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 1501–1510 of 1723 papers

Title	Date	Tasks	Status
On the iterative refinement of densely connected representation levels for semantic segmentation	Apr 30, 2018	Image SegmentationScene Understanding	CodeCode Available
One model to use them all: Training a segmentation model with complementary datasets	Feb 29, 2024	AllAnatomy	CodeCode Available
Image interpretation by iterative bottom-up top-down processing	May 12, 2021	Scene Understanding	CodeCode Available
Depth-Induced Multi-Scale Recurrent Attention Network for Saliency Detection	Oct 1, 2019	RGB-D Salient Object DetectionSaliency Detection	CodeCode Available
PSA-SSL: Pose and Size-aware Self-Supervised Learning on LiDAR Point Clouds	Mar 18, 2025	3D Object Detection3D Semantic Segmentation	CodeCode Available
Adapting Deep Network Features to Capture Psychological Representations	Aug 6, 2016	Object RecognitionScene Understanding	CodeCode Available
Single Image 3D Object Estimation with Primitive Graph Networks	Sep 9, 2021	Graph Neural NetworkObject	CodeCode Available
Towards Ambiguity-Free Spatial Foundation Model: Rethinking and Decoupling Depth Ambiguity	Mar 8, 2025	Depth EstimationScene Understanding	CodeCode Available
Omni-Recon: Harnessing Image-based Rendering for General-Purpose Neural Radiance Fields	Mar 17, 2024	3D ReconstructionNeRF	CodeCode Available
Unsupervised Single-shot Depth Estimation using Perceptual Reconstruction	Jan 28, 2022	3D ReconstructionDepth Estimation	CodeCode Available

Show:10 25 50

← PrevPage 151 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