SOTAVerified

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 AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 351–400 of 1723 papers

TitleStatusHype
Towards Robust Algorithms for Surgical Phase Recognition via Digital Twin-based Scene Representation—0
Surgical Scene Segmentation by Transformer With Asymmetric Feature EnhancementCode0
PerspectiveNet: Multi-View Perception for Dynamic Scene Understanding—0
Large Language Models for Autonomous Driving (LLM4AD): Concept, Benchmark, Experiments, and Challenges—0
Part-Whole Relational Fusion Towards Multi-Modal Scene UnderstandingCode0
ARKit LabelMaker: A New Scale for Indoor 3D Scene UnderstandingCode2
VLM-Grounder: A VLM Agent for Zero-Shot 3D Visual GroundingCode2
SAM-Guided Masked Token Prediction for 3D Scene Understanding—0
3DArticCyclists: Generating Synthetic Articulated 8D Pose-Controllable Cyclist Data for Computer Vision Applications—0
LoLI-Street: Benchmarking Low-Light Image Enhancement and BeyondCode1
Enhancing Single Image to 3D Generation using Gaussian Splatting and Hybrid Diffusion Priors—0
3D Vision-Language Gaussian Splatting—0
A transition towards virtual representations of visual scenes—0
Test-Time Intensity Consistency Adaptation for Shadow Detection—0
Open-RGBT: Open-vocabulary RGB-T Zero-shot Semantic Segmentation in Open-world Environments—0
Evaluating the Impact of Point Cloud Colorization on Semantic Segmentation Accuracy—0
Resource-Efficient Multiview Perception: Integrating Semantic Masking with Masked Autoencoders—0
Diffusion Models in 3D Vision: A Survey—0
In-Place Panoptic Radiance Field Segmentation with Perceptual Prior for 3D Scene Understanding—0
Fast Object Detection with a Machine Learning Edge Device—0
SPARTUN3D: Situated Spatial Understanding of 3D World in Large Language Models—0
RESSCAL3D++: Joint Acquisition and Semantic Segmentation of 3D Point CloudsCode0
A Critical Assessment of Visual Sound Source Localization Models Including Negative AudioCode0
Procedure-Aware Surgical Video-language Pretraining with Hierarchical Knowledge AugmentationCode2
Class-Agnostic Visio-Temporal Scene Sketch Semantic Segmentation—0
You Only Speak Once to See—0
LLaVA-3D: A Simple yet Effective Pathway to Empowering LMMs with 3D-awareness—0
Scene Understanding in Pick-and-Place Tasks: Analyzing Transformations Between Initial and Final Scenes—0
OW-Rep: Open World Object Detection with Instance Representation Learning—0
Learning Multiple Probabilistic Decisions from Latent World Model in Autonomous DrivingCode2
Diffusion-based RGB-D Semantic Segmentation with Deformable Attention Transformer—0
Multilateral Cascading Network for Semantic Segmentation of Large-Scale Outdoor Point Clouds—0
Relevance-driven Decision Making for Safer and More Efficient Human Robot Collaboration—0
MOSE: Monocular Semantic Reconstruction Using NeRF-Lifted Noisy Priors—0
Hier-SLAM: Scaling-up Semantics in SLAM with a Hierarchically Categorical Gaussian SplattingCode2
CLAIR-A: Leveraging Large Language Models to Judge Audio CaptionsCode0
DAF-Net: A Dual-Branch Feature Decomposition Fusion Network with Domain Adaptive for Infrared and Visible Image FusionCode1
Towards Global Localization using Multi-Modal Object-Instance Re-IdentificationCode0
Video Token Sparsification for Efficient Multimodal LLMs in Autonomous Driving—0
DAE-Fuse: An Adaptive Discriminative Autoencoder for Multi-Modality Image Fusion—0
PrimeDepth: Efficient Monocular Depth Estimation with a Stable Diffusion PreimageCode2
Relevance for Human Robot Collaboration—0
LED: Light Enhanced Depth Estimation at NightCode1
Loss Distillation via Gradient Matching for Point Cloud Completion with Weighted Chamfer DistanceCode0
Towards Localizing Structural Elements: Merging Geometrical Detection with Semantic Verification in RGB-D Data—0
Online 3D reconstruction and dense tracking in endoscopic videosCode1
TanDepth: Leveraging Global DEMs for Metric Monocular Depth Estimation in UAVs—0
RCNet: Deep Recurrent Collaborative Network for Multi-View Low-Light Image EnhancementCode0
Future Does Matter: Boosting 3D Object Detection with Temporal Motion Estimation in Point Cloud Sequences—0
Lexicon3D: Probing Visual Foundation Models for Complex 3D Scene UnderstandingCode2
Show:102550
← PrevPage 8 of 35Next →
All datasetsSemantic Scene Understanding Challenge (passive actuation & ground-truth localisation)ADE20K valSemantic Scene Understanding Challenge (active actuation & ground-truth localisation)

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1ACRV BaselineOMQ0.44—Unverified
2Team VGAI (TCS Research)OMQ0.37—Unverified
3Demo_semantic_SLAMOMQ0.11—Unverified
#ModelMetricClaimedVerifiedStatus
1CPN(ResNet-101)Mean IoU46.3—Unverified
#ModelMetricClaimedVerifiedStatus
1ACRV BaselineOMQ0.35—Unverified