<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom" xmlns:content="http://purl.org/rss/1.0/modules/content/"><channel><title>Video on Dylan Ler</title><link>http://dylanler.github.io/tags/video/</link><description>Recent content in Video on Dylan Ler</description><generator>Hugo -- 0.133.0</generator><language>en-us</language><lastBuildDate>Thu, 27 Aug 2026 10:00:00 -0700</lastBuildDate><atom:link href="http://dylanler.github.io/tags/video/index.xml" rel="self" type="application/rss+xml"/><item><title>Coordinates for an Unseen Camera</title><link>http://dylanler.github.io/posts/coordinates-for-an-unseen-camera/</link><pubDate>Tue, 17 Mar 2026 07:42:00 -0700</pubDate><guid>http://dylanler.github.io/posts/coordinates-for-an-unseen-camera/</guid><description>A camera moves left. Or perhaps the subject moves right. The pixels alone do not tell us which coordinate system the sentence meant.
That ambiguity became the experimental question for this month:
Does adding explicit camera coordinates make a movement label meaningfully more reconstructable than ordinary cinematic language?
The larger camera dataset project in this repository proposes generated environments, depth estimation, scene reconstruction, scripted camera paths, and captions derived from those paths.</description></item></channel></rss>