| 2019-05 |
ACCV18 |
Visual graphs from motion (vgfm): Scene understanding with object geometry reasoning |
Italian Institute of Technology |
project, github |
| 2019-08 |
TOC19 |
3-D Scene Graph: A Sparse and Semantic Representation of Physical Environments for Intelligent Agents |
KAIST |
github |
| 2019-10 |
ICCV19 |
3D Scene Graph: A Structure for Unified Semantics, 3D Space, and Camera |
Stanford |
project, github |
| 2020-02 |
RSS20 |
3D Dynamic Scene Graphs: Actionable Spatial Perception with Places, Objects, and Humans |
MIT |
- |
| 2020-04 |
CVPR20 |
Learning 3D Semantic Scene Graphs from 3D Indoor Reconstructions |
TUM |
project, github |
| 2021-01 |
IJRR21 |
Kimera: from SLAM to Spatial Perception with 3D Dynamic Scene Graphs |
MIT |
github |
| 2021-03 |
CVPR21 |
Exploiting Edge-Oriented Reasoning for 3D Point-based Scene Graph Analysis |
USYD |
project, github |
| 2021-03 |
CVPR21 |
SceneGraphFusion: Incremental 3D Scene Graph Prediction from RGB-D Sequences |
TUM |
project, github |
| 2021-08 |
ICRA22 |
Hierarchical Representations and Explicit Memory: Learning Effective Navigation Policies on 3D Scene Graphs using Graph Neural Networks |
MIT |
github |
| 2021-12 |
NeurIPS21 |
Knowledge-inspired 3D Scene Graph Prediction in Point Cloud |
BUAA |
- |
| 2022-01 |
RSS22 |
Hydra: A Real-time Spatial Perception System for 3D Scene Graph Construction and Optimization |
MIT |
github |
| 2022-02 |
RAL22 |
Situational Graphs for Robot Navigation in Structured Indoor Environments |
UniLu |
project, github |
| 2022-03 |
MICCAI22 |
4D-OR: Semantic Scene Graphs for OR Domain Modeling |
TUM |
project, github |
| 2022-09 |
RAL23 |
D-Lite: Navigation-Oriented Compression of 3D Scene Graphs for Multi-Robot Collaboration |
MIT |
- |
| 2022-09 |
ICRA23 |
3D VSG: Long-term Semantic Scene Change Prediction through 3D Variable Scene Graphs |
ETH |
github |
| 2022-10 |
TVCG22 |
Explore Contextual Information for 3D Scene Graph Generation |
DUT |
- |
| 2022-12 |
RAL23 |
S-Graphs+: Real-time Localization and Mapping leveraging Hierarchical Representations |
UniLu |
project, github |
| 2023-02 |
RAL23 |
Towards Long-Term Retrieval-Based Visual Localization in Indoor Environments with Changes |
TUM |
- |
| 2023-03 |
AAAI24 |
SGFormer: Semantic Graph Transformer for Point Cloud-based 3D Scene Graph Generation |
BJUT |
github |
| 2023-03 |
CVPR23 |
VL-SAT: Visual-Linguistic Semantics Assisted Training for 3D Semantic Scene Graph Prediction in Point Cloud |
BUAA |
github |
| 2023-04 |
IROS23 |
Hydra-Multi: Collaborative Online Construction of 3D Scene Graphs with Multi-Robot Teams |
MIT |
- |
| 2023-04 |
ICCV23 |
SGAligner: 3D Scene Alignment with Scene Graphs |
ETH |
project, github |
| 2023-05 |
CVPR23 |
Incremental 3D Semantic Scene Graph Prediction from RGB Sequences |
TUM |
- |
| 2023-05 |
IJRR24 |
Foundations of Spatial Perception for Robotics: Hierarchical Representations and Real-time Systems |
MIT |
project, github |
| 2023-06 |
CVPR23 |
3D Spatial Multimodal Knowledge Accumulation for Scene Graph Prediction in Point Cloud |
XDU |
project, github |
| 2023-07 |
CoRL23 |
SayPlan: Grounding Large Language Models using 3D Scene Graphs for Scalable Robot Task Planning |
QUT |
project |
| 2023-08 |
CASE23 |
