Hi3D: Pursuing High-Resolution Image-to-3D Generation with Video Diffusion Models

TL;DR

Hi3D introduces a novel video diffusion-based approach for high-resolution 3D generation from a single image, achieving superior multi-view consistency and detailed textures through 3D-aware modeling and reconstruction.

Contribution

The paper presents Hi3D, a new paradigm combining video diffusion models with 3D-aware priors and Gaussian Splatting for high-resolution 3D object generation from a single image.

Findings

Produces high-fidelity, multi-view consistent images with detailed textures.

Outperforms existing methods in novel view synthesis and single view reconstruction.

Demonstrates effective 3D reconstruction from high-resolution multi-view images.

Abstract

Despite having tremendous progress in image-to-3D generation, existing methods still struggle to produce multi-view consistent images with high-resolution textures in detail, especially in the paradigm of 2D diffusion that lacks 3D awareness. In this work, we present High-resolution Image-to-3D model (Hi3D), a new video diffusion based paradigm that redefines a single image to multi-view images as 3D-aware sequential image generation (i.e., orbital video generation). This methodology delves into the underlying temporal consistency knowledge in video diffusion model that generalizes well to geometry consistency across multiple views in 3D generation. Technically, Hi3D first empowers the pre-trained video diffusion model with 3D-aware prior (camera pose condition), yielding multi-view images with low-resolution texture details. A 3D-aware video-to-video refiner is learnt to further scale up the multi-view images with high-resolution texture details. Such high-resolution multi-view images are further augmented with novel views through 3D Gaussian Splatting, which are finally leveraged to obtain high-fidelity meshes via 3D reconstruction. Extensive experiments on both novel view synthesis and single view reconstruction demonstrate that our Hi3D manages to produce superior multi-view consistency images with highly-detailed textures. Source code and data are available at \url{https://github.com/yanghb22-fdu/Hi3D-Official}.