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 701–750 of 1723 papers

TitleStatusHype
Shape Anchor Guided Holistic Indoor Scene UnderstandingCode0
LiON: Learning Point-wise Abstaining Penalty for LiDAR Outlier DetectioN Using Diverse Synthetic DataCode1
Mask4D: End-to-End Mask-Based 4D Panoptic Segmentation for LiDAR SequencesCode1
PanoMixSwap Panorama Mixing via Structural Swapping for Indoor Scene Understanding—0
So you think you can track?—0
Rank2Tell: A Multimodal Driving Dataset for Joint Importance Ranking and Reasoning—0
AmodalSynthDrive: A Synthetic Amodal Perception Dataset for Autonomous Driving—0
HOC-Search: Efficient CAD Model and Pose Retrieval from RGB-D ScansCode1
Can you text what is happening? Integrating pre-trained language encoders into trajectory prediction models for autonomous driving—0
Multi3DRefer: Grounding Text Description to Multiple 3D ObjectsCode1
PAg-NeRF: Towards fast and efficient end-to-end panoptic 3D representations for agricultural robotics—0
Weakly Supervised Point Clouds Transformer for 3D Object Detection—0
Vote2Cap-DETR++: Decoupling Localization and Describing for End-to-End 3D Dense CaptioningCode1
Structural Concept Learning via Graph Attention for Multi-Level Rearrangement Planning—0
OpenIns3D: Snap and Lookup for 3D Open-vocabulary Instance SegmentationCode2
Expanding Frozen Vision-Language Models without Retraining: Towards Improved Robot Perception—0
Semi-Supervised Semantic Depth Estimation using Symbiotic Transformer and NearFarMix Augmentation—0
End-to-end Autonomous Driving using Deep Learning: A Systematic Review—0
Synergizing Contrastive Learning and Optimal Transport for 3D Point Cloud Domain Adaptation—0
SurGNN: Explainable visual scene understanding and assessment of surgical skill using graph neural networks—0
SUMMIT: Source-Free Adaptation of Uni-Modal Models to Multi-Modal TargetsCode1
Multi-stage Factorized Spatio-Temporal Representation for RGB-D Action and Gesture RecognitionCode1
Understanding Dark Scenes by Contrasting Multi-Modal ObservationsCode1
ScanNet++: A High-Fidelity Dataset of 3D Indoor ScenesCode2
Novel-view Synthesis and Pose Estimation for Hand-Object Interaction from Sparse Views—0
Explore and Tell: Embodied Visual Captioning in 3D Environments—0
Vision Relation Transformer for Unbiased Scene Graph GenerationCode1
Chat-3D: Data-efficiently Tuning Large Language Model for Universal Dialogue of 3D ScenesCode2
CASPNet++: Joint Multi-Agent Motion Prediction—0
FocusFlow: Boosting Key-Points Optical Flow Estimation for Autonomous DrivingCode1
Temporal DINO: A Self-supervised Video Strategy to Enhance Action Prediction—0
Syn-Mediverse: A Multimodal Synthetic Dataset for Intelligent Scene Understanding of Healthcare Facilities—0
Cognitive TransFuser: Semantics-guided Transformer-based Sensor Fusion for Improved Waypoint PredictionCode0
Scene-aware Human Pose Generation using Transformer—0
Weakly Supervised 3D Instance Segmentation without Instance-level Annotations—0
Interpretable End-to-End Driving Model for Implicit Scene Understanding—0
Gated Driver Attention PredictorCode0
Lowis3D: Language-Driven Open-World Instance-Level 3D Scene Understanding—0
TaskExpert: Dynamically Assembling Multi-Task Representations with Memorial Mixture-of-ExpertsCode2
OAFuser: Towards Omni-Aperture Fusion for Light Field Semantic SegmentationCode1
Human-centric Scene Understanding for 3D Large-scale ScenariosCode1
Enhancing image captioning with depth information using a Transformer-based framework—0
Challenges for Monocular 6D Object Pose Estimation in Robotics—0
Revisiting Distillation for Continual Learning on Visual Question Localized-Answering in Robotic SurgeryCode0
Improving Online Lane Graph Extraction by Object-Lane Clustering—0
Mining Conditional Part Semantics with Occluded Extrapolation for Human-Object Interaction Detection—0
CPCM: Contextual Point Cloud Modeling for Weakly-supervised Point Cloud Semantic SegmentationCode1
Towards A Unified Agent with Foundation Models—0
Human Action Recognition in Still Images Using ConViT—0
A Survey on Open-Vocabulary Detection and Segmentation: Past, Present, and FutureCode2
Show:102550
← PrevPage 15 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