3D Scene Graph Prediction on Point Clouds Using Knowledge Graphs |
UCSD |
- |
| 2023-09 |
CoRL23 |
Context-Aware Entity Grounding with Open-Vocabulary 3D Scene Graphs |
Rutgers |
project, github |
| 2023-09 |
ICRA24 |
ConceptGraphs: Open-Vocabulary 3D Scene Graphs for Perception and Planning |
UToronto |
project, github |
| 2023-09 |
ICRA24 |
Collaborative Dynamic 3D Scene Graphs for Automated Driving |
UniFreiburg |
project, github |
| 2023-09 |
WACV24 |
SGRec3D: Self-Supervised 3D Scene Graph Learning via Object-Level Scene Reconstruction |
Bosch |
project |
| 2023-09 |
AAAI25 |
SayNav: Grounding Large Language Models for Dynamic Planning to Navigation in New Environments |
SRI |
project |
| 2023-09 |
IROS24 |
Learning High-level Semantic-Relational Concepts for SLAM |
UniLu |
- |
| 2023-10 |
3DV24 |
Lang3DSG: Language-based contrastive pre-training for 3D Scene Graph prediction |
Bosch |
project |
| 2023-12 |
RAL24 |
Indoor and Outdoor 3D Scene Graph Generation via Language-Enabled Spatial Ontologies |
MIT |
- |
| 2024-01 |
IJCARS24 |
Holistic OR domain modeling: a semantic scene graph approach |
TUM |
github |
| 2024-02 |
CVPR24 |
Open3DSG: Open-Vocabulary 3D Scene Graphs from Point Clouds with Queryable Objects and Open-Set Relationships |
Bosch |
project, github |
| 2024-02 |
CoRL24 |
RoboEXP: Action-Conditioned Scene Graph via Interactive Exploration for Robotic Manipulation |
UIUC |
project, github |
| 2024-03 |
RSS24 |
Hierarchical Open-Vocabulary 3D Scene Graphs for Language-Grounded Robot Navigation |
UniFreiburg |
project, github |
| 2024-03 |
ECCV24 |
SceneGraphLoc: Cross-Modal Coarse Visual Localization on 3D Scene Graphs |
ETH |
project, github |
| 2024-03 |
RAL24 |
OpenGraph: Open-Vocabulary Hierarchical 3D Graph Representation in Large-Scale Outdoor Environments |
BIT |
github |
| 2024-03 |
RAL24 |
Language-Grounded Dynamic Scene Graphs for Interactive Object Search with Mobile Manipulation |
UniFreiburg |
project, github |
| 2024-04 |
ECCV24 |
“Where am I?” Scene Retrieval with Language |
ETH |
- |
| 2024-04 |
TMM24 |
Weakly-Supervised 3D Scene Graph Generation via Visual-Linguistic Assisted Pseudo-labeling |
SZU |
- |
| 2024-04 |
RAL24 |
Clio: Real-time Task-Driven Open-Set 3D Scene Graphs |
MIT |
github |
| 2024-04 |
ICRA25 |
DELTA: Decomposed Efficient Long-Term Robot Task Planning using Large Language Models |
Bosch |
project, github |
| 2024-05 |
RAL24 |
Long-Term Human Trajectory Prediction using 3D Dynamic Scene Graphs |
MIT |
github |
| 2024-06 |
NeurIPS24 |
SpatialRGPT: Grounded Spatial Reasoning in Vision-Language Models |
UCSD |
project, github |
| 2024-06 |
CVPR24 |
CLIP-Driven Open-Vocabulary 3D Scene Graph Generation via Cross-Modality Contrastive Learning |
ECNU |
- |
| 2024-06 |
CVPRW24 |
EgoSG: Learning 3D Scene Graphs from Egocentric RGB-D Sequences |
USYD |
- |
| 2024-06 |
ICRA25 |
Beyond Bare Queries: Open-Vocabulary Object Grounding with 3D Scene Graph |
MIPT |
project, github |
| 2024-07 |
RAL24 |
ViewInfer3D: 3D Visual Grounding Based on Embodied Viewpoint Inference |
BUPT |
- |
| 2024-07 |
IJRR25 |
Open Scene Graphs for Open World Object-Goal Navigation |
NUS |
project, github |
| 2024-09 |
ICRA25 |
Metric-Semantic Factor Graph Generation based on Graph Neural Networks |
