One Image is All You Need: Agentic One-Shot Image Generation via Text-Based World Models for Long-Tail Spatial Perception

• URL: http://arxiv.org/abs/2606.20764v1
• Date: Thu, 18 Jun 2026 11:56:04 GMT
• Title: One Image is All You Need: Agentic One-Shot Image Generation via Text-Based World Models for Long-Tail Spatial Perception
• Abstract summary: Real-world data severe, often manifesting as extreme long-tail distributions for safety-critical scenarios.<n>We introduce WMGen-v1, an agentic text-based world model framework for long-tail spatial data generation.<n> Notably, detectors trained solely on WMGen-v1 synthetic data approach real-only performance on aggregate dataset-level metrics.
• Score: 9.723987776806466
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Reliable spatial decision automation, such as autonomous driving and maritime surveillance, critically depends on robust visual perception. However, real-world spatiotemporal data exhibits severe heterogeneity, often manifesting as extreme long-tail distributions for safety-critical scenarios. This data scarcity induces dataset shift that degrades detection performance and pose safety risks. While synthetic data generation offers a potential solution, existing generative approaches, such as diffusion models and Generative Adversarial Networks (GANs), often lack explicit spatial grounding and structural constraints, resulting in spatial and physical inconsistencies in generated scenes. To address these challenges, we introduce WMGen-v1, an agentic text-based world model framework for long-tail spatial data generation. WMGen-v1 employs a Large Vision-Language Model (LVLM) to construct a structured scene representation from a single reference image, while a Large Language Model (LLM) performs guidance-based scene expansion under physical plausibility and commonsense constraints. Subsequently, conditioned on the structured semantic representations produced by this reasoning process, a diffusion model generates diverse and physically grounded long-tail training data. Experiments on internal industrial datasets, ROADWork, and LaRS benchmarks demonstrate that WMGen-v1 outperforms baseline approaches. Notably, detectors trained solely on WMGen-v1 synthetic data approach real-only performance on aggregate dataset-level metrics, highlighting its potential to alleviate long-tail data scarcity for downstream spatial perception.

