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 351–400 of 1723 papers

TitleStatusHype
Grounding Consistency: Distilling Spatial Common Sense for Precise Visual Relationship DetectionCode1
General Geometry-aware Weakly Supervised 3D Object DetectionCode1
Multi-view 3D Object Reconstruction and Uncertainty Modelling with Neural Shape PriorCode1
Deep Learning for Event-based Vision: A Comprehensive Survey and BenchmarksCode1
Deep learning for radar data exploitation of autonomous vehicleCode1
Bayesian SegNet: Model Uncertainty in Deep Convolutional Encoder-Decoder Architectures for Scene UnderstandingCode1
Generating Visual Spatial Description via Holistic 3D Scene UnderstandingCode1
NeuSyRE: Neuro-Symbolic Visual Understanding and Reasoning Framework based on Scene Graph EnrichmentCode1
OAFuser: Towards Omni-Aperture Fusion for Light Field Semantic SegmentationCode1
DeepPanoContext: Panoramic 3D Scene Understanding with Holistic Scene Context Graph and Relation-based OptimizationCode1
Behind the Curtain: Learning Occluded Shapes for 3D Object DetectionCode1
Object Pose Estimation via the Aggregation of Diffusion FeaturesCode1
AeroRIT: A New Scene for Hyperspectral Image AnalysisCode1
OFFSEG: A Semantic Segmentation Framework For Off-Road DrivingCode1
DeepScores -- A Dataset for Segmentation, Detection and Classification of Tiny ObjectsCode1
One-Shot Object Affordance Detection in the WildCode1
F-ViTA: Foundation Model Guided Visible to Thermal TranslationCode1
CLIP2Scene: Towards Label-efficient 3D Scene Understanding by CLIPCode1
Comprehensive Visual Question Answering on Point Clouds through Compositional Scene ManipulationCode1
Dynamic Graph Message Passing Networks for Visual RecognitionCode1
GFF: Gated Fully Fusion for Semantic SegmentationCode1
Beyond Appearances: Material Segmentation with Embedded Spectral Information from RGB-D imageryCode1
Group Contextual Encoding for 3D Point CloudsCode1
Class-Incremental Domain Adaptation with Smoothing and Calibration for Surgical Report GenerationCode1
FocusFlow: Boosting Key-Points Optical Flow Estimation for Autonomous DrivingCode1
Open Scene Understanding: Grounded Situation Recognition Meets Segment Anything for Helping People with Visual ImpairmentsCode1
FPS-Net: A Convolutional Fusion Network for Large-Scale LiDAR Point Cloud SegmentationCode1
Few-Shot Object Detection and Viewpoint Estimation for Objects in the WildCode1
FloodNet: A High Resolution Aerial Imagery Dataset for Post Flood Scene UnderstandingCode1
FreDSNet: Joint Monocular Depth and Semantic Segmentation with Fast Fourier ConvolutionsCode1
P3Depth: Monocular Depth Estimation with a Piecewise Planarity PriorCode1
PanoOcc: Unified Occupancy Representation for Camera-based 3D Panoptic SegmentationCode1
Expressive Scene Graph Generation Using Commonsense Knowledge Infusion for Visual Understanding and ReasoningCode1
Exploring Data-Efficient 3D Scene Understanding with Contrastive Scene ContextsCode1
Extending Large Vision-Language Model for Diverse Interactive Tasks in Autonomous DrivingCode1
Explainable Object-induced Action Decision for Autonomous VehiclesCode1
Bidirectional Projection Network for Cross Dimension Scene UnderstandingCode1
PC-BEV: An Efficient Polar-Cartesian BEV Fusion Framework for LiDAR Semantic SegmentationCode1
EPMF: Efficient Perception-aware Multi-sensor Fusion for 3D Semantic SegmentationCode1
Photon-Starved Scene Inference using Single Photon CamerasCode1
DIP: Unsupervised Dense In-Context Post-training of Visual RepresentationsCode1
Bi-level Dynamic Learning for Jointly Multi-modality Image Fusion and BeyondCode1
Point Cloud Pre-Training With Natural 3D StructuresCode1
PointContrast: Unsupervised Pre-training for 3D Point Cloud UnderstandingCode1
Exploiting Edge-Oriented Reasoning for 3D Point-based Scene Graph AnalysisCode1
Digging Into Self-Supervised Monocular Depth EstimationCode1
A2-FPN for Semantic Segmentation of Fine-Resolution Remotely Sensed ImagesCode1
Pola4All: survey of polarimetric applications and an open-source toolkit to analyze polarizationCode1
From General to Specific: Informative Scene Graph Generation via Balance AdjustmentCode1
Estimating and Exploiting the Aleatoric Uncertainty in Surface Normal EstimationCode1
Show:102550
← PrevPage 8 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