Zero-1-to-3: Zero-shot One Image to 3D Object

TL;DR

Zero-1-to-3 introduces a diffusion-based framework that synthesizes novel object views from a single image by leveraging geometric priors learned from large-scale models, enabling effective 3D reconstruction and view synthesis.

Contribution

It presents a novel viewpoint-conditioned diffusion model trained on synthetic data that generalizes zero-shot to real-world images for 3D object view synthesis.

Findings

Outperforms existing single-view 3D reconstruction models

Retains strong zero-shot generalization to in-the-wild images

Effectively synthesizes novel views from a single image

Abstract

We introduce Zero-1-to-3, a framework for changing the camera viewpoint of an object given just a single RGB image. To perform novel view synthesis in this under-constrained setting, we capitalize on the geometric priors that large-scale diffusion models learn about natural images. Our conditional diffusion model uses a synthetic dataset to learn controls of the relative camera viewpoint, which allow new images to be generated of the same object under a specified camera transformation. Even though it is trained on a synthetic dataset, our model retains a strong zero-shot generalization ability to out-of-distribution datasets as well as in-the-wild images, including impressionist paintings. Our viewpoint-conditioned diffusion approach can further be used for the task of 3D reconstruction from a single image. Qualitative and quantitative experiments show that our method significantly outperforms state-of-the-art single-view 3D reconstruction and novel view synthesis models by leveraging Internet-scale pre-training.