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
Stag-1: Towards Realistic 4D Driving Simulation with Video Generation ModelCode2
EmbodiedOcc: Embodied 3D Occupancy Prediction for Vision-based Online Scene UnderstandingCode2
LSceneLLM: Enhancing Large 3D Scene Understanding Using Adaptive Visual PreferencesCode2
GEOBench-VLM: Benchmarking Vision-Language Models for Geospatial TasksCode2
An End-to-End Robust Point Cloud Semantic Segmentation Network with Single-Step Conditional Diffusion ModelsCode2
GaussianPretrain: A Simple Unified 3D Gaussian Representation for Visual Pre-training in Autonomous DrivingCode2
OSMLoc: Single Image-Based Visual Localization in OpenStreetMap with Fused Geometric and Semantic GuidanceCode2
On Deep Learning for Geometric and Semantic Scene Understanding Using On-Vehicle 3D LiDARCode2
VLM-Grounder: A VLM Agent for Zero-Shot 3D Visual GroundingCode2
ARKit LabelMaker: A New Scale for Indoor 3D Scene UnderstandingCode2
Procedure-Aware Surgical Video-language Pretraining with Hierarchical Knowledge AugmentationCode2
Learning Multiple Probabilistic Decisions from Latent World Model in Autonomous DrivingCode2
Hier-SLAM: Scaling-up Semantics in SLAM with a Hierarchically Categorical Gaussian SplattingCode2
PrimeDepth: Efficient Monocular Depth Estimation with a Stable Diffusion PreimageCode2
Lexicon3D: Probing Visual Foundation Models for Complex 3D Scene UnderstandingCode2
Unveiling Deep Shadows: A Survey and Benchmark on Image and Video Shadow Detection, Removal, and Generation in the Deep Learning EraCode2
RoboSense: Large-scale Dataset and Benchmark for Egocentric Robot Perception and Navigation in Crowded and Unstructured EnvironmentsCode2
A Unified Framework for 3D Scene UnderstandingCode2
StableSemantics: A Synthetic Language-Vision Dataset of Semantic Representations in Naturalistic ImagesCode2
RS-Agent: Automating Remote Sensing Tasks through Intelligent AgentCode2
MTVQA: Benchmarking Multilingual Text-Centric Visual Question AnsweringCode2
Grounded 3D-LLM with Referent TokensCode2
OpenESS: Event-based Semantic Scene Understanding with Open VocabulariesCode2
SPIdepth: Strengthened Pose Information for Self-supervised Monocular Depth EstimationCode2
NeRF-MAE: Masked AutoEncoders for Self-Supervised 3D Representation Learning for Neural Radiance FieldsCode2
Is Your LiDAR Placement Optimized for 3D Scene Understanding?Code2
Calib3D: Calibrating Model Preferences for Reliable 3D Scene UnderstandingCode2
Volumetric Environment Representation for Vision-Language NavigationCode2
FusionVision: A comprehensive approach of 3D object reconstruction and segmentation from RGB-D cameras using YOLO and fast segment anythingCode2
Delving into Multi-modal Multi-task Foundation Models for Road Scene Understanding: From Learning Paradigm PerspectivesCode2
Pixel-Wise Recognition for Holistic Surgical Scene UnderstandingCode2
MAPLM: A Real-World Large-Scale Vision-Language Benchmark for Map and Traffic Scene UnderstandingCode2
EmbodiedScan: A Holistic Multi-Modal 3D Perception Suite Towards Embodied AICode2
Chat-Scene: Bridging 3D Scene and Large Language Models with Object IdentifiersCode2
Gaussian Grouping: Segment and Edit Anything in 3D ScenesCode2
SpectralGPT: Spectral Remote Sensing Foundation ModelCode2
On the Road with GPT-4V(ision): Early Explorations of Visual-Language Model on Autonomous DrivingCode2
OpenIns3D: Snap and Lookup for 3D Open-vocabulary Instance SegmentationCode2
ScanNet++: A High-Fidelity Dataset of 3D Indoor ScenesCode2
Chat-3D: Data-efficiently Tuning Large Language Model for Universal Dialogue of 3D ScenesCode2
TaskExpert: Dynamically Assembling Multi-Task Representations with Memorial Mixture-of-ExpertsCode2
A Survey on Open-Vocabulary Detection and Segmentation: Past, Present, and FutureCode2
Towards Open Vocabulary Learning: A SurveyCode2
OpenMask3D: Open-Vocabulary 3D Instance SegmentationCode2
InvPT++: Inverted Pyramid Multi-Task Transformer for Visual Scene UnderstandingCode2
TextSLAM: Visual SLAM with Semantic Planar Text FeaturesCode2
TaskPrompter: Spatial-Channel Multi-Task Prompting for Dense Scene UnderstandingCode2
Swin3D: A Pretrained Transformer Backbone for 3D Indoor Scene UnderstandingCode2
Graph-based Topology Reasoning for Driving ScenesCode2
RegionPLC: Regional Point-Language Contrastive Learning for Open-World 3D Scene UnderstandingCode2
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