跳到正文
研踪PaperTrail
← 研踪 PaperTrail

arXiv:2611.26431 · v1

FFGaussType: Feed-Forward Conversion of Glyph and SVG Geometry into Compact Gaussian Assets

首次提交 2026-11-20 01:08
版本更新 2026-11-20 01:08
雷达观测 2026-11-20 12:52
arXiv ↗PDF ↗

摘要

Immersive 3D content allows text and graphical elements, such as subtitles, annotations, and icons, to be placed inside a scene rather than displayed as flat overlays. Placed this way, they respect occlusion and perspective and take on user-assigned materials and lighting while preserving their original shapes. In Gaussian scenes, however, each new glyph or icon requires its own iterative optimization, which limits scalable content creation. We present FFGaussType, which converts extruded glyph and SVG outlines into Gaussian assets in a single forward pass. A point encoder maps anchors sampled on the known surface to a single feature plane, from which a decoder shared by all assets predicts neural Gaussians carrying surface normals. This separates geometric conversion from material and lighting choices, and the feature plane supports image and video coding for compact delivery. We construct a paired dataset of 27,221 glyph and SVG icon assets with anchors and calibrated normal and silhouette renderings, holding out font families for evaluation. Conversion from prepared anchors takes 9.1 ms per asset, at a fraction of the compute and memory of prior baselines. On unseen font families and test icons, FFGaussType achieves 1.62∘1.62^\circ normal error and 0.9850.985 silhouette IoU, the best among the compared feed-forward converters, matching the fidelity that per-asset fitting needs thousands of steps to reach. The code and dataset will be released after publication.

作者备注:20 pages. Project page: https://fengyee.github.io/FFGaussType/

AI 论文解读

基于摘要 · 非全文审阅

此版本尚未生成 AI 解读。解读由后台任务生成并按论文版本保存,登录后共享已有结果。

版本差异

目前只收录了一个版本。收录下一版后,可以对照标题、作者、分类和摘要。

观测到的版本

相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。

v1 · 2026-11-20 01:08 · 最新观测版本

FFGaussType: Feed-Forward Conversion of Glyph and SVG Geometry into Compact Gaussian Assets

Immersive 3D content allows text and graphical elements, such as subtitles, annotations, and icons, to be placed inside a scene rather than displayed as flat overlays. Placed this way, they respect occlusion and perspective and take on user-assigned materials and lighting while preserving their original shapes. In Gaussian scenes, however, each new glyph or icon requires its own iterative optimization, which limits scalable content creation. We present FFGaussType, which converts extruded glyph and SVG outlines into Gaussian assets in a single forward pass. A point encoder maps anchors sampled on the known surface to a single feature plane, from which a decoder shared by all assets predicts neural Gaussians carrying surface normals. This separates geometric conversion from material and lighting choices, and the feature plane supports image and video coding for compact delivery. We construct a paired dataset of 27,221 glyph and SVG icon assets with anchors and calibrated normal and silhouette renderings, holding out font families for evaluation. Conversion from prepared anchors takes 9.1 ms per asset, at a fraction of the compute and memory of prior baselines. On unseen font families and test icons, FFGaussType achieves 1.62∘1.62^\circ normal error and 0.9850.985 silhouette IoU, the best among the compared feed-forward converters, matching the fidelity that per-asset fitting needs thousands of steps to reach. The code and dataset will be released after publication.

查看此版本解读 →查看此版本原文 ↗