Matches in SemOpenAlex for { <https://semopenalex.org/work/W4297295155> ?p ?o ?g. }
Showing items 1 to 75 of
75
with 100 items per page.
- W4297295155 abstract "In this paper, we present a learning based approach to depth fusion, i.e., dense 3D reconstruction from multiple depth images. The most common approach to depth fusion is based on averaging truncated signed distance functions, which was originally proposed by Curless and Levoy in 1996. While this method is simple and provides great results, it is not able to reconstruct (partially) occluded surfaces and requires a large number frames to filter out sensor noise and outliers. Motivated by the availability of large 3D model repositories and recent advances in deep learning, we present a novel 3D CNN architecture that learns to predict an implicit surface representation from the input depth maps. Our learning based method significantly outperforms the traditional volumetric fusion approach in terms of noise reduction and outlier suppression. By learning the structure of real world 3D objects and scenes, our approach is further able to reconstruct occluded regions and to fill in gaps in the reconstruction. We demonstrate that our learning based approach outperforms both vanilla TSDF fusion as well as TV-L1 fusion on the task of volumetric fusion. Further, we demonstrate state-of-the-art 3D shape completion results." @default.
- W4297295155 created "2022-09-28" @default.
- W4297295155 creator A5011359067 @default.
- W4297295155 creator A5016606943 @default.
- W4297295155 creator A5062072482 @default.
- W4297295155 creator A5067881740 @default.
- W4297295155 date "2017-04-04" @default.
- W4297295155 modified "2023-09-23" @default.
- W4297295155 title "OctNetFusion: Learning Depth Fusion from Data" @default.
- W4297295155 doi "https://doi.org/10.48550/arxiv.1704.01047" @default.
- W4297295155 hasPublicationYear "2017" @default.
- W4297295155 type Work @default.
- W4297295155 citedByCount "0" @default.
- W4297295155 crossrefType "posted-content" @default.
- W4297295155 hasAuthorship W4297295155A5011359067 @default.
- W4297295155 hasAuthorship W4297295155A5016606943 @default.
- W4297295155 hasAuthorship W4297295155A5062072482 @default.
- W4297295155 hasAuthorship W4297295155A5067881740 @default.
- W4297295155 hasBestOaLocation W42972951551 @default.
- W4297295155 hasConcept C106131492 @default.
- W4297295155 hasConcept C108583219 @default.
- W4297295155 hasConcept C115961682 @default.
- W4297295155 hasConcept C138885662 @default.
- W4297295155 hasConcept C153180895 @default.
- W4297295155 hasConcept C154945302 @default.
- W4297295155 hasConcept C158525013 @default.
- W4297295155 hasConcept C162324750 @default.
- W4297295155 hasConcept C163294075 @default.
- W4297295155 hasConcept C17744445 @default.
- W4297295155 hasConcept C187736073 @default.
- W4297295155 hasConcept C199539241 @default.
- W4297295155 hasConcept C2776359362 @default.
- W4297295155 hasConcept C2780451532 @default.
- W4297295155 hasConcept C31972630 @default.
- W4297295155 hasConcept C41008148 @default.
- W4297295155 hasConcept C41895202 @default.
- W4297295155 hasConcept C79337645 @default.
- W4297295155 hasConcept C94625758 @default.
- W4297295155 hasConcept C99498987 @default.
- W4297295155 hasConceptScore W4297295155C106131492 @default.
- W4297295155 hasConceptScore W4297295155C108583219 @default.
- W4297295155 hasConceptScore W4297295155C115961682 @default.
- W4297295155 hasConceptScore W4297295155C138885662 @default.
- W4297295155 hasConceptScore W4297295155C153180895 @default.
- W4297295155 hasConceptScore W4297295155C154945302 @default.
- W4297295155 hasConceptScore W4297295155C158525013 @default.
- W4297295155 hasConceptScore W4297295155C162324750 @default.
- W4297295155 hasConceptScore W4297295155C163294075 @default.
- W4297295155 hasConceptScore W4297295155C17744445 @default.
- W4297295155 hasConceptScore W4297295155C187736073 @default.
- W4297295155 hasConceptScore W4297295155C199539241 @default.
- W4297295155 hasConceptScore W4297295155C2776359362 @default.
- W4297295155 hasConceptScore W4297295155C2780451532 @default.
- W4297295155 hasConceptScore W4297295155C31972630 @default.
- W4297295155 hasConceptScore W4297295155C41008148 @default.
- W4297295155 hasConceptScore W4297295155C41895202 @default.
- W4297295155 hasConceptScore W4297295155C79337645 @default.
- W4297295155 hasConceptScore W4297295155C94625758 @default.
- W4297295155 hasConceptScore W4297295155C99498987 @default.
- W4297295155 hasLocation W42972951551 @default.
- W4297295155 hasOpenAccess W4297295155 @default.
- W4297295155 hasPrimaryLocation W42972951551 @default.
- W4297295155 hasRelatedWork W1987645221 @default.
- W4297295155 hasRelatedWork W2005185696 @default.
- W4297295155 hasRelatedWork W2044124120 @default.
- W4297295155 hasRelatedWork W2161229648 @default.
- W4297295155 hasRelatedWork W2483420468 @default.
- W4297295155 hasRelatedWork W2733060750 @default.
- W4297295155 hasRelatedWork W2766146978 @default.
- W4297295155 hasRelatedWork W2773120646 @default.
- W4297295155 hasRelatedWork W2998718015 @default.
- W4297295155 hasRelatedWork W3185738386 @default.
- W4297295155 isParatext "false" @default.
- W4297295155 isRetracted "false" @default.
- W4297295155 workType "article" @default.