ainewsblitz.com

Breaking

VAST AI Research Releases TripoSplat, an Open-Source Model That Turns a Single Image Into Variable-Count 3D Gaussians

VAST AI Research Releases TripoSplat, an Open-Source Model That Turns a Single Image Into Variable-Count 3D Gaussians
  • Media Generation
  • Open Source
  • Research & Papers

VAST AI Research has released TripoSplat, an open-source model that converts a single 2D image into high-quality 3D Gaussian Splatting assets with a user-selectable number of Gaussians, published under a permissive MIT license. The model, from the team behind TripoAI, targets a persistent bottleneck in generative 3D: producing splat-based assets whose density adapts to scene complexity rather than being locked to a fixed structure.

Continue reading

The rest of this article is for AI News Blitz readers. Choose an option below to keep reading.

$20
Read this article
$29/month
Unlimited — all 27,934 articles, the full archive, and comprehension quizzes
Save 72%
$98/year
≈ $8.17/month
Unlimited, billed once a year