SynCity 3000: Bootstrapping Scene-Scale 3D Diffusion

Hugging Face Daily Papers Papers
3d-generation scene-generation diffusion-models fine-tuning synthetic-data image-to-3d convolutional-operators

Summary

SynCity 3000 introduces a framework for generating large, globally coherent 3D scenes by adapting image-to-3D generators as convolutional operators, fine-tuned on synthetic scene data from a new data engine.

We present SynCity 3000, a framework for generating 3D scenes that are globally coherent while enabling fine-grained layout control. Building on the ability of current image-to-3D generators to produce complex 3D assets from a single image, we extend this capability to the scale of entire scenes by adapting the generator to be applicable as a convolutional operator. We achieve this by fine-tuning the model on scene-like data generated by a new synthetic data engine, which we propose to address the scarcity of 3D scene data for training. The convolutional generator is then applied to a dimetric image of the entire scene, generated from the user prompt, resulting in 3D scenes of arbitrary size and complexity. Across diverse prompts and layouts, SynCity 3000 produces large, coherent, and detailed scenes, addressing the shortcomings of prior approaches to 3D scene generation.
Original Article
View Cached Full Text

Cached at: 07/07/26, 02:44 PM

Paper page - SynCity 3000: Bootstrapping Scene-Scale 3D Diffusion

Source: https://huggingface.co/papers/2607.05392

Abstract

SynCity 3000 generates large, coherent 3D scenes by adapting image-to-3D generators as convolutional operators through fine-tuning on synthetic scene data.

We present SynCity 3000, a framework for generating 3D scenes that are globally coherent while enabling fine-grained layout control. Building on the ability of currentimage-to-3D generatorsto produce complex 3D assets from a single image, we extend this capability to the scale of entire scenes by adapting the generator to be applicable as aconvolutional operator. We achieve this byfine-tuningthe model on scene-like data generated by a newsynthetic data engine, which we propose to address the scarcity of 3D scene data for training. The convolutional generator is then applied to adimetric imageof the entire scene, generated from the user prompt, resulting in 3D scenes of arbitrary size and complexity. Across diverse prompts and layouts, SynCity 3000 produces large, coherent, and detailed scenes, addressing the shortcomings of prior approaches to3D scene generation.

View arXiv pageView PDFProject pageGitHubAdd to collection

Get this paper in your agent:

hf papers read 2607\.05392

Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2607.05392 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2607.05392 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2607.05392 in a Space README.md to link it from this page.

Collections including this paper0

No Collection including this paper

Add this paper to acollectionto link it from this page.

Similar Articles

Sat3DGen: Comprehensive Street-Level 3D Scene Generation from Single Satellite Image

Hugging Face Daily Papers

Sat3DGen introduces a geometry-first approach for generating street-level 3D scenes from a single satellite image, achieving improved geometric accuracy and photorealism through novel constraints and training strategies. The method demonstrates significant improvements over prior work on the VIGOR-OOD benchmark.