Matches in SemOpenAlex for { <https://semopenalex.org/work/W4310560219> ?p ?o ?g. }
Showing items 1 to 70 of
70
with 100 items per page.
- W4310560219 abstract "Normal estimation for unstructured point clouds is an important task in 3D computer vision. Current methods achieve encouraging results by mapping local patches to normal vectors or learning local surface fitting using neural networks. However, these methods are not generalized well to unseen scenarios and are sensitive to parameter settings. To resolve these issues, we propose an implicit function to learn an angle field around the normal of each point in the spherical coordinate system, which is dubbed as Neural Angle Fields (NeAF). Instead of directly predicting the normal of an input point, we predict the angle offset between the ground truth normal and a randomly sampled query normal. This strategy pushes the network to observe more diverse samples, which leads to higher prediction accuracy in a more robust manner. To predict normals from the learned angle fields at inference time, we randomly sample query vectors in a unit spherical space and take the vectors with minimal angle values as the predicted normals. To further leverage the prior learned by NeAF, we propose to refine the predicted normal vectors by minimizing the angle offsets. The experimental results with synthetic data and real scans show significant improvements over the state-of-the-art under widely used benchmarks." @default.
- W4310560219 created "2022-12-12" @default.
- W4310560219 creator A5015894529 @default.
- W4310560219 creator A5034970671 @default.
- W4310560219 creator A5042932900 @default.
- W4310560219 creator A5060588302 @default.
- W4310560219 creator A5078945863 @default.
- W4310560219 date "2022-11-30" @default.
- W4310560219 modified "2023-09-26" @default.
- W4310560219 title "NeAF: Learning Neural Angle Fields for Point Normal Estimation" @default.
- W4310560219 doi "https://doi.org/10.48550/arxiv.2211.16869" @default.
- W4310560219 hasPublicationYear "2022" @default.
- W4310560219 type Work @default.
- W4310560219 citedByCount "0" @default.
- W4310560219 crossrefType "posted-content" @default.
- W4310560219 hasAuthorship W4310560219A5015894529 @default.
- W4310560219 hasAuthorship W4310560219A5034970671 @default.
- W4310560219 hasAuthorship W4310560219A5042932900 @default.
- W4310560219 hasAuthorship W4310560219A5060588302 @default.
- W4310560219 hasAuthorship W4310560219A5078945863 @default.
- W4310560219 hasBestOaLocation W43105602191 @default.
- W4310560219 hasConcept C11413529 @default.
- W4310560219 hasConcept C118732077 @default.
- W4310560219 hasConcept C131979681 @default.
- W4310560219 hasConcept C153083717 @default.
- W4310560219 hasConcept C153180895 @default.
- W4310560219 hasConcept C154945302 @default.
- W4310560219 hasConcept C175291020 @default.
- W4310560219 hasConcept C199360897 @default.
- W4310560219 hasConcept C2524010 @default.
- W4310560219 hasConcept C2776214188 @default.
- W4310560219 hasConcept C2776799497 @default.
- W4310560219 hasConcept C28719098 @default.
- W4310560219 hasConcept C31972630 @default.
- W4310560219 hasConcept C33923547 @default.
- W4310560219 hasConcept C41008148 @default.
- W4310560219 hasConcept C50644808 @default.
- W4310560219 hasConceptScore W4310560219C11413529 @default.
- W4310560219 hasConceptScore W4310560219C118732077 @default.
- W4310560219 hasConceptScore W4310560219C131979681 @default.
- W4310560219 hasConceptScore W4310560219C153083717 @default.
- W4310560219 hasConceptScore W4310560219C153180895 @default.
- W4310560219 hasConceptScore W4310560219C154945302 @default.
- W4310560219 hasConceptScore W4310560219C175291020 @default.
- W4310560219 hasConceptScore W4310560219C199360897 @default.
- W4310560219 hasConceptScore W4310560219C2524010 @default.
- W4310560219 hasConceptScore W4310560219C2776214188 @default.
- W4310560219 hasConceptScore W4310560219C2776799497 @default.
- W4310560219 hasConceptScore W4310560219C28719098 @default.
- W4310560219 hasConceptScore W4310560219C31972630 @default.
- W4310560219 hasConceptScore W4310560219C33923547 @default.
- W4310560219 hasConceptScore W4310560219C41008148 @default.
- W4310560219 hasConceptScore W4310560219C50644808 @default.
- W4310560219 hasLocation W43105602191 @default.
- W4310560219 hasLocation W43105602192 @default.
- W4310560219 hasOpenAccess W4310560219 @default.
- W4310560219 hasPrimaryLocation W43105602191 @default.
- W4310560219 hasRelatedWork W1974774383 @default.
- W4310560219 hasRelatedWork W2130319516 @default.
- W4310560219 hasRelatedWork W2169427544 @default.
- W4310560219 hasRelatedWork W2807388419 @default.
- W4310560219 hasRelatedWork W2897576080 @default.
- W4310560219 hasRelatedWork W2979718872 @default.
- W4310560219 hasRelatedWork W3158534694 @default.
- W4310560219 hasRelatedWork W3206828132 @default.
- W4310560219 hasRelatedWork W4290774832 @default.
- W4310560219 hasRelatedWork W4293067784 @default.
- W4310560219 isParatext "false" @default.
- W4310560219 isRetracted "false" @default.
- W4310560219 workType "article" @default.