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 26–50 of 1723 papers

TitleStatusHype
Unified Representation Space for 3D Visual Grounding—0
FreeQ-Graph: Free-form Querying with Semantic Consistent Scene Graph for 3D Scene Understanding—0
SceneCompleter: Dense 3D Scene Completion for Generative Novel View Synthesis—0
SemanticSplat: Feed-Forward 3D Scene Understanding with Language-Aware Gaussian Fields—0
PhyBlock: A Progressive Benchmark for Physical Understanding and Planning via 3D Block Assembly—0
Robust Visual Localization via Semantic-Guided Multi-Scale Transformer—0
SceneSplat++: A Large Dataset and Comprehensive Benchmark for Language Gaussian Splatting—0
OpenSplat3D: Open-Vocabulary 3D Instance Segmentation using Gaussian Splatting—0
Design and Evaluation of Deep Learning-Based Dual-Spectrum Image Fusion Methods—0
SpatialLM: Training Large Language Models for Structured Indoor Modeling—0
STSBench: A Spatio-temporal Scenario Benchmark for Multi-modal Large Language Models in Autonomous DrivingCode1
Does Your 3D Encoder Really Work? When Pretrain-SFT from 2D VLMs Meets 3D VLMs—0
ProJo4D: Progressive Joint Optimization for Sparse-View Inverse Physics Estimation—0
OWMM-Agent: Open World Mobile Manipulation With Multi-modal Agentic Data SynthesisCode1
Tactile MNIST: Benchmarking Active Tactile Perception—0
Attention-based transformer models for image captioning across languages: An in-depth survey and evaluation—0
Trajectory Prediction Meets Large Language Models: A SurveyCode5
PhysGaia: A Physics-Aware Dataset of Multi-Body Interactions for Dynamic Novel View SynthesisCode1
SAM2-LOVE: Segment Anything Model 2 in Language-aided Audio-Visual Scenes—0
Learning Sparsity for Effective and Efficient Music Performance Question Answering—0
Tackling View-Dependent Semantics in 3D Language Gaussian SplattingCode2
Learning from Videos for 3D World: Enhancing MLLMs with 3D Vision Geometry PriorsCode0
SeG-SR: Integrating Semantic Knowledge into Remote Sensing Image Super-Resolution via Vision-Language ModelCode0
DORAEMON: Decentralized Ontology-aware Reliable Agent with Enhanced Memory Oriented Navigation—0
LiDAR Based Semantic Perception for Forklifts in Outdoor Environments—0
Show:102550
← PrevPage 2 of 69Next →
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