SyncDreamer：从单视角图像生成多视角一致图像

摘要

在本文中，我们提出了一种名为SyncDreamer的新型扩散模型，可以从单视角图像生成多视角一致的图像。利用预训练的大规模2D扩散模型，最近的工作Zero123展示了从物体的单视角图像生成合理的新视角的能力。然而，对生成的图像在几何和颜色上保持一致性仍然是一个挑战。为了解决这个问题，我们提出了一种同步多视角扩散模型，该模型建模了多视角图像的联合概率分布，从而能够通过单个逆向过程生成多视角一致的图像。SyncDreamer通过一种3D感知特征注意机制，在逆向过程的每一步同步所有生成图像的中间状态，从而相关联不同视角之间的对应特征。实验表明，SyncDreamer生成的图像在不同视角之间具有高一致性，因此非常适用于各种3D生成任务，如新视角合成、文本到3D和图像到3D。

English

In this paper, we present a novel diffusion model called that generates multiview-consistent images from a single-view image. Using pretrained large-scale 2D diffusion models, recent work Zero123 demonstrates the ability to generate plausible novel views from a single-view image of an object. However, maintaining consistency in geometry and colors for the generated images remains a challenge. To address this issue, we propose a synchronized multiview diffusion model that models the joint probability distribution of multiview images, enabling the generation of multiview-consistent images in a single reverse process. SyncDreamer synchronizes the intermediate states of all the generated images at every step of the reverse process through a 3D-aware feature attention mechanism that correlates the corresponding features across different views. Experiments show that SyncDreamer generates images with high consistency across different views, thus making it well-suited for various 3D generation tasks such as novel-view-synthesis, text-to-3D, and image-to-3D.

SyncDreamer：从单视角图像生成多视角一致图像

SyncDreamer: Generating Multiview-consistent Images from a Single-view Image

摘要

Support