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 101110 of 1723 papers

TitleStatusHype
FusionVision: A comprehensive approach of 3D object reconstruction and segmentation from RGB-D cameras using YOLO and fast segment anythingCode2
RelationField: Relate Anything in Radiance FieldsCode2
GaussianPretrain: A Simple Unified 3D Gaussian Representation for Visual Pre-training in Autonomous DrivingCode2
Emma-X: An Embodied Multimodal Action Model with Grounded Chain of Thought and Look-ahead Spatial ReasoningCode2
A Survey on Open-Vocabulary Detection and Segmentation: Past, Present, and FutureCode2
Scene-Centric Unsupervised Panoptic SegmentationCode2
EmbodiedScan: A Holistic Multi-Modal 3D Perception Suite Towards Embodied AICode2
EmbodiedOcc: Embodied 3D Occupancy Prediction for Vision-based Online Scene UnderstandingCode2
Feed-Forward SceneDINO for Unsupervised Semantic Scene CompletionCode2
IRef-VLA: A Benchmark for Interactive Referential Grounding with Imperfect Language in 3D ScenesCode2
Show:102550
← PrevPage 11 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