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 201–250 of 1723 papers

TitleStatusHype
Label-Efficient LiDAR Panoptic Segmentation—0
vS-Graphs: Integrating Visual SLAM and Situational Graphs through Multi-level Scene Understanding—0
Every SAM Drop Counts: Embracing Semantic Priors for Multi-Modality Image Fusion and Beyond—0
OpenGS-SLAM: Open-Set Dense Semantic SLAM with 3D Gaussian Splatting for Object-Level Scene Understanding—0
Inst3D-LMM: Instance-Aware 3D Scene Understanding with Multi-modal Instruction TuningCode2
Floorplan-SLAM: A Real-Time, High-Accuracy, and Long-Term Multi-Session Point-Plane SLAM for Efficient Floorplan Reconstruction—0
Distill Any Depth: Distillation Creates a Stronger Monocular Depth EstimatorCode4
VLM-E2E: Enhancing End-to-End Autonomous Driving with Multimodal Driver Attention Fusion—0
AAD-LLM: Neural Attention-Driven Auditory Scene Understanding—0
Dr. Splat: Directly Referring 3D Gaussian Splatting via Direct Language Embedding Registration—0
Hierarchical Context Transformer for Multi-level Semantic Scene UnderstandingCode0
CrossOver: 3D Scene Cross-Modal AlignmentCode3
AVD2: Accident Video Diffusion for Accident Video Description—0
Sce2DriveX: A Generalized MLLM Framework for Scene-to-Drive Learning—0
Understanding and Evaluating Hallucinations in 3D Visual Language Models—0
Surgical Scene Understanding in the Era of Foundation AI Models: A Comprehensive Review—0
NavRAG: Generating User Demand Instructions for Embodied Navigation through Retrieval-Augmented LLMCode2
Occlusion-aware Non-Rigid Point Cloud Registration via Unsupervised Neural Deformation CorrentropyCode1
FLARES: Fast and Accurate LiDAR Multi-Range Semantic Segmentation—0
3D-Grounded Vision-Language Framework for Robotic Task Planning: Automated Prompt Synthesis and Supervised Reasoning—0
sshELF: Single-Shot Hierarchical Extrapolation of Latent Features for 3D Reconstruction from Sparse-Views—0
Mosaic3D: Foundation Dataset and Model for Open-Vocabulary 3D Segmentation—0
Event-aided Semantic Scene CompletionCode1
AquaticCLIP: A Vision-Language Foundation Model for Underwater Scene Analysis—0
Integrating LMM Planners and 3D Skill Policies for Generalizable Manipulation—0
Efficient Interactive 3D Multi-Object Removal—0
Contextual Self-paced Learning for Weakly Supervised Spatio-Temporal Video Grounding—0
PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding—0
Unveiling the Potential of iMarkers: Invisible Fiducial Markers for Advanced Robotics—0
HERMES: A Unified Self-Driving World Model for Simultaneous 3D Scene Understanding and GenerationCode3
Scene Understanding Enabled Semantic Communication with Open Channel Coding—0
GeomGS: LiDAR-Guided Geometry-Aware Gaussian Splatting for Robot Localization—0
Separated Inter/Intra-Modal Fusion Prompts for Compositional Zero-Shot Learning—0
Neural Radiance Fields for the Real World: A Survey—0
EndoChat: Grounded Multimodal Large Language Model for Endoscopic SurgeryCode1
Dynamic Scene Understanding from Vision-Language Representations—0
A Survey of World Models for Autonomous DrivingCode1
A Vision-Language Framework for Multispectral Scene Representation Using Language-Grounded Features—0
CrossModalityDiffusion: Multi-Modal Novel View Synthesis with Unified Intermediate RepresentationCode0
YETI (YET to Intervene) Proactive Interventions by Multimodal AI Agents in Augmented Reality Tasks—0
Embodied Scene Understanding for Vision Language Models via MetaVQA—0
3UR-LLM: An End-to-End Multimodal Large Language Model for 3D Scene UnderstandingCode1
Hierarchical Superpixel Segmentation via Structural Information TheoryCode0
Zero-Shot Scene Understanding for Automatic Target Recognition Using Large Vision-Language Models—0
Application of Vision-Language Model to Pedestrians Behavior and Scene Understanding in Autonomous Driving—0
Self-Supervised Partial Cycle-Consistency for Multi-View MatchingCode0
UniQ: Unified Decoder with Task-specific Queries for Efficient Scene Graph Generation—0
Vision-Language Models for Autonomous Driving: CLIP-Based Dynamic Scene Understanding—0
A Systematic Literature Review on Deep Learning-based Depth Estimation in Computer Vision—0
NextStop: An Improved Tracker For Panoptic LIDAR Segmentation DataCode0
Show:102550
← PrevPage 5 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