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 111–120 of 1723 papers

Title	Date	Tasks	Status	Hype
CMX: Cross-Modal Fusion for RGB-X Semantic Segmentation with Transformers	Mar 9, 2022	3D Object DetectionAutonomous Vehicles	CodeCode Available	2
GroupViT: Semantic Segmentation Emerges from Text Supervision	Feb 22, 2022	Object DetectionScene Understanding	CodeCode Available	2
HAKE: A Knowledge Engine Foundation for Human Activity Understanding	Feb 14, 2022	Action RecognitionHuman-Object Interaction Detection	CodeCode Available	2
Panoptic nuScenes: A Large-Scale Benchmark for LiDAR Panoptic Segmentation and Tracking	Sep 8, 2021	BenchmarkingDiversity	CodeCode Available	2
Hypersim: A Photorealistic Synthetic Dataset for Holistic Indoor Scene Understanding	Nov 4, 2020	Multi-Task LearningScene Understanding	CodeCode Available	2
Multi-Task Learning as Multi-Objective Optimization	Oct 10, 2018	Depth EstimationGeneral Classification	CodeCode Available	2
Learning to Tune Like an Expert: Interpretable and Scene-Aware Navigation via MLLM Reasoning and CVAE-Based Adaptation	Jul 15, 2025	Large Language ModelScene Understanding	CodeCode Available	1
SurgTPGS: Semantic 3D Surgical Scene Understanding with Text Promptable Gaussian Splatting	Jun 29, 2025	3D ReconstructionScene Understanding	CodeCode Available	1
ReME: A Data-Centric Framework for Training-Free Open-Vocabulary Segmentation	Jun 26, 2025	Open Vocabulary Semantic SegmentationOpen-Vocabulary Semantic Segmentation	CodeCode Available	1
DIP: Unsupervised Dense In-Context Post-training of Visual Representations	Jun 23, 2025	GPUMeta-Learning	CodeCode Available	1

Show:10 25 50

← PrevPage 12 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