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 2130 of 1723 papers

TitleStatusHype
GARField: Group Anything with Radiance FieldsCode3
4D Panoptic Scene Graph GenerationCode3
AudioBench: A Universal Benchmark for Audio Large Language ModelsCode3
CrossOver: 3D Scene Cross-Modal AlignmentCode3
DeepInteraction++: Multi-Modality Interaction for Autonomous DrivingCode3
DFormerv2: Geometry Self-Attention for RGBD Semantic SegmentationCode3
HERMES: A Unified Self-Driving World Model for Simultaneous 3D Scene Understanding and GenerationCode3
SceneSplat: Gaussian Splatting-based Scene Understanding with Vision-Language PretrainingCode3
Embodied Understanding of Driving ScenariosCode3
EmbodiedScan: A Holistic Multi-Modal 3D Perception Suite Towards Embodied AICode2
Show:102550
← PrevPage 3 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