Paired 360 + first-person video of photoreal scenes, with per-frame depth, camera pose and actions.
xjxu
xjxu21
·
AI & ML interests
generative models, computer vision
Recent Activity
upvoted a paper 6 days ago
WorldSculpt: Generating Compositional Worlds from Grounded Videos updated a dataset 17 days ago
xjxu21/WorldRover-med_village updated a dataset 26 days ago
xjxu21/WorldRoverOrganizations
