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 161–170 of 1723 papers

Title	Date	Tasks	Status	Hype
FocusFlow: Boosting Key-Points Optical Flow Estimation for Autonomous Driving	Aug 14, 2023	Autonomous DrivingOptical Flow Estimation	CodeCode Available	1
Activation Modulation and Recalibration Scheme for Weakly Supervised Semantic Segmentation	Dec 16, 2021	Feature ImportanceScene Understanding	CodeCode Available	1
EndoChat: Grounded Multimodal Large Language Model for Endoscopic Surgery	Jan 20, 2025	Language ModelingLanguage Modelling	CodeCode Available	1
Enhancing Scene Graph Generation with Hierarchical Relationships and Commonsense Knowledge	Nov 21, 2023	Large Language ModelMultimodal Deep Learning	CodeCode Available	1
Egocentric Scene Understanding via Multimodal Spatial Rectifier	Jul 14, 2022	Scene UnderstandingSurface Normal Estimation	CodeCode Available	1
Efficient Multi-Task RGB-D Scene Analysis for Indoor Environments	Jul 10, 2022	Instance SegmentationPanoptic Segmentation	CodeCode Available	1
Behind the Curtain: Learning Occluded Shapes for 3D Object Detection	Dec 4, 2021	3D Object DetectionObject	CodeCode Available	1
3DP3: 3D Scene Perception via Probabilistic Programming	Oct 30, 2021	ObjectPose Estimation	CodeCode Available	1
ECLAIR: A High-Fidelity Aerial LiDAR Dataset for Semantic Segmentation	Apr 16, 2024	3D Semantic SegmentationManagement	CodeCode Available	1
Dual-Hybrid Attention Network for Specular Highlight Removal	Jul 17, 2024	highlight removalObject Recognition	CodeCode Available	1

Show:10 25 50

← PrevPage 17 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