SOTAVerified

Scene Understanding

Scene understanding involves interpreting the visual information of a scene, including objects, their spatial relationships, and the overall layout. It goes beyond simple object recognition by considering the context and how objects relate to each other and the environment.

Papers

Showing 331340 of 1723 papers

TitleStatusHype
PolyphonicFormer: Unified Query Learning for Depth-aware Video Panoptic SegmentationCode1
Behind the Curtain: Learning Occluded Shapes for 3D Object DetectionCode1
AirObject: A Temporally Evolving Graph Embedding for Object IdentificationCode1
Instance-wise Occlusion and Depth Orders in Natural ScenesCode1
Cerberus Transformer: Joint Semantic, Affordance and Attribute ParsingCode1
Grounded Situation Recognition with TransformersCode1
ARKitScenes: A Diverse Real-World Dataset For 3D Indoor Scene Understanding Using Mobile RGB-D DataCode1
Learning Object-Centric Representations of Multi-Object Scenes from Multiple ViewsCode1
Panoptic 3D Scene Reconstruction From a Single RGB ImageCode1
3DP3: 3D Scene Perception via Probabilistic ProgrammingCode1
Show:102550
← PrevPage 34 of 173Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1ACRV BaselineOMQ0.44Unverified
2Team VGAI (TCS Research)OMQ0.37Unverified
3Demo_semantic_SLAMOMQ0.11Unverified
#ModelMetricClaimedVerifiedStatus
1CPN(ResNet-101)Mean IoU46.3Unverified
#ModelMetricClaimedVerifiedStatus
1ACRV BaselineOMQ0.35Unverified