用图像空间方法解决低多边形模型的轮廓锯齿问题，无需修改模型。
Neural Image Space Tessellation effect
- 在图像空间通过学习对轮廓进行隐式变形和外观重分配
- 显著降低视觉上的几何分块感，生成平滑连贯的轮廓
- 适合游戏、实时渲染等对性能敏感的应用场景
我们提出神经图像空间镶嵌效应（NIST），一种轻量级的屏幕空间后处理方法，用于减少低多边形渲染中明显的分块轮廓。NIST不进行原始几何体细分、不创建新几何体，也不修改底层网格，而是利用低多边形渲染结果与简单的辅助G缓冲属性，在图像空间学习几何引导的轮廓平滑。其核心机制是先隐式变形图像空间轮廓，再学习对整个图像空间（包括变形区域）的外观重分配，以保持纹理连续性并避免接缝伪影。实验表明，NIST能有效降低视觉上明显的几何分块现象，生成接近基于细分的平滑参考结果的平滑连贯轮廓，且在测试环境下每帧开销几乎恒定。据我们所知，NIST是首个将低多边形轮廓分块问题的解决方案从预渲染几何阶段转移到后渲染屏幕空间阶段的工作。
原文摘要 · Abstract (English)
We present Neural Image Space Tessellation effect (NIST), a lightweight screen-space post-processing approach for reducing the faceted silhouettes of low-poly renderings. Instead of tessellating primitives, creating new geometry, or modifying the underlying mesh, NIST uses the low-poly rendering result together with simple auxiliary G-buffer attributes to learn geometry-guided smoothing of object contours in image space. At its core, NIST first deforms image-space contours implicitly and then learns to reassign appearance in the whole image-space, including the deformed regions, preserving texture continuity and avoiding seam artifacts. Experiments show that NIST reduces visually apparent geometric faceting and produces smooth, coherent silhouettes close to tessellation-based smoothing references, with a nearly constant per-frame cost in our tested settings. To the best of our knowledge, NIST is the first work to move the solution of low-poly silhouette faceting from the pre-rendering geometry stage to a post-rendering screen-space stage.
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。