GenerativeVideoTransformer:CanObjectsbetheWords?Yi-FuWu1JaesikYoon12SungjinAhn13Abstractinteresttodevelopananalogousgenerativepre-trainingpro-cedureforvideos,thecomputationaloverheadindealingTransf...
GEOMetrics:ExploitingGeometricStructureforGraph-EncodedObjectsEdwardJ.Smith1ScottFujimoto12AdrianaRomero31DavidMeger1Abstract(a)Voxels(b)Pointcloud(262144units)(30000points)Meshmodelsareapromisinga...
GenerativeModelingofInfiniteOccludedObjectsforCompositionalSceneRepresentationJinyangYuan1BinLi1XiangyangXue1Abstractcanautomaticallysegregatethevisualsceneintoconceptualentities(e.g.Objects)throug...