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 501–550 of 1723 papers

TitleStatusHype
Physics-as-Inverse-Graphics: Unsupervised Physical Parameter Estimation from VideoCode0
PENet: A Joint Panoptic Edge Detection NetworkCode0
Instance-Warp: Saliency Guided Image Warping for Unsupervised Domain AdaptationCode0
Parsing Natural Scenes and Natural Language with Recursive Neural NetworksCode0
Efficient ConvNet for Real-time Semantic SegmentationCode0
Efficient Computation Sharing for Multi-Task Visual Scene UnderstandingCode0
Parsing Geometry Using Structure-Aware Shape TemplatesCode0
Part-Whole Relational Fusion Towards Multi-Modal Scene UnderstandingCode0
PanoRecon: Real-Time Panoptic 3D Reconstruction from Monocular VideoCode0
Parallel Neural Computing for Scene Understanding from LiDAR Perception in Autonomous RacingCode0
3D Semantic Segmentation of Modular Furniture using rjMCMCCode0
Planning Safety Trajectories with Dual-Phase, Physics-Informed, and Transportation Knowledge-Driven Large Language ModelsCode0
Real-time 3D Traffic Cone Detection for Autonomous DrivingCode0
SemanticKITTI: A Dataset for Semantic Scene Understanding of LiDAR SequencesCode0
P2AT: Pyramid Pooling Axial Transformer for Real-time Semantic SegmentationCode0
Bridging Stereo Matching and Optical Flow via Spatiotemporal CorrespondenceCode0
AP-MTL: Attention Pruned Multi-task Learning Model for Real-time Instrument Detection and Segmentation in Robot-assisted SurgeryCode0
DualMLP: a two-stream fusion model for 3D point cloud classificationCode0
OVeNet: Offset Vector Network for Semantic SegmentationCode0
Dual-Glance Model for Deciphering Social RelationshipsCode0
A Plug-and-Play Method for Rare Human-Object Interactions Detection by Bridging Domain GapCode0
OVGaussian: Generalizable 3D Gaussian Segmentation with Open VocabulariesCode0
Box for Mask and Mask for Box: weak losses for multi-task partially supervised learningCode0
APCoTTA: Continual Test-Time Adaptation for Semantic Segmentation of Airborne LiDAR Point CloudsCode0
OST-Bench: Evaluating the Capabilities of MLLMs in Online Spatio-temporal Scene UnderstandingCode0
DRRNet: Macro-Micro Feature Fusion and Dual Reverse Refinement for Camouflaged Object DetectionCode0
Boundary-Seeking Generative Adversarial NetworksCode0
OpenOcc: Open Vocabulary 3D Scene Reconstruction via Occupancy RepresentationCode0
Doubly Contrastive End-to-End Semantic Segmentation for Autonomous Driving under Adverse WeatherCode0
On the iterative refinement of densely connected representation levels for semantic segmentationCode0
AdaptVision: Dynamic Input Scaling in MLLMs for Versatile Scene UnderstandingCode0
On the Structures of Representation for the Robustness of Semantic Segmentation to Input CorruptionCode0
DOCTR: Disentangled Object-Centric Transformer for Point Scene UnderstandingCode0
D-Net: A Generalised and Optimised Deep Network for Monocular Depth EstimationCode0
Adaptive Visual Scene Understanding: Incremental Scene Graph GenerationCode0
BOLD5000: A public fMRI dataset of 5000 imagesCode0
Distance Matters in Human-Object Interaction DetectionCode0
An Information-Theoretic Metric of Transferability for Task Transfer LearningCode0
Omni-Recon: Harnessing Image-based Rendering for General-Purpose Neural Radiance FieldsCode0
BlitzNet: A Real-Time Deep Network for Scene UnderstandingCode0
Non-central panorama indoor datasetCode0
Dirty Pixels: Towards End-to-End Image Processing and PerceptionCode0
Object Attribute Matters in Visual Question AnsweringCode0
Neural RGB->D Sensing: Depth and Uncertainty from a Video CameraCode0
NextStop: An Improved Tracker For Panoptic LIDAR Segmentation DataCode0
Neural Radiance Field CodebooksCode0
Object-aware Sound Source Localization via Audio-Visual Scene UnderstandingCode0
Dilated Residual NetworksCode0
A New Lightweight Hybrid Graph Convolutional Neural Network -- CNN Scheme for Scene Classification using Object Detection InferenceCode0
Adapting Deep Network Features to Capture Psychological RepresentationsCode0
Show:102550
← PrevPage 11 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