DreamTime: An Improved Optimization Strategy for Diffusion-Guided 3D Generation

TL;DR

DreamTime introduces a novel optimization strategy for diffusion-guided 3D generation that enhances convergence speed, quality, and diversity by aligning timestep sampling with the 3D optimization process.

Contribution

The paper proposes a new timestep sampling method that resolves conflicts in score distillation, significantly improving 3D content creation quality and efficiency.

Findings

Faster convergence in 3D diffusion models

Improved quality with fewer artifacts

Enhanced diversity in generated 3D content

Abstract

Text-to-image diffusion models pre-trained on billions of image-text pairs have recently enabled 3D content creation by optimizing a randomly initialized differentiable 3D representation with score distillation. However, the optimization process suffers slow convergence and the resultant 3D models often exhibit two limitations: (a) quality concerns such as missing attributes and distorted shape and texture; (b) extremely low diversity comparing to text-guided image synthesis. In this paper, we show that the conflict between the 3D optimization process and uniform timestep sampling in score distillation is the main reason for these limitations. To resolve this conflict, we propose to prioritize timestep sampling with monotonically non-increasing functions, which aligns the 3D optimization process with the sampling process of diffusion model. Extensive experiments show that our simple redesign significantly improves 3D content creation with faster convergence, better quality and diversity.