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 1551–1560 of 1723 papers

Title	Date	Tasks	Status
Neighbor-Vote: Improving Monocular 3D Object Detection through Neighbor Distance Voting	Jul 6, 2021	3D Object DetectionAutonomous Driving	CodeCode Available
Multi-task Planar Reconstruction with Feature Warping Guidance	Nov 25, 2023	3D ReconstructionInstance Segmentation	CodeCode Available
Multi-task Geometric Estimation of Depth and Surface Normal from Monocular 360° Images	Nov 4, 2024	Multi-Task LearningScene Understanding	CodeCode Available
Holistic 3D Scene Parsing and Reconstruction from a Single RGB Image	Aug 7, 2018	3D Object DetectionMonocular 3D Object Detection	CodeCode Available
Multi-Resolution Multi-Modal Sensor Fusion For Remote Sensing Data With Label Uncertainty	May 2, 2018	Scene UnderstandingSensor Fusion	CodeCode Available
ShelfNet for Fast Semantic Segmentation	Nov 27, 2018	Autonomous DrivingDecoder	CodeCode Available
Multimodal Scale Consistency and Awareness for Monocular Self-Supervised Depth Estimation	Mar 3, 2021	Autonomous DrivingDepth Estimation	CodeCode Available
Deep Depth from Defocus: how can defocus blur improve 3D estimation using dense neural networks?	Sep 5, 2018	3D ReconstructionDepth Estimation	CodeCode Available
BACS: Background Aware Continual Semantic Segmentation	Apr 19, 2024	Autonomous DrivingContinual Learning	CodeCode Available
RESSCAL3D++: Joint Acquisition and Semantic Segmentation of 3D Point Clouds	Oct 3, 2024	Scene UnderstandingSemantic Segmentation	CodeCode Available

Show:10 25 50

← PrevPage 156 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