正在加载视频...

视频加载失败

"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

17,837 次观看 • 1 年前 •via X (Twitter)

3 条评论

Alexandre Morgand 的头像
Alexandre Morgand1 年前

1,2*, @brenthyi 1*, @JunchenLiu77 1*, @hangg70 1, @YiMaTweets 1,3, @akanazawa 1 ( *Equal contribution ) 1 @UCBerkeley 2 @nvidia 3 @HKUniversity Project page: Paper: Source code:

Ruilong Li 的头像
Ruilong Li1 年前

thanks for sharing!

Alexandre Morgand 的头像
Alexandre Morgand1 年前

Anytime!

相关视频