Related papers

• Policy-as-Data: Learning Generalizable HOI Diffusion Models from Simulated Physics [23.400128774539812]
  We propose a novel framework to overcome the data-scarcity bottleneck in HOI generation.<n>Our method demonstrates enhanced generalization to unseen objects and the capability of long-horizon generation.
  arXiv  Detail & Related papers  (2026-06-22T03:32:35Z)
• Reinforcement-Guided Synthetic Data Generation for Privacy-Sensitive Identity Recognition [60.52810518437911]
  High-fidelity generative models are increasingly needed in privacy-sensitive scenarios.<n> limited data leads to poor generative models, which in turn fail to mitigate data scarcity.<n>We propose a reinforcement-guided synthetic data generation framework that adapts general-domain generative priors to identity recognition tasks.
  arXiv  Detail & Related papers  (2026-04-09T06:52:03Z)
• Central-to-Local Adaptive Generative Diffusion Framework for Improving Gene Expression Prediction in Data-Limited Spatial Transcriptomics [2.3129926848389633]
  Spatial Transcriptomics (ST) provides spatially resolved gene expression profiles within intact tissue architecture.<n>We present a Central-to-Local adaptive generative diffusion framework for ST (C2L-ST) that integrates large-scale morphological priors with limited molecular guidance.<n>C2L-ST provides a scalable and data-efficient framework for molecular-level data augmentation.
  arXiv  Detail & Related papers  (2026-03-27T02:32:00Z)
• Scaling Up Occupancy-centric Driving Scene Generation: Dataset and Method [54.461213497603154]
  Occupancy-centric methods have recently achieved state-of-the-art results by offering consistent conditioning across frames and modalities.<n>Nuplan-Occ is the largest occupancy dataset to date, constructed from the widely used Nuplan benchmark.<n>We develop a unified framework that jointly synthesizes high-quality occupancy, multi-view videos, and LiDAR point clouds.
  arXiv  Detail & Related papers  (2025-10-27T03:52:45Z)
• Vision-LLMs for Spatiotemporal Traffic Forecasting [14.700408329373998]
  Large Language Models (LLMs) inherently struggle to model the complex spatial dependencies of grid-based traffic data.<n>We propose ST-Vision-LLM, a novel framework reframe thatstemporal forecasting as a vision-language fusion problem.<n>We show that ST-Vision-LLM outperforms existing methods by 15.6% in long-term prediction accuracy and exceeds the second-best baseline by over 30.04% in cross-domain scenarios.
  arXiv  Detail & Related papers  (2025-10-13T11:15:56Z)
• R2RGEN: Real-to-Real 3D Data Generation for Spatially Generalized Manipulation [74.41728218960465]
  We propose a real-to-real 3D data generation framework (R2RGen) that directly augments the pointcloud observation-action pairs to generate real-world data.<n>R2RGen substantially enhances data efficiency on extensive experiments and demonstrates strong potential for scaling and application on mobile manipulation.
  arXiv  Detail & Related papers  (2025-10-09T17:55:44Z)
• Domain Generalized Stereo Matching with Uncertainty-guided Data Augmentation [11.938635624781313]
  State-of-the-art stereo matching (SM) models often fail to generalize to real data domains due to domain differences.<n>We leverage data augmentation to expand the training domain, encouraging the model to acquire robust cross-domain feature representations.<n>Our approach is simple, architecture-agnostic, and can be integrated into any SM networks.
  arXiv  Detail & Related papers  (2025-08-02T10:26:53Z)
• Spatial-Temporal-Spectral Unified Modeling for Remote Sensing Dense Prediction [20.1863553357121]
  Current deep learning architectures for remote sensing are fundamentally rigid.<n>We introduce the Spatial-Temporal-Spectral Unified Network (STSUN) for unified modeling.<n> STSUN can adapt to input and output data with arbitrary spatial sizes, temporal lengths, and spectral bands.<n>It unifies various dense prediction tasks and diverse semantic class predictions.
  arXiv  Detail & Related papers  (2025-05-18T07:39:17Z)
• Efficient High-Resolution Visual Representation Learning with State Space Model for Human Pose Estimation [60.80423207808076]
  Capturing long-range dependencies while preserving high-resolution visual representations is crucial for dense prediction tasks such as human pose estimation.<n>We propose the Dynamic Visual State Space (DVSS) block, which augments visual state space models with multi-scale convolutional operations.<n>We build HRVMamba, a novel model for efficient high-resolution representation learning.
  arXiv  Detail & Related papers  (2024-10-04T06:19:29Z)
• Towards Realistic Data Generation for Real-World Super-Resolution [58.99206459754721]
  RealDGen is an unsupervised learning data generation framework designed for real-world super-resolution.<n>We develop content and degradation extraction strategies, which are integrated into a novel content-degradation decoupled diffusion model.<n>Experiments demonstrate that RealDGen excels in generating large-scale, high-quality paired data that mirrors real-world degradations.
  arXiv  Detail & Related papers  (2024-06-11T13:34:57Z)
• Spatiotemporal Implicit Neural Representation as a Generalized Traffic Data Learner [46.866240648471894]
  Spatiotemporal Traffic Data (STTD) measures the complex dynamical behaviors of the multiscale transportation system. We present a novel paradigm to address the STTD learning problem by parameterizing STTD as an implicit neural representation. We validate its effectiveness through extensive experiments in real-world scenarios, showcasing applications from corridor to network scales.
  arXiv  Detail & Related papers  (2024-05-06T06:23:06Z)
• Synthetic location trajectory generation using categorical diffusion models [50.809683239937584]
  Diffusion models (DPMs) have rapidly evolved to be one of the predominant generative models for the simulation of synthetic data. We propose using DPMs for the generation of synthetic individual location trajectories (ILTs) which are sequences of variables representing physical locations visited by individuals.
  arXiv  Detail & Related papers  (2024-02-19T15:57:39Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.