ride-splat
Code for RIDE-Splat: Reflection Removal for In-the-Wild Driving Environments
Get picks like this daily. Today's launch numbers, the top launches, AI and tech news, and a daily opportunity pick, straight to your inbox.
Want to reach these readers? Sponsor an issue.
GITHUB · launched Oct 27, 2026 · 22 upvotes (top 54%) · 0 views
Niche: computer vision software and models · 225 launches, 11 in the last 7 days ▼ -45% · Explore this niche →
Category and tags
- Horizontal
- Developer
- AI-native
- Hobby / open-source project
Visit website ↗ Source listing ↗
More like this: all 225 launches in computer vision software and models →
Could you build this?
No The project is research code for reflection removal in driving scenes, which requires novel computer vision methods and GPU-heavy model training.
What it would actually take: A real version means reimplementing the RIDE-Splat method, which builds on 3D Gaussian splatting and learned reflection separation. It requires ML researchers, a curated in-the-wild driving dataset with reflection annotations, and multi-GPU training and evaluation.
Competitors
Other products that read as similar to this one : 3234 launches clear the similarity bar, closest 8 shown.
Attention rank: #1711 of 3235 (itself plus its competitors, highest first, normalized so YC and Product Hunt are compared fairly).
Launched 361 days after the earliest competitor.
- testdrive-enhanced · github · 2026-09-16 · 11 upvotes · similarity 0.60
- playstunts · github · 2026-09-10 · 22 upvotes · similarity 0.56
- Odyssey · github · 2026-09-29 · 28 upvotes · similarity 0.55
- Remap · hn · 2026-08-26 · 12 upvotes · similarity 0.53
- invisible-cities-opus-5.5 · github · 2026-10-05 · 17 upvotes · similarity 0.53
- jevpilot · github · 2026-09-17 · 150 upvotes · similarity 0.52
- PhysicalRSI · github · 2026-10-04 · 39 upvotes · similarity 0.51
- cars-racing-enhancement · github · 2026-11-10 · 102 upvotes · similarity 0.51
The niche, labels, vibe code rating and competitor comparison on this page are analysis by Nicheloom. If you use them, please credit nicheloom.com. How you may use our data.