📚 세현's Vault

🌍 도메인

  • 🔮3D-Vision
  • 🎨Rendering
  • 🤖Robotics
  • 🧠LLM
  • 👁️VLM
  • 🎬GenAI
  • 🥽XR
  • 🎮Simulation
  • 🛠️Dev-Tools
  • 💰Crypto
  • 📈Finance
  • 📋Productivity
  • 📦기타

📄 Papers

  • 📚전체 논문172
Home

❯

bookmarks

❯

cameras as relative positional encoding tldr study absolute raymap and relative

cameras-as-relative-positional-encoding-tldr-study-absolute-raymap-and-relative

2025년 7월 15일1 min read

  • 3D-Vision
  • multiview-transformer

Zhenjun Zhao (@zhenjun_zhao)

2025-07-15 | ❤️ 148 | 🔁 25


Cameras as Relative Positional Encoding

@ruilong_li, @brenthyi, @JunchenLiu77, @hangg70, @YiMaTweets, @akanazawa

tl;dr: study absolute raymap and relative SE(3) encoding; viewing frustums→intrinsics and extrinsics→transformer’s self-attention

https://arxiv.org/abs/2507.10496 https://x.com/zhenjun_zhao/status/1945072030614733233/photo/1


🔗 Related

See similar notes in domain-llm

Tags

type-resource domain-llm


그래프 뷰

  • Zhenjun Zhao (@zhenjun_zhao)
  • 🔗 Related
  • Tags

백링크

  • domain-LLM
  • enriched-codex

Created with Quartz v4.5.2 © 2026

  • GitHub
  • Sehyeon Park