5× faster fast_blur in image-rs
The article details a performance optimization of the fast_blur function in the Rust image-rs crate, achieving up to 5.9× faster execution for u8 pixel images. The improvement stems from replacing floating-point operations with integer arithmetic in the blur's hot path. This change reduces reliance on costly float conversions and rounding functions while maintaining the algorithm's visual quality.
- ▪The fast_blur function in image-rs was optimized to be up to 5.9× faster for u8 pixel images.
- ▪The optimization replaced floating-point arithmetic with integer arithmetic to avoid costly roundf and to_f32 operations.
- ▪fast_blur approximates a Gaussian blur using three successive box blurs, maintaining O(1) per-pixel complexity regardless of blur radius.
Hacker News (Newest) files mainly under programming. We currently carry 5,306 of its stories.
Story provenance
Source · retrieval · rights · ranking — open for full record
inspect →
Attribution is not the same as permission. This drawer separates discovery metadata, excerpts, WeSearch-generated summaries, reuse status, and whether the publisher receives the visit. Nothing here claims a legal grant the publisher has not made.
Record
| Original publisher | Arthur Pastel |
| Canonical URL | https://apas.tel/blog/optimizing-image-rs-blur |
| Publication time | Sat, 16 May 2026 08:42:05 +0000 |
| Retrieval time | 2026-05-16T09:10:17.965Z |
| Last seen | 2026-05-16T09:10:17.965Z |
| Headline source | Publisher (no WeSearch rewrite) |
| Excerpt source | publisher body |
| Excerpt method | First ~120 words (~800 chars) of extracted publisher body, fair-use limited. |
| Summary | WeSearch · cerebras-chat (WeSearch summarizer) |
| Summary source text | contentText |
| Citation coverage | Summary is a WeSearch-generated derivative; primary citation is the original publisher URL. |
| Cluster | kuWsdKnzb0Sd |
| Cluster logic | Grouped by semantic title/content similarity across sources within a rolling window. Same-publisher template collisions are excluded from coverage comparison. |
| Ranking reason | Story pages are not engagement-ranked. Hub feeds use recency, with optional source-diversified chronological ordering (cap consecutive stories per source). No personalized ranking. |
| Publisher visit | Yes — open original |
| Substitutes article? | No — link-out required for full text |
Rights status (four layers)
WeSearch handling by dimension
| Indexing | May the item be indexed (stored, ranked, made findable)? | Allowed |
| Snippet | May a short excerpt of the publisher's text be shown? | Allowed |
| AI summary | May WeSearch generate its own short summary of the article? | Limited |
| Retrieval / RAG | May the content be exposed for third-party retrieval-augmented generation? | Not asserted |
| Model training | May the content be used to train AI models? | Not asserted |
| Commercial reuse | May the content be reused commercially? | Not permitted |
Basis: Derived from the published RSS/Atom feed. Contact: [email protected]. Reviewed: 2026-07-24.
Opening excerpt (first ~120 words) tap to expand
Arthur PastelBlogAbout5× faster fast_blur in image-rs A few weeks ago, I went looking for something to optimize, for fun. The Rust image crate jumped out: I'd used it before, it's one of the most downloaded crates, and image work is heavy by nature. I quickly found a method called fast_blur. With a name like that, it seemed worth trying to optimize. The result: up to 5.9x faster on images with u8 pixels. fast_blur σ=3×5.9 fasterbefore51.1 msafter8.6 msfast_blur σ=7×5.7 fasterbefore51.5 msafter9.0 msfast_blur σ=50×5.1 fasterbefore52.2 msafter10.2 ms(lower is better)Wall-time measurement on x86_64 Before we get into the optimizations, let's take a step back and understand how blurs work, the tradeoffs between different algorithms, and where fast_blur fits in the spectrum of blur quality and…
Excerpt limited to ~120 words for fair-use compliance. The full article is at Arthur Pastel.
Discussion
0 commentsMore from Arthur Pastel
