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 1–25 of 1723 papers

TitleStatusHype
City-VLM: Towards Multidomain Perception Scene Understanding via Multimodal Incomplete Learning—0
Argus: Leveraging Multiview Images for Improved 3-D Scene Understanding With Large Language Models—0
Advancing Complex Wide-Area Scene Understanding with Hierarchical Coresets Selection—0
Seeing the Signs: A Survey of Edge-Deployable OCR Models for Billboard Visibility Analysis—0
Tactical Decision for Multi-UGV Confrontation with a Vision-Language Model-Based Commander—0
Learning to Tune Like an Expert: Interpretable and Scene-Aware Navigation via MLLM Reasoning and CVAE-Based AdaptationCode1
EmbRACE-3K: Embodied Reasoning and Action in Complex Environments—0
OST-Bench: Evaluating the Capabilities of MLLMs in Online Spatio-temporal Scene UnderstandingCode0
MUVOD: A Novel Multi-view Video Object Segmentation Dataset and A Benchmark for 3D Segmentation—0
What Demands Attention in Urban Street Scenes? From Scene Understanding towards Road Safety: A Survey of Vision-driven Datasets and Studies—0
Feed-Forward SceneDINO for Unsupervised Semantic Scene CompletionCode2
SIU3R: Simultaneous Scene Understanding and 3D Reconstruction Beyond Feature AlignmentCode2
SurgTPGS: Semantic 3D Surgical Scene Understanding with Text Promptable Gaussian SplattingCode1
VoteSplat: Hough Voting Gaussian Splatting for 3D Scene Understanding—0
ReME: A Data-Centric Framework for Training-Free Open-Vocabulary SegmentationCode1
CoPa-SG: Dense Scene Graphs with Parametric and Proto-Relations—0
DreamAnywhere: Object-Centric Panoramic 3D Scene Generation—0
IPFormer: Visual 3D Panoptic Scene Completion with Context-Adaptive Instance Proposals—0
Case-based Reasoning Augmented Large Language Model Framework for Decision Making in Realistic Safety-Critical Driving Scenarios—0
HOIverse: A Synthetic Scene Graph Dataset With Human Object Interactions—0
DIP: Unsupervised Dense In-Context Post-training of Visual RepresentationsCode1
Scene-R1: Video-Grounded Large Language Models for 3D Scene Reasoning without 3D Annotations—0
Unified Representation Space for 3D Visual Grounding—0
Image Segmentation with Large Language Models: A Survey with Perspectives for Intelligent Transportation Systems—0
Leader360V: The Large-scale, Real-world 360 Video Dataset for Multi-task Learning in Diverse Environment—0
Show:102550
← PrevPage 1 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