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 1571–1580 of 1723 papers

Title	Date	Tasks	Status
MonoGRNet: A Geometric Reasoning Network for Monocular 3D Object Localization	Nov 26, 2018	2D Object Detection3D Object Detection	CodeCode Available
Monocular 3D Object Detection with Pseudo-LiDAR Point Cloud	Mar 23, 2019	3D Object DetectionDepth Estimation	CodeCode Available
DC-Scene: Data-Centric Learning for 3D Scene Understanding	May 21, 2025	Autonomous DrivingScene Understanding	CodeCode Available
RIO: 3D Object Instance Re-Localization in Changing Indoor Environments	Aug 16, 2019	ObjectScene Understanding	CodeCode Available
Video-3D LLM: Learning Position-Aware Video Representation for 3D Scene Understanding	Nov 30, 2024	3D Question Answering (3D-QA)Position	CodeCode Available
Good at captioning, bad at counting: Benchmarking GPT-4V on Earth observation data	Jan 31, 2024	BenchmarkingChange Detection	CodeCode Available
Modeling Expectation Violation in Intuitive Physics with Coarse Probabilistic Object Representations	Dec 1, 2019	Scene Understanding	CodeCode Available
General-Purpose Deep Point Cloud Feature Extractor	Mar 12, 2018	3D Object Classification3D Point Cloud Classification	CodeCode Available
Generalizing Surgical Instruments Segmentation to Unseen Domains with One-to-Many Synthesis	Jun 28, 2023	Scene Understanding	CodeCode Available
APCoTTA: Continual Test-Time Adaptation for Semantic Segmentation of Airborne LiDAR Point Clouds	May 15, 2025	Point Cloud SegmentationScene Understanding	CodeCode Available

Show:10 25 50

← PrevPage 158 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