UniLu |
- |
| 2024-09 |
ICRA25 |
Point2Graph: An End-to-end Point Cloud-based 3D Open-Vocabulary Scene Graph for Robot Navigation |
UMich |
project |
| 2024-09 |
HUMANOIDS25 |
SpotLight: Robotic Scene Understanding through Interaction and Affordance Detection |
ETH |
project, github |
| 2024-09 |
arXiv25 |
Embodied-RAG: General Non-parametric Embodied Memory for Retrieval and Generation |
CMU |
project |
| 2024-10 |
ICRA25 |
ConceptAgent: LLM-Driven Precondition Grounding and Tree Search for Robust Task Planning and Execution |
JHU |
- |
| 2024-10 |
NeurIPS24 |
SG-Nav: Online 3D Scene Graph Prompting for LLM-based Zero-shot Object Navigation |
THU |
project, github |
| 2024-10 |
RAL25 |
Dynamic Open-Vocabulary 3D Scene Graphs for Long-term Language-Guided Mobile Manipulation |
BUAA |
project, github |
| 2024-10 |
ECCV24 |
Heterogeneous Graph Learning for Scene Graph Prediction in 3D Point Clouds |
SYSU |
github |
| 2024-11 |
ICCV25 |
Open-Vocabulary Octree-Graph for 3D Scene Understanding |
ShanghaiAI |
- |
| 2024-11 |
RAL25 |
Lost & Found: Tracking Changes from Egocentric Observations in 3D Dynamic Scene Graphs |
ETH |
project, github |
| 2024-12 |
arXiv24 |
3DGraphLLM: Combining Semantic Graphs and Large Language Models for 3D Scene Understanding |
AIRI |
github |
| 2024-12 |
IROS25 |
MR-COGraphs: Communication-efficient Multi-Robot Open-vocabulary Mapping System via 3D Scene Graphs |
THU |
github |
| 2024-12 |
CVPR25 |
Relationfield: Relate anything in radiance fields |
Bosch |
project, github |
| 2024-12 |
AAAI25 |
TB-HSU: Hierarchical 3D Scene Understanding with Contextual Affordances |
USYD |
github |
| 2024-12 |
CoRL25 |
GraphEQA: Using 3D Semantic Scene Graphs for Real-time Embodied Question Answering |
CMU |
project |
| 2025-01 |
RAL25 |
CuriousBot: Interactive Mobile Exploration via Actionable 3D Relational Object Graph |
Columbia |
project |
| 2025-02 |
IROS25 |
DynamicGSG: Dynamic 3D Gaussian Scene Graphs for Environment Adaptation |
BIT |
github |
| 2025-02 |
RAL25 |
S-Graphs 2.0 – A Hierarchical-Semantic Optimization and Loop Closure for SLAM |
UniLu |
- |
| 2025-02 |
ICMCR25 |
Latent 3D Scene Graph with Aligned Visual-Language Perception for Object-Goal Navigation |
SUSTech |
- |
| 2025-03 |
CVPR25 |
Open-Vocabulary Functional 3D Scene Graphs for Real-World Indoor Spaces |
ETH |
project, github |
| 2025-03 |
IROS25 |
FunGraph: Functionality Aware 3D Scene Graphs for Language-Prompted Scene Interaction |
UniStuttgart |
project, github |
| 2025-03 |
TCSVT25 |
History-Enhanced 3D Scene Graph Reasoning from RGB-D Sequences |
XDU |
github |
| 2025-03 |
IROS25 |
Collaborative Dynamic 3D Scene Graphs for Open-Vocabulary Urban Scene Understanding |
UniFreiburg |
project, github |
| 2025-03 |
IROS25 |
GaussianGraph: 3D Gaussian-based Scene Graph Generation for Open-world Scene Understanding |
BIT |
project, github |
| 2025-03 |
arXiv25 |
DYNEMO-SLAM: Dynamic Entity and Motion-Aware 3D Scene Graph SLAM |
UniLu |
- |
| 2025-03 |
arXiv25 |
vS-Graphs: Integrating Visual SLAM and Situational Graphs through Multi-level Scene Understanding |
UniLu |
project |
| 2025-03 |
CVPR25 |
MM-OR: A Large Multimodal Operating Room Dataset for Semantic Understanding of High-Intensity Surgical Environments |
