search

google-research-datasets / Objectron

Objectron is a dataset of short, object-centric video clips. In addition, the videos also contain AR session metadata including camera poses, sparse point-clouds and planes. In each video, the camera moves around and above the object and captures it from different views. Each object is annotated with a 3D bounding box. The 3D bounding box describes the object’s position, orientation, and dimensions. The dataset contains about 15K annotated video clips and 4M annotated images in the following categories: bikes, books, bottles, cameras, cereal boxes, chairs, cups, laptops, and shoes
Other
2.24k stars 263 forks source link

notebook for 3d projection #45

Closed jinlinyi closed 3 years ago

jinlinyi commented 3 years ago

Solving issue https://github.com/google-research-datasets/Objectron/issues/14

ahmadyan commented 3 years ago

Thanks for the PR. Looks great. I couldn't leave comments on the notebook, so I'll leave them here: For the functionn project_by_intrinsics, you are passing example in the function API but you are using the element in the function body. Make sure you are passing the element to the function, so each function does not have any dependency on the state of the notebook.

jinlinyi commented 3 years ago

Oops, good catch!

ahmadyan commented 3 years ago

LGTM, thanks

relh commented 3 months ago

Just an FYI but after talking to my labmate Linyi (@jinlinyi) we realized that the three functions project_by_point2d, project_by_intrinsics, and project_by_camera_projection all produce slightly different results