VectorSynth: Fine-Grained Satellite Image Synthesis with Structured Semantics

• URL: http://arxiv.org/abs/2511.07744v1
• Date: Wed, 12 Nov 2025 01:14:30 GMT
• Title: VectorSynth: Fine-Grained Satellite Image Synthesis with Structured Semantics
• Abstract summary: We introduce Vector Synth, a diffusion-based framework for pixel-accurate satellite image conditioned on synthesisal geographic annotations with semantic attributes.<n>Unlike prior text- or layout-conditioned models, Vector Synth learns dense cross-modal correspondences that align and semantic vector geometry, enabling fine-grained, spatially grounded edits.
• Score: 16.29123003949871
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We introduce VectorSynth, a diffusion-based framework for pixel-accurate satellite image synthesis conditioned on polygonal geographic annotations with semantic attributes. Unlike prior text- or layout-conditioned models, VectorSynth learns dense cross-modal correspondences that align imagery and semantic vector geometry, enabling fine-grained, spatially grounded edits. A vision language alignment module produces pixel-level embeddings from polygon semantics; these embeddings guide a conditional image generation framework to respect both spatial extents and semantic cues. VectorSynth supports interactive workflows that mix language prompts with geometry-aware conditioning, allowing rapid what-if simulations, spatial edits, and map-informed content generation. For training and evaluation, we assemble a collection of satellite scenes paired with pixel-registered polygon annotations spanning diverse urban scenes with both built and natural features. We observe strong improvements over prior methods in semantic fidelity and structural realism, and show that our trained vision language model demonstrates fine-grained spatial grounding. The code and data are available at https://github.com/mvrl/VectorSynth.

