让位图图像也能被高效微分渲染，支持千级位图一键优化。
DiffBMP: Differentiable Rendering with Bitmap Primitives
- 用自研CUDA实现并行化位图微分渲染，支持批量参数优化。
- 千个位图在消费级显卡上1分钟内完成位置、旋转、透明度等优化。
- 可嵌入创意工作流，支持导出分层文件，开源易用。
我们提出DiffBMP，一种针对位图图像集合的可微分渲染引擎。传统可微渲染器仅限于矢量图形，而现实中绝大多数图像为位图，该限制制约了实际应用。本工作核心在于设计一个高度并行化的渲染管道，并基于自定义CUDA实现梯度计算。系统可在消费级GPU上，于1分钟内对数千个位图的的位置、旋转、缩放、颜色和不透明度等参数进行联合优化。我们引入多种优化技术：通过高斯模糊实现软光栅化，结构感知初始化，噪声画布，以及针对视频或空间约束图像设计的专用损失函数与启发式策略。实验表明，DiffBMP不仅是独立工具，更是可融入创作流程的实用系统，支持导出原生分层文件格式，整个框架以简单易用的Python包形式公开可用。
原文摘要 · Abstract (English)
We introduce DiffBMP, a scalable and efficient differentiable rendering engine for a collection of bitmap images. Our work addresses a limitation that traditional differentiable renderers are constrained to vector graphics, given that most images in the world are bitmaps. Our core contribution is a highly parallelized rendering pipeline, featuring a custom CUDA implementation for calculating gradients. This system can, for example, optimize the position, rotation, scale, color, and opacity of thousands of bitmap primitives all in under 1 min using a consumer GPU. We employ and validate several techniques to facilitate the optimization: soft rasterization via Gaussian blur, structure-aware initialization, noisy canvas, and specialized losses/heuristics for videos or spatially constrained images. We demonstrate DiffBMP is not just an isolated tool, but a practical one designed to integrate into creative workflows. It supports exporting compositions to a native, layered file format, and the entire framework is publicly accessible via an easy-to-hack Python package.
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。