Matches in SemOpenAlex for { <https://semopenalex.org/work/W4312513149> ?p ?o ?g. }
Showing items 1 to 87 of
87
with 100 items per page.
- W4312513149 abstract "Our work learns a unified model for single-view 3D reconstruction of objects from hundreds of semantic categories. As a scalable alternative to direct 3D supervision, our work relies on segmented image collections for learning 3D of generic categories. Unlike prior works that use similar supervision but learn independent category-specific models from scratch, our approach of learning a unified model simplifies the training process while also allowing the model to benefit from the common structure across categories. Using image collections from standard recognition datasets, we show that our approach allows learning 3D inference for over 150 object categories. We evaluate using two datasets and qualitatively and quantitatively show that our unified reconstruction approach improves over prior category-specific reconstruction baselines. Our final 3D reconstruction model is also capable of zero-shot inference on images from unseen object categories and we empirically show that increasing the number of training categories improves the reconstruction quality." @default.
- W4312513149 created "2023-01-05" @default.
- W4312513149 creator A5029932788 @default.
- W4312513149 creator A5053034244 @default.
- W4312513149 creator A5078659702 @default.
- W4312513149 date "2022-06-01" @default.
- W4312513149 modified "2023-10-18" @default.
- W4312513149 title "Pretrain, Self-train, Distill: A simple recipe for Supersizing 3D Reconstruction" @default.
- W4312513149 cites W1991264156 @default.
- W4312513149 cites W2108598243 @default.
- W4312513149 cites W2194775991 @default.
- W4312513149 cites W2295355433 @default.
- W4312513149 cites W2560722161 @default.
- W4312513149 cites W2760103357 @default.
- W4312513149 cites W2948672349 @default.
- W4312513149 cites W2962770929 @default.
- W4312513149 cites W2962946389 @default.
- W4312513149 cites W2963627347 @default.
- W4312513149 cites W2963926543 @default.
- W4312513149 cites W2981081013 @default.
- W4312513149 cites W2982024234 @default.
- W4312513149 cites W2982191424 @default.
- W4312513149 cites W3008102851 @default.
- W4312513149 cites W3034299016 @default.
- W4312513149 cites W3035148830 @default.
- W4312513149 cites W3035358681 @default.
- W4312513149 cites W3173531806 @default.
- W4312513149 cites W3173617232 @default.
- W4312513149 cites W3176368002 @default.
- W4312513149 cites W3196466825 @default.
- W4312513149 cites W4200150166 @default.
- W4312513149 cites W4288083516 @default.
- W4312513149 doi "https://doi.org/10.1109/cvpr52688.2022.00375" @default.
- W4312513149 hasPublicationYear "2022" @default.
- W4312513149 type Work @default.
- W4312513149 citedByCount "1" @default.
- W4312513149 countsByYear W43125131492023 @default.
- W4312513149 crossrefType "proceedings-article" @default.
- W4312513149 hasAuthorship W4312513149A5029932788 @default.
- W4312513149 hasAuthorship W4312513149A5053034244 @default.
- W4312513149 hasAuthorship W4312513149A5078659702 @default.
- W4312513149 hasBestOaLocation W43125131492 @default.
- W4312513149 hasConcept C109950114 @default.
- W4312513149 hasConcept C111919701 @default.
- W4312513149 hasConcept C119857082 @default.
- W4312513149 hasConcept C141379421 @default.
- W4312513149 hasConcept C153180895 @default.
- W4312513149 hasConcept C154945302 @default.
- W4312513149 hasConcept C204321447 @default.
- W4312513149 hasConcept C2776214188 @default.
- W4312513149 hasConcept C2781238097 @default.
- W4312513149 hasConcept C31972630 @default.
- W4312513149 hasConcept C41008148 @default.
- W4312513149 hasConcept C48044578 @default.
- W4312513149 hasConcept C77088390 @default.
- W4312513149 hasConcept C98045186 @default.
- W4312513149 hasConceptScore W4312513149C109950114 @default.
- W4312513149 hasConceptScore W4312513149C111919701 @default.
- W4312513149 hasConceptScore W4312513149C119857082 @default.
- W4312513149 hasConceptScore W4312513149C141379421 @default.
- W4312513149 hasConceptScore W4312513149C153180895 @default.
- W4312513149 hasConceptScore W4312513149C154945302 @default.
- W4312513149 hasConceptScore W4312513149C204321447 @default.
- W4312513149 hasConceptScore W4312513149C2776214188 @default.
- W4312513149 hasConceptScore W4312513149C2781238097 @default.
- W4312513149 hasConceptScore W4312513149C31972630 @default.
- W4312513149 hasConceptScore W4312513149C41008148 @default.
- W4312513149 hasConceptScore W4312513149C48044578 @default.
- W4312513149 hasConceptScore W4312513149C77088390 @default.
- W4312513149 hasConceptScore W4312513149C98045186 @default.
- W4312513149 hasLocation W43125131491 @default.
- W4312513149 hasLocation W43125131492 @default.
- W4312513149 hasOpenAccess W4312513149 @default.
- W4312513149 hasPrimaryLocation W43125131491 @default.
- W4312513149 hasRelatedWork W2093747323 @default.
- W4312513149 hasRelatedWork W2169256201 @default.
- W4312513149 hasRelatedWork W2397188463 @default.
- W4312513149 hasRelatedWork W2517246325 @default.
- W4312513149 hasRelatedWork W2792605344 @default.
- W4312513149 hasRelatedWork W2901697715 @default.
- W4312513149 hasRelatedWork W2914011423 @default.
- W4312513149 hasRelatedWork W3011087369 @default.
- W4312513149 hasRelatedWork W3109244347 @default.
- W4312513149 hasRelatedWork W4210454584 @default.
- W4312513149 isParatext "false" @default.
- W4312513149 isRetracted "false" @default.
- W4312513149 workType "article" @default.