一键生成物理一致的材质图，速度提升百倍。
SuperMat: Physically Consistent PBR Material Estimation at Interactive Rates
- 单步推理替代多步去噪，大幅提速。
- 毫秒级完成材质分解，3秒内处理3D物体。
- 适合实时渲染与3D建模用户使用。
从图像中分解出基于物理的材质属性仍具挑战性，尤其在兼顾计算效率与物理一致性方面。现有基于扩散的方法虽有潜力，但因需多次去噪步骤及针对不同材质属性的独立模型，导致计算开销大。本文提出 SuperMat，一个单步框架，可实现高质量的材质分解，支持端到端训练并结合感知损失与重渲染损失，同时在毫秒级速度下完成反照率、金属度和粗糙度图的分解。通过引入UV优化网络，该框架进一步扩展至3D物体，实现跨视角的一致材质估计且保持高效。实验表明，SuperMat 在材质分解质量上达到当前最佳水平，推理时间由秒级降至毫秒级，3D物体的PBR材质估计耗时约3秒。
原文摘要 · Abstract (English)
Decomposing physically-based materials from images into their constituent properties remains challenging, particularly when maintaining both computational efficiency and physical consistency. While recent diffusion-based approaches have shown promise, they face substantial computational overhead due to multiple denoising steps and separate models for different material properties. We present SuperMat, a single-step framework that achieves high-quality material decomposition with one-step inference. This enables end-to-end training with perceptual and re-render losses while decomposing albedo, metallic, and roughness maps at millisecond-scale speeds. We further extend our framework to 3D objects through a UV refinement network, enabling consistent material estimation across viewpoints while maintaining efficiency. Experiments demonstrate that SuperMat achieves state-of-the-art PBR material decomposition quality while reducing inference time from seconds to milliseconds per image, and completes PBR material estimation for 3D objects in approximately 3 seconds. The project page is at https://hyj542682306.github.io/SuperMat/.
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。