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 1051–1100 of 1723 papers

TitleStatusHype
Point Cloud Pre-Training With Natural 3D StructuresCode1
MSeg: A Composite Dataset for Multi-domain Semantic SegmentationCode1
Channel-Wise Attention-Based Network for Self-Supervised Monocular Depth EstimationCode1
HSPACE: Synthetic Parametric Humans Animated in Complex Environments—0
Comprehensive Visual Question Answering on Point Clouds through Compositional Scene ManipulationCode1
ScanQA: 3D Question Answering for Spatial Scene UnderstandingCode1
Distillation of Human-Object Interaction Contexts for Action Recognition—0
Activation Modulation and Recalibration Scheme for Weakly Supervised Semantic SegmentationCode1
Improving Human-Object Interaction Detection via Phrase Learning and Label Composition—0
Image-to-Height Domain Translation for Synthetic Aperture Sonar—0
3D Scene Understanding at Urban Intersection using Stereo Vision and Digital Map—0
Roominoes: Generating Novel 3D Floor Plans From Existing 3D Rooms—0
4DContrast: Contrastive Learning with Dynamic Correspondences for 3D Scene Understanding—0
PolyphonicFormer: Unified Query Learning for Depth-aware Video Panoptic SegmentationCode1
Behind the Curtain: Learning Occluded Shapes for 3D Object DetectionCode1
Contrastive Instance Association for 4D Panoptic Segmentation using Sequences of 3D LiDAR ScansCode0
Both Style and Fog Matter: Cumulative Domain Adaptation for Semantic Foggy Scene Understanding—0
REMIPS: Physically Consistent 3D Reconstruction of Multiple Interacting People under Weak Supervision—0
Joint Modeling of Visual Objects and Relations for Scene Graph Generation—0
AirObject: A Temporally Evolving Graph Embedding for Object IdentificationCode1
Zero-Shot Semantic Segmentation via Spatial and Multi-Scale Aware Visual Class Embedding—0
DiffSDFSim: Differentiable Rigid-Body Dynamics With Implicit Shapes—0
Instance-wise Occlusion and Depth Orders in Natural ScenesCode1
PAPooling: Graph-based Position Adaptive Aggregation of Local Geometry in Point Clouds—0
Not All Relations are Equal: Mining Informative Labels for Scene Graph Generation—0
Joint stereo 3D object detection and implicit surface reconstructionCode0
Cerberus Transformer: Joint Semantic, Affordance and Attribute ParsingCode1
Panoptic Segmentation Meets Remote Sensing—0
Talk-to-Resolve: Combining scene understanding and spatial dialogue to resolve granular task ambiguity for a collocated robot—0
Grounded Situation Recognition with TransformersCode1
ARKitScenes: A Diverse Real-World Dataset For 3D Indoor Scene Understanding Using Mobile RGB-D DataCode1
Robust 3D Scene Segmentation through Hierarchical and Learnable Part-Fusion—0
Learning Object-Centric Representations of Multi-Object Scenes from Multiple ViewsCode1
Robust deep learning-based semantic organ segmentation in hyperspectral images—0
DriveGuard: Robustification of Automated Driving Systems with Deep Spatio-Temporal Convolutional Autoencoder—0
When Neural Networks Using Different Sensors Create Similar Features—0
Panoptic 3D Scene Reconstruction From a Single RGB ImageCode1
3DP3: 3D Scene Perception via Probabilistic ProgrammingCode1
A Versatile and Efficient Reinforcement Learning Framework for Autonomous DrivingCode1
Semantic Detection of Potential Wind-borne Debris in Construction Jobsites: Digital Twining for Hurricane Preparedness and Jobsite Safety—0
PlaneRecNet: Multi-Task Learning with Cross-Task Consistency for Piece-Wise Plane Detection and Reconstruction from a Single RGB ImageCode1
Adversarial Scene Reconstruction and Object Detection System for Assisting Autonomous Vehicle—0
Monocular Depth Estimation with Sharp Boundary—0
Structured Bird's-Eye-View Traffic Scene Understanding from Onboard ImagesCode1
Unsupervised Domain Adaptation for LiDAR Panoptic Segmentation—0
Semantic Dense Reconstruction with Consistent Scene Segments—0
D-Net: A Generalised and Optimised Deep Network for Monocular Depth EstimationCode0
Referring Self-supervised Learning on 3D Point Cloud—0
Efficient Point Transformer for Large-scale 3D Scene Understanding—0
KITTI-360: A Novel Dataset and Benchmarks for Urban Scene Understanding in 2D and 3DCode1
Show:102550
← PrevPage 22 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