Matches in SemOpenAlex for { <https://semopenalex.org/work/W3197646906> ?p ?o ?g. }
- W3197646906 abstract "Point clouds are often sparse and incomplete, which imposes difficulties for real-world applications. Existing shape completion methods tend to generate rough shapes without fine-grained details. Considering this, we introduce a two-branch network for shape completion. The first branch is a cascaded shape completion sub-network to synthesize complete objects, where we propose to use the partial input together with the coarse output to preserve the object details during the dense point reconstruction. The second branch is an auto-encoder to reconstruct the original partial input. The two branches share a same feature extractor to learn an accurate global feature for shape completion. Furthermore, we propose two strategies to enable the training of our network when ground truth data are not available. This is to mitigate the dependence of existing approaches on large amounts of ground truth training data that are often difficult to obtain in real-world applications. Additionally, our proposed strategies are also able to improve the reconstruction quality for fully supervised learning. We verify our approach in self-supervised, semi-supervised and fully supervised settings with superior performances. Quantitative and qualitative results on different datasets demonstrate that our method achieves more realistic outputs than state-of-the-art approaches on the point cloud completion task." @default.
- W3197646906 created "2021-09-13" @default.
- W3197646906 creator A5064469965 @default.
- W3197646906 creator A5071967339 @default.
- W3197646906 creator A5079410647 @default.
- W3197646906 date "2020-10-17" @default.
- W3197646906 modified "2023-10-16" @default.
- W3197646906 title "Cascaded Refinement Network for Point Cloud Completion with Self-supervision" @default.
- W3197646906 cites W1849085266 @default.
- W3197646906 cites W1920022804 @default.
- W3197646906 cites W2115579991 @default.
- W3197646906 cites W2139910390 @default.
- W3197646906 cites W2511691466 @default.
- W3197646906 cites W2546066744 @default.
- W3197646906 cites W2559882727 @default.
- W3197646906 cites W2560609797 @default.
- W3197646906 cites W2560722161 @default.
- W3197646906 cites W2593414223 @default.
- W3197646906 cites W2604493845 @default.
- W3197646906 cites W2796426482 @default.
- W3197646906 cites W2798314605 @default.
- W3197646906 cites W2798777114 @default.
- W3197646906 cites W2886499109 @default.
- W3197646906 cites W2891624360 @default.
- W3197646906 cites W2894705404 @default.
- W3197646906 cites W2902302021 @default.
- W3197646906 cites W2904332125 @default.
- W3197646906 cites W2914390273 @default.
- W3197646906 cites W2940600945 @default.
- W3197646906 cites W2944579304 @default.
- W3197646906 cites W2953668091 @default.
- W3197646906 cites W2953823434 @default.
- W3197646906 cites W2960986959 @default.
- W3197646906 cites W2962778872 @default.
- W3197646906 cites W2962885944 @default.
- W3197646906 cites W2962922818 @default.
- W3197646906 cites W2963053547 @default.
- W3197646906 cites W2963057320 @default.
- W3197646906 cites W2963121255 @default.
- W3197646906 cites W2963197375 @default.
- W3197646906 cites W2963231572 @default.
- W3197646906 cites W2963399829 @default.
- W3197646906 cites W2963627347 @default.
- W3197646906 cites W2963640720 @default.
- W3197646906 cites W2963648573 @default.
- W3197646906 cites W2963719584 @default.
- W3197646906 cites W2963872169 @default.
- W3197646906 cites W2963926543 @default.
- W3197646906 cites W2963981733 @default.
- W3197646906 cites W2964121744 @default.
- W3197646906 cites W2964310454 @default.
- W3197646906 cites W2964339842 @default.
- W3197646906 cites W2968296999 @default.
- W3197646906 cites W2979750740 @default.
- W3197646906 cites W2985683375 @default.
- W3197646906 cites W2990613095 @default.
- W3197646906 cites W2995437133 @default.
- W3197646906 cites W2997088169 @default.
- W3197646906 cites W3034239841 @default.
- W3197646906 cites W3034493208 @default.
- W3197646906 cites W3034584726 @default.
- W3197646906 cites W3034961469 @default.
- W3197646906 cites W3035014292 @default.
- W3197646906 cites W3039448353 @default.
- W3197646906 cites W3104141662 @default.
- W3197646906 cites W3108012830 @default.
- W3197646906 cites W3109518641 @default.
- W3197646906 cites W3116155584 @default.
- W3197646906 cites W3118496930 @default.
- W3197646906 cites W3118644257 @default.
- W3197646906 cites W3127529150 @default.
- W3197646906 cites W3129103333 @default.
- W3197646906 cites W3170469318 @default.
- W3197646906 doi "https://doi.org/10.48550/arxiv.2010.08719" @default.
- W3197646906 hasPublicationYear "2020" @default.
- W3197646906 type Work @default.
- W3197646906 sameAs 3197646906 @default.
- W3197646906 citedByCount "0" @default.
- W3197646906 crossrefType "posted-content" @default.
- W3197646906 hasAuthorship W3197646906A5064469965 @default.
- W3197646906 hasAuthorship W3197646906A5071967339 @default.
- W3197646906 hasAuthorship W3197646906A5079410647 @default.
- W3197646906 hasBestOaLocation W31976469061 @default.
- W3197646906 hasConcept C111919701 @default.
- W3197646906 hasConcept C118505674 @default.
- W3197646906 hasConcept C119857082 @default.
- W3197646906 hasConcept C124101348 @default.
- W3197646906 hasConcept C131979681 @default.
- W3197646906 hasConcept C136389625 @default.
- W3197646906 hasConcept C138885662 @default.
- W3197646906 hasConcept C146849305 @default.
- W3197646906 hasConcept C154945302 @default.
- W3197646906 hasConcept C162324750 @default.
- W3197646906 hasConcept C187736073 @default.
- W3197646906 hasConcept C2524010 @default.
- W3197646906 hasConcept C2776401178 @default.
- W3197646906 hasConcept C2780451532 @default.
- W3197646906 hasConcept C2781238097 @default.
- W3197646906 hasConcept C28719098 @default.
- W3197646906 hasConcept C33923547 @default.