发表机构
University of Science, Ho Chi Minh City; Vietnam National University, Ho Chi Minh City; University of Dayton; Monash University; VinFast; VinUniversity（胡志明市科学大学; 胡志明市越南国家大学; 代顿大学; 莫纳什大学; VinFast公司; Vin大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对现代文本到图像扩散模型合成物理精确镜像反射的挑战，提出物理感知生成框架PhysMirror，通过3D空间先验执行投影几何，引入评估指标，实验表明其在反射精度等方面优于基线。
AI 中文摘要
合成物理精确的镜像反射对现代文本到图像扩散模型仍是重大挑战。这些模型常因严格几何约束而产生幻觉，降低合成数据效用。为此，我们引入了新颖的端到端物理感知生成框架PhysMirror，通过显式3D空间先验来执行投影几何。我们的方法自动将提示对象提升为3D网格，并在模拟环境中构建轻量级、数学精确的镜像场景。通过渲染这个显式3D场景，我们提取精确的2D条件元素，如深度图和分割图，作为下游扩散模型的强大引导信号，引导它们生成具有物理正确镜像反射的图像。此外，我们引入了镜像一致性分数（MCS），这是一种无需参考、完全自动化的度量，使用密集特征匹配和消失点收敛来量化物理正确性。在我们新构建的MirrOB数据集上的实验结果表明，我们的方法在反射精度和物理逼真度方面优于现有最先进的基线，同时保持了强大的文本到图像语义对齐，为具身人工智能数据生成提供了可靠的管道。源代码可在这个https URL上获取。
英文摘要
Synthesizing physically accurate mirror reflections remains a fundamental challenge for modern text-to-image diffusion models, which are increasingly critical for generating synthetic training data for embodied AI and robotic perception. These models typically struggle with strict geometric constraints, leading to hallucinations that degrade the utility of the synthetic data. To address this, we introduce a novel, end-to-end physics-aware generation framework namely PhysMirror that natively enforces projective geometry through explicit 3D spatial priors. Our method automatically lifts prompted objects into 3D meshes and constructs a lightweight, mathematically exact mirror scene within a simulated environment. By rendering this explicit 3D scene, we extract precise 2D conditioning elements, such as depth maps and segmentation maps, that serve as robust guiding signals for downstream diffusion models, guiding them to generate images with physically correct mirror reflections. Moreover, we introduce Mirror Consistency Score (MCS), reference-free, fully automated metric that quantifies physical correctness using dense feature matching and vanishing point convergence. Experimental results on our newly constructed MirrOB dataset demonstrate that our approach outperforms state-of-the-art baselines in reflection accuracy and physical realism, while maintaining strong text-to-image semantic alignment, providing a reliable pipeline for embodied AI data generation. The source code is released at https://duyphuc0701.github.io/PhysMirror.
CommentsAccepted to IROS 2026