TUM |
project, github |
| 2025-03 |
arXiv25 |
Long-Term Planning Around Humans in Domestic Environments with 3D Scene Graphs |
KTH |
- |
| 2025-03 |
ICRA25 |
IRef-VLA: A Benchmark for Interactive Referential Grounding with Imperfect Language in 3D Scenes |
CMU |
github |
| 2025-03 |
CVPR25 |
UniGoal: Towards Universal Zero-shot Goal-oriented Navigation |
THU |
project, github |
| 2025-03 |
CVPR25 |
Universal Scene Graph Generation |
NUS |
- |
| 2025-03 |
IROS25 |
REACT: Real-time Efficient Attribute Clustering and Transfer for Updatable 3D Scene Graph |
AALTO |
- |
| 2025-04 |
arXiv25 |
Graph2Nav: 3D Object-Relation Graph Generation to Robot Navigation |
SRI |
- |
| 2025-04 |
PAMI25 |
Hyperrectangle Embedding for Debiased 3D Scene Graph Prediction From RGB Sequences |
XDU |
- |
| 2025-04 |
CVPR25 |
ASHiTA: Automatic Scene-grounded HIerarchical Task Analysis |
MIT |
- |
| 2025-04 |
TCSVT25 |
Visual Environment-Interactive Planning for Embodied Complex-Question Answering |
XDU |
- |
| 2025-05 |
NeurIPS25 |
EgoExOR: An Ego-Exo-Centric Operating Room Dataset for Surgical Activity Understanding |
TUM |
project, github |
| 2025-05 |
arXiv25 |
SayCoNav: Utilizing Large Language Models for Adaptive Collaboration in Decentralized Multi-Robot Navigation |
SRI |
- |
| 2025-05 |
IROS25 |
SPADE: Towards Scalable Path Planning Architecture on Actionable Multi-Domain 3D ScenE Graphs |
LTU |
- |
| 2025-05 |
arXiv25 |
Situationally-aware Path Planning Exploiting 3D Scene Graphs |
UniLu |
- |
| 2025-05 |
ICRA25 |
Parking-SG: Open-Vocabulary Hierarchical 3D Scene Graph Representation for Open Parking Environments |
BIT |
- |
| 2025-05 |
arXiv26 |
Hi-Dyna Graph: Hierarchical Dynamic Scene Graph for Robotic Autonomy in Human-Centric Environments |
Fudan |
- |
| 2025-05 |
ICRA25 |
Interaction-Driven Updates: 3D Scene Graph Maintenance During Robot Task Execution |
BUAA |
- |
| 2025-06 |
CASE25 |
Pixels-to-Graph: Real-time Integration of Building Information Models and Scene Graphs for Semantic-Geometric Human-Robot Understanding |
NASA |
- |
| 2025-06 |
IROS25 |
TACS-Graphs: Traversability-Aware Consistent Scene Graphs for Ground Robot Indoor Localization and Mapping |
KAIST |
- |
| 2025-06 |
arXiv25 |
IRS: Instance-Level 3D Scene Graphs via Room Prior Guided LiDAR-Camera Fusion |
SYSU |
- |
| 2025-06 |
arXiv25 |
Language-Grounded Hierarchical Planning and Execution with Multi-Robot 3D Scene Graphs |
MIT |
- |
| 2025-06 |
ICME25 |
Open-Scene Understanding-oriented 3D Scene Graph Generation |
HIT |
github |
| 2025-06 |
arXiv25 |
FreeQ-Graph: Free-form Querying with Semantic Consistent Scene Graph for 3D Scene Understanding |
ZJU |
- |
| 2025-06 |
arXiv25 |
Towards Terrain-Aware Task-Driven 3D Scene Graph Generation in Outdoor Environments |
BYU |
- |
| 2025-07 |
ICCV25 |
FROSS: Faster-than-Real-Time Online 3D Semantic Scene Graph Generation from RGB-D Images |
NTHU |
github |
| 2025-07 |
arXiv25 |
Open-Vocabulary Indoor Object Grounding with 3D Hierarchical Scene Graph |
MIPT |
github |
| 2025-08 |
TCDS25 |
SELM: From Efficient Autonomous Exploration to Long-term Monitoring in Semantic Level |
ZJU |
- |
| 2025-08 |
ICRA25 |
Imaginative World Modeling with Scene Graphs for Embodied Agent Navigation |
UMich |
- |
