Pyramid Diffusion for Fine 3D Large Scene Generation
Yuheng Liu, Xinke Li, Xueting Li, Lu Qi, Chongshou Li, Ming-Hsuan Yang

TL;DR
This paper introduces Pyramid Discrete Diffusion (PDD), a multi-scale framework for generating large-scale 3D outdoor scenes by progressively refining details, overcoming data complexity and size limitations.
Contribution
The paper presents a novel coarse-to-fine diffusion model architecture for large-scale 3D scene synthesis, enabling unconditional and conditional generation with high data compatibility.
Findings
Successful generation of outdoor 3D scenes unconditionally and conditionally
Multi-scale architecture allows easy fine-tuning across datasets
Demonstrated high-quality, scalable 3D scene synthesis
Abstract
Diffusion models have shown remarkable results in generating 2D images and small-scale 3D objects. However, their application to the synthesis of large-scale 3D scenes has been rarely explored. This is mainly due to the inherent complexity and bulky size of 3D scenery data, particularly outdoor scenes, and the limited availability of comprehensive real-world datasets, which makes training a stable scene diffusion model challenging. In this work, we explore how to effectively generate large-scale 3D scenes using the coarse-to-fine paradigm. We introduce a framework, the Pyramid Discrete Diffusion model (PDD), which employs scale-varied diffusion models to progressively generate high-quality outdoor scenes. Experimental results of PDD demonstrate our successful exploration in generating 3D scenes both unconditionally and conditionally. We further showcase the data compatibility of the PDD…
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.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsAdvanced Vision and Imaging · Computer Graphics and Visualization Techniques · Generative Adversarial Networks and Image Synthesis
MethodsDiffusion
