WorldGrow: Generating Infinite 3D World
Sikuang Li, Chen Yang, Jiemin Fang, Taoran Yi, Jia Lu, Jiazhong Cen, Lingxi Xie, Wei Shen, Qi Tian

TL;DR
WorldGrow introduces a hierarchical 3D scene generation framework that leverages pre-trained models to produce infinite, coherent, and photorealistic virtual environments, overcoming previous scalability and consistency challenges.
Contribution
It presents a novel hierarchical method combining data curation, scene inpainting, and coarse-to-fine generation for scalable, infinite 3D scene synthesis.
Findings
Achieves state-of-the-art geometry reconstruction on 3D-FRONT dataset.
Supports infinite scene generation with consistent and realistic visuals.
Demonstrates potential for large-scale virtual environment creation.
Abstract
We tackle the challenge of generating the infinitely extendable 3D world -- large, continuous environments with coherent geometry and realistic appearance. Existing methods face key challenges: 2D-lifting approaches suffer from geometric and appearance inconsistencies across views, 3D implicit representations are hard to scale up, and current 3D foundation models are mostly object-centric, limiting their applicability to scene-level generation. Our key insight is leveraging strong generation priors from pre-trained 3D models for structured scene block generation. To this end, we propose WorldGrow, a hierarchical framework for unbounded 3D scene synthesis. Our method features three core components: (1) a data curation pipeline that extracts high-quality scene blocks for training, making the 3D structured latent representations suitable for scene generation; (2) a 3D block inpainting…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
Taxonomy
Topics3D Shape Modeling and Analysis · Generative Adversarial Networks and Image Synthesis · Computer Graphics and Visualization Techniques
