Tootfinder

Opt-in global Mastodon full text search. Join the index!

No exact results. Similar results found.
@elduvelle@neuromatch.social
2026-02-24 08:40:02

😱
"Un quart des étudiants vivent avec moins de 100 euros par mois une fois leur loyer réglé"
lemonde.fr/societe/article/202

@drbruced@aus.social
2026-02-25 23:23:35

I really like this viewpoint on AI performing "semantic ablation". It hits home as I work diligently to write a textbook that contains plenty of nuance and (I hope) a unique perspective on the topic (computer networking).
"By running a text through successive AI "refinement" loops, the vocabulary diversity (type-token ratio) collapses. The process performs a systematic lobotomy across three distinct stages:
- Stage 1: Metaphoric cleansing. The AI identifi…

@arXiv_csGR_bot@mastoxiv.page
2026-01-27 07:37:15

LoD-Structured 3D Gaussian Splatting for Streaming Video Reconstruction
Xinhui Liu, Can Wang, Lei Liu, Zhenghao Chen, Wei Jiang, Wei Wang, Dong Xu
arxiv.org/abs/2601.18475 arxiv.org/pdf/2601.18475 arxiv.org/html/2601.18475
arXiv:2601.18475v1 Announce Type: new
Abstract: Free-Viewpoint Video (FVV) reconstruction enables photorealistic and interactive 3D scene visualization; however, real-time streaming is often bottlenecked by sparse-view inputs, prohibitive training costs, and bandwidth constraints. While recent 3D Gaussian Splatting (3DGS) has advanced FVV due to its superior rendering speed, Streaming Free-Viewpoint Video (SFVV) introduces additional demands for rapid optimization, high-fidelity reconstruction under sparse constraints, and minimal storage footprints. To bridge this gap, we propose StreamLoD-GS, an LoD-based Gaussian Splatting framework designed specifically for SFVV. Our approach integrates three core innovations: 1) an Anchor- and Octree-based LoD-structured 3DGS with a hierarchical Gaussian dropout technique to ensure efficient and stable optimization while maintaining high-quality rendering; 2) a GMM-based motion partitioning mechanism that separates dynamic and static content, refining dynamic regions while preserving background stability; and 3) a quantized residual refinement framework that significantly reduces storage requirements without compromising visual fidelity. Extensive experiments demonstrate that StreamLoD-GS achieves competitive or state-of-the-art performance in terms of quality, efficiency, and storage.
toXiv_bot_toot

@Dragofix@mastodontti.fi
2026-03-11 21:31:14

Suomi tarvitsee viipymättä luonnon monimuotoisuusstrategian sttinfo.fi/tiedote/71863404/su