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 851–900 of 1723 papers

TitleStatusHype
FastLGS: Speeding up Language Embedded Gaussians with Feature Grid Mapping—0
Object Aware Egocentric Online Action Detection—0
EAGLE: Efficient Adaptive Geometry-based Learning in Cross-view Understanding—0
CYCLO: Cyclic Graph Transformer Approach to Multi-Object Relationship Modeling in Aerial Videos—0
Semi-supervised Video Semantic Segmentation Using Unreliable Pseudo Labels for PVUW2024—0
Learning 3D Robotics Perception using Inductive Priors—0
SAM-E: Leveraging Visual Foundation Model with Sequence Imitation for Embodied Manipulation—0
Kestrel: Point Grounding Multimodal LLM for Part-Aware 3D Vision-Language Understanding—0
GOI: Find 3D Gaussians of Interest with an Optimizable Open-vocabulary Semantic-space Hyperplane—0
Open-Vocabulary SAM3D: Towards Training-free Open-Vocabulary 3D Scene Understanding—0
Generative Camera Dolly: Extreme Monocular Dynamic Novel View Synthesis—0
Transformers for Image-Goal Navigation—0
GameVLM: A Decision-making Framework for Robotic Task Planning Based on Visual Language Models and Zero-sum Games—0
TS40K: a 3D Point Cloud Dataset of Rural Terrain and Electrical Transmission System—0
Anticipating Object State Changes in Long Procedural Videos—0
A Preprocessing and Postprocessing Voxel-based Method for LiDAR Semantic Segmentation Improvement in Long Distance—0
BEHAVIOR Vision Suite: Customizable Dataset Generation via Simulation—0
3D Shape Augmentation with Content-Aware Shape Resizing—0
DriveWorld: 4D Pre-trained Scene Understanding via World Models for Autonomous Driving—0
Q-GroundCAM: Quantifying Grounding in Vision Language Models via GradCAM—0
Seeing Beyond Classes: Zero-Shot Grounded Situation Recognition via Language Explainer—0
CloudFort: Enhancing Robustness of 3D Point Cloud Classification Against Backdoor Attacks via Spatial Partitioning and Ensemble Prediction—0
On Support Relations Inference and Scene Hierarchy Graph Construction from Point Cloud in Clustered Environments—0
Unified Scene Representation and Reconstruction for 3D Large Language Models—0
BACS: Background Aware Continual Semantic SegmentationCode0
AccidentBlip: Agent of Accident Warning based on MA-former—0
Multimodal 3D Object Detection on Unseen Domains—0
PreGSU-A Generalized Traffic Scene Understanding Model for Autonomous Driving based on Pre-trained Graph Attention Network—0
Mitigating Object Dependencies: Improving Point Cloud Self-Supervised Learning through Object ExchangeCode0
Depth Estimation using Weighted-loss and Transfer Learning—0
Gaga: Group Any Gaussians via 3D-aware Memory Bank—0
Incorporating Explanations into Human-Machine Interfaces for Trust and Situation Awareness in Autonomous Vehicles—0
O2V-Mapping: Online Open-Vocabulary Mapping with Neural Implicit Representation—0
DaF-BEVSeg: Distortion-aware Fisheye Camera based Bird's Eye View Segmentation with Occlusion Reasoning—0
QueSTMaps: Queryable Semantic Topological Maps for 3D Scene Understanding—0
Panoptic Perception: A Novel Task and Fine-grained Dataset for Universal Remote Sensing Image Interpretation—0
You Only Scan Once: A Dynamic Scene Reconstruction Pipeline for 6-DoF Robotic Grasping of Novel Objects—0
MM3DGS SLAM: Multi-modal 3D Gaussian Splatting for SLAM Using Vision, Depth, and Inertial Measurements—0
360+x: A Panoptic Multi-modal Scene Understanding Dataset—0
Adapting to Length Shift: FlexiLength Network for Trajectory Prediction—0
Neural Radiance Field-based Visual Rendering: A Comprehensive Review—0
HGS-Mapping: Online Dense Mapping Using Hybrid Gaussian Representation in Urban Scenes—0
Efficient 3D Instance Mapping and Localization with Neural Fields—0
DOCTR: Disentangled Object-Centric Transformer for Point Scene UnderstandingCode0
Towards Trustworthy Automated Driving through Qualitative Scene Understanding and Explanations—0
Semantic Is Enough: Only Semantic Information For NeRF Reconstruction—0
Multi-Task Learning with Multi-Task Optimization—0
DiffusionMTL: Learning Multi-Task Denoising Diffusion Model from Partially Annotated Data—0
Semantic Gaussians: Open-Vocabulary Scene Understanding with 3D Gaussian Splatting—0
3D Object Detection from Point Cloud via Voting Step DiffusionCode0
Show:102550
← PrevPage 18 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