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 51–100 of 1723 papers

TitleStatusHype
Right Side Up? Disentangling Orientation Understanding in MLLMs with Fine-grained Multi-axis Perception Tasks—0
Compositional Scene Understanding through Inverse Generative Modeling—0
OccLE: Label-Efficient 3D Semantic Occupancy Prediction—0
A Graph Completion Method that Jointly Predicts Geometry and Topology Enables Effective Molecule Assembly—0
OmniIndoor3D: Comprehensive Indoor 3D Reconstruction—0
Underwater Diffusion Attention Network with Contrastive Language-Image Joint Learning for Underwater Image Enhancement—0
Co-AttenDWG: Co-Attentive Dimension-Wise Gating and Expert Fusion for Multi-Modal Offensive Content Detection—0
FHGS: Feature-Homogenized Gaussian Splatting—0
Can MLLMs Guide Me Home? A Benchmark Study on Fine-Grained Visual Reasoning from Transit Maps—0
Self-Supervised and Generalizable Tokenization for CLIP-Based 3D Understanding—0
From Flight to Insight: Semantic 3D Reconstruction for Aerial Inspection via Gaussian Splatting and Language-Guided Segmentation—0
Assessing the generalization performance of SAM for ureteroscopy scene understanding—0
CoNav: Collaborative Cross-Modal Reasoning for Embodied NavigationCode1
DC-Scene: Data-Centric Learning for 3D Scene UnderstandingCode0
HAMF: A Hybrid Attention-Mamba Framework for Joint Scene Context Understanding and Future Motion Representation Learning—0
RAZER: Robust Accelerated Zero-Shot 3D Open-Vocabulary Panoptic Reconstruction with Spatio-Temporal Aggregation—0
Robo2VLM: Visual Question Answering from Large-Scale In-the-Wild Robot Manipulation Datasets—0
AdaToken-3D: Dynamic Spatial Gating for Efficient 3D Large Multimodal-Models Reasoning—0
Predicting Reaction Time to Comprehend Scenes with Foveated Scene Understanding Maps—0
SEPT: Standard-Definition Map Enhanced Scene Perception and Topology Reasoning for Autonomous Driving—0
LLaVA-4D: Embedding SpatioTemporal Prompt into LMMs for 4D Scene Understanding—0
Can Large Multimodal Models Understand Agricultural Scenes? Benchmarking with AgroMind—0
TinyRS-R1: Compact Multimodal Language Model for Remote Sensing—0
APCoTTA: Continual Test-Time Adaptation for Semantic Segmentation of Airborne LiDAR Point CloudsCode0
StoryReasoning Dataset: Using Chain-of-Thought for Scene Understanding and Grounded Story GenerationCode1
DRRNet: Macro-Micro Feature Fusion and Dual Reverse Refinement for Camouflaged Object DetectionCode0
Seeing Beyond the Scene: Enhancing Vision-Language Models with Interactional Reasoning—0
Extending Large Vision-Language Model for Diverse Interactive Tasks in Autonomous DrivingCode1
Deep Learning Advances in Vision-Based Traffic Accident Anticipation: A Comprehensive Review of Methods,Datasets,and Future Directions—0
Boosting Cross-spectral Unsupervised Domain Adaptation for Thermal Semantic Segmentation—0
Technical Report for ICRA 2025 GOOSE 2D Semantic Segmentation Challenge: Leveraging Color Shift Correction, RoPE-Swin Backbone, and Quantile-based Label Denoising Strategy for Robust Outdoor Scene Understanding—0
Camera Control at the Edge with Language Models for Scene Understanding—0
Camera-Only Bird's Eye View Perception: A Neural Approach to LiDAR-Free Environmental Mapping for Autonomous Vehicles—0
Does CLIP perceive art the same way we do?—0
Hearing and Seeing Through CLIP: A Framework for Self-Supervised Sound Source LocalizationCode1
PADriver: Towards Personalized Autonomous Driving—0
RAFT: Robust Augmentation of FeaTures for Image Segmentation—0
Benchmarking Feature Upsampling Methods for Vision Foundation Models using Interactive SegmentationCode0
Segment Any RGB-Thermal Model with Language-aided Distillation—0
Beyond Recognition: Evaluating Visual Perspective Taking in Vision Language Models—0
Embracing Diffraction: A Paradigm Shift in Wireless Sensing and Communication—0
V3LMA: Visual 3D-enhanced Language Model for Autonomous Driving—0
LLM-Empowered Embodied Agent for Memory-Augmented Task Planning in Household RoboticsCode1
Masked Point-Entity Contrast for Open-Vocabulary 3D Scene Understanding—0
Category-Level and Open-Set Object Pose Estimation for Robotics—0
TraveLLaMA: Facilitating Multi-modal Large Language Models to Understand Urban Scenes and Provide Travel Assistance—0
Multimodal Large Language Models for Enhanced Traffic Safety: A Comprehensive Review and Future Trends—0
Are Vision LLMs Road-Ready? A Comprehensive Benchmark for Safety-Critical Driving Video UnderstandingCode0
Vision-Centric Representation-Efficient Fine-Tuning for Robust Universal Foreground Segmentation—0
Leveraging Automatic CAD Annotations for Supervised Learning in 3D Scene UnderstandingCode0
Show:102550
← PrevPage 2 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