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
Leveraging Automatic CAD Annotations for Supervised Learning in 3D Scene UnderstandingCode0
HAECcity: Open-Vocabulary Scene Understanding of City-Scale Point Clouds with Superpoint Graph Clustering—0
Training-Free Hierarchical Scene Understanding for Gaussian Splatting with Superpoint GraphsCode1
Explainable Scene Understanding with Qualitative Representations and Graph Neural Networks—0
DC-SAM: In-Context Segment Anything in Images and Videos via Dual ConsistencyCode1
CAGS: Open-Vocabulary 3D Scene Understanding with Context-Aware Gaussian Splatting—0
Single-Input Multi-Output Model Merging: Leveraging Foundation Models for Dense Multi-Task Learning—0
Foundation Models for Remote Sensing: An Analysis of MLLMs for Object Localization—0
SoccerNet-v3D: Leveraging Sports Broadcast Replays for 3D Scene UnderstandingCode1
FindAnything: Open-Vocabulary and Object-Centric Mapping for Robot Exploration in Any Environment—0
FMLGS: Fast Multilevel Language Embedded Gaussians for Part-level Interactive Agents—0
DSM: Building A Diverse Semantic Map for 3D Visual Grounding—0
DGOcc: Depth-aware Global Query-based Network for Monocular 3D Occupancy Prediction—0
Masked Scene Modeling: Narrowing the Gap Between Supervised and Self-Supervised Learning in 3D Scene UnderstandingCode1
MovSAM: A Single-image Moving Object Segmentation Framework Based on Deep ThinkingCode0
RayFronts: Open-Set Semantic Ray Frontiers for Online Scene Understanding and Exploration—0
Attributes-aware Visual Emotion Representation Learning—0
Audio-visual Event Localization on Portrait Mode Short Videos—0
PRIMEDrive-CoT: A Precognitive Chain-of-Thought Framework for Uncertainty-Aware Object Interaction in Driving Scene Scenario—0
CamContextI2V: Context-aware Controllable Video GenerationCode1
RS-RAG: Bridging Remote Sensing Imagery and Comprehensive Knowledge with a Multi-Modal Dataset and Retrieval-Augmented Generation Model—0
DFormerv2: Geometry Self-Attention for RGBD Semantic SegmentationCode3
Planning Safety Trajectories with Dual-Phase, Physics-Informed, and Transportation Knowledge-Driven Large Language ModelsCode0
Multimodal Fusion and Vision-Language Models: A Survey for Robot VisionCode1
F-ViTA: Foundation Model Guided Visible to Thermal TranslationCode1
Overlap-Aware Feature Learning for Robust Unsupervised Domain Adaptation for 3D Semantic Segmentation—0
CoMatcher: Multi-View Collaborative Feature Matching—0
TransforMerger: Transformer-based Voice-Gesture Fusion for Robust Human-Robot Communication—0
Ross3D: Reconstructive Visual Instruction Tuning with 3D-Awareness—0
Scene-Centric Unsupervised Panoptic SegmentationCode2
WikiVideo: Article Generation from Multiple VideosCode1
Zero-Shot 4D Lidar Panoptic Segmentation—0
Context-Aware Human Behavior Prediction Using Multimodal Large Language Models: Challenges and Insights—0
PhysPose: Refining 6D Object Poses with Physical Constraints—0
Boosting Omnidirectional Stereo Matching with a Pre-trained Depth Foundation ModelCode1
OpenDriveVLA: Towards End-to-end Autonomous Driving with Large Vision Language Action ModelCode4
Empowering Large Language Models with 3D Situation Awareness—0
Evaluating Compositional Scene Understanding in Multimodal Generative ModelsCode0
Can DeepSeek Reason Like a Surgeon? An Empirical Evaluation for Vision-Language Understanding in Robotic-Assisted Surgery—0
Open-Vocabulary Semantic Segmentation with Uncertainty Alignment for Robotic Scene Understanding in Indoor Building Environments—0
Mitigating Trade-off: Stream and Query-guided Aggregation for Efficient and Effective 3D Occupancy PredictionCode1
Evaluating Multimodal Language Models as Visual Assistants for Visually Impaired Users—0
A Dataset for Semantic Segmentation in the Presence of Unknowns—0
Endo-TTAP: Robust Endoscopic Tissue Tracking via Multi-Facet Guided Attention and Hybrid Flow-point Supervision—0
Next-Best-Trajectory Planning of Robot Manipulators for Effective Observation and Exploration—0
NuGrounding: A Multi-View 3D Visual Grounding Framework in Autonomous Driving—0
Visual Jenga: Discovering Object Dependencies via Counterfactual Inpainting—0
Towards Generating Realistic 3D Semantic Training Data for Autonomous DrivingCode2
DINeMo: Learning Neural Mesh Models with no 3D Annotations—0
COB-GS: Clear Object Boundaries in 3DGS Segmentation Based on Boundary-Adaptive Gaussian SplittingCode2
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