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 376–400 of 1723 papers

TitleStatusHype
OAFuser: Towards Omni-Aperture Fusion for Light Field Semantic SegmentationCode1
Activation Modulation and Recalibration Scheme for Weakly Supervised Semantic SegmentationCode1
IRS: A Large Naturalistic Indoor Robotics Stereo Dataset to Train Deep Models for Disparity and Surface Normal EstimationCode1
DTCLMapper: Dual Temporal Consistent Learning for Vectorized HD Map ConstructionCode1
Dynamic Graph Message Passing NetworksCode1
KITTI-360: A Novel Dataset and Benchmarks for Urban Scene Understanding in 2D and 3DCode1
Knowledge Distillation from 3D to Bird's-Eye-View for LiDAR Semantic SegmentationCode1
NuPlanQA: A Large-Scale Dataset and Benchmark for Multi-View Driving Scene Understanding in Multi-Modal Large Language ModelsCode1
DynaVol: Unsupervised Learning for Dynamic Scenes through Object-Centric VoxelizationCode1
Detecting Human-Object Interaction via Fabricated Compositional LearningCode1
NeuSyRE: Neuro-Symbolic Visual Understanding and Reasoning Framework based on Scene Graph EnrichmentCode1
Bidirectional Projection Network for Cross Dimension Scene UnderstandingCode1
Learning How To Robustly Estimate Camera Pose in Endoscopic VideosCode1
NODIS: Neural Ordinary Differential Scene UnderstandingCode1
Learning Multi-Granular Spatio-Temporal Graph Network for Skeleton-based Action RecognitionCode1
Dynamic Graph Message Passing Networks for Visual RecognitionCode1
Bi-level Dynamic Learning for Jointly Multi-modality Image Fusion and BeyondCode1
DPF: Learning Dense Prediction Fields with Weak SupervisionCode1
LiON: Learning Point-wise Abstaining Penalty for LiDAR Outlier DetectioN Using Diverse Synthetic DataCode1
No Train, all Gain: Self-Supervised Gradients Improve Deep Frozen RepresentationsCode1
Digging Into Self-Supervised Monocular Depth EstimationCode1
Object Pose Estimation via the Aggregation of Diffusion FeaturesCode1
Learning to Tune Like an Expert: Interpretable and Scene-Aware Navigation via MLLM Reasoning and CVAE-Based AdaptationCode1
Bird's-Eye-View Panoptic Segmentation Using Monocular Frontal View ImagesCode1
Cityscapes-Panoptic-Parts and PASCAL-Panoptic-Parts datasets for Scene UnderstandingCode1
Show:102550
← PrevPage 16 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