Alexandre Morgand (@Almorgand)
2025-08-01 | ❤️ 459 | 🔁 52
“Cameras as Relative Positional Encoding” TLDR: comparison for conditioning transformers on cameras: token-level raymap, attention-level relative pose encodings, a (new) relative encoding Projective Positional Encoding → camera frustums, (int|ext)insics for relative pos encoding https://x.com/Almorgand/status/1951331762463822212/video/1
미디어
