{
  "abstract": "Contemporary image generation methods commonly construct visual content through learned latent representations, iterative denoising, autoregressive prediction, or direct optimization of image parameters. This paper develops a conceptual framework for Granular Deposition Image Generation (GDIG), in which an image emerges through the sequential or parallel transport, deposition, accumulation, and possible rearrangement of discrete visual particles. Unlike approaches that treat particles merely as rendering primitives or simulate granular materials for physical analysis, GDIG formulates particle placement as a target-guided generation process. Each particle possesses a spatial state, appearance attributes, mobility, and deposition status. Its behavior is influenced by local neighborhood structure, spatial deposition demand, global image constraints, and computational cost. The framework integrates five principal mechanisms: particle transport, conditional deposition, competitive occupancy, selective remobilization, and stability-aware termination. A unified objective is proposed to balance image reconstruction, semantic consistency, structural coherence, deposition regularity, particle movement, and computational expenditure. A learning architecture combining local deposition policies with global visual guidance is outlined, together with a training strategy, algorithmic procedure, and evaluation protocol. The framework is intended to support both procedural image synthesis and learned generative systems. Its central research question is whether target-guided particle deposition can provide a useful alternative or complementary mechanism for constructing visual structures. The paper presents a formalized research proposal rather than a validated empirical result; implementation, comparative evaluation, and claims of performance advantage remain subjects for future investigation.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": null,
  "author_total": 1,
  "authors": [
    {
      "name": "Jincheng Zhang",
      "orcid": "0009-0005-1860-0009"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/3qcvqh0zeep7k.bib",
  "cited_by": 0,
  "doi": "10.5281/zenodo.23556085",
  "fulltext_url": null,
  "id": "3qcvqh0zeep7k",
  "issns": [],
  "landing_url": "https://zenodo.org/records/23556085",
  "language": null,
  "licence": "CC-BY-4.0",
  "licence_label": "CC BY 4.0",
  "licence_source": "article",
  "licence_url": "https://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": null,
  "native_subjects": [],
  "openalex": null,
  "pdf_url": "https://zenodo.org/api/records/23556085/files/Granular%20Deposition%20Image%20Generation.pdf/content",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-22",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/3qcvqh0zeep7k.ris",
  "sources": [
    {
      "first_seen": "2026-11-05T12:20:44Z",
      "native_id": "23556085",
      "source": "zenodo",
      "url": "https://zenodo.org/records/23556085"
    }
  ],
  "subjects": [],
  "title": "Granular Deposition Image Generation: A Framework for Target-Guided Visual Synthesis Through Particle Transport, Selective Deposition, and Dynamic Reorganization",
  "title_text": "Granular Deposition Image Generation: A Framework for Target-Guided Visual Synthesis Through Particle Transport, Selective Deposition, and Dynamic Reorganization",
  "type": "preprint",
  "updated_at": "2026-11-05T12:20:44Z",
  "url": "https://research.draconitic.com/paper/3qcvqh0zeep7k",
  "venue": "Zenodo",
  "versions": []
}