基于对比偏好优化的文本驱动三维人体生成
Text-driven 3D Human Generation via Contrastive Preference Optimization
AI总结：
针对文本驱动三维人体生成中对齐困难，提出引入对比偏好与否定偏好模块的框架，提升长复杂文本下的纹理真实感和视觉对齐，达到最先进性能。
摘要：
近年来，分数蒸馏采样（SDS）的进展改善了从文本描述生成三维人体的效果。然而，现有方法在将三维模型与长且复杂的文本输入精确对齐方面仍面临挑战。为解决这一问题，我们提出了一种新颖框架，引入对比偏好，其中由正面和负面提示引导的人类级别偏好模型辅助SDS以实现更好的对齐。具体而言，我们设计了一个偏好优化模块，集成多个模型以全面捕获文本特征的完整范围。此外，我们引入了一个否定偏好模块，通过利用静态-动态否定提示来缓解对无关细节的过度优化，有效防止“奖励黑客”。大量实验表明，我们的方法达到了最先进的结果，显著增强了纹理真实感和与文本描述的视觉对齐，尤其对于长且复杂的输入。
英文摘要：
Recent advances in Score Distillation Sampling (SDS) have improved 3D human generation from textual descriptions. However, existing methods still face challenges in accurately aligning 3D models with long and complex textual inputs. To address this challenge, we propose a novel framework that introduces contrastive preferences, where human-level preference models, guided by both positive and negative prompts, assist SDS for improved alignment. Specifically, we design a preference optimization module that integrates multiple models to comprehensively capture the full range of textual features. Furthermore, we introduce a negation preference module to mitigate over-optimization of irrelevant details by leveraging static-dynamic negation prompts, effectively preventing ``reward hacking". Extensive experiments demonstrate that our method achieves state-of-the-art results, significantly enhancing texture realism and visual alignment with textual descriptions, particularly for long and complex inputs.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
