发表机构
Zelostech; Huaxin Design Institute; Communication University of China（泽洛科技; 华信设计院; 中国传媒大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对数字大理石纹模型，提出利用重放伴随优化胶囊插入程序以近似目标图像，实现低内存高效恢复，支持程序级编辑重放。
AI 中文摘要
纸大理石纹中的颜料沉积会置换已存在的图案，将每个手势的外观与后续动作耦合在一起。我们为基于沉积的数字大理石纹模型恢复可执行程序：给定目标图像，我们优化一个胶囊插入的有序程序，其重放效果近似于该图像。胶囊原语将圆形液滴连续连接成细长沉积物。其输运精确保持面积，并在沉积区域外部具有闭式逆变换。重放伴随重构中间状态，保留沉积物内部丢失的坐标和周期性位置检查点。在2000个手势和1024^2像素下，PyTorch重放实现比测试的检查点自动梯度配置节省8.7倍内存，且步进时间相当；融合实现可在单个工作站GPU上约四分钟内拟合一个程序。我们在五张大理石纹纸上评估图像重建，与禁用输运的拟合、单程几何补偿以及已发表的基于笔画的拟合器在匹配笔画数下进行比较，并测量对替代有序液滴输运的敏感性。恢复的程序可在4倍线性分辨率范围内重放。按程序顺序或调色板空间指定的编辑——插入手势、重新着色阶段、平移阶段——在同一模型下正确重放；按图像内容指定的编辑（如移动图案）则不能。在具有已知生成程序的合成目标上，恢复的程序匹配图像，但在位置匹配统计下不匹配生成手势。输出是指定数字媒介中的可编辑程序。
英文摘要
We present a stroke design in which strokes are transport-coupled: each stroke deposits material of its own area and moves every earlier mark without changing its area, so later strokes deform earlier ones. We then solve the inverse problem under this design: given a target image, we optimise an ordered program of such strokes whose replay approximates it, with digital marbling as the motivating medium. The stroke is a capsule that continuously joins circular drops to drawn deposits; its transport is exactly area-preserving, with a closed-form inverse outside the deposit, and a variant with the same inverse differs from line-source potential flow by 8% of the mean displacement. A replay adjoint regenerates intermediate states instead of storing them and uses 8.7x less memory than checkpointed automatic differentiation; a fused implementation fits a 2000-stroke program at 1024x1024 in about four minutes on one GPU. On five marbled sheets the recovered programs are level with a published stroke-based fitter as rasters, replay across a fourfold resolution range, and support edits in program order and palette space that stay valid under transport.
