SynCity: Training-Free Generation of 3D Worlds

Paul Engstler, Aleksandar Shtedritski, Iro Laina, Christian Rupprecht, Andrea Vedaldi; Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2025, pp. 27585-27595

Abstract

We propose SynCity, a method for generating explorable 3D worlds from textual descriptions. Our approach leverages pre-trained textual, image, and 3D generators without requiring fine-tuning or inference-time optimization. While most 3D generators are object-centric and unable to create large-scale worlds, we demonstrate how 2D and 3D generators can be combined to produce ever-expanding scenes. The world is generated tile by tile, with each new tile created within its context and seamlessly integrated into the scene. SynCity enables fine-grained control over the appearance and layout of the generated worlds, which are both detailed and diverse.

Related Material

[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Engstler_2025_ICCV, author = {Engstler, Paul and Shtedritski, Aleksandar and Laina, Iro and Rupprecht, Christian and Vedaldi, Andrea}, title = {SynCity: Training-Free Generation of 3D Worlds}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {27585-27595} }