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

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1–25 of 1723 papers

TitleStatusHype
When LLMs step into the 3D World: A Survey and Meta-Analysis of 3D Tasks via Multi-modal Large Language ModelsCode7
Trajectory Prediction Meets Large Language Models: A SurveyCode5
Distill Any Depth: Distillation Creates a Stronger Monocular Depth EstimatorCode4
Repurposing Diffusion-Based Image Generators for Monocular Depth EstimationCode4
SplaTAM: Splat, Track & Map 3D Gaussians for Dense RGB-D SLAMCode4
Senna: Bridging Large Vision-Language Models and End-to-End Autonomous DrivingCode4
OpenDriveVLA: Towards End-to-end Autonomous Driving with Large Vision Language Action ModelCode4
Prismatic VLMs: Investigating the Design Space of Visually-Conditioned Language ModelsCode4
GPT4Scene: Understand 3D Scenes from Videos with Vision-Language ModelsCode4
Sigma: Siamese Mamba Network for Multi-Modal Semantic SegmentationCode3
SceneSplat: Gaussian Splatting-based Scene Understanding with Vision-Language PretrainingCode3
DeepInteraction++: Multi-Modality Interaction for Autonomous DrivingCode3
SGS-SLAM: Semantic Gaussian Splatting For Neural Dense SLAMCode3
DFormerv2: Geometry Self-Attention for RGBD Semantic SegmentationCode3
Multi-Modal Data-Efficient 3D Scene Understanding for Autonomous DrivingCode3
HERMES: A Unified Self-Driving World Model for Simultaneous 3D Scene Understanding and GenerationCode3
iDisc: Internal Discretization for Monocular Depth EstimationCode3
4D Panoptic Scene Graph GenerationCode3
EPRecon: An Efficient Framework for Real-Time Panoptic 3D Reconstruction from Monocular VideoCode3
GARField: Group Anything with Radiance FieldsCode3
MoAI: Mixture of All Intelligence for Large Language and Vision ModelsCode3
Monkey: Image Resolution and Text Label Are Important Things for Large Multi-modal ModelsCode3
AudioBench: A Universal Benchmark for Audio Large Language ModelsCode3
CrossOver: 3D Scene Cross-Modal AlignmentCode3
Embodied Understanding of Driving ScenariosCode3
Show:102550
← PrevPage 1 of 69Next →
All datasetsSemantic Scene Understanding Challenge (passive actuation & ground-truth localisation)ADE20K valSemantic Scene Understanding Challenge (active actuation & ground-truth localisation)

Benchmark Results

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