Matches in SemOpenAlex for { <https://semopenalex.org/work/W4385804912> ?p ?o ?g. }
- W4385804912 abstract "Inferring 3D object structures from a single image is an ill-posed task due to depth ambiguity and occlusion. Typical resolutions in the literature include leveraging 2D or 3D ground truth for supervised learning, as well as imposing hand-crafted symmetry priors or using an implicit representation to hallucinate novel viewpoints for unsupervised methods. In this work, we propose a general adversarial learning framework for solving Unsupervised 2D to Explicit 3D Style Transfer (UE3DST). Specifically, we merge two architectures: the unsupervised explicit 3D reconstruction network of Wu et al. and the Generative Adversarial Network (GAN) named StarGAN-v2. We experiment across three facial datasets (Basel Face Model, 3DFAW and CelebA-HQ) and show that our solution is able to outperform well established solutions such as DepthNet in 3D reconstruction and Pix2NeRF in conditional style transfer, while we also justify the individual contributions of our model components via ablation. In contrast to the aforementioned baselines, our scheme produces features for explicit 3D rendering, which can be manipulated and utilized in downstream tasks." @default.
- W4385804912 created "2023-08-15" @default.
- W4385804912 creator A5045790971 @default.
- W4385804912 creator A5076265557 @default.
- W4385804912 creator A5086118610 @default.
- W4385804912 date "2023-06-01" @default.
- W4385804912 modified "2023-10-14" @default.
- W4385804912 title "Unsupervised Style-based Explicit 3D Face Reconstruction from Single Image" @default.
- W4385804912 cites W1520997877 @default.
- W4385804912 cites W1567532702 @default.
- W4385804912 cites W1834627138 @default.
- W4385804912 cites W2017814585 @default.
- W4385804912 cites W2044147530 @default.
- W4385804912 cites W2051297709 @default.
- W4385804912 cites W2097307110 @default.
- W4385804912 cites W2107037917 @default.
- W4385804912 cites W2118304946 @default.
- W4385804912 cites W2124600577 @default.
- W4385804912 cites W2520707372 @default.
- W4385804912 cites W2603777577 @default.
- W4385804912 cites W2609883120 @default.
- W4385804912 cites W2883221003 @default.
- W4385804912 cites W2902266071 @default.
- W4385804912 cites W2912990735 @default.
- W4385804912 cites W2962770929 @default.
- W4385804912 cites W2962793481 @default.
- W4385804912 cites W2962907415 @default.
- W4385804912 cites W2963073614 @default.
- W4385804912 cites W2963475767 @default.
- W4385804912 cites W2963590054 @default.
- W4385804912 cites W2963654727 @default.
- W4385804912 cites W2963767194 @default.
- W4385804912 cites W2964053173 @default.
- W4385804912 cites W2964094607 @default.
- W4385804912 cites W2964239644 @default.
- W4385804912 cites W2968940310 @default.
- W4385804912 cites W3000817459 @default.
- W4385804912 cites W3034371424 @default.
- W4385804912 cites W3034600949 @default.
- W4385804912 cites W3035499195 @default.
- W4385804912 cites W3035523051 @default.
- W4385804912 cites W3172610252 @default.
- W4385804912 cites W3173531806 @default.
- W4385804912 cites W3176179930 @default.
- W4385804912 cites W3186205335 @default.
- W4385804912 cites W3188353775 @default.
- W4385804912 cites W4233857083 @default.
- W4385804912 cites W4238767840 @default.
- W4385804912 cites W4312500989 @default.
- W4385804912 cites W4313013782 @default.
- W4385804912 doi "https://doi.org/10.1109/cvprw59228.2023.00079" @default.
- W4385804912 hasPublicationYear "2023" @default.
- W4385804912 type Work @default.
- W4385804912 citedByCount "0" @default.
- W4385804912 crossrefType "proceedings-article" @default.
- W4385804912 hasAuthorship W4385804912A5045790971 @default.
- W4385804912 hasAuthorship W4385804912A5076265557 @default.
- W4385804912 hasAuthorship W4385804912A5086118610 @default.
- W4385804912 hasBestOaLocation W43858049122 @default.
- W4385804912 hasConcept C107673813 @default.
- W4385804912 hasConcept C119857082 @default.
- W4385804912 hasConcept C153180895 @default.
- W4385804912 hasConcept C154945302 @default.
- W4385804912 hasConcept C177769412 @default.
- W4385804912 hasConcept C197129107 @default.
- W4385804912 hasConcept C199360897 @default.
- W4385804912 hasConcept C205711294 @default.
- W4385804912 hasConcept C23123220 @default.
- W4385804912 hasConcept C2780522230 @default.
- W4385804912 hasConcept C2911011789 @default.
- W4385804912 hasConcept C31972630 @default.
- W4385804912 hasConcept C37736160 @default.
- W4385804912 hasConcept C41008148 @default.
- W4385804912 hasConcept C59404180 @default.
- W4385804912 hasConcept C8038995 @default.
- W4385804912 hasConceptScore W4385804912C107673813 @default.
- W4385804912 hasConceptScore W4385804912C119857082 @default.
- W4385804912 hasConceptScore W4385804912C153180895 @default.
- W4385804912 hasConceptScore W4385804912C154945302 @default.
- W4385804912 hasConceptScore W4385804912C177769412 @default.
- W4385804912 hasConceptScore W4385804912C197129107 @default.
- W4385804912 hasConceptScore W4385804912C199360897 @default.
- W4385804912 hasConceptScore W4385804912C205711294 @default.
- W4385804912 hasConceptScore W4385804912C23123220 @default.
- W4385804912 hasConceptScore W4385804912C2780522230 @default.
- W4385804912 hasConceptScore W4385804912C2911011789 @default.
- W4385804912 hasConceptScore W4385804912C31972630 @default.
- W4385804912 hasConceptScore W4385804912C37736160 @default.
- W4385804912 hasConceptScore W4385804912C41008148 @default.
- W4385804912 hasConceptScore W4385804912C59404180 @default.
- W4385804912 hasConceptScore W4385804912C8038995 @default.
- W4385804912 hasLocation W43858049121 @default.
- W4385804912 hasLocation W43858049122 @default.
- W4385804912 hasOpenAccess W4385804912 @default.
- W4385804912 hasPrimaryLocation W43858049121 @default.
- W4385804912 hasRelatedWork W1503414886 @default.
- W4385804912 hasRelatedWork W1863533157 @default.
- W4385804912 hasRelatedWork W2048402902 @default.
- W4385804912 hasRelatedWork W2095660797 @default.
- W4385804912 hasRelatedWork W2292254049 @default.