Image de couverture de livre

GHOST: Ground-projected Hypotheses from Observed Structure-from-Motion Trajectories

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Frelek, Tomasz, Patil, Rohan, Tumu, Akshar, Christensen, Henrik I.
Format:	Preprint
Publié:	2026
Sujets:	Robotics Computer Vision and Pattern Recognition
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

SD++: Enhancing Standard Definition Maps by Incorporating Road Knowledge using LLMs
par: Diwanji, Hitvarth, et autres
Publié: (2025)

Exploring Spatial Language Grounding Through Referring Expressions
par: Tumu, Akshar, et autres
Publié: (2025)

Merging and Disentangling Views in Visual Reinforcement Learning for Robotic Manipulation
par: Almuzairee, Abdulaziz, et autres
Publié: (2025)

Referring Expressions as a Lens into Spatial Language Grounding in Vision-Language Models
par: Tumu, Akshar, et autres
Publié: (2025)

Look Ma, No Ground Truth! Ground-Truth-Free Tuning of Structure from Motion and Visual SLAM
par: Fontan, Alejandro, et autres
Publié: (2024)

Squint: Fast Visual Reinforcement Learning for Sim-to-Real Robotics
par: Almuzairee, Abdulaziz, et autres
Publié: (2026)

Context-aware Multi-task Learning for Pedestrian Intent and Trajectory Prediction
par: Munir, Farzeen, et autres
Publié: (2024)

Online Mapping for Autonomous Driving: Addressing Sensor Generalization and Dynamic Map Updates in Campus Environments
par: Zhang, Zihan, et autres
Publié: (2025)

A Recipe for Unbounded Data Augmentation in Visual Reinforcement Learning
par: Almuzairee, Abdulaziz, et autres
Publié: (2024)

PPT: Pretraining with Pseudo-Labeled Trajectories for Motion Forecasting
par: Xu, Yihong, et autres
Publié: (2024)

Foresight in Motion: Reinforcing Trajectory Prediction with Reward Heuristics
par: Pei, Muleilan, et autres
Publié: (2025)

SemVecNet: Generalizable Vector Map Generation for Arbitrary Sensor Configurations
par: Ranganatha, Narayanan Elavathur, et autres
Publié: (2024)

MapGS: Generalizable Pretraining and Data Augmentation for Online Mapping via Novel View Synthesis
par: Zhang, Hengyuan, et autres
Publié: (2025)

CuSfM: CUDA-Accelerated Structure-from-Motion
par: Yu, Jingrui, et autres
Publié: (2025)

Structure from Motion-based Motion Estimation and 3D Reconstruction of Unknown Shaped Space Debris
par: Uno, Kentaro, et autres
Publié: (2024)

GHOST: Grounded Human Motion Generation with Open Vocabulary Scene-and-Text Contexts
par: Milacski, Zoltán Á., et autres
Publié: (2024)

Ground Reaction Inertial Poser: Physics-based Human Motion Capture from Sparse IMUs and Insole Pressure Sensors
par: Hori, Ryosuke, et autres
Publié: (2026)

Efficient Data Representation for Motion Forecasting: A Scene-Specific Trajectory Set Approach
par: Vivekanandan, Abhishek, et autres
Publié: (2024)

E-TIDE: Fast, Structure-Preserving Motion Forecasting from Event Sequences
par: Sen, Biswadeep, et autres
Publié: (2026)

MP-SfM: Monocular Surface Priors for Robust Structure-from-Motion
par: Pataki, Zador, et autres
Publié: (2025)

Enhancing Online Road Network Perception and Reasoning with Standard Definition Maps
par: Zhang, Hengyuan, et autres
Publié: (2024)

SMART: Advancing Scalable Map Priors for Driving Topology Reasoning
par: Ye, Junjie, et autres
Publié: (2025)

Non-Rigid Structure-from-Motion via Differential Geometry with Recoverable Conformal Scale
par: Chen, Yongbo, et autres
Publié: (2025)

Robust Surgical Tool Tracking with Pixel-based Probabilities for Projected Geometric Primitives
par: D'Ambrosia, Christopher, et autres
Publié: (2024)

Efficient Motion Prediction: A Lightweight & Accurate Trajectory Prediction Model With Fast Training and Inference Speed
par: Prutsch, Alexander, et autres
Publié: (2024)

Initialization of Monocular Visual Navigation for Autonomous Agents Using Modified Structure from Small Motion
par: Florez, Juan-Diego, et autres
Publié: (2024)

Joint Flow Trajectory Optimization For Feasible Robot Motion Generation from Video Demonstrations
par: Dong, Xiaoxiang, et autres
Publié: (2025)

Large Trajectory Models are Scalable Motion Predictors and Planners
par: Sun, Qiao, et autres
Publié: (2023)

Visual Grounding from Event Cameras
par: Kong, Lingdong, et autres
Publié: (2025)

Estimation of Kinematic Motion from Dashcam Footage
par: Zhang, Evelyn, et autres
Publié: (2025)

Observe Then Act: Asynchronous Active Vision-Action Model for Robotic Manipulation
par: Wang, Guokang, et autres
Publié: (2024)

Decoupling Ego-Motion from Target Dynamics via Dual-Interval Motion Cues for UAV Detection
par: Wang, Liuyang, et autres
Publié: (2026)

Flowing from Reasoning to Motion: Learning 3D Hand Trajectory Prediction from Egocentric Human Interaction Videos
par: Chen, Mingfei, et autres
Publié: (2025)

Category-level Neural Field for Reconstruction of Partially Observed Objects in Indoor Environment
par: Lee, Taekbeom, et autres
Publié: (2024)

Characterizing Structured versus Unstructured Environments based on Pedestrians' and Vehicles' Motion Trajectories
par: Golchoubian, Mahsa, et autres
Publié: (2025)

CVD-SfM: A Cross-View Deep Front-end Structure-from-Motion System for Sparse Localization in Multi-Altitude Scenes
par: Li, Yaxuan, et autres
Publié: (2025)

AffordanceLLM: Grounding Affordance from Vision Language Models
par: Qian, Shengyi, et autres
Publié: (2024)

EventFly: Event Camera Perception from Ground to the Sky
par: Kong, Lingdong, et autres
Publié: (2025)

SeeGround: See and Ground for Zero-Shot Open-Vocabulary 3D Visual Grounding
par: Li, Rong, et autres
Publié: (2024)

Synthetic-to-Real Self-supervised Robust Depth Estimation via Learning with Motion and Structure Priors
par: Yan, Weilong, et autres
Publié: (2025)