Pyramid Diffusion for Fine 3D Large Scene Generation
Authors:
Preprint
Abstract
Directly transferring the 2D techniques to 3D scene generation is challenging due to significant resolution reduction and the scarcity of comprehensive real-world 3D scene datasets. To address these issues, our work introduces the Pyramid Discrete Diffusion model (PDD) for 3D scene generation. This novel approach employs a multi-scale model capable of progressively generating high-quality 3D scenes from coarse to fine. In this way, the PDD can generate high-quality scenes within limited resource constraints and does not require additional data sources. To the best of our knowledge, we are the first to adopt the simple but effective coarse-to-fine strategy for 3D large scene generation. Our experiments, covering both unconditional and conditional generation, have yielded impressive results, showcasing the model's effectiveness and robustness in generating realistic and detailed 3D scenes. Our code will be available to the public.Keywords
All Related Versions
This publication has 24 references indexed in Scilit:
- Multi-modality 3D object detection in autonomous driving: A reviewNeurocomputing, 2023
- Learning to Generate Realistic LiDAR Point Clouds2022
- InfiniteNature-Zero: Learning Perpetual View Generation of Natural Scenes from Single Images2022
- High-Resolution Image Synthesis with Latent Diffusion Models2022
- DeepFusion: Lidar-Camera Deep Fusion for Multi-Modal 3D Object Detection2022
- Diffusion Probabilistic Models for 3D Point Cloud Generation2021
- Generation of Virtual Reality Environment Based on 3D Scanned Indoor Physical Space2021
- Robust Point Cloud Based Reconstruction of Large-Scale Outdoor Scenes2019
- 3D Semantic Segmentation with Submanifold Sparse Convolutional Networks2018
- Are we ready for autonomous driving? The KITTI vision benchmark suite2012