Objectron
Objectron copied to clipboard
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...
Hi, I'm a researcher working on a paper related to Object 6D Pose estimation. The proposed method in Objectron is an important baseline method for us so we do hope...
Hi, Great work! Do you have any plans on releasing the GT segmentation masks of these objects or the pre-trained Mask-RCNN used in [FiG-NeRF](https://fig-nerf.github.io/)? Thanks in advance!
Great work! Can you share more details (code) for extracting segmentation mask by culling the depth mask with 3D bounding box in 3D using a trained NeRF? Thanks in advance!
Hi @ahmadyan @daeyun @jinlinyi @ChadCYB @soskek @jianingwei @lzhang57 Could you please share the Video 3D Bounding Box Annotation tool which was used for your Objectron ? I want to make...
Hello, In the recently published [arXiv paper](https://arxiv.org/pdf/2012.09988.pdf) describing the dataset, there was a mention that the trained models (and their evaluation reports) would be posted on `objectron.dev`, which redirects here....
I need to load the poses obtained from this dataset into COLMAP. While I am aware of [this thread](https://github.com/google-research-datasets/Objectron/issues/39), following it does not yield satisfactory results. Given the convention, one...
Thanks a lot for releasing this great dataset! While parsing the 2D projections of the 3D bounding boxes using the provided [notebook](https://github.com/google-research-datasets/Objectron/blob/master/notebooks/Parse%20Annotations.ipynb), I realized that the annotations are not correct...
Hello, I need to develop an solution to detect and track some kind of boxes like delivery boxes etc. How to start here? I read that there is already data...
Hi, I noticed that in the class method from_transformation in box.py, the transformation itself is thrown away, only the points are kept, upon calling cls(vertices=vertices). That cannot be right? For...
As mentioned in #46, directly fitting a 2D bbox by the projected vertices of 3D bbox can be very inaccurate. For example, the actual 2d bbox in green and the...