870 @default.
• W3042778412 cites W2146814781 @default.
• W3042778412 cites W2150066425 @default.
• W3042778412 cites W2155256157 @default.
• W3042778412 cites W2171740948 @default.
• W3042778412 cites W218762409 @default.
• W3042778412 cites W2194775991 @default.
• W3042778412 cites W2210972093 @default.
• W3042778412 cites W2300779272 @default.
• W3042778412 cites W2303211814 @default.
• W3042778412 cites W2336968928 @default.
• W3042778412 cites W2474281075 @default.
• W3042778412 cites W2519683295 @default.
• W3042778412 cites W2520333321 @default.
• W3042778412 cites W2520707372 @default.
• W3042778412 cites W2604909019 @default.
• W3042778412 cites W2605938684 @default.
• W3042778412 cites W2742262683 @default.
• W3042778412 cites W2798927139 @default.
• W3042778412 cites W2889002172 @default.
• W3042778412 cites W2890949887 @default.
• W3042778412 cites W2895040125 @default.
• W3042778412 cites W2895401575 @default.
• W3042778412 cites W2905139627 @default.
• W3042778412 cites W2905260191 @default.
• W3042778412 cites W2917562521 @default.
• W3042778412 cites W2962807621 @default.
• W3042778412 cites W2963265330 @default.
• W3042778412 cites W2963488291 @default.
• W3042778412 cites W2963583471 @default.
• W3042778412 cites W2963591054 @default.
• W3042778412 cites W2963654727 @default.
• W3042778412 cites W2963710007 @default.
• W3042778412 cites W2963911235 @default.
• W3042778412 cites W2965851327 @default.
• W3042778412 cites W2970971581 @default.
• W3042778412 cites W2976566494 @default.
• W3042778412 cites W2981352086 @default.
• W3042778412 cites W2985775862 @default.
• W3042778412 cites W2990394353 @default.
• W3042778412 cites W2990946490 @default.
• W3042778412 cites W2995687155 @default.
• W3042778412 cites W337610345 @default.
• W3042778412 cites W603908379 @default.
• W3042778412 doi "https://doi.org/10.48550/arxiv.2007.07696" @default.
• W3042778412 hasPublicationYear "2020" @default.
• W3042778412 type Work @default.
• W3042778412 sameAs 3042778412 @default.
• W3042778412 citedByCount "5" @default.
• W3042778412 countsByYear W30427784122021 @default.
• W3042778412 crossrefType "posted-content" @default.
• W3042778412 hasAuthorship W3042778412A5034339267 @default.
• W3042778412 hasAuthorship W3042778412A5040658030 @default.
• W3042778412 hasAuthorship W3042778412A5086486425 @default.
• W3042778412 hasBestOaLocation W30427784121 @default.
• W3042778412 hasConcept C104317684 @default.
• W3042778412 hasConcept C119857082 @default.
• W3042778412 hasConcept C153083717 @default.
• W3042778412 hasConcept C153180895 @default.
• W3042778412 hasConcept C154945302 @default.
• W3042778412 hasConcept C177264268 @default.
• W3042778412 hasConcept C185592680 @default.
• W3042778412 hasConcept C199360897 @default.
• W3042778412 hasConcept C2776135515 @default.
• W3042778412 hasConcept C2776760102 @default.
• W3042778412 hasConcept C31972630 @default.
• W3042778412 hasConcept C41008148 @default.
• W3042778412 hasConcept C55493867 @default.
• W3042778412 hasConcept C63479239 @default.
• W3042778412 hasConcept C774472 @default.
• W3042778412 hasConcept C97931131 @default.
• W3042778412 hasConceptScore W3042778412C104317684 @default.
• W3042778412 hasConceptScore W3042778412C119857082 @default.
• W3042778412 hasConceptScore W3042778412C153083717 @default.
• W3042778412 hasConceptScore W3042778412C153180895 @default.
• W3042778412 hasConceptScore W3042778412C154945302 @default.
• W3042778412 hasConceptScore W3042778412C177264268 @default.
• W3042778412 hasConceptScore W3042778412C185592680 @default.

• next