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 551–600 of 1723 papers

TitleStatusHype
Semantic Is Enough: Only Semantic Information For NeRF Reconstruction—0
AutoInst: Automatic Instance-Based Segmentation of LiDAR 3D ScansCode1
Multi-Task Learning with Multi-Task Optimization—0
Semantic Gaussians: Open-Vocabulary Scene Understanding with 3D Gaussian Splatting—0
DiffusionMTL: Learning Multi-Task Denoising Diffusion Model from Partially Annotated Data—0
Exosense: A Vision-Based Scene Understanding System For Exoskeletons—0
SurroundSDF: Implicit 3D Scene Understanding Based on Signed Distance Field—0
3D Object Detection from Point Cloud via Voting Step DiffusionCode0
Volumetric Environment Representation for Vision-Language NavigationCode2
What if...?: Thinking Counterfactual Keywords Helps to Mitigate Hallucination in Large Multi-modal ModelsCode1
Instance-Warp: Saliency Guided Image Warping for Unsupervised Domain AdaptationCode0
Geometric Constraints in Deep Learning Frameworks: A Survey—0
HUGS: Holistic Urban 3D Scene Understanding via Gaussian Splatting—0
M2DA: Multi-Modal Fusion Transformer Incorporating Driver Attention for Autonomous Driving—0
R3DS: Reality-linked 3D Scenes for Panoramic Scene Understanding—0
OpenOcc: Open Vocabulary 3D Scene Reconstruction via Occupancy RepresentationCode0
Hierarchical Spatial Proximity Reasoning for Vision-and-Language NavigationCode0
Agent3D-Zero: An Agent for Zero-shot 3D Understanding—0
Urban Scene Diffusion through Semantic Occupancy Map—0
Omni-Recon: Harnessing Image-based Rendering for General-Purpose Neural Radiance FieldsCode0
N2F2: Hierarchical Scene Understanding with Nested Neural Feature Fields—0
Segment Any Object Model (SAOM): Real-to-Simulation Fine-Tuning Strategy for Multi-Class Multi-Instance Segmentation—0
Enhancing Human-Centered Dynamic Scene Understanding via Multiple LLMs Collaborated Reasoning—0
GroupContrast: Semantic-aware Self-supervised Representation Learning for 3D UnderstandingCode1
MoAI: Mixture of All Intelligence for Large Language and Vision ModelsCode3
Mapping High-level Semantic Regions in Indoor Environments without Object Recognition—0
Optimizing Latent Graph Representations of Surgical Scenes for Zero-Shot Domain TransferCode1
Stealing Stable Diffusion Prior for Robust Monocular Depth EstimationCode1
Embodied Understanding of Driving ScenariosCode3
Out of the Room: Generalizing Event-Based Dynamic Motion Segmentation for Complex Scenes—0
GSNeRF: Generalizable Semantic Neural Radiance Fields with Enhanced 3D Scene Understanding—0
HUNTER: Unsupervised Human-centric 3D Detection via Transferring Knowledge from Synthetic Instances to Real Scenes—0
FusionVision: A comprehensive approach of 3D object reconstruction and segmentation from RGB-D cameras using YOLO and fast segment anythingCode2
WHU-Synthetic: A Synthetic Perception Dataset for 3-D Multitask Model ResearchCode1
One model to use them all: Training a segmentation model with complementary datasetsCode0
PCDepth: Pattern-based Complementary Learning for Monocular Depth Estimation by Best of Both Worlds—0
LiveHPS: LiDAR-based Scene-level Human Pose and Shape Estimation in Free Environment—0
AVS-Net: Point Sampling with Adaptive Voxel Size for 3D Scene UnderstandingCode0
OpenSUN3D: 1st Workshop Challenge on Open-Vocabulary 3D Scene Understanding—0
Swin3D++: Effective Multi-Source Pretraining for 3D Indoor Scene UnderstandingCode3
DriveVLM: The Convergence of Autonomous Driving and Large Vision-Language Models—0
Semantically-aware Neural Radiance Fields for Visual Scene Understanding: A Comprehensive ReviewCode1
Moving Object Proposals with Deep Learned Optical Flow for Video Object Segmentation—0
Prismatic VLMs: Investigating the Design Space of Visually-Conditioned Language ModelsCode4
InCoRo: In-Context Learning for Robotics Control with Feedback Loops—0
Delving into Multi-modal Multi-task Foundation Models for Road Scene Understanding: From Learning Paradigm PerspectivesCode2
SGS-SLAM: Semantic Gaussian Splatting For Neural Dense SLAMCode3
Neural Language of Thought Models—0
Good at captioning, bad at counting: Benchmarking GPT-4V on Earth observation dataCode0
Non-central panorama indoor datasetCode0
Show:102550
← PrevPage 12 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