Matches in SemOpenAlex for { <https://semopenalex.org/work/W2965103194> ?p ?o ?g. }
Showing items 1 to 89 of
89
with 100 items per page.
- W2965103194 endingPage "411" @default.
- W2965103194 startingPage "399" @default.
- W2965103194 abstract "Scientific imaging techniques such as optical and electron microscopy and computed tomography (CT) scanning are used to study the 3D structure of an object through 2D observations. These observations are related to the original 3D object through orthogonal integral projections. For common 3D reconstruction algorithms, computational efficiency requires the modeling of the 3D structures to take place in Fourier space by applying the Fourier slice theorem. At present, it is unclear how to differentiate through the projection operator, and hence current learning algorithms can not rely on gradient based methods to optimize 3D structure models. In this paper we show how back-propagation through the projection operator in Fourier space can be achieved. We demonstrate the validity of the approach with experiments on 3D reconstruction of proteins. We further extend our approach to learning probabilistic models of 3D objects. This allows us to predict regions of low sampling rates or estimate noise. A higher sample efficiency can be reached by utilizing the learned uncertainties of the 3D structure as an unsupervised estimate of the model fit. Finally, we demonstrate how the reconstruction algorithm can be extended with an amortized inference scheme on unknown attributes such as object pose. Through empirical studies we show that joint inference of the 3D structure and the object pose becomes more difficult when the ground truth object contains more symmetries. Due to the presence of for instance (approximate) rotational symmetries, the pose estimation can easily get stuck in local optima, inhibiting a fine-grained high-quality estimate of the 3D structure." @default.
- W2965103194 created "2019-08-13" @default.
- W2965103194 creator A5018601296 @default.
- W2965103194 creator A5035123135 @default.
- W2965103194 creator A5058031547 @default.
- W2965103194 creator A5069522766 @default.
- W2965103194 creator A5087368991 @default.
- W2965103194 date "2019-06-18" @default.
- W2965103194 modified "2023-10-02" @default.
- W2965103194 title "Differentiable Probabilistic Models of Scientific Imaging with the Fourier Slice Theorem." @default.
- W2965103194 cites W1516111018 @default.
- W2965103194 cites W1997581342 @default.
- W2965103194 cites W2017508876 @default.
- W2965103194 cites W2052341985 @default.
- W2965103194 cites W2070183703 @default.
- W2965103194 cites W2082841340 @default.
- W2965103194 cites W2100455255 @default.
- W2965103194 cites W2101866544 @default.
- W2965103194 cites W2104234755 @default.
- W2965103194 cites W2129908184 @default.
- W2965103194 cites W2142338805 @default.
- W2965103194 cites W2152562710 @default.
- W2965103194 cites W2469266052 @default.
- W2965103194 cites W2587625522 @default.
- W2965103194 cites W2786623728 @default.
- W2965103194 cites W570638918 @default.
- W2965103194 cites W603908379 @default.
- W2965103194 hasPublicationYear "2019" @default.
- W2965103194 type Work @default.
- W2965103194 sameAs 2965103194 @default.
- W2965103194 citedByCount "1" @default.
- W2965103194 countsByYear W29651031942020 @default.
- W2965103194 crossrefType "proceedings-article" @default.
- W2965103194 hasAuthorship W2965103194A5018601296 @default.
- W2965103194 hasAuthorship W2965103194A5035123135 @default.
- W2965103194 hasAuthorship W2965103194A5058031547 @default.
- W2965103194 hasAuthorship W2965103194A5069522766 @default.
- W2965103194 hasAuthorship W2965103194A5087368991 @default.
- W2965103194 hasConcept C102519508 @default.
- W2965103194 hasConcept C11413529 @default.
- W2965103194 hasConcept C134306372 @default.
- W2965103194 hasConcept C141379421 @default.
- W2965103194 hasConcept C154945302 @default.
- W2965103194 hasConcept C2776214188 @default.
- W2965103194 hasConcept C31972630 @default.
- W2965103194 hasConcept C33923547 @default.
- W2965103194 hasConcept C41008148 @default.
- W2965103194 hasConcept C49937458 @default.
- W2965103194 hasConcept C57493831 @default.
- W2965103194 hasConceptScore W2965103194C102519508 @default.
- W2965103194 hasConceptScore W2965103194C11413529 @default.
- W2965103194 hasConceptScore W2965103194C134306372 @default.
- W2965103194 hasConceptScore W2965103194C141379421 @default.
- W2965103194 hasConceptScore W2965103194C154945302 @default.
- W2965103194 hasConceptScore W2965103194C2776214188 @default.
- W2965103194 hasConceptScore W2965103194C31972630 @default.
- W2965103194 hasConceptScore W2965103194C33923547 @default.
- W2965103194 hasConceptScore W2965103194C41008148 @default.
- W2965103194 hasConceptScore W2965103194C49937458 @default.
- W2965103194 hasConceptScore W2965103194C57493831 @default.
- W2965103194 hasLocation W29651031941 @default.
- W2965103194 hasOpenAccess W2965103194 @default.
- W2965103194 hasPrimaryLocation W29651031941 @default.
- W2965103194 hasRelatedWork W129947213 @default.
- W2965103194 hasRelatedWork W141094298 @default.
- W2965103194 hasRelatedWork W1517794406 @default.
- W2965103194 hasRelatedWork W1543662664 @default.
- W2965103194 hasRelatedWork W1602589451 @default.
- W2965103194 hasRelatedWork W1940260009 @default.
- W2965103194 hasRelatedWork W2025089058 @default.
- W2965103194 hasRelatedWork W2125315716 @default.
- W2965103194 hasRelatedWork W2151489423 @default.
- W2965103194 hasRelatedWork W2469166317 @default.
- W2965103194 hasRelatedWork W2579022742 @default.
- W2965103194 hasRelatedWork W2902905851 @default.
- W2965103194 hasRelatedWork W2912351097 @default.
- W2965103194 hasRelatedWork W2951801519 @default.
- W2965103194 hasRelatedWork W2963564867 @default.
- W2965103194 hasRelatedWork W2998732054 @default.
- W2965103194 hasRelatedWork W3099953080 @default.
- W2965103194 hasRelatedWork W3129179760 @default.
- W2965103194 hasRelatedWork W3195979123 @default.
- W2965103194 hasRelatedWork W3200228484 @default.
- W2965103194 isParatext "false" @default.
- W2965103194 isRetracted "false" @default.
- W2965103194 magId "2965103194" @default.
- W2965103194 workType "article" @default.