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 5160 of 1723 papers

TitleStatusHype
A Survey on Open-Vocabulary Detection and Segmentation: Past, Present, and FutureCode2
HAKE: A Knowledge Engine Foundation for Human Activity UnderstandingCode2
EmbodiedScan: A Holistic Multi-Modal 3D Perception Suite Towards Embodied AICode2
Hypersim: A Photorealistic Synthetic Dataset for Holistic Indoor Scene UnderstandingCode2
A Unified Framework for 3D Scene UnderstandingCode2
IRef-VLA: A Benchmark for Interactive Referential Grounding with Imperfect Language in 3D ScenesCode2
Learning Multiple Probabilistic Decisions from Latent World Model in Autonomous DrivingCode2
Calib3D: Calibrating Model Preferences for Reliable 3D Scene UnderstandingCode2
EmbodiedOcc: Embodied 3D Occupancy Prediction for Vision-based Online Scene UnderstandingCode2
Gaussian Grouping: Segment and Edit Anything in 3D ScenesCode2
Show:102550
← PrevPage 6 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