Log inSign up
Chris Rockwell
133 posts
@_crockwell

Chris Rockwell

@_crockwell
AI Scientist @Roblox | Video world models
crockwell.github.io
Joined March 2013
695
Following
683
Followers
RepliesRepliesRepostsRepostsMediaMedia

Log in or sign up for X

See what’s happening and join the conversation

Continue with phone
or
Log in with username or email
Terms·Privacy·Cookies·Accessibility·Ads Info·© 2026 X Corp.
  • Pinned
    @_crockwell
    Chris Rockwell
    @_crockwell
    Jun 3
    Excited to share Morpheus AI is coming out of stealth and joining Roblox! Grateful to have joined Xun as a founding member and helped build video world models over the past several months, alongside some of the most talented people I've worked with. Thanks to the entire team.
    @xxunhuang
    Xun Huang
    @xxunhuang
    Jun 2
    I'm excited to announce that the Morpheus AI team is joining Roblox! Over the past two years, I’ve focused on developing the foundational architectures behind modern video world models, including Self Forcing and AR-DiT. This work unlocked something unprecedented: the ability to
    8
  • @_crockwell
    Chris Rockwell
    @_crockwell
    May 13, 2025
    Excited to share ☀️Lightspeed⚡, a photorealistic, synthetic dataset with ground truth pose used for benchmarking alongside DynPose-100K! Now available for download: huggingface.co/datasets/nvidi… Paper accepted to #CVPR2025: arxiv.org/abs/2504.17788
    Image
    00:00
    @_crockwell
    Chris Rockwell
    @_crockwell
    Apr 25, 2025
    Image
    00:21
    Ever wish YouTube had 3D labels? 🚀Introducing🎥DynPose-100K🎥, an Internet-scale collection of diverse videos annotated with camera pose! Applications include camera-controlled video generation🤩and learned dynamic pose estimation😯 Download: huggingface.co/datasets/nvidi…
    3
  • @_crockwell
    Chris Rockwell
    @_crockwell
    Apr 25, 2025
    Ever wish YouTube had 3D labels? 🚀Introducing🎥DynPose-100K🎥, an Internet-scale collection of diverse videos annotated with camera pose! Applications include camera-controlled video generation🤩and learned dynamic pose estimation😯 Download: huggingface.co/datasets/nvidi…
    Image
    00:00
    2
  • @_crockwell
    Chris Rockwell
    @_crockwell
    Jun 20, 2024
    Excited to present our #CVPR2024 *Highlight* FAR on Friday at 10:30 a.m, Arch 4A-E Poster #31. Please feel free to stop by! FAR significantly improves correspondence-based methods using end-to-end pose prediction, making it applicable to many SOTA approaches!
    @_crockwell
    Chris Rockwell
    @_crockwell
    Mar 6, 2024
    📢 Presenting 𝐅𝐀𝐑: 𝐅𝐥𝐞𝐱𝐢𝐛𝐥𝐞, 𝐀𝐜𝐜𝐮𝐫𝐚𝐭𝐞 𝐚𝐧𝐝 𝐑𝐨𝐛𝐮𝐬𝐭 𝟔𝐃𝐨𝐅 𝐑𝐞𝐥𝐚𝐭𝐢𝐯𝐞 𝐂𝐚𝐦𝐞𝐫𝐚 𝐏𝐨𝐬𝐞 𝐄𝐬𝐭𝐢𝐦𝐚𝐭𝐢𝐨𝐧 #CVPR2024 FAR builds upon complimentary Solver and Learning-Based works yielding accurate *and* robust pose! crockwell.github.io/far/
    Image
  • @_crockwell
    Chris Rockwell
    @_crockwell
    Mar 6, 2024
    📢 Presenting 𝐅𝐀𝐑: 𝐅𝐥𝐞𝐱𝐢𝐛𝐥𝐞, 𝐀𝐜𝐜𝐮𝐫𝐚𝐭𝐞 𝐚𝐧𝐝 𝐑𝐨𝐛𝐮𝐬𝐭 𝟔𝐃𝐨𝐅 𝐑𝐞𝐥𝐚𝐭𝐢𝐯𝐞 𝐂𝐚𝐦𝐞𝐫𝐚 𝐏𝐨𝐬𝐞 𝐄𝐬𝐭𝐢𝐦𝐚𝐭𝐢𝐨𝐧 #CVPR2024 FAR builds upon complimentary Solver and Learning-Based works yielding accurate *and* robust pose! crockwell.github.io/far/
    Image
    1
Advertisement
Advertisement