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 151–200 of 1723 papers

TitleStatusHype
SuperFlow++: Enhanced Spatiotemporal Consistency for Cross-Modal Data PretrainingCode2
OpenLex3D: A New Evaluation Benchmark for Open-Vocabulary 3D Scene Representations—0
The Coralscapes Dataset: Semantic Scene Understanding in Coral ReefsCode1
Predicting the Road Ahead: A Knowledge Graph based Foundation Model for Scene Understanding in Autonomous Driving—0
SceneSplat: Gaussian Splatting-based Scene Understanding with Vision-Language PretrainingCode3
MLLM-For3D: Adapting Multimodal Large Language Model for 3D Reasoning Segmentation—0
PanoGS: Gaussian-based Panoptic Segmentation for 3D Open Vocabulary Scene Understanding—0
PolarFree: Polarization-based Reflection-free ImagingCode2
PanopticSplatting: End-to-End Panoptic Gaussian Splatting—0
Geometric Constrained Non-Line-of-Sight Imaging—0
ClaraVid: A Holistic Scene Reconstruction Benchmark From Aerial Perspective With Delentropy-Based Complexity Profiling—0
ExCap3D: Expressive 3D Scene Understanding via Object Captioning with Varying Detail—0
Cross-Modal and Uncertainty-Aware Agglomeration for Open-Vocabulary 3D Scene UnderstandingCode1
IRef-VLA: A Benchmark for Interactive Referential Grounding with Imperfect Language in 3D ScenesCode2
From Monocular Vision to Autonomous Action: Guiding Tumor Resection via 3D Reconstruction—0
SemanticFlow: A Self-Supervised Framework for Joint Scene Flow Prediction and Instance Segmentation in Dynamic Environments—0
These Magic Moments: Differentiable Uncertainty Quantification of Radiance Field Models—0
PSA-SSL: Pose and Size-aware Self-Supervised Learning on LiDAR Point CloudsCode0
ChatBEV: A Visual Language Model that Understands BEV Maps—0
Crab: A Unified Audio-Visual Scene Understanding Model with Explicit CooperationCode2
HIS-GPT: Towards 3D Human-In-Scene Multimodal Understanding—0
Learning-based 3D Reconstruction in Autonomous Driving: A Comprehensive Survey—0
NuPlanQA: A Large-Scale Dataset and Benchmark for Multi-View Driving Scene Understanding in Multi-Modal Large Language ModelsCode1
Logic-RAG: Augmenting Large Multimodal Models with Visual-Spatial Knowledge for Road Scene UnderstandingCode1
EgoSplat: Open-Vocabulary Egocentric Scene Understanding with Language Embedded 3D Gaussian Splatting—0
Road Rage Reasoning with Vision-language Models (VLMs): Task Definition and Evaluation Dataset—0
TARS: Traffic-Aware Radar Scene Flow Estimation—0
TGP: Two-modal occupancy prediction with 3D Gaussian and sparse points for 3D Environment Awareness—0
Graph-Grounded LLMs: Leveraging Graphical Function Calling to Minimize LLM Hallucinations—0
Object-Aware DINO (Oh-A-Dino): Enhancing Self-Supervised Representations for Multi-Object Instance Retrieval—0
DIV-FF: Dynamic Image-Video Feature Fields For Environment Understanding in Egocentric Videos—0
MaskAttn-UNet: A Mask Attention-Driven Framework for Universal Low-Resolution Image Segmentation—0
TrackOcc: Camera-based 4D Panoptic Occupancy TrackingCode2
General-Purpose Aerial Intelligent Agents Empowered by Large Language Models—0
Generating Robot Constitutions & Benchmarks for Semantic Safety—0
LLaFEA: Frame-Event Complementary Fusion for Fine-Grained Spatiotemporal Understanding in LMMs—0
Chameleon: Fast-slow Neuro-symbolic Lane Topology ExtractionCode2
A Data-Centric Revisit of Pre-Trained Vision Models for Robot LearningCode1
CoT-Drive: Efficient Motion Forecasting for Autonomous Driving with LLMs and Chain-of-Thought Prompting—0
Segment Anything, Even Occluded—0
Feature-EndoGaussian: Feature Distilled Gaussian Splatting in Surgical Deformable Scene Reconstruction—0
SplatTalk: 3D VQA with Gaussian Splatting—0
VLScene: Vision-Language Guidance Distillation for Camera-Based 3D Semantic Scene CompletionCode1
Towards Ambiguity-Free Spatial Foundation Model: Rethinking and Decoupling Depth AmbiguityCode0
An Egocentric Vision-Language Model based Portable Real-time Smart AssistantCode2
EvidMTL: Evidential Multi-Task Learning for Uncertainty-Aware Semantic Surface Mapping from Monocular RGB Images—0
Vision-Language Models Struggle to Align Entities across Modalities—0
SurgiSAM2: Fine-tuning a foundational model for surgical video anatomy segmentation and detection—0
Improving 6D Object Pose Estimation of metallic Household and Industry Objects—0
SSNet: Saliency Prior and State Space Model-based Network for Salient Object Detection in RGB-D Images—0
Show:102550
← PrevPage 4 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