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
On the Road with GPT-4V(ision): Early Explorations of Visual-Language Model on Autonomous DrivingCode2
Multi-Task Learning as Multi-Objective OptimizationCode2
RS-Agent: Automating Remote Sensing Tasks through Intelligent AgentCode2
Safety-Enhanced Autonomous Driving Using Interpretable Sensor Fusion TransformerCode2
NavRAG: Generating User Demand Instructions for Embodied Navigation through Retrieval-Augmented LLMCode2
Chat-3D: Data-efficiently Tuning Large Language Model for Universal Dialogue of 3D ScenesCode2
OSMLoc: Single Image-Based Visual Localization in OpenStreetMap with Fused Geometric and Semantic GuidanceCode2
MAPLM: A Real-World Large-Scale Vision-Language Benchmark for Map and Traffic Scene UnderstandingCode2
Crab: A Unified Audio-Visual Scene Understanding Model with Explicit CooperationCode2
MTVQA: Benchmarking Multilingual Text-Centric Visual Question AnsweringCode2
Chameleon: Fast-slow Neuro-symbolic Lane Topology ExtractionCode2
StableSemantics: A Synthetic Language-Vision Dataset of Semantic Representations in Naturalistic ImagesCode2
Lexicon3D: Probing Visual Foundation Models for Complex 3D Scene UnderstandingCode2
InvPT++: Inverted Pyramid Multi-Task Transformer for Visual Scene UnderstandingCode2
IRef-VLA: A Benchmark for Interactive Referential Grounding with Imperfect Language in 3D ScenesCode2
LSceneLLM: Enhancing Large 3D Scene Understanding Using Adaptive Visual PreferencesCode2
Panoptic Lifting for 3D Scene Understanding with Neural FieldsCode2
Hypersim: A Photorealistic Synthetic Dataset for Holistic Indoor Scene UnderstandingCode2
HAKE: A Knowledge Engine Foundation for Human Activity UnderstandingCode2
GroupViT: Semantic Segmentation Emerges from Text SupervisionCode2
GEOBench-VLM: Benchmarking Vision-Language Models for Geospatial TasksCode2
ARKit LabelMaker: A New Scale for Indoor 3D Scene UnderstandingCode2
COB-GS: Clear Object Boundaries in 3DGS Segmentation Based on Boundary-Adaptive Gaussian SplittingCode2
Grounded 3D-LLM with Referent TokensCode2
Inst3D-LMM: Instance-Aware 3D Scene Understanding with Multi-modal Instruction TuningCode2
GALIP: Generative Adversarial CLIPs for Text-to-Image SynthesisCode2
A Survey on Open-Vocabulary Detection and Segmentation: Past, Present, and FutureCode2
Hier-SLAM: Scaling-up Semantics in SLAM with a Hierarchically Categorical Gaussian SplattingCode2
FusionVision: A comprehensive approach of 3D object reconstruction and segmentation from RGB-D cameras using YOLO and fast segment anythingCode2
A Unified Framework for 3D Scene UnderstandingCode2
PLA: Language-Driven Open-Vocabulary 3D Scene UnderstandingCode2
Learning Multiple Probabilistic Decisions from Latent World Model in Autonomous DrivingCode2
BinsFormer: Revisiting Adaptive Bins for Monocular Depth EstimationCode2
AutoTrust: Benchmarking Trustworthiness in Large Vision Language Models for Autonomous DrivingCode2
CMX: Cross-Modal Fusion for RGB-X Semantic Segmentation with TransformersCode2
CLIP goes 3D: Leveraging Prompt Tuning for Language Grounded 3D RecognitionCode2
Feed-Forward SceneDINO for Unsupervised Semantic Scene CompletionCode2
Gaussian Grouping: Segment and Edit Anything in 3D ScenesCode2
NeRF-MAE: Masked AutoEncoders for Self-Supervised 3D Representation Learning for Neural Radiance FieldsCode2
On Deep Learning for Geometric and Semantic Scene Understanding Using On-Vehicle 3D LiDARCode2
OpenESS: Event-based Semantic Scene Understanding with Open VocabulariesCode2
OpenIns3D: Snap and Lookup for 3D Open-vocabulary Instance SegmentationCode2
An Egocentric Vision-Language Model based Portable Real-time Smart AssistantCode2
An End-to-End Robust Point Cloud Semantic Segmentation Network with Single-Step Conditional Diffusion ModelsCode2
EmbodiedScan: A Holistic Multi-Modal 3D Perception Suite Towards Embodied AICode2
Emma-X: An Embodied Multimodal Action Model with Grounded Chain of Thought and Look-ahead Spatial ReasoningCode2
Panoptic Scene Graph GenerationCode2
Chat-Scene: Bridging 3D Scene and Large Language Models with Object IdentifiersCode2
EmbodiedOcc: Embodied 3D Occupancy Prediction for Vision-based Online Scene UnderstandingCode2
GaussianPretrain: A Simple Unified 3D Gaussian Representation for Visual Pre-training in Autonomous DrivingCode2
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