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
PC-BEV: An Efficient Polar-Cartesian BEV Fusion Framework for LiDAR Semantic SegmentationCode1
Dense Audio-Visual Event Localization under Cross-Modal Consistency and Multi-Temporal Granularity CollaborationCode1
WiseAD: Knowledge Augmented End-to-End Autonomous Driving with Vision-Language ModelCode1
LLaVA-SpaceSGG: Visual Instruct Tuning for Open-vocabulary Scene Graph Generation with Enhanced Spatial RelationsCode1
Bootstraping Clustering of Gaussians for View-consistent 3D Scene UnderstandingCode1
ROOT: VLM based System for Indoor Scene Understanding and BeyondCode1
TESGNN: Temporal Equivariant Scene Graph Neural Networks for Efficient and Robust Multi-View 3D Scene UnderstandingCode1
LoLI-Street: Benchmarking Low-Light Image Enhancement and BeyondCode1
DAF-Net: A Dual-Branch Feature Decomposition Fusion Network with Domain Adaptive for Infrared and Visible Image FusionCode1
LED: Light Enhanced Depth Estimation at NightCode1
Online 3D reconstruction and dense tracking in endoscopic videosCode1
UrBench: A Comprehensive Benchmark for Evaluating Large Multimodal Models in Multi-View Urban ScenariosCode1
MTMamba++: Enhancing Multi-Task Dense Scene Understanding via Mamba-Based DecodersCode1
RSTeller: Scaling Up Visual Language Modeling in Remote Sensing with Rich Linguistic Semantics from Openly Available Data and Large Language ModelsCode1
OpenScan: A Benchmark for Generalized Open-Vocabulary 3D Scene UnderstandingCode1
Query3D: LLM-Powered Open-Vocabulary Scene Segmentation with Language Embedded 3D GaussianCode1
Dynamic Scene Understanding through Object-Centric Voxelization and Neural RenderingCode1
General Geometry-aware Weakly Supervised 3D Object DetectionCode1
Dual-Hybrid Attention Network for Specular Highlight RemovalCode1
No Train, all Gain: Self-Supervised Gradients Improve Deep Frozen RepresentationsCode1
MTMamba: Enhancing Multi-Task Dense Scene Understanding by Mamba-Based DecodersCode1
Uni-DVPS: Unified Model for Depth-Aware Video Panoptic SegmentationCode1
CSFNet: A Cosine Similarity Fusion Network for Real-Time RGB-X Semantic Segmentation of Driving ScenesCode1
A Two-Stage Masked Autoencoder Based Network for Indoor Depth CompletionCode1
MuirBench: A Comprehensive Benchmark for Robust Multi-image UnderstandingCode1
CoPeD-Advancing Multi-Robot Collaborative Perception: A Comprehensive Dataset in Real-World EnvironmentsCode1
Beyond Appearances: Material Segmentation with Embedded Spectral Information from RGB-D imageryCode1
Pre-trained Text-to-Image Diffusion Models Are Versatile Representation Learners for ControlCode1
DTCLMapper: Dual Temporal Consistent Learning for Vectorized HD Map ConstructionCode1
ECLAIR: A High-Fidelity Aerial LiDAR Dataset for Semantic SegmentationCode1
PyTorchGeoNodes: Enabling Differentiable Shape Programs for 3D Shape ReconstructionCode1
GOV-NeSF: Generalizable Open-Vocabulary Neural Semantic FieldsCode1
Improving Visual Recognition with Hyperbolical Visual Hierarchy MappingCode1
VSRD: Instance-Aware Volumetric Silhouette Rendering for Weakly Supervised 3D Object DetectionCode1
Object Pose Estimation via the Aggregation of Diffusion FeaturesCode1
AutoInst: Automatic Instance-Based Segmentation of LiDAR 3D ScansCode1
What if...?: Thinking Counterfactual Keywords Helps to Mitigate Hallucination in Large Multi-modal ModelsCode1
GroupContrast: Semantic-aware Self-supervised Representation Learning for 3D UnderstandingCode1
Optimizing Latent Graph Representations of Surgical Scenes for Zero-Shot Domain TransferCode1
Stealing Stable Diffusion Prior for Robust Monocular Depth EstimationCode1
WHU-Synthetic: A Synthetic Perception Dataset for 3-D Multitask Model ResearchCode1
Semantically-aware Neural Radiance Fields for Visual Scene Understanding: A Comprehensive ReviewCode1
Towards Precise 3D Human Pose Estimation with Multi-Perspective Spatial-Temporal Relational TransformersCode1
UniM-OV3D: Uni-Modality Open-Vocabulary 3D Scene Understanding with Fine-Grained Feature RepresentationCode1
RSUD20K: A Dataset for Road Scene Understanding In Autonomous DrivingCode1
3DMIT: 3D Multi-modal Instruction Tuning for Scene UnderstandingCode1
DI-V2X: Learning Domain-Invariant Representation for Vehicle-Infrastructure Collaborative 3D Object DetectionCode1
WildScenes: A Benchmark for 2D and 3D Semantic Segmentation in Large-scale Natural EnvironmentsCode1
Pola4All: survey of polarimetric applications and an open-source toolkit to analyze polarizationCode1
Open3DIS: Open-Vocabulary 3D Instance Segmentation with 2D Mask GuidanceCode1
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