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 231–240 of 1723 papers

Title	Date	Tasks	Status	Hype
CAT-ViL: Co-Attention Gated Vision-Language Embedding for Visual Question Localized-Answering in Robotic Surgery	Jul 11, 2023	Question AnsweringScene Understanding	CodeCode Available	1
Towards accurate instance segmentation in large-scale LiDAR point clouds	Jul 6, 2023	ClusteringInstance Segmentation	CodeCode Available	1
AVSegFormer: Audio-Visual Segmentation with Transformer	Jul 3, 2023	DecoderScene Understanding	CodeCode Available	1
SSC-RS: Elevate LiDAR Semantic Scene Completion with Representation Separation and BEV Fusion	Jun 27, 2023	Autonomous DrivingScene Understanding	CodeCode Available	1
Multi-view 3D Object Reconstruction and Uncertainty Modelling with Neural Shape Prior	Jun 17, 2023	3D Object ReconstructionObject	CodeCode Available	1
PanoOcc: Unified Occupancy Representation for Camera-based 3D Panoptic Segmentation	Jun 16, 2023	3D Panoptic SegmentationAutonomous Driving	CodeCode Available	1
Estimating Generic 3D Room Structures from 2D Annotations	Jun 15, 2023	Scene Understanding	CodeCode Available	1
SNAP: Self-Supervised Neural Maps for Visual Positioning and Semantic Understanding	Jun 8, 2023	Scene Understanding	CodeCode Available	1
Towards Label-free Scene Understanding by Vision Foundation Models	Jun 6, 2023	image-classificationImage Classification	CodeCode Available	1
Towards In-context Scene Understanding	Jun 2, 2023	Depth EstimationIn-Context Learning	CodeCode Available	1

Show:10 25 50

← PrevPage 24 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