๐Ÿ“š ์„ธํ˜„'s Vault

๐ŸŒ ๋„๋ฉ”์ธ

  • ๐Ÿ”ฎ3D-Vision
  • ๐ŸŽจRendering
  • ๐Ÿค–Robotics
  • ๐Ÿง LLM
  • ๐Ÿ‘๏ธVLM
  • ๐ŸŽฌGenAI
  • ๐ŸฅฝXR
  • ๐ŸŽฎSimulation
  • ๐Ÿ› ๏ธDev-Tools
  • ๐Ÿ’ฐCrypto
  • ๐Ÿ“ˆFinance
  • ๐Ÿ“‹Productivity
  • ๐Ÿ“ฆ๊ธฐํƒ€

๐Ÿ“„ Papers

  • ๐Ÿ“š์ „์ฒด ๋…ผ๋ฌธ172
Home

โฏ

bookmarks

โฏ

reconstructs 3d scenes from 1000 images in one forward pass

reconstructs-3d-scenes-from-1000-images-in-one-forward-pass

2025๋…„ 12์›” 26์ผ1 min read

  • 3D-Vision
  • reconstruction

Tom Dรถrr (@tom_doerr)

2025-12-26 | โค๏ธ 777 | ๐Ÿ” 92


Reconstructs 3D scenes from 1000+ images in one forward pass

https://github.com/facebookresearch/fast3r/ https://x.com/tom_doerr/status/2004429386523521125/photo/1

๐Ÿ”— ์›๋ณธ ๋งํฌ

  • https://github.com/facebookresearch/fast3r/
  • https://x.com/tom_doerr/status/2004429386523521125/photo/1

๋ฏธ๋””์–ด

image


๐Ÿ”— Related

  • no-3d-representations-are-a-terrible-way-of-maintaining
  • something-was-off-with-the-colors-but-i-finally-found-out
  • neoverse-enhancing-4d-world-model-with-in-the-wild
  • dream2flow-bridging-video-generation-and-open-world
  • wu-et-al-from-rays-to-projections-better-inputs-for-feed

Tags

3D


๊ทธ๋ž˜ํ”„ ๋ทฐ

  • Tom Dรถrr (@tom_doerr)
  • ๐Ÿ”— ์›๋ณธ ๋งํฌ
  • ๋ฏธ๋””์–ด
  • ๐Ÿ”— Related
  • Tags

๋ฐฑ๋งํฌ

  • domain-3D-Vision

Created with Quartz v4.5.2 ยฉ 2026

  • GitHub
  • Sehyeon Park