| 2025-08 |
IoTJ25 |
Hierarchical 3D Scene Graph based Semantic-Metric SLAM for Plant Inspection and Fruit Counting in Intelligent Hydroponics System |
PolyU |
github |
| 2025-08 |
ICCV25 |
Statistical Confidence Rescoring for Robust 3D Scene Graph Generation from Multi-View Images |
NUS |
project, github |
| 2025-09 |
arXiv25 |
SGAligner++: Cross-Modal Language-Aided 3D Scene Graph Alignment |
TUM |
project |
| 2025-09 |
arXiv25 |
Terra: Hierarchical Terrain-Aware 3D Scene Graph for Task-Agnostic Outdoor Mapping |
BYU |
- |
| 2025-09 |
ICMLA25 |
Integrating Prior Observations for Incremental 3D Scene Graph Prediction |
DFKI |
github |
| 2025-09 |
ICRA26 |
Compose by Focus: Scene Graph-based Atomic Skills |
Harvard |
project |
| 2025-09 |
arXiv25 |
Human Interaction for Collaborative Semantic SLAM using Extended Reality |
UniLu |
- |
| 2025-09 |
IROS26 |
Social 3D Scene Graphs: Modeling Human Actions and Relations for Interactive Service Robots |
KTH |
- |
| 2025-09 |
ICR25 |
Fast Path Planning with Hierarchical Approach Based on 3D Scene Graphs |
CAPITI |
- |
| 2025-09 |
CoRL25 |
ObjectReact: Learning Object-Relative Control for Visual Navigation |
UniAdelaide |
project, github |
| 2025-09 |
arXiv25 |
Open-Vocabulary Spatio-Temporal Scene Graph for Robot Perception and Teleoperation Planning |
SCUT |
- |
| 2025-09 |
arXiv25 |
FSR-VLN: Fast and Slow Reasoning for Vision-Language Navigation with Hierarchical Multi-modal Scene Graph |
HorizonRobotics |
project |
| 2025-09 |
arXiv25 |
Queryable 3D Scene Representation: A Multi-Modal Framework for Semantic Reasoning and Robotic Task Planning |
CSIRO |
- |
| 2025-09 |
OMNN25 |
ElevNav: Large Language Model-Guided Robot Navigation via 3D Scene Graphs in Elevator Environments |
MIPT |
github |
| 2025-10 |
RAL25 |
Have We Scene It All? Scene Graph-Aware Deep Point Cloud Compression |
LTU |
- |
| 2025-10 |
ICRA26 |
KeySG: Hierarchical Keyframe-Based 3D Scene Graphs |
UniStuttgart |
project |
| 2025-10 |
arXiv25 |
ZING-3D: Zero-shot Incremental 3D Scene Graphs via Vision-Language Models |
BITS Pilani |
- |
| 2025-10 |
NeurIPS25 |
Object-Centric Representation Learning for Enhanced 3D Scene Graph Prediction |
KHU |
github |
| 2025-10 |
RAL25 |
Event-Grounding Graph: Unified Spatio-Temporal Scene Graph from Robotic Observations |
AALTO |
github |
| 2025-10 |
TVCG25 |
SGSG: Stroke-Guided Scene Graph Generation |
BUAA |
github |
| 2025-10 |
ICCV25 |
Hierarchical 3D Scene Graphs Construction Outdoors |
ETH |
github |
| 2025-10 |
IROS25 |
OSMa-Bench: Evaluating Open Semantic Mapping Under Varying Lighting Conditions |
ITMO University |
project, github |
| 2025-11 |
BMVC25 |
Pandora: Articulated 3D Scene Graphs from Egocentric Vision |
MIT |
- |
| 2025-11 |
CVPR26 |
MSGNav: Unleashing the Power of Multi-modal 3D Scene Graph for Zero-Shot Embodied Navigation |
XMU |
github |
| 2025-11 |
AAAI26 |
Open-World 3D Scene Graph Generation for Retrieval-Augmented Reasoning |
LNUT |
- |
| 2025-11 |
AAAI26 |
Sparse3DPR: Training-Free 3D Hierarchical Scene Parsing and Task-Adaptive Subgraph Reasoning from Sparse RGB Views |
CAS |
- |
| 2025-11 |
CVPR26 |
Describe Anything Anywhere At Any Moment |
MIT |
project, github |
| 2025-11 |
AAAI26 |
Edge-Centric Relational Reasoning for 3D Scene Graph Prediction |
