Dreamer XL: Towards High-Resolution Text-to-3D Generation via Trajectory Score Matching

Abstract

In this work, we propose Trajectory Score Matching (TSM), a method designed to address the pseudo-ground truth inconsistency caused by accumulated error in Interval Score Matching (ISM) with Denoising Diffusion Implicit Models (DDIM) inversion process. Unlike ISM which adopts the inversion process of DDIM to calculate on a single path, our TSM method leverages the inversion process of DDIM to generate two paths from the same starting point for calculation. Since both paths start from the same starting point, TSM can reduce the accumulated error compared to ISM, thus alleviating the problem of pseudo-ground truth inconsistency. TSM enhances the stability and consistency of the model’s generated paths during the distillation process. We demonstrate this experimentally and further show that ISM is a special case of TSM. Furthermore, to optimize the current multi-stage optimization process from high-resolution text to 3D generation, we adopt Stable Diffusion XL for guidance. In response to the issues of abnormal replication and splitting caused by unstable gradients during the 3D Gaussian splatting process when using Stable Diffusion XL, we propose a pixel-by-pixel gradient clipping method. Extensive experiments show significant improvement over the baseline methods in visual quality and performance, demonstrating the effectiveness of TSM and gradient clipping in enhancing model stability and output fidelity.