Cover Image

UniGround: Universal 3D Visual Grounding via Training-Free Scene Parsing

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zhang, Jiaxi, Wang, Yunheng, Lu, Wei, Wang, Taowen, Xu, Weisheng, Zhang, Shuning, Feng, Yixiao, Fang, Yuetong, Xu, Renjing
Format:	Preprint
Published:	2026
Subjects:	Robotics Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

HERO: Hierarchical Traversable 3D Scene Graphs for Embodied Navigation Among Movable Obstacles
by: Wang, Yunheng, et al.
Published: (2025)

DreamNav: A Trajectory-Based Imaginative Framework for Zero-Shot Vision-and-Language Navigation
by: Wang, Yunheng, et al.
Published: (2025)

What Limits Vision-and-Language Navigation ?
by: Wang, Yunheng, et al.
Published: (2026)

High-Precision Climbing Robot Localization Using Planar Array UWB/GPS/IMU/Barometer Integration
by: Zhang, Shuning, et al.
Published: (2025)

Spherical Latent Motion Prior for Physics-Based Simulated Humanoid Control
by: Tan, Jing, et al.
Published: (2026)

Iterative Closed-Loop Motion Synthesis for Scaling the Capabilities of Humanoid Control
by: Xu, Weisheng, et al.
Published: (2026)

Morphology-Consistent Humanoid Interaction through Robot-Centric Video Synthesis
by: Xu, Weisheng, et al.
Published: (2026)

SignScene: Visual Sign Grounding for Mapless Navigation
by: Zimmerman, Nicky, et al.
Published: (2026)

GroundSLAM: A Robust Visual SLAM System for Warehouse Robots Using Ground Textures
by: Xu, Kuan, et al.
Published: (2017)

FARM: Frame-Accelerated Augmentation and Residual Mixture-of-Experts for Physics-Based High-Dynamic Humanoid Control
by: Jing, Tan, et al.
Published: (2025)

Towards Unified Interactive Visual Grounding in The Wild
by: Xu, Jie, et al.
Published: (2024)

Physical Priors Augmented Event-Based 3D Reconstruction
by: Wang, Jiaxu, et al.
Published: (2024)

SceneGraphGrounder: Zero-Shot 3D Visual Grounding via Structured Scene Graph Matching
by: Sun, Xuefei, et al.
Published: (2026)

Learning Geometrically-Grounded 3D Visual Representations for View-Generalizable Robotic Manipulation
by: Zhang, Di, et al.
Published: (2026)

IRef-VLA: A Benchmark for Interactive Referential Grounding with Imperfect Language in 3D Scenes
by: Zhang, Haochen, et al.
Published: (2025)

Query-based Semantic Gaussian Field for Scene Representation in Reinforcement Learning
by: Wang, Jiaxu, et al.
Published: (2024)

Domain-Conditioned Scene Graphs for State-Grounded Task Planning
by: Herzog, Jonas, et al.
Published: (2025)

Global-State-Free Obstacle Avoidance for Quadrotor Control in Air-Ground Cooperation
by: Zhang, Baozhe, et al.
Published: (2025)

INVIGORATE: Interactive Visual Grounding and Grasping in Clutter
by: Zhang, Hanbo, et al.
Published: (2021)

Grounded Curriculum Learning
by: Wang, Linji, et al.
Published: (2024)

HELIOS: Hierarchical Exploration for Language-Grounded Interaction in Open Scenes
by: Ashton, Katrina, et al.
Published: (2025)

SGFormer: Satellite-Ground Fusion for 3D Semantic Scene Completion
by: Guo, Xiyue, et al.
Published: (2025)

Contact-Grounded Policy: Dexterous Visuotactile Policy with Generative Contact Grounding
by: Xu, Zhengtong, et al.
Published: (2026)

VLM-Grounder: A VLM Agent for Zero-Shot 3D Visual Grounding
by: Xu, Runsen, et al.
Published: (2024)

On-the-Fly VLA Adaptation via Test-Time Reinforcement Learning
by: Liu, Changyu, et al.
Published: (2026)

SeeGround: See and Ground for Zero-Shot Open-Vocabulary 3D Visual Grounding
by: Li, Rong, et al.
Published: (2024)

Event-Based Visual Odometry on Non-Holonomic Ground Vehicles
by: Xu, Wanting, et al.
Published: (2024)

ShanghaiTech Mapping Robot is All You Need: Robot System for Collecting Universal Ground Vehicle Datasets
by: Xu, Bowen, et al.
Published: (2024)

Beyond Geometry: Efficient Topologically-Grounded Navigation in Complex 3D Environments
by: Du, Yifan, et al.
Published: (2026)

Semi-distributed Cross-modal Air-Ground Relative Localization
by: Lu, Weining, et al.
Published: (2025)

BEV-DWPVO: BEV-based Differentiable Weighted Procrustes for Low Scale-drift Monocular Visual Odometry on Ground
by: Wei, Yufei, et al.
Published: (2025)

RoboOcc: Enhancing the Geometric and Semantic Scene Understanding for Robots
by: Zhang, Zhang, et al.
Published: (2025)

TaskGround: Structured Executable Task Inference for Full-Scene Household Reasoning
by: Feng, ZhiYuan, et al.
Published: (2026)

Grounding 3D Object Affordance with Language Instructions, Visual Observations and Interactions
by: Zhu, He, et al.
Published: (2025)

Look Ma, No Ground Truth! Ground-Truth-Free Tuning of Structure from Motion and Visual SLAM
by: Fontan, Alejandro, et al.
Published: (2024)

Restoring Linguistic Grounding in VLA Models via Train-Free Attention Recalibration
by: Zhang, Ninghao, et al.
Published: (2026)

Prompting Multi-Modal Tokens to Enhance End-to-End Autonomous Driving Imitation Learning with LLMs
by: Duan, Yiqun, et al.
Published: (2024)

VEGA: Visual Encoder Grounding Alignment for Spatially-Aware Vision-Language-Action Models
by: Wang, Hao, et al.
Published: (2026)

A Physics-Informed Neural Network Approach for UAV Path Planning in Dynamic Environments
by: Zhang, Shuning
Published: (2025)

Ground Compliance Improves Retention of Visual Feedback-Based Propulsion Training for Gait Rehabilitation
by: Hobbs, Bradley, et al.
Published: (2025)