SYSU |
- |
| 2025-12 |
arXiv25 |
Vision to Geometry: 3D Spatial Memory for Sequential Embodied MLLM Reasoning and Exploration |
MSU |
- |
| 2025-12 |
ICRA26 |
Aion: Towards Hierarchical 4D Scene Graphs with Temporal Flow Dynamics |
UTU |
github |
| 2025-12 |
arXiv25 |
ArtiSG: Functional 3D Scene Graph Construction via Human-demonstrated Articulated Objects Manipulation |
Tsinghua |
- |
| 2025-12 |
arXiv25 |
View-on-Graph: Zero-Shot 3D Visual Grounding via Vision-Language Reasoning on Scene Graphs |
DUT |
- |
| 2026-01 |
AAAI26 |
Multi-view Invariance Learning for 3D Scene Graph Pre-training via Collaborative Cross-Modal Regularization |
UESTC |
- |
| 2026-01 |
arXiv26 |
Lost-3DSG: Lightweight Open-Vocabulary 3D Scene Graphs with Semantic Tracking in Dynamic Environments |
Sapienza |
project, github |
| 2026-01 |
WACV26 |
VIZOR: Viewpoint-Invariant Zero-Shot Scene Graph Generation for 3D Scene Reasoning |
IIIT-H |
project |
| 2026-01 |
arXiv26 |
RAG-3DSG: Enhancing 3D Scene Graphs with Re-Shot Guided Retrieval-Augmented Generation |
HKUST |
- |
| 2026-02 |
arXiv26 |
INHerit-SG: Incremental Hierarchical Semantic Scene Graphs with RAG-Style Retrieval |
NJU |
project |
| 2026-02 |
arXiv26 |
MA3DSG: Multi-Agent 3D Scene Graph Generation for Large-Scale Indoor Environments |
GIST |
- |
| 2026-02 |
arXiv26 |
Relational Scene Graphs for Object Grounding of Natural Language Commands |
AALTO |
- |
| 2026-02 |
arXiv26 |
A Scene Graph Backed Approach to Open Set Semantic Mapping |
DFKI |
- |
| 2026-02 |
arXiv26 |
Articulated 3D Scene Graphs for Open-World Mobile Manipulation |
UniFreiburg |
- |
| 2026-02 |
ICRA26 |
Relationship-Aware Hierarchical 3D Scene Graph for Task Reasoning |
NTNU |
- |
| 2026-03 |
arXiv26 |
Rheos: Modelling Continuous Motion Dynamics in Hierarchical 3D Scene Graphs |
UTU |
- |
| 2026-03 |
arXiv26 |
SGR3 Model: Scene Graph Retrieval-Reasoning Model in 3D |
KIT |
- |
| 2026-03 |
arXiv26 |
ToLL: Topological Layout Learning with Asymmetric Cross-View Structural Distillation for 3D Scene Graph Generation Pretraining |
UESTC |
github |
| 2026-03 |
ICRA26 |
Knowledge-Guided Manipulation Using Multi-Task Reinforcement Learning |
MIRAI |
- |
| 2026-03 |
arXiv26 |
Relational Semantic Reasoning on 3D Scene Graphs for Open World Interactive Object Search |
UniFreiburg |
- |
| 2026-03 |
arXiv26 |
OGScene3D: Incremental Open-Vocabulary 3D Gaussian Scene Graph Mapping for Scene Understanding |
Shanghai Jiao Tong University |
github |
| 2026-03 |
arXiv26 |
M2H-MX: Multi-Task Semantic and Geometric Perception for Real-Time Monocular 3D Scene Graph Construction |
UT |
- |
| 2026-04 |
ACL26 |
CAPruner: Conceptual-Adjacent Scene Graph Pruner for Enhancing 3D Spatial Reasoning of Large Language Models |
SUSTech |
github |
| 2026-04 |
arXiv26 |
Predictive Spatio-Temporal Scene Graphs for Semi-Static Scenes |
Mila |
- |
| 2026-04 |
ICML26 |
Learning Gaussian Mixture-distributed Prototypes for 3D Scene Graph Generation from RGB-D Sequences |
NJUST |
- |
| 2026-04 |
TMLR26 |
Incremental3D: Real-time Incremental 3D Scene Generation with Scene Graphs |
IIT |
- |
| 2026-04 |
CVPR26 |
FunFact: Building Probabilistic Functional 3D Scene Graphs via Factor-Graph Reasoning |
ETH |
project |