Related papers

• TerraDiT-$Ω$: Unified Spatial Control for Satellite Image Synthesis with Any Geospatial Primitive [19.699267665705715]
  We introduce TerraDiT-$$, a unified spatial control framework that generates satellite imagery directly from any native primitive.<n>Generative models have achieved remarkable progress, yet applying them to satellite imagery remains challenging.
  arXiv  Detail & Related papers  (2026-06-30T01:56:41Z)
• GeoMeld: Toward Semantically Grounded Foundation Models for Remote Sensing [33.72621953693859]
  GeoMeld is a large-scale multimodal dataset with approximately 2.5 million spatially aligned samples.<n>GeoMeld provides semantically grounded language supervision through an agentic captioning framework.<n>GeoMeld-FM is a pretraining framework that combines multi-pretext masked autoencoding over aligned modalities, JEPA representation learning, and caption-vision contrastive alignment.
  arXiv  Detail & Related papers  (2026-04-12T11:47:11Z)
• Learning 3D Representations for Spatial Intelligence from Unposed Multi-View Images [81.94999489820974]
  UniSplat is a feed-forward framework for learning 3D representations from unposed multi-view images.<n>We introduce a dual-masking strategy that strengthens geometry induction in the encoder.<n>Second, we develop a coarse-to-fine Gaussian splatting strategy that reduces appearance-semantics inconsistencies.<n>Third, we introduce a pose-conditioned recalibration mechanism that interrelates predicted 3D point and semantic maps into the image plane.
  arXiv  Detail & Related papers  (2026-04-12T10:36:18Z)
• Thinking with Spatial Code for Physical-World Video Reasoning [27.397518169065634]
  Thinking with Spatial Code is a framework that transforms RGB video into explicit, temporally coherent 3D representations.<n>We highlight the empirical finding that our proposed spatial encoder can parse videos into structured spatial code with explicit 3D oriented bounding boxes and semantic labels.
  arXiv  Detail & Related papers  (2026-03-05T19:00:02Z)
• Synthesizing Multimodal Geometry Datasets from Scratch and Enabling Visual Alignment via Plotting Code [27.26235987246201]
  Multimodal geometry reasoning requires models to jointly understand visual diagrams and perform structured symbolic inference.<n>We propose a pipeline for complex multimodal geometry problems from scratch and construct a dataset named textbfGeoCode, which decouples problem generation into symbolic seed construction.<n>We further introduce code prediction as an explicit alignment objective, transforming visual understanding into a supervised structured prediction task.
  arXiv  Detail & Related papers  (2026-02-21T07:53:48Z)
• Joint Semantic and Rendering Enhancements in 3D Gaussian Modeling with Anisotropic Local Encoding [86.55824709875598]
  We propose a joint enhancement framework for 3D semantic Gaussian modeling that synergizes both semantic and rendering branches.<n>Unlike conventional point cloud shape encoding, we introduce an anisotropic 3D Gaussian Chebyshev descriptor to capture fine-grained 3D shape details.<n>We employ a cross-scene knowledge transfer module to continuously update learned shape patterns, enabling faster convergence and robust representations.
  arXiv  Detail & Related papers  (2026-01-05T18:33:50Z)
• Aligned Novel View Image and Geometry Synthesis via Cross-modal Attention Instillation [62.87088388345378]
  We introduce a diffusion-based framework that performs aligned novel view image and geometry generation via a warping-and-inpainting methodology.<n>Method leverages off-the-shelf geometry predictors to predict partial geometries viewed from reference images.<n>Cross-modal attention distillation is proposed to ensure accurate alignment between generated images and geometry.
  arXiv  Detail & Related papers  (2025-06-13T16:19:00Z)
• Agentic 3D Scene Generation with Spatially Contextualized VLMs [67.31920821192323]
  We introduce a new paradigm that enables vision-language models to generate, understand, and edit complex 3D environments.<n>We develop an agentic 3D scene generation pipeline in which the VLM iteratively reads from and updates the spatial context.<n>Results show that our framework can handle diverse and challenging inputs, achieving a level of generalization not observed in prior work.
  arXiv  Detail & Related papers  (2025-05-26T15:28:17Z)
• CrossModalityDiffusion: Multi-Modal Novel View Synthesis with Unified Intermediate Representation [0.5242869847419834]
  CrossModalityDiffusion is a modular framework designed to generate images across different modalities without prior knowledge of scene geometry.<n>We show that jointly training different modules ensures consistent geometric understanding across all modalities within the framework.<n>We validate CrossModalityDiffusion's capabilities on the synthetic ShapeNet cars dataset.
  arXiv  Detail & Related papers  (2025-01-16T20:56:32Z)
• Semantic Lens: Instance-Centric Semantic Alignment for Video Super-Resolution [36.48329560039897]
  inter-frame alignment is a critical clue of video super-resolution (VSR) We introduce a novel paradigm for VSR named Semantic Lens. Video is modeled as instances, events, and scenes via a Semantic Extractor.
  arXiv  Detail & Related papers  (2023-12-13T01:16:50Z)
• A geometrically aware auto-encoder for multi-texture synthesis [1.2891210250935146]
  We propose an auto-encoder architecture for multi-texture synthesis. Images are embedded in a compact and geometrically consistent latent space. Texture synthesis and tasks can be performed directly from these latent codes.
  arXiv  Detail & Related papers  (2023-02-03T09:28:39Z)
• MoDi: Unconditional Motion Synthesis from Diverse Data [51.676055380546494]
  We present MoDi, an unconditional generative model that synthesizes diverse motions. Our model is trained in a completely unsupervised setting from a diverse, unstructured and unlabeled motion dataset. We show that despite the lack of any structure in the dataset, the latent space can be semantically clustered.
  arXiv  Detail & Related papers  (2022-06-16T09:06:25Z)
• TediGAN: Text-Guided Diverse Face Image Generation and Manipulation [52.83401421019309]
  TediGAN is a framework for multi-modal image generation and manipulation with textual descriptions. StyleGAN inversion module maps real images to the latent space of a well-trained StyleGAN. visual-linguistic similarity learns the text-image matching by mapping the image and text into a common embedding space. instance-level optimization is for identity preservation in manipulation.
  arXiv  Detail & Related papers  (2020-12-06T16:20:19Z)
• Deep Geometric Texture Synthesis [83.9404865744028]
  We propose a novel framework for synthesizing geometric textures. It learns texture statistics from local neighborhoods of a single reference 3D model. Our network displaces mesh vertices in any direction, enabling synthesis of geometric textures.
  arXiv  Detail & Related papers  (2020-06-30T19:36:38Z)

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.