Oriel — AI & technology worth noticing, every day.

InfiniDream: Open-Ended Photorealistic 3D Worlds Through Procedural Generation

Paper · https://arxiv.org/abs/2610.26853

Procedural generation plays a key role in synthetic data creation and game development, offering greater controllability, editability, and diversity than static mesh representations. However, VLM-based code generation often produces relatively simple 3D assets, while sophisticated photorealistic procedural systems require extensive manual development. Existing VLM-guided procedural methods remain largely constrained by predefined factories and APIs, limiting their ability to create novel asset types. We introduce InfiniDream, a VLM-driven framework for open-ended procedural 3D world generation. First, we propose Symbolically Constrained Asset Generation, which leverages existing procedural algorithms to create novel, photorealistic assets while preserving editability and seed-based diversity. Second, we develop an end-to-end text-to-world pipeline that combines semantic scene planning with Deterministic Frustum-Guided Grid Placement to construct large-scale 3D worlds with precise object placement, procedural population, and animation. Extensive evaluations on 100 object and 20 scene generation tasks demonstrate improvements across four perceptual metrics. Diversity analysis, ablation studies, and human preference evaluations further validate the effectiveness of our framework. Project page: https://yichuanh.github.io/infinidream-page/

First seen by Oriel on .

AI summary

InfiniDream is a VLM-driven framework for generating editable, photorealistic 3D assets and large-scale worlds beyond predefined procedural factories.

  • Symbolically Constrained Asset Generation uses existing procedural algorithms to create novel assets while retaining editability and seed-based diversity.
  • A text-to-world pipeline combines semantic scene planning with Deterministic Frustum-Guided Grid Placement for object placement, procedural population, and animation.
  • Evaluations across 100 object and 20 scene tasks report improvements on four perceptual metrics.
  • Diversity analysis, ablation studies, and human preference evaluations are also used to assess the framework.

#3d generation #procedural generation #vision-language models

Generated by gpt-5.6-sol. Check the original for details.

Metric trends

Last 30 days · Up to 120 recorded samples per source and metric, with reposts kept separate · First and latest retained

Points

Score reported by the source.

  • Hugging Face Papers: 26, latest observation ; +2 over observed period since

Comments

Comment count reported by the source.

  • Hugging Face Papers: 2, latest observation ; +1 over observed period since

Aliases

SourceExternal IDURL
Hugging Face Papers2610.26853https://arxiv.org/abs/2610.26853 Read discussion