# Stable Score Distillation for High-Quality 3D Generation Source: [Stable Score Distillation for High-Quality 3D Generation]() Collection index: [llms.txt]() Data updated: 2025-10-26T02:18:23.013Z Authors: Boshi Tang, Jianan Wang, Zhiyong Wu, Lei Zhang Published: 2023-12-14T19:18:38.000Z ## Abstract Although Score Distillation Sampling (SDS) has exhibited remarkable performance in conditional 3D content generation, a comprehensive understanding of its formulation is still lacking, hindering the development of 3D generation. In this work, we decompose SDS as a combination of three functional components, namely mode-seeking, mode-disengaging and variance-reducing terms, analyzing the properties of each. We show that problems such as over-smoothness and implausibility result from the intrinsic deficiency of the first two terms and propose a more advanced variance-reducing term than that introduced by SDS. Based on the analysis, we propose a simple yet effective approach named Stable Score Distillation (SSD) which strategically orchestrates each term for high-quality 3D generation and can be readily incorporated to various 3D generation frameworks and 3D representations. Extensive experiments validate the efficacy of our approach, demonstrating its ability to generate high-fidelity 3D content without succumbing to issues such as over-smoothness. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Human Avatar Texture Editing on User Study 10 full-body and 3 localized human avatar edits](): Human Avatar Texture Editing; User Study 10 full-body and 3 localized human avatar edits; Visual Quality: 19.42. ## Original sources and implementation [Original paper]() [PDF]()