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 451–500 of 1723 papers

TitleStatusHype
One-Shot Object Affordance Detection in the WildCode1
Real-Time Semantic Segmentation using Hyperspectral Images for Mapping Unstructured and Unknown EnvironmentsCode1
You Only Need One Thing One Click: Self-Training for Weakly Supervised 3D Scene UnderstandingCode1
Online 3D reconstruction and dense tracking in endoscopic videosCode1
ReorientBot: Learning Object Reorientation for Specific-Posed PlacementCode1
CAKES: Channel-wise Automatic KErnel Shrinking for Efficient 3D NetworksCode1
Expressive Scene Graph Generation Using Commonsense Knowledge Infusion for Visual Understanding and ReasoningCode1
Open3DIS: Open-Vocabulary 3D Instance Segmentation with 2D Mask GuidanceCode1
Egocentric Scene Understanding via Multimodal Spatial RectifierCode1
Cityscapes-Panoptic-Parts and PASCAL-Panoptic-Parts datasets for Scene UnderstandingCode1
FocusFlow: Boosting Key-Points Optical Flow Estimation for Autonomous DrivingCode1
Exploiting Edge-Oriented Reasoning for 3D Point-based Scene Graph AnalysisCode1
Exploring Data-Efficient 3D Scene Understanding with Contrastive Scene ContextsCode1
Extending Large Vision-Language Model for Diverse Interactive Tasks in Autonomous DrivingCode1
Open Scene Understanding: Grounded Situation Recognition Meets Segment Anything for Helping People with Visual ImpairmentsCode1
ARKitScenes: A Diverse Real-World Dataset For 3D Indoor Scene Understanding Using Mobile RGB-D DataCode1
3UR-LLM: An End-to-End Multimodal Large Language Model for 3D Scene UnderstandingCode1
OvarNet: Towards Open-vocabulary Object Attribute RecognitionCode1
Campus3D: A Photogrammetry Point Cloud Benchmark for Hierarchical Understanding of Outdoor SceneCode1
Who2com: Collaborative Perception via Learnable Handshake CommunicationCode1
Channel-Wise Attention-Based Network for Self-Supervised Monocular Depth EstimationCode1
Explainable Object-induced Action Decision for Autonomous VehiclesCode1
PyTorchGeoNodes: Enabling Differentiable Shape Programs for 3D Shape ReconstructionCode1
Panoptic 3D Scene Reconstruction From a Single RGB ImageCode1
RSUD20K: A Dataset for Road Scene Understanding In Autonomous DrivingCode1
Semantic Segmentation-Assisted Instance Feature Fusion for Multi-Level 3D Part Instance SegmentationCode1
Panoptic Video Scene Graph GenerationCode1
Panoramic Panoptic Segmentation: Insights Into Surrounding Parsing for Mobile Agents via Unsupervised Contrastive LearningCode1
Towards Efficient Scene Understanding via Squeeze ReasoningCode1
Predicting Deeper into the Future of Semantic SegmentationCode0
Category-level Neural Field for Reconstruction of Partially Observed Objects in Indoor EnvironmentCode0
Are Vision LLMs Road-Ready? A Comprehensive Benchmark for Safety-Critical Driving Video UnderstandingCode0
Pose-aware Multi-level Feature Network for Human Object Interaction DetectionCode0
Planning Safety Trajectories with Dual-Phase, Physics-Informed, and Transportation Knowledge-Driven Large Language ModelsCode0
Evaluating Compositional Scene Understanding in Multimodal Generative ModelsCode0
A Review on Deep Learning Techniques Applied to Semantic SegmentationCode0
ERFNet: Efficient Residual Factorized ConvNet for Real-time Semantic SegmentationCode0
Physics-as-Inverse-Graphics: Unsupervised Physical Parameter Estimation from VideoCode0
PENet: A Joint Panoptic Edge Detection NetworkCode0
CARL-D: A vision benchmark suite and large scale dataset for vehicle detection and scene segmentationCode0
Part-Whole Relational Fusion Towards Multi-Modal Scene UnderstandingCode0
Parsing Geometry Using Structure-Aware Shape TemplatesCode0
Parsing Natural Scenes and Natural Language with Recursive Neural NetworksCode0
Panoramic Depth Estimation via Supervised and Unsupervised Learning in Indoor ScenesCode0
PanoRecon: Real-Time Panoptic 3D Reconstruction from Monocular VideoCode0
OVeNet: Offset Vector Network for Semantic SegmentationCode0
OVGaussian: Generalizable 3D Gaussian Segmentation with Open VocabulariesCode0
OST-Bench: Evaluating the Capabilities of MLLMs in Online Spatio-temporal Scene UnderstandingCode0
P2AT: Pyramid Pooling Axial Transformer for Real-time Semantic SegmentationCode0
Parallel Neural Computing for Scene Understanding from LiDAR Perception in Autonomous RacingCode0
Show:102550
← PrevPage 10 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