Show HN: Apple's Sharp Running in the Browser via ONNX Runtime Web
A new browser-based tool called ml-sharp-web enables users to generate Gaussian splats from a single image using Apple's SHARP model and ONNX Runtime Web. The application runs entirely in the browser, allowing users to preview and download results as .ply files. It requires significant system resources due to the large model size and is intended for research use under Apple's licensing terms.
- ▪The project is built on Apple's SHARP model and uses ONNX Runtime Web for browser-based inference.
- ▪Users can upload an image, generate Gaussian splats, preview the output, and download a .ply file.
- ▪The SHARP model requires both .onnx and .onnx.data files to function, with the latter containing most of the model weights.
- ▪Running the app requires Bun, a modern browser like Chrome or Edge, and sufficient RAM and disk space.
- ▪The model is licensed for research use only when using Apple's released weights.
Opening excerpt (first ~120 words) tap to expand
ml-sharp-web A browser-based Gaussian splat generator built on top of Apple SHARP. ✨ This project lets you: upload one image generate Gaussian splats in the browser preview the result download a .ply file Links Project repo: bring-shrubbery/ml-sharp-web Follow the author on X: @bringshrubberyy Upstream SHARP repo (Apple): apple/ml-sharp SHARP project page: apple.github.io/ml-sharp SHARP paper: arXiv:2512.10685 Before you start (important license note) Apple's SHARP repository has separate licenses for code and model weights. SHARP code license: LICENSE SHARP model license: LICENSE_MODEL If you use Apple's released SHARP checkpoint/weights, you must follow LICENSE_MODEL (research-use restrictions apply).
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at Hacker News: Front Page.
Discussion
0 commentsMore from Hacker News: Front Page
