We propose a multi-view cross-domain diffusion scheme, which operates on two distinct domains to generate multi-view consistent normal maps and color images.

We propose that the distribution of 3d assets can be modeled as a joint distribution of its corresponding 2d multi-view normal maps and corresponding images.

Diffusion models [22, 52] are first proposed to gradually recover images from a specifically designed degradation process

Recent compelling successes in 2D diffusion models and large vision language models provide new possibilities for generating 3d assets.

In this work, we introduce Wonder3D, a novel method for efficiently generating high-fidelity textured meshes from single-view images.

We train our model on the LVIS subset of the Objaverse dataset [9], which comprises approximately 30,000+ objects following a cleanup process.

In this paper, we present Wonder3D, an innovative approach designed for efficiently generating high10 fidelity textured meshes from single-view images.