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 451–500 of 1723 papers

TitleStatusHype
General Geometry-aware Weakly Supervised 3D Object DetectionCode1
Dual-Hybrid Attention Network for Specular Highlight RemovalCode1
InfoNorm: Mutual Information Shaping of Normals for Sparse-View ReconstructionCode0
Benchmarking Vision Language Models for Cultural Understanding—0
No Train, all Gain: Self-Supervised Gradients Improve Deep Frozen RepresentationsCode1
Shape2Scene: 3D Scene Representation Learning Through Pre-training on Shape DataCode0
Dense Multimodal Alignment for Open-Vocabulary 3D Scene Understanding—0
BLOS-BEV: Navigation Map Enhanced Lane Segmentation Network, Beyond Line of Sight—0
Pareto Low-Rank Adapters: Efficient Multi-Task Learning with Preferences—0
Swiss DINO: Efficient and Versatile Vision Framework for On-device Personal Object SearchCode0
LVLM-empowered Multi-modal Representation Learning for Visual Place Recognition—0
Joint prototype and coefficient prediction for 3D instance segmentation—0
Self-supervised Learning via Cluster Distance Prediction for Operating Room Context Awareness—0
Hybrid Primal Sketch: Combining Analogy, Qualitative Representations, and Computer Vision for Scene Understanding—0
A Unified Framework for 3D Scene UnderstandingCode2
MTMamba: Enhancing Multi-Task Dense Scene Understanding by Mamba-Based DecodersCode1
Uni-DVPS: Unified Model for Depth-Aware Video Panoptic SegmentationCode1
PanopticRecon: Leverage Open-vocabulary Instance Segmentation for Zero-shot Panoptic Reconstruction—0
CSFNet: A Cosine Similarity Fusion Network for Real-Time RGB-X Semantic Segmentation of Driving ScenesCode1
ESGNN: Towards Equivariant Scene Graph Neural Network for 3D Scene Understanding—0
EgoGaussian: Dynamic Scene Understanding from Egocentric Video with 3D Gaussian Splatting—0
PPTFormer: Pseudo Multi-Perspective Transformer for UAV Segmentation—0
3D-MVP: 3D Multiview Pretraining for Robotic Manipulation—0
GPT-4V Explorations: Mining Autonomous Driving—0
AudioBench: A Universal Benchmark for Audio Large Language ModelsCode3
EvSegSNN: Neuromorphic Semantic Segmentation for Event Data—0
StableSemantics: A Synthetic Language-Vision Dataset of Semantic Representations in Naturalistic ImagesCode2
DistillNeRF: Perceiving 3D Scenes from Single-Glance Images by Distilling Neural Fields and Foundation Model Features—0
Enhancing Generalizability of Representation Learning for Data-Efficient 3D Scene Understanding—0
MapVision: CVPR 2024 Autonomous Grand Challenge Mapless Driving Tech Report—0
A Two-Stage Masked Autoencoder Based Network for Indoor Depth CompletionCode1
MuirBench: A Comprehensive Benchmark for Robust Multi-image UnderstandingCode1
Category-level Neural Field for Reconstruction of Partially Observed Objects in Indoor EnvironmentCode0
RS-Agent: Automating Remote Sensing Tasks through Intelligent AgentCode2
FastLGS: Speeding up Language Embedded Gaussians with Feature Grid Mapping—0
EAGLE: Efficient Adaptive Geometry-based Learning in Cross-view Understanding—0
Object Aware Egocentric Online Action Detection—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
SAM-E: Leveraging Visual Foundation Model with Sequence Imitation for Embodied Manipulation—0
Learning 3D Robotics Perception using Inductive Priors—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
CoPeD-Advancing Multi-Robot Collaborative Perception: A Comprehensive Dataset in Real-World EnvironmentsCode1
TS40K: a 3D Point Cloud Dataset of Rural Terrain and Electrical Transmission System—0
GameVLM: A Decision-making Framework for Robotic Task Planning Based on Visual Language Models and Zero-sum Games—0
Anticipating Object State Changes in Long Procedural Videos—0
Show:102550
← PrevPage 10 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