FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3048809134> ?p ?o ?g. }

• W3048809134 abstract "This paper focuses on the challenging task of learning 3D object surface reconstructions from RGB images. Existingmethods achieve varying degrees of success by using different surface representations. However, they all have their own drawbacks,and cannot properly reconstruct the surface shapes of complex topologies, arguably due to a lack of constraints on the topologicalstructures in their learning frameworks. To this end, we propose to learn and use the topology-preserved, skeletal shape representationto assist the downstream task of object surface reconstruction from RGB images. Technically, we propose the novelSkeletonNetdesign that learns a volumetric representation of a skeleton via a bridged learning of a skeletal point set, where we use paralleldecoders each responsible for the learning of points on 1D skeletal curves and 2D skeletal sheets, as well as an efficient module ofglobally guided subvolume synthesis for a refined, high-resolution skeletal volume; we present a differentiablePoint2Voxellayer tomake SkeletonNet end-to-end and trainable. With the learned skeletal volumes, we propose two models, the Skeleton-Based GraphConvolutional Neural Network (SkeGCNN) and the Skeleton-Regularized Deep Implicit Surface Network (SkeDISN), which respectivelybuild upon and improve over the existing frameworks of explicit mesh deformation and implicit field learning for the downstream surfacereconstruction task. We conduct thorough experiments that verify the efficacy of our proposed SkeletonNet. SkeGCNN and SkeDISNoutperform existing methods as well, and they have their own merits when measured by different metrics. Additional results ingeneralized task settings further demonstrate the usefulness of our proposed methods. We have made both our implementation codeand the ShapeNet-Skeleton dataset publicly available at ble at https://github.com/tangjiapeng/SkeletonNet." @default.
• W3048809134 created "2020-08-18" @default.
• W3048809134 creator A5015737161 @default.
• W3048809134 creator A5032352025 @default.
• W3048809134 creator A5042771880 @default.
• W3048809134 creator A5065964089 @default.
• W3048809134 creator A5090954747 @default.
• W3048809134 date "2020-08-13" @default.
• W3048809134 modified "2023-10-01" @default.
• W3048809134 title "SkeletonNet: A Topology-Preserving Solution for Learning Mesh Reconstruction of Object Surfaces from RGB Images" @default.
• W3048809134 cites W1591870335 @default.
• W3048809134 cites W1826313674 @default.
• W3048809134 cites W1901129140 @default.
• W3048809134 cites W1963962785 @default.
• W3048809134 cites W1967554269 @default.
• W3048809134 cites W1971169262 @default.
• W3048809134 cites W1987648924 @default.
• W3048809134 cites W1992855374 @default.
• W3048809134 cites W1995756857 @default.
• W3048809134 cites W2025973801 @default.
• W3048809134 cites W2074178568 @default.
• W3048809134 cites W2080751646 @default.
• W3048809134 cites W2097117768 @default.
• W3048809134 cites W2099471712 @default.
• W3048809134 cites W2115309634 @default.
• W3048809134 cites W2115920764 @default.
• W3048809134 cites W2117248802 @default.
• W3048809134 cites W2128052895 @default.
• W3048809134 cites W2163605009 @default.
• W3048809134 cites W2167335287 @default.
• W3048809134 cites W2171056981 @default.
• W3048809134 cites W2190691619 @default.
• W3048809134 cites W2194775991 @default.
• W3048809134 cites W2229412420 @default.
• W3048809134 cites W2270381286 @default.
• W3048809134 cites W2342277278 @default.
• W3048809134 cites W2495603374 @default.
• W3048809134 cites W2546066744 @default.
• W3048809134 cites W2556802233 @default.
• W3048809134 cites W2560722161 @default.
• W3048809134 cites W2603429625 @default.
• W3048809134 cites W2606840594 @default.
• W3048809134 cites W2609754928 @default.
• W3048809134 cites W2738835886 @default.
• W3048809134 cites W2794693922 @default.
• W3048809134 cites W2890556874 @default.
• W3048809134 cites W2895596173 @default.
• W3048809134 cites W2897619360 @default.
• W3048809134 cites W2914390273 @default.
• W3048809134 cites W2929245070 @default.
• W3048809134 cites W2930206194 @default.
• W3048809134 cites W2962778872 @default.
• W3048809134 cites W2962835968 @default.
• W3048809134 cites W2962849139 @default.
• W3048809134 cites W2962885944 @default.
• W3048809134 cites W2963527086 @default.
• W3048809134 cites W2963563548 @default.
• W3048809134 cites W2963627347 @default.
• W3048809134 cites W2963648573 @default.
• W3048809134 cites W2963926543 @default.
• W3048809134 cites W2963942118 @default.
• W3048809134 cites W2963966978 @default.
• W3048809134 cites W2964121028 @default.
• W3048809134 cites W2964137676 @default.
• W3048809134 cites W2964310454 @default.
• W3048809134 cites W2970899367 @default.
• W3048809134 cites W2973014570 @default.
• W3048809134 cites W2981978060 @default.
• W3048809134 cites W2984210651 @default.
• W3048809134 cites W2991621301 @default.
• W3048809134 cites W2993195924 @default.
• W3048809134 cites W3024451790 @default.
• W3048809134 cites W3034395814 @default.
• W3048809134 cites W3034513883 @default.
• W3048809134 cites W3034812707 @default.
• W3048809134 cites W3035163517 @default.
• W3048809134 cites W3035424742 @default.
• W3048809134 cites W3035507572 @default.
• W3048809134 cites W3098903961 @default.
• W3048809134 cites W3100484988 @default.
• W3048809134 cites W3101027576 @default.
• W3048809134 cites W3104141662 @default.
• W3048809134 cites W3105974636 @default.
• W3048809134 cites W3106148219 @default.
• W3048809134 cites W3117476483 @default.
• W3048809134 cites W3128614118 @default.
• W3048809134 cites W3159914786 @default.
• W3048809134 cites W3181584201 @default.
• W3048809134 cites W77022496 @default.
• W3048809134 cites W3103352717 @default.
• W3048809134 doi "https://doi.org/10.48550/arxiv.2008.05742" @default.
• W3048809134 hasPublicationYear "2020" @default.
• W3048809134 type Work @default.
• W3048809134 sameAs 3048809134 @default.
• W3048809134 citedByCount "2" @default.
• W3048809134 countsByYear W30488091342021 @default.
• W3048809134 crossrefType "posted-content" @default.
• W3048809134 hasAuthorship W3048809134A5015737161 @default.
• W3048809134 hasAuthorship W3048809134A5032352025 @default.
• W3048809134 hasAuthorship W3048809134A5042771880 @default.

• next