提升文生图模型的空间理解能力，让图像更准确反映物体位置关系。
CoMPaSS: Enhancing Spatial Understanding in Text-to-Image Diffusion Models
- 用约束规则筛选空间精准的数据，解决训练数据模糊问题。
- 保留提示词顺序信息，增强文本编码对空间语义的捕捉能力。
- 在多个评测上大幅领先，适合需要精确布局生成的研究者。
文生图扩散模型虽能生成逼真图像，但常无法正确表达物体间空间关系。我们识别出两大根本原因：现有数据集中的空间关系标注模糊，以及当前文本编码器难以准确解析输入描述的空间语义。为此提出 CoMPaSS 框架，首先通过空间约束导向配对（SCOP）数据引擎，以合理约束构建空间精准的训练数据；其次引入令牌编码排序（TENOR）模块，保留文本编码中丢失的关键词序信息，强化提示语的语言结构。在四个主流文生图模型（基于 UNet 与 MMDiT）上的实验表明，CoMPaSS 在关键空间评估基准上达到新最优，相对提升显著：VISOR +98%，T2I-CompBench Spatial +67%，GenEval Position +131%。代码已开源：https://github.com/blurgyy/CoMPaSS。
原文摘要 · Abstract (English)
Text-to-image (T2I) diffusion models excel at generating photorealistic images but often fail to render accurate spatial relationships. We identify two core issues underlying this common failure: 1) the ambiguous nature of data concerning spatial relationships in existing datasets, and 2) the inability of current text encoders to accurately interpret the spatial semantics of input descriptions. We propose CoMPaSS, a versatile framework that enhances spatial understanding in T2I models. It first addresses data ambiguity with the Spatial Constraints-Oriented Pairing (SCOP) data engine, which curates spatially-accurate training data via principled constraints. To leverage these priors, CoMPaSS also introduces the Token ENcoding ORdering (TENOR) module, which preserves crucial token ordering information lost by text encoders, thereby reinforcing the prompt's linguistic structure. Extensive experiments on four popular T2I models (UNet and MMDiT-based) show CoMPaSS sets a new state of the art on key spatial benchmarks, with substantial relative gains on VISOR (+98%), T2I-CompBench Spatial (+67%), and GenEval Position (+131%). Code is available at https://github.com/blurgyy/CoMPaSS.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。