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 101–150 of 1723 papers

TitleStatusHype
CLIP goes 3D: Leveraging Prompt Tuning for Language Grounded 3D RecognitionCode2
GALIP: Generative Adversarial CLIPs for Text-to-Image SynthesisCode2
Diffusion-based Generation, Optimization, and Planning in 3D ScenesCode2
Panoptic Lifting for 3D Scene Understanding with Neural FieldsCode2
PLA: Language-Driven Open-Vocabulary 3D Scene UnderstandingCode2
OpenScene: 3D Scene Understanding with Open VocabulariesCode2
Safety-Enhanced Autonomous Driving Using Interpretable Sensor Fusion TransformerCode2
Panoptic Scene Graph GenerationCode2
BinsFormer: Revisiting Adaptive Bins for Monocular Depth EstimationCode2
InvPT: Inverted Pyramid Multi-task Transformer for Dense Scene UnderstandingCode2
CMX: Cross-Modal Fusion for RGB-X Semantic Segmentation with TransformersCode2
GroupViT: Semantic Segmentation Emerges from Text SupervisionCode2
HAKE: A Knowledge Engine Foundation for Human Activity UnderstandingCode2
Panoptic nuScenes: A Large-Scale Benchmark for LiDAR Panoptic Segmentation and TrackingCode2
Hypersim: A Photorealistic Synthetic Dataset for Holistic Indoor Scene UnderstandingCode2
Multi-Task Learning as Multi-Objective OptimizationCode2
Learning to Tune Like an Expert: Interpretable and Scene-Aware Navigation via MLLM Reasoning and CVAE-Based AdaptationCode1
SurgTPGS: Semantic 3D Surgical Scene Understanding with Text Promptable Gaussian SplattingCode1
ReME: A Data-Centric Framework for Training-Free Open-Vocabulary SegmentationCode1
DIP: Unsupervised Dense In-Context Post-training of Visual RepresentationsCode1
STSBench: A Spatio-temporal Scenario Benchmark for Multi-modal Large Language Models in Autonomous DrivingCode1
OWMM-Agent: Open World Mobile Manipulation With Multi-modal Agentic Data SynthesisCode1
PhysGaia: A Physics-Aware Dataset of Multi-Body Interactions for Dynamic Novel View SynthesisCode1
CoNav: Collaborative Cross-Modal Reasoning for Embodied NavigationCode1
StoryReasoning Dataset: Using Chain-of-Thought for Scene Understanding and Grounded Story GenerationCode1
Extending Large Vision-Language Model for Diverse Interactive Tasks in Autonomous DrivingCode1
Hearing and Seeing Through CLIP: A Framework for Self-Supervised Sound Source LocalizationCode1
LLM-Empowered Embodied Agent for Memory-Augmented Task Planning in Household RoboticsCode1
Training-Free Hierarchical Scene Understanding for Gaussian Splatting with Superpoint GraphsCode1
DC-SAM: In-Context Segment Anything in Images and Videos via Dual ConsistencyCode1
SoccerNet-v3D: Leveraging Sports Broadcast Replays for 3D Scene UnderstandingCode1
Masked Scene Modeling: Narrowing the Gap Between Supervised and Self-Supervised Learning in 3D Scene UnderstandingCode1
CamContextI2V: Context-aware Controllable Video GenerationCode1
F-ViTA: Foundation Model Guided Visible to Thermal TranslationCode1
Multimodal Fusion and Vision-Language Models: A Survey for Robot VisionCode1
WikiVideo: Article Generation from Multiple VideosCode1
Boosting Omnidirectional Stereo Matching with a Pre-trained Depth Foundation ModelCode1
Mitigating Trade-off: Stream and Query-guided Aggregation for Efficient and Effective 3D Occupancy PredictionCode1
The Coralscapes Dataset: Semantic Scene Understanding in Coral ReefsCode1
Cross-Modal and Uncertainty-Aware Agglomeration for Open-Vocabulary 3D Scene UnderstandingCode1
NuPlanQA: A Large-Scale Dataset and Benchmark for Multi-View Driving Scene Understanding in Multi-Modal Large Language ModelsCode1
Logic-RAG: Augmenting Large Multimodal Models with Visual-Spatial Knowledge for Road Scene UnderstandingCode1
A Data-Centric Revisit of Pre-Trained Vision Models for Robot LearningCode1
VLScene: Vision-Language Guidance Distillation for Camera-Based 3D Semantic Scene CompletionCode1
Occlusion-aware Non-Rigid Point Cloud Registration via Unsupervised Neural Deformation CorrentropyCode1
Event-aided Semantic Scene CompletionCode1
EndoChat: Grounded Multimodal Large Language Model for Endoscopic SurgeryCode1
A Survey of World Models for Autonomous DrivingCode1
3UR-LLM: An End-to-End Multimodal Large Language Model for 3D Scene UnderstandingCode1
All-Day Multi-Camera Multi-Target TrackingCode1
Show:102550
← PrevPage 3 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