Matches in SemOpenAlex for { <https://semopenalex.org/work/W4386076101> ?p ?o ?g. }
- W4386076101 abstract "While current multi-frame restoration methods combine information from multiple input images using 2D alignment techniques, recent advances in novel view synthesis are paving the way for a new paradigm relying on volu-metric scene representations. In this work, we introduce the first 3D-based multi-frame denoising method that significantly outperforms its 2D-based counterparts with lower computational requirements. Our method extends the mul-tiplane image (MPI) framework for novel view synthesis by introducing a learnable encoder-renderer pair manipulating multiplane representations in feature space. The encoder fuses information across views and operates in a depth-wise manner while the renderer fuses information across depths and operates in a view-wise manner. The two modules are trained end-to-end and learn to separate depths in an unsupervised way, giving rise to Multiplane Feature (MPF) representations. Experiments on the Spaces and Real Forward-Facing datasets as well as on raw burst data validate our approach for view synthesis, multi-frame denoising, and view synthesis under noisy conditions." @default.
- W4386076101 created "2023-08-23" @default.
- W4386076101 creator A5043251921 @default.
- W4386076101 creator A5078105554 @default.
- W4386076101 creator A5085971943 @default.
- W4386076101 date "2023-06-01" @default.
- W4386076101 modified "2023-10-18" @default.
- W4386076101 title "Efficient View Synthesis and 3D-based Multi-Frame Denoising with Multiplane Feature Representations" @default.
- W4386076101 cites W1906648922 @default.
- W4386076101 cites W1965221572 @default.
- W4386076101 cites W1978508694 @default.
- W4386076101 cites W2028687412 @default.
- W4386076101 cites W2471962767 @default.
- W4386076101 cites W2551052086 @default.
- W4386076101 cites W2699847703 @default.
- W4386076101 cites W2758175304 @default.
- W4386076101 cites W2798664922 @default.
- W4386076101 cites W2943445277 @default.
- W4386076101 cites W2949657144 @default.
- W4386076101 cites W2962927175 @default.
- W4386076101 cites W2963200935 @default.
- W4386076101 cites W2963557767 @default.
- W4386076101 cites W2963604457 @default.
- W4386076101 cites W2964040059 @default.
- W4386076101 cites W2964288609 @default.
- W4386076101 cites W2965669158 @default.
- W4386076101 cites W3010644855 @default.
- W4386076101 cites W3034475761 @default.
- W4386076101 cites W3035331337 @default.
- W4386076101 cites W3035524985 @default.
- W4386076101 cites W3085056143 @default.
- W4386076101 cites W3098620092 @default.
- W4386076101 cites W3102015846 @default.
- W4386076101 cites W3109297856 @default.
- W4386076101 cites W3157035436 @default.
- W4386076101 cites W3171145773 @default.
- W4386076101 cites W3176148916 @default.
- W4386076101 cites W3186630079 @default.
- W4386076101 cites W3202343472 @default.
- W4386076101 cites W3202559727 @default.
- W4386076101 cites W3204568876 @default.
- W4386076101 cites W4214731463 @default.
- W4386076101 cites W4312408681 @default.
- W4386076101 cites W4312480149 @default.
- W4386076101 cites W4312651515 @default.
- W4386076101 cites W4312746348 @default.
- W4386076101 cites W4319299837 @default.
- W4386076101 doi "https://doi.org/10.1109/cvpr52729.2023.02002" @default.
- W4386076101 hasPublicationYear "2023" @default.
- W4386076101 type Work @default.
- W4386076101 citedByCount "0" @default.
- W4386076101 crossrefType "proceedings-article" @default.
- W4386076101 hasAuthorship W4386076101A5043251921 @default.
- W4386076101 hasAuthorship W4386076101A5078105554 @default.
- W4386076101 hasAuthorship W4386076101A5085971943 @default.
- W4386076101 hasConcept C111919701 @default.
- W4386076101 hasConcept C118505674 @default.
- W4386076101 hasConcept C126042441 @default.
- W4386076101 hasConcept C138885662 @default.
- W4386076101 hasConcept C153180895 @default.
- W4386076101 hasConcept C154945302 @default.
- W4386076101 hasConcept C162324750 @default.
- W4386076101 hasConcept C163294075 @default.
- W4386076101 hasConcept C176217482 @default.
- W4386076101 hasConcept C205711294 @default.
- W4386076101 hasConcept C21547014 @default.
- W4386076101 hasConcept C2776401178 @default.
- W4386076101 hasConcept C2776449333 @default.
- W4386076101 hasConcept C31972630 @default.
- W4386076101 hasConcept C41008148 @default.
- W4386076101 hasConcept C41895202 @default.
- W4386076101 hasConcept C76155785 @default.
- W4386076101 hasConceptScore W4386076101C111919701 @default.
- W4386076101 hasConceptScore W4386076101C118505674 @default.
- W4386076101 hasConceptScore W4386076101C126042441 @default.
- W4386076101 hasConceptScore W4386076101C138885662 @default.
- W4386076101 hasConceptScore W4386076101C153180895 @default.
- W4386076101 hasConceptScore W4386076101C154945302 @default.
- W4386076101 hasConceptScore W4386076101C162324750 @default.
- W4386076101 hasConceptScore W4386076101C163294075 @default.
- W4386076101 hasConceptScore W4386076101C176217482 @default.
- W4386076101 hasConceptScore W4386076101C205711294 @default.
- W4386076101 hasConceptScore W4386076101C21547014 @default.
- W4386076101 hasConceptScore W4386076101C2776401178 @default.
- W4386076101 hasConceptScore W4386076101C2776449333 @default.
- W4386076101 hasConceptScore W4386076101C31972630 @default.
- W4386076101 hasConceptScore W4386076101C41008148 @default.
- W4386076101 hasConceptScore W4386076101C41895202 @default.
- W4386076101 hasConceptScore W4386076101C76155785 @default.
- W4386076101 hasLocation W43860761011 @default.
- W4386076101 hasOpenAccess W4386076101 @default.
- W4386076101 hasPrimaryLocation W43860761011 @default.
- W4386076101 hasRelatedWork W1504288058 @default.
- W4386076101 hasRelatedWork W2017205855 @default.
- W4386076101 hasRelatedWork W2031347084 @default.
- W4386076101 hasRelatedWork W2048505601 @default.
- W4386076101 hasRelatedWork W2080322084 @default.
- W4386076101 hasRelatedWork W2167293474 @default.
- W4386076101 hasRelatedWork W2331674254 @default.
- W4386076101 hasRelatedWork W2358403311 @default.