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 Added Most Hyped Most Active Needs Verification Most Verified

Showing 681–690 of 1723 papers

Title	Date	Tasks	Status	Score
Leveraging Automatic CAD Annotations for Supervised Learning in 3D Scene Understanding	Apr 18, 2025	Deep LearningPoint Cloud Completion	CodeCode Available	5
IGFNet: Illumination-Guided Fusion Network for Semantic Scene Understanding using RGB-Thermal Images	Dec 4, 2023	Autonomous DrivingScene Understanding	CodeCode Available	5
Lightweight integration of 3D features to improve 2D image segmentation	Dec 16, 2022	Image SegmentationScene Understanding	CodeCode Available	5
FlowGrad: Using Motion for Visual Sound Source Localization	Nov 15, 2022	Optical Flow EstimationScene Understanding	CodeCode Available	5
Learning Rigidity in Dynamic Scenes with a Moving Camera for 3D Motion Field Estimation	Apr 12, 2018	Optical Flow EstimationScene Flow Estimation	CodeCode Available	5
Flow-based GAN for 3D Point Cloud Generation from a Single Image	Oct 8, 2022	Point Cloud GenerationScene Understanding	CodeCode Available	5
Aerial Scene Understanding in The Wild: Multi-Scene Recognition via Prototype-based Memory Networks	Apr 22, 2021	RetrievalScene Recognition	CodeCode Available	5
Learning Regional Purity for Instance Segmentation on 3D Point Clouds	Nov 3, 2020	3D Instance Segmentation3D Semantic Segmentation	CodeCode Available	5
Learning Panoptic Segmentation from Instance Contours	Oct 16, 2020	ClusteringInstance Segmentation	CodeCode Available	5
Fine-Grained is Too Coarse: A Novel Data-Centric Approach for Efficient Scene Graph Generation	May 30, 2023	Graph GenerationImage Generation	CodeCode Available	5

Show:10 25 50

← PrevPage 69 of 173Next →

All datasets Semantic Scene Understanding Challenge (passive actuation & ground-truth localisation)ADE20K val Semantic Scene Understanding Challenge (active actuation & ground-truth localisation)

Benchmark Results

#	Model	Metric	Claimed	Verified	Status
1	ACRV Baseline	OMQ	0.44	—	Unverified
2	Team VGAI (TCS Research)	OMQ	0.37	—	Unverified
3	Demo_semantic_SLAM	OMQ	0.11	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	CPN(ResNet-101)	Mean IoU	46.3	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	ACRV Baseline	OMQ	0.35	—	Unverified