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 151–200 of 1723 papers

TitleStatusHype
Divide and Conquer: 3D Point Cloud Instance Segmentation With Point-Wise BinarizationCode1
3DRM:Pair-wise relation module for 3D object detectionCode1
DTCLMapper: Dual Temporal Consistent Learning for Vectorized HD Map ConstructionCode1
KITTI-360: A Novel Dataset and Benchmarks for Urban Scene Understanding in 2D and 3DCode1
LayoutMP3D: Layout Annotation of Matterport3DCode1
Instance-wise Occlusion and Depth Orders in Natural ScenesCode1
Distilled Semantics for Comprehensive Scene Understanding from VideosCode1
Bird's-Eye-View Panoptic Segmentation Using Monocular Frontal View ImagesCode1
DIP: Unsupervised Dense In-Context Post-training of Visual RepresentationsCode1
Instance Segmentation in 3D Scenes using Semantic Superpoint Tree NetworksCode1
Improving Visual Recognition with Hyperbolical Visual Hierarchy MappingCode1
Digging Into Self-Supervised Monocular Depth EstimationCode1
RGB-D Indiscernible Object Counting in Underwater ScenesCode1
Bidirectional Projection Network for Cross Dimension Scene UnderstandingCode1
DI-V2X: Learning Domain-Invariant Representation for Vehicle-Infrastructure Collaborative 3D Object DetectionCode1
Dense Audio-Visual Event Localization under Cross-Modal Consistency and Multi-Temporal Granularity CollaborationCode1
Explainable Object-induced Action Decision for Autonomous VehiclesCode1
Learning and Reasoning with the Graph Structure Representation in Robotic SurgeryCode1
Learning Triadic Belief Dynamics in Nonverbal Communication from VideosCode1
DeepScores -- A Dataset for Segmentation, Detection and Classification of Tiny ObjectsCode1
Human-centric Scene Understanding for 3D Large-scale ScenariosCode1
IBISCape: A Simulated Benchmark for multi-modal SLAM Systems Evaluation in Large-scale Dynamic EnvironmentsCode1
Holistic 3D Scene Understanding from a Single Image with Implicit RepresentationCode1
DeepPanoContext: Panoramic 3D Scene Understanding with Holistic Scene Context Graph and Relation-based OptimizationCode1
Segmenting Known Objects and Unseen Unknowns without Prior KnowledgeCode1
IDA-3D: Instance-Depth-Aware 3D Object Detection From Stereo Vision for Autonomous DrivingCode1
Hearing and Seeing Through CLIP: A Framework for Self-Supervised Sound Source LocalizationCode1
Behind the Curtain: Learning Occluded Shapes for 3D Object DetectionCode1
Deep Learning for Event-based Vision: A Comprehensive Survey and BenchmarksCode1
HiLo: Exploiting High Low Frequency Relations for Unbiased Panoptic Scene Graph GenerationCode1
DD-PPO: Learning Near-Perfect PointGoal Navigators from 2.5 Billion FramesCode1
Bayesian SegNet: Model Uncertainty in Deep Convolutional Encoder-Decoder Architectures for Scene UnderstandingCode1
Bending Reality: Distortion-aware Transformers for Adapting to Panoramic Semantic SegmentationCode1
BEVDistill: Cross-Modal BEV Distillation for Multi-View 3D Object DetectionCode1
Beyond Appearances: Material Segmentation with Embedded Spectral Information from RGB-D imageryCode1
HOC-Search: Efficient CAD Model and Pose Retrieval from RGB-D ScansCode1
GroupContrast: Semantic-aware Self-supervised Representation Learning for 3D UnderstandingCode1
Activation Modulation and Recalibration Scheme for Weakly Supervised Semantic SegmentationCode1
DC-SAM: In-Context Segment Anything in Images and Videos via Dual ConsistencyCode1
3DP3: 3D Scene Perception via Probabilistic ProgrammingCode1
Deep learning for radar data exploitation of autonomous vehicleCode1
Curriculum Model Adaptation with Synthetic and Real Data for Semantic Foggy Scene UnderstandingCode1
AVSegFormer: Audio-Visual Segmentation with TransformerCode1
Detecting Human-Object Interaction via Fabricated Compositional LearningCode1
Bi-level Dynamic Learning for Jointly Multi-modality Image Fusion and BeyondCode1
CSFNet: A Cosine Similarity Fusion Network for Real-Time RGB-X Semantic Segmentation of Driving ScenesCode1
DAF-Net: A Dual-Branch Feature Decomposition Fusion Network with Domain Adaptive for Infrared and Visible Image FusionCode1
Diffusion-SS3D: Diffusion Model for Semi-supervised 3D Object DetectionCode1
Grounded Situation Recognition with TransformersCode1
Global Aggregation then Local Distribution in Fully Convolutional NetworksCode1
Show:102550
← PrevPage 4 of 35Next →
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