Matches in SemOpenAlex for { <https://semopenalex.org/work/W4312311962> ?p ?o ?g. }
- W4312311962 endingPage "228" @default.
- W4312311962 startingPage "211" @default.
- W4312311962 abstract "We propose a transformer-based neural network architecture for multi-object 3D reconstruction from RGB videos. It relies on two alternative ways to represent its knowledge: as a global 3D grid of features and an array of view-specific 2D grids. We progressively exchange information between the two with a dedicated bidirectional attention mechanism. We exploit knowledge about the image formation process to significantly sparsify the attention weight matrix, making our architecture feasible on current hardware, both in terms of memory and computation. We attach a DETR-style head [9] on top of the 3D feature grid in order to detect the objects in the scene and to predict their 3D pose and 3D shape. Compared to previous methods, our architecture is single stage, end-to-end trainable, and it can reason holistically about a scene from multiple video frames without needing a brittle tracking step. We evaluate our method on the challenging Scan2CAD dataset [3], where we outperform (1) state-of-the-art methods [15, 34, 35, 39] for 3D object pose estimation from RGB videos; and (2) a strong alternative method combining Multi-View Stereo [17] with RGB-D CAD alignment [4]." @default.
- W4312311962 created "2023-01-04" @default.
- W4312311962 creator A5003940396 @default.
- W4312311962 creator A5025102675 @default.
- W4312311962 creator A5038897190 @default.
- W4312311962 creator A5057962431 @default.
- W4312311962 date "2022-01-01" @default.
- W4312311962 modified "2023-10-15" @default.
- W4312311962 title "RayTran: 3D Pose Estimation and Shape Reconstruction of Multiple Objects from Videos with Ray-Traced Transformers" @default.
- W4312311962 cites W1489405158 @default.
- W4312311962 cites W1564871316 @default.
- W4312311962 cites W1953319329 @default.
- W4312311962 cites W2049351243 @default.
- W4312311962 cites W2083461908 @default.
- W4312311962 cites W2097374608 @default.
- W4312311962 cites W2097696373 @default.
- W4312311962 cites W2105303354 @default.
- W4312311962 cites W2138302688 @default.
- W4312311962 cites W2194775991 @default.
- W4312311962 cites W2342277278 @default.
- W4312311962 cites W2471962767 @default.
- W4312311962 cites W2474281075 @default.
- W4312311962 cites W2543696449 @default.
- W4312311962 cites W2560544142 @default.
- W4312311962 cites W2594519801 @default.
- W4312311962 cites W2799123546 @default.
- W4312311962 cites W2810389316 @default.
- W4312311962 cites W2885364117 @default.
- W4312311962 cites W2903435684 @default.
- W4312311962 cites W2962778872 @default.
- W4312311962 cites W2963627347 @default.
- W4312311962 cites W2963893349 @default.
- W4312311962 cites W2963926543 @default.
- W4312311962 cites W2964137676 @default.
- W4312311962 cites W2981393651 @default.
- W4312311962 cites W2987505621 @default.
- W4312311962 cites W2989738721 @default.
- W4312311962 cites W2990578762 @default.
- W4312311962 cites W3034902354 @default.
- W4312311962 cites W3035163517 @default.
- W4312311962 cites W3035269921 @default.
- W4312311962 cites W3035424742 @default.
- W4312311962 cites W3096609285 @default.
- W4312311962 cites W3098467253 @default.
- W4312311962 cites W3099201369 @default.
- W4312311962 cites W3103648783 @default.
- W4312311962 cites W3107210737 @default.
- W4312311962 cites W3108776058 @default.
- W4312311962 cites W3108800063 @default.
- W4312311962 cites W3116978940 @default.
- W4312311962 cites W3119686997 @default.
- W4312311962 cites W3131863794 @default.
- W4312311962 cites W3166512471 @default.
- W4312311962 cites W3170841864 @default.
- W4312311962 cites W3171032126 @default.
- W4312311962 cites W3175502768 @default.
- W4312311962 cites W3191372372 @default.
- W4312311962 cites W3194241004 @default.
- W4312311962 cites W3194468757 @default.
- W4312311962 cites W4214612132 @default.
- W4312311962 cites W4214893857 @default.
- W4312311962 cites W4226020718 @default.
- W4312311962 cites W4226082556 @default.
- W4312311962 cites W4250952223 @default.
- W4312311962 doi "https://doi.org/10.1007/978-3-031-20080-9_13" @default.
- W4312311962 hasPublicationYear "2022" @default.
- W4312311962 type Work @default.
- W4312311962 citedByCount "0" @default.
- W4312311962 crossrefType "book-chapter" @default.
- W4312311962 hasAuthorship W4312311962A5003940396 @default.
- W4312311962 hasAuthorship W4312311962A5025102675 @default.
- W4312311962 hasAuthorship W4312311962A5038897190 @default.
- W4312311962 hasAuthorship W4312311962A5057962431 @default.
- W4312311962 hasBestOaLocation W43123119622 @default.
- W4312311962 hasConcept C109950114 @default.
- W4312311962 hasConcept C126057942 @default.
- W4312311962 hasConcept C154945302 @default.
- W4312311962 hasConcept C165696696 @default.
- W4312311962 hasConcept C187691185 @default.
- W4312311962 hasConcept C2524010 @default.
- W4312311962 hasConcept C31972630 @default.
- W4312311962 hasConcept C33923547 @default.
- W4312311962 hasConcept C38652104 @default.
- W4312311962 hasConcept C41008148 @default.
- W4312311962 hasConcept C52102323 @default.
- W4312311962 hasConcept C82990744 @default.
- W4312311962 hasConceptScore W4312311962C109950114 @default.
- W4312311962 hasConceptScore W4312311962C126057942 @default.
- W4312311962 hasConceptScore W4312311962C154945302 @default.
- W4312311962 hasConceptScore W4312311962C165696696 @default.
- W4312311962 hasConceptScore W4312311962C187691185 @default.
- W4312311962 hasConceptScore W4312311962C2524010 @default.
- W4312311962 hasConceptScore W4312311962C31972630 @default.
- W4312311962 hasConceptScore W4312311962C33923547 @default.
- W4312311962 hasConceptScore W4312311962C38652104 @default.
- W4312311962 hasConceptScore W4312311962C41008148 @default.
- W4312311962 hasConceptScore W4312311962C52102323 @default.
- W4312311962 hasConceptScore W4312311962C82990744 @default.