Matches in SemOpenAlex for { <https://semopenalex.org/work/W3107175280> ?p ?o ?g. }
- W3107175280 endingPage "15" @default.
- W3107175280 startingPage "1" @default.
- W3107175280 abstract "In this paper, we present iOrthoPredictor, a novel system to visually predict teeth alignment in photographs. Our system takes a frontal face image of a patient with visible malpositioned teeth along with a corresponding 3D teeth model as input, and generates a facial image with aligned teeth, simulating a real orthodontic treatment effect. The key enabler of our method is an effective disentanglement of an explicit representation of the teeth geometry from the in-mouth appearance, where the accuracy of teeth geometry transformation is ensured by the 3D teeth model while the in-mouth appearance is modeled as a latent variable. The disentanglement enables us to achieve fine-scale geometry control over the alignment while retaining the original teeth appearance attributes and lighting conditions. The whole pipeline consists of three deep neural networks: a U-Net architecture to explicitly extract the 2D teeth silhouette maps representing the teeth geometry in the input photo, a novel multilayer perceptron (MLP) based network to predict the aligned 3D teeth model, and an encoder-decoder based generative model to synthesize the in-mouth appearance conditional on the original teeth appearance and the aligned teeth geometry. Extensive experimental results and a user study demonstrate that iOrthoPredictor is effective in qualitatively predicting teeth alignment, and applicable to the orthodontic industry." @default.
- W3107175280 created "2020-12-07" @default.
- W3107175280 creator A5008384374 @default.
- W3107175280 creator A5008766810 @default.
- W3107175280 creator A5027671723 @default.
- W3107175280 creator A5035236015 @default.
- W3107175280 creator A5046142379 @default.
- W3107175280 creator A5046810069 @default.
- W3107175280 creator A5050890792 @default.
- W3107175280 date "2020-12-31" @default.
- W3107175280 modified "2023-10-15" @default.
- W3107175280 title "iOrthoPredictor" @default.
- W3107175280 cites W1763426478 @default.
- W3107175280 cites W1901129140 @default.
- W3107175280 cites W1967577110 @default.
- W3107175280 cites W1987010331 @default.
- W3107175280 cites W1999360130 @default.
- W3107175280 cites W2004068758 @default.
- W3107175280 cites W2015454174 @default.
- W3107175280 cites W2030521412 @default.
- W3107175280 cites W2033759568 @default.
- W3107175280 cites W2057016804 @default.
- W3107175280 cites W2062618418 @default.
- W3107175280 cites W2066813690 @default.
- W3107175280 cites W2072637632 @default.
- W3107175280 cites W2082997166 @default.
- W3107175280 cites W2086331119 @default.
- W3107175280 cites W2095297868 @default.
- W3107175280 cites W2100415658 @default.
- W3107175280 cites W2105038642 @default.
- W3107175280 cites W2107813907 @default.
- W3107175280 cites W2115273023 @default.
- W3107175280 cites W2146991130 @default.
- W3107175280 cites W2147901574 @default.
- W3107175280 cites W2152516042 @default.
- W3107175280 cites W2164490837 @default.
- W3107175280 cites W2432954115 @default.
- W3107175280 cites W2468764576 @default.
- W3107175280 cites W2508756538 @default.
- W3107175280 cites W2555445683 @default.
- W3107175280 cites W2557414982 @default.
- W3107175280 cites W2558151185 @default.
- W3107175280 cites W2601564443 @default.
- W3107175280 cites W2603777577 @default.
- W3107175280 cites W2738406145 @default.
- W3107175280 cites W2738588019 @default.
- W3107175280 cites W2776121517 @default.
- W3107175280 cites W2798600195 @default.
- W3107175280 cites W2806833697 @default.
- W3107175280 cites W2807725536 @default.
- W3107175280 cites W2883861033 @default.
- W3107175280 cites W2898174740 @default.
- W3107175280 cites W2902266071 @default.
- W3107175280 cites W2903093723 @default.
- W3107175280 cites W2955353723 @default.
- W3107175280 cites W2957407072 @default.
- W3107175280 cites W2962793481 @default.
- W3107175280 cites W2962963674 @default.
- W3107175280 cites W2963073614 @default.
- W3107175280 cites W2963245486 @default.
- W3107175280 cites W2963255313 @default.
- W3107175280 cites W2963266880 @default.
- W3107175280 cites W2963444790 @default.
- W3107175280 cites W2963516695 @default.
- W3107175280 cites W2963767194 @default.
- W3107175280 cites W2963890275 @default.
- W3107175280 cites W2963901923 @default.
- W3107175280 cites W2964148878 @default.
- W3107175280 cites W2966926453 @default.
- W3107175280 cites W2976736845 @default.
- W3107175280 cites W2981682056 @default.
- W3107175280 cites W2985764327 @default.
- W3107175280 cites W2986780196 @default.
- W3107175280 cites W2988149145 @default.
- W3107175280 cites W2989149111 @default.
- W3107175280 cites W3001217199 @default.
- W3107175280 cites W3043547428 @default.
- W3107175280 cites W3144890709 @default.
- W3107175280 cites W345598540 @default.
- W3107175280 cites W4231326516 @default.
- W3107175280 cites W4236231454 @default.
- W3107175280 cites W4240726888 @default.
- W3107175280 cites W845365781 @default.
- W3107175280 doi "https://doi.org/10.1145/3414685.3417771" @default.
- W3107175280 hasPublicationYear "2020" @default.
- W3107175280 type Work @default.
- W3107175280 sameAs 3107175280 @default.
- W3107175280 citedByCount "4" @default.
- W3107175280 countsByYear W31071752802021 @default.
- W3107175280 countsByYear W31071752802022 @default.
- W3107175280 countsByYear W31071752802023 @default.
- W3107175280 crossrefType "journal-article" @default.
- W3107175280 hasAuthorship W3107175280A5008384374 @default.
- W3107175280 hasAuthorship W3107175280A5008766810 @default.
- W3107175280 hasAuthorship W3107175280A5027671723 @default.
- W3107175280 hasAuthorship W3107175280A5035236015 @default.
- W3107175280 hasAuthorship W3107175280A5046142379 @default.
- W3107175280 hasAuthorship W3107175280A5046810069 @default.