DiffBMP: Differentiable Rendering with Bitmap Primitives
This work provides a practical tool for creative professionals and researchers working with bitmap image manipulation and optimization, enabling differentiable rendering for a widely used image format.
This paper introduces DiffBMP, a differentiable rendering engine for bitmap images, addressing the limitation of traditional renderers being restricted to vector graphics. It can optimize thousands of bitmap primitives (position, rotation, scale, color, opacity) in under 1 minute using a consumer GPU.
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.