| 2026-05 |
arXiv26 |
Fixed External Cameras as Common Prior Maps for Active 3D Scene Graph Generation |
Oxford |
- |
| 2026-05 |
arXiv26 |
Hierarchical and Holistic Open-Vocabulary Functional 3D Scene Graphs for Indoor Spaces |
THU |
- |
| 2026-05 |
arXiv26 |
LEXI-SG: Monocular 3D Scene Graph Mapping with Room-Guided Feed-Forward Reconstruction |
Oxford |
project |
| 2026-05 |
arXiv26 |
DGSG-Mind: Dynamic 3D Gaussian Scene Graphs for Long-Term Scene Understanding and Grounding |
BIT |
project |
| 2026-05 |
arXiv26 |
FOUND-IT: Foundation-model-first Task-driven 3D Scene Graphs with Granularity on Demand |
MIT |
- |
| 2026-05 |
arXiv26 |
Mono-Hydra++: Real-Time Monocular Scene Graph Construction with Multi-Task Learning for 3D Indoor Mapping |
UT |
github |
| 2026-05 |
arXiv26 |
OpenSGA: Efficient 3D Scene Graph Alignment in the Open World |
TU Delft |
project |
| 2026-05 |
ICML26 |
PSG-Nav: Probabilistic Scene Graph Navigation via Multiverse Decision Making |
HKUST |
project |
| 2026-05 |
arXiv26 |
SceneGraphGrounder: Zero-Shot 3D Visual Grounding via Structured Scene Graph Matching |
CU Boulder |
- |
| 2026-06 |
ECCV26 |
Think While You Map: Asynchronous Vision-Language Agents for Incremental 3D Scene Graphs |
UniStuttgart |
project |
| 2026-06 |
ICRA26 |
T-FunS3D: Task-Driven Hierarchical Open-Vocabulary 3D Functionality Segmentation |
TU Delft |
project |
| 2026-06 |
arXiv26 |
SG2Loc: Sequential Visual Localization on 3D Scene Graphs |
ETH |
github |
| 2026-06 |
arXiv26 |
Remember with Confidence: Uncertainty Quantification for Spatio-temporal Memory with Probabilistic Guarantees |
MIT |
- |
| 2026-06 |
arXiv26 |
Worth Remembering: Surprise-Gated Robot Episodic Memory |
MIT |
- |
| 2026-06 |
IROS26 |
From Pixels to Concepts: Growing Rich 3D Semantic Scene Graph Forests utilizing Foundation Models |
FZI |
github |
| 2026-06 |
arXiv26 |
PhysGraph: A Physics-aware 3D Scene Graph for Perception and Reasoning |
DUKE |
project |
| 2026-06 |
arXiv26 |
Not All Relations Rotate Alike: Transformation-Aware Decoupling for Viewpoint-Robust 3D Scene Graph Generation |
NWPU |
project, github |
| 2026-07 |
arXiv26 |
Just-In-Time Scene Graph Growth: Combating Perceptual Saturation in Long-Horizon Robotics |
HKUST |
- |
| 2026-07 |
RSS26 |
SuperMap: A Spatio-Temporal SLAM System for Visual-Language Navigation |
CMU |
project |
| 2026-07 |
IROS26 |
Hydra++: Real-Time Hierarchical 3D Scene Graph Construction With Object-Level Shape Estimation |
MIT |
project, github |
| 2026-07 |
arXiv26 |
CinemaTraj: Composing Atomic Camera Trajectories for 3D Scenes with LLM Agents |
TUM |
project |
| 2026-07 |
ECCV26 |
Beyond Isolated Objects: Relationship-aware Open-Vocabulary 3D Scene Understanding via 3D Scene Graph Analysis |
ZJU |
project, github |
| 2026-07 |
ECCV26 |
PUF: Plug-and-Play Uncertainty-Aware Fusion for Online 3D Scene Graph Generation |
LUH |
github |
| 2026-07 |
ECCV26 |
NoPA: Non-Parametric Online 3D Scene Graph Generation |
NUS |
- |
| 2026-07 |
ECCV26 |
DeWorldSG: Depth-Aware 3D Semantic Scene Graph Generation via World-Model Priors |
KAIST |
project |
| 2026-08 |
arXiv26 |
Prior-SG: Task and Prior Driven Region Segmentation for Scene Graphs in Arbitrarily-Structured Environments |
RAI Institute |
- |
