面向多样化文本到3D生成的多模态语义偏差缓解
Multimodal Semantic Bias Mitigation for Diverse Text-To-3D Generation
针对文本到3D大模型对提示词格式敏感、难以理解复杂提示词的问题，提出用质量评价模型定位跨模态偏差、以质量分数量化提示词文本对偏差的贡献，并构造成对样本重建无偏的视觉-文本连接；做文本到3D或扩散先验的人可借鉴这套偏差定位与成对偏好式微调流程。
原文依据 we propose a framework to localize and mitigate the bias in the current text-to-3D large model
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论文本到3D生成模型的最新进展使生成高质量3D内容成为可能。近期的文本到3D大模型在多视角一致性方面取得了显著突破。然而，其有效性常常受到固有偏差的影响，导致对提示词格式等设计设置较为敏感，进而难以理解复杂提示词。为帮助文本到3D生成模型理解更多样的提示词，我们提出一个框架，用于定位并缓解当前文本到3D大模型中的偏差。具体而言，我们首先利用现有模型生成3D内容，并使用质量评价模型识别跨模态偏差；随后，利用预测的质量分数量化提示词文本对偏差的贡献；最后，为降低这些偏差，我们构造多样化的成对样本，帮助当前文本到3D大模型建立无偏的视觉-文本连接。实验表明，我们的方法取得了有竞争力的结果，与现有方法相比能够提供更高质量、更多样的3D内容。
英文原文摘要 1123 字符
The latest progress in text-to-3D generative models makes it possible to generate high-quality 3D content. Recent text-to-3D large model have achieved remarkable breakthroughs in multi-view consistency. However, their effectiveness is often affected by inherent biases, resulting in sensitivity to design settings such as prompt format, leading to difficulty understanding complex prompts. To help text-to3D generative models understand more diverse prompts, we propose a framework to localize and mitigate the bias in the current text-to-3D large model. Specifically, we first use the existing model to generate 3D content and use the quality evaluation model to identify the cross-modality bias. Then, we use the predicted quality score to quantify the contribution of the prompt text to the bias. Finally, in order to reduce these biases, we construct diverse pairwise examples to help the current text-to-3D large model construct unbiased visual-text connections. The experiment shows that our method has achieved competitive results and can provide higher quality, more diverse 3D content compared to existing methods.