ExplorerComputer VisionComputer Vision
Research PaperResearchia:202603.27007

Less Gaussians, Texture More: 4K Feed-Forward Textured Splatting

Yixing Lao

Abstract

Existing feed-forward 3D Gaussian Splatting methods predict pixel-aligned primitives, leading to a quadratic growth in primitive count as resolution increases. This fundamentally limits their scalability, making high-resolution synthesis such as 4K intractable. We introduce LGTM (Less Gaussians, Texture More), a feed-forward framework that overcomes this resolution scaling barrier. By predicting compact Gaussian primitives coupled with per-primitive textures, LGTM decouples geometric complexity ...

Submitted: March 27, 2026Subjects: Computer Vision; Computer Vision

Description / Details

Existing feed-forward 3D Gaussian Splatting methods predict pixel-aligned primitives, leading to a quadratic growth in primitive count as resolution increases. This fundamentally limits their scalability, making high-resolution synthesis such as 4K intractable. We introduce LGTM (Less Gaussians, Texture More), a feed-forward framework that overcomes this resolution scaling barrier. By predicting compact Gaussian primitives coupled with per-primitive textures, LGTM decouples geometric complexity from rendering resolution. This approach enables high-fidelity 4K novel view synthesis without per-scene optimization, a capability previously out of reach for feed-forward methods, all while using significantly fewer Gaussian primitives. Project page: https://yxlao.github.io/lgtm/


Source: arXiv:2603.25745v1 - http://arxiv.org/abs/2603.25745v1 PDF: https://arxiv.org/pdf/2603.25745v1 Original Link: http://arxiv.org/abs/2603.25745v1

Please sign in to join the discussion.

No comments yet. Be the first to share your thoughts!

Access Paper
View Source PDF
Submission Info
Date:
Mar 27, 2026
Topic:
Computer Vision
Area:
Computer Vision
Comments:
0
Bookmark