FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3175617025> ?p ?o ?g. }

• W3175617025 abstract "Due to the scarcity of annotated scene flow data, self-supervised scene flow learning in point clouds has attracted increasing attention. In the self-supervised manner, establishing correspondences between two point clouds to ap-proximate scene flow is an effective approach. Previous methods often obtain correspondences by applying point-wise matching that only takes the distance on 3D point co-ordinates into account, introducing two critical issues: (1) it overlooks other discriminative measures, such as color and surface normal, which often bring fruitful clues for ac-curate matching; and (2) it often generates sub-par performance, as the matching is operated in an unconstrained situation, where multiple points can be ended up with the same corresponding point. To address the issues, we formulate this matching task as an optimal transport problem. The output optimal assignment matrix can be utilized to guide the generation of pseudo ground truth. In this optimal transport, we design the transport cost by considering multiple descriptors and encourage one-to-one matching by mass equality constraints. Also, constructing a graph on the points, a random walk module is introduced to encourage the local consistency of the pseudo labels. Comprehensive experiments on FlyingThings3D and KITTI show that our method achieves state-of-the-art performance among self-supervised learning methods. Our self-supervised method even performs on par with some supervised learning approaches, although we do not need any ground truth flow for training." @default.
• W3175617025 created "2021-07-05" @default.
• W3175617025 creator A5025731189 @default.
• W3175617025 creator A5029912845 @default.
• W3175617025 creator A5082874896 @default.
• W3175617025 date "2021-06-01" @default.
• W3175617025 modified "2023-10-11" @default.
• W3175617025 title "Self-Point-Flow: Self-Supervised Scene Flow Estimation from Point Clouds with Optimal Transport and Random Walk" @default.
• W3175617025 cites W1508115313 @default.
• W3175617025 cites W1921093919 @default.
• W3175617025 cites W1993850091 @default.
• W3175617025 cites W2017849585 @default.
• W3175617025 cites W2088692258 @default.
• W3175617025 cites W2098500213 @default.
• W3175617025 cites W2134670261 @default.
• W3175617025 cites W2286655030 @default.
• W3175617025 cites W2560722161 @default.
• W3175617025 cites W2563098792 @default.
• W3175617025 cites W2604909019 @default.
• W3175617025 cites W2737996100 @default.
• W3175617025 cites W2788158258 @default.
• W3175617025 cites W2798458055 @default.
• W3175617025 cites W2949023359 @default.
• W3175617025 cites W2962771259 @default.
• W3175617025 cites W2963342403 @default.
• W3175617025 cites W2963583471 @default.
• W3175617025 cites W2963652593 @default.
• W3175617025 cites W2963954891 @default.
• W3175617025 cites W2971686478 @default.
• W3175617025 cites W3012255272 @default.
• W3175617025 cites W3034275286 @default.
• W3175617025 cites W3034308492 @default.
• W3175617025 cites W3034321406 @default.
• W3175617025 cites W3035574168 @default.
• W3175617025 cites W3097139398 @default.
• W3175617025 cites W3100388886 @default.
• W3175617025 cites W3106932526 @default.
• W3175617025 cites W3122159272 @default.
• W3175617025 cites W4206471589 @default.
• W3175617025 doi "https://doi.org/10.1109/cvpr46437.2021.01532" @default.
• W3175617025 hasPublicationYear "2021" @default.
• W3175617025 type Work @default.
• W3175617025 sameAs 3175617025 @default.
• W3175617025 citedByCount "19" @default.
• W3175617025 countsByYear W31756170252021 @default.
• W3175617025 countsByYear W31756170252022 @default.
• W3175617025 countsByYear W31756170252023 @default.
• W3175617025 crossrefType "proceedings-article" @default.
• W3175617025 hasAuthorship W3175617025A5025731189 @default.
• W3175617025 hasAuthorship W3175617025A5029912845 @default.
• W3175617025 hasAuthorship W3175617025A5082874896 @default.
• W3175617025 hasBestOaLocation W31756170252 @default.
• W3175617025 hasConcept C105795698 @default.
• W3175617025 hasConcept C119857082 @default.
• W3175617025 hasConcept C131979681 @default.
• W3175617025 hasConcept C146849305 @default.
• W3175617025 hasConcept C153180895 @default.
• W3175617025 hasConcept C154945302 @default.
• W3175617025 hasConcept C165064840 @default.
• W3175617025 hasConcept C200336642 @default.
• W3175617025 hasConcept C2524010 @default.
• W3175617025 hasConcept C2776436953 @default.
• W3175617025 hasConcept C28719098 @default.
• W3175617025 hasConcept C31972630 @default.
• W3175617025 hasConcept C33923547 @default.
• W3175617025 hasConcept C38349280 @default.
• W3175617025 hasConcept C41008148 @default.
• W3175617025 hasConcept C97931131 @default.
• W3175617025 hasConceptScore W3175617025C105795698 @default.
• W3175617025 hasConceptScore W3175617025C119857082 @default.
• W3175617025 hasConceptScore W3175617025C131979681 @default.
• W3175617025 hasConceptScore W3175617025C146849305 @default.
• W3175617025 hasConceptScore W3175617025C153180895 @default.
• W3175617025 hasConceptScore W3175617025C154945302 @default.
• W3175617025 hasConceptScore W3175617025C165064840 @default.
• W3175617025 hasConceptScore W3175617025C200336642 @default.
• W3175617025 hasConceptScore W3175617025C2524010 @default.
• W3175617025 hasConceptScore W3175617025C2776436953 @default.
• W3175617025 hasConceptScore W3175617025C28719098 @default.
• W3175617025 hasConceptScore W3175617025C31972630 @default.
• W3175617025 hasConceptScore W3175617025C33923547 @default.
• W3175617025 hasConceptScore W3175617025C38349280 @default.
• W3175617025 hasConceptScore W3175617025C41008148 @default.
• W3175617025 hasConceptScore W3175617025C97931131 @default.
• W3175617025 hasFunder F4320320671 @default.
• W3175617025 hasLocation W31756170251 @default.
• W3175617025 hasLocation W31756170252 @default.
• W3175617025 hasOpenAccess W3175617025 @default.
• W3175617025 hasPrimaryLocation W31756170251 @default.
• W3175617025 hasRelatedWork W2153315159 @default.
• W3175617025 hasRelatedWork W2343679784 @default.
• W3175617025 hasRelatedWork W2345979715 @default.
• W3175617025 hasRelatedWork W2562256921 @default.
• W3175617025 hasRelatedWork W259157601 @default.
• W3175617025 hasRelatedWork W2965546495 @default.
• W3175617025 hasRelatedWork W3103844505 @default.
• W3175617025 hasRelatedWork W4205463238 @default.
• W3175617025 hasRelatedWork W4229439434 @default.
• W3175617025 hasRelatedWork W4386821908 @default.
• W3175617025 isParatext "false" @default.

• next