Cycle3D: High-quality and Consistent Image-to-3D Generation via Generation-Reconstruction Cycle

TL;DR

Cycle3D introduces a unified framework that cyclically combines 2D diffusion and 3D reconstruction modules, resulting in high-quality, consistent, and diverse 3D content generation from images.

Contribution

It proposes a novel cyclic generation-reconstruction framework that improves 3D content quality and consistency by integrating diffusion-based texture generation with reconstruction.

Findings

Outperforms state-of-the-art methods in 3D quality and consistency

Enhances diversity and texture control during 3D generation

Demonstrates superior results through extensive experiments

Abstract

Recent 3D large reconstruction models typically employ a two-stage process, including first generate multi-view images by a multi-view diffusion model, and then utilize a feed-forward model to reconstruct images to 3D content.However, multi-view diffusion models often produce low-quality and inconsistent images, adversely affecting the quality of the final 3D reconstruction. To address this issue, we propose a unified 3D generation framework called Cycle3D, which cyclically utilizes a 2D diffusion-based generation module and a feed-forward 3D reconstruction module during the multi-step diffusion process. Concretely, 2D diffusion model is applied for generating high-quality texture, and the reconstruction model guarantees multi-view consistency.Moreover, 2D diffusion model can further control the generated content and inject reference-view information for unseen views, thereby enhancing the diversity and texture consistency of 3D generation during the denoising process. Extensive experiments demonstrate the superior ability of our method to create 3D content with high-quality and consistency compared with state-of-the-art baselines.