{
  "id": "2303.14184",
  "version": "v1",
  "published": "2023-03-24T17:54:22.000Z",
  "updated": "2023-03-24T17:54:22.000Z",
  "title": "Make-It-3D: High-Fidelity 3D Creation from A Single Image with Diffusion Prior",
  "authors": [
    "Junshu Tang",
    "Tengfei Wang",
    "Bo Zhang",
    "Ting Zhang",
    "Ran Yi",
    "Lizhuang Ma",
    "Dong Chen"
  ],
  "comment": "Project page: https://make-it-3d.github.io/",
  "categories": [
    "cs.CV"
  ],
  "abstract": "In this work, we investigate the problem of creating high-fidelity 3D content from only a single image. This is inherently challenging: it essentially involves estimating the underlying 3D geometry while simultaneously hallucinating unseen textures. To address this challenge, we leverage prior knowledge from a well-trained 2D diffusion model to act as 3D-aware supervision for 3D creation. Our approach, Make-It-3D, employs a two-stage optimization pipeline: the first stage optimizes a neural radiance field by incorporating constraints from the reference image at the frontal view and diffusion prior at novel views; the second stage transforms the coarse model into textured point clouds and further elevates the realism with diffusion prior while leveraging the high-quality textures from the reference image. Extensive experiments demonstrate that our method outperforms prior works by a large margin, resulting in faithful reconstructions and impressive visual quality. Our method presents the first attempt to achieve high-quality 3D creation from a single image for general objects and enables various applications such as text-to-3D creation and texture editing.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2023-03-24T17:54:22.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "diffusion prior",
      "high-fidelity 3d creation",
      "single image",
      "make-it-3d",
      "achieve high-quality 3d creation"
    ],
    "tags": [
      "github project"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 0,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}