cvg / emap Goto Github PK

Could you please provide details on the performance overhead, required computational resources, and the average time consumption for running the experiments described in your paper? Specifically, I am interested in:

The hardware configuration used (e.g., CPU, GPU, RAM).
The average runtime for each experiment.
Any significant performance bottlenecks encountered.
Thank you.

When trying to download the datasets provided by the huggingface, the .zip files are invalid, i.e., when using python scripts/download_data.py, an error message pops up saying zipfile.BadZipFile: File is not a zip file.

Thanks for sharing your excellent work. Could you please provide the used TT dataset? By the way, would you like to share how you generate the displayed video?

Hello,

Thanks for this amazing work! I have a question about section of Edge Direction in the paper. I think there are two possible directions along the edge, so how to determine the desired one?

Then, I find the function def line_fitting(endpoints). Based on my understanding, two points are finally used to represent the edge, so there is no need to determine its direction. Is my understanding correct?

Thanks for your time and patience.

Regards,
Zhenshan

I have a few questions on your evaluations:

1. For the ABC_NEF dataset, the GT parametric curves have to be shifted and scaled so that they are located at the correct coordinate (see this issue). And since this dataset is a synthetic dataset, the 3D points are unit-less. How do you relate the threshold $\tau$ in millimeters mentioned in your paper to the threshold of the unit-less 3D GT? (In the NEF paper, they set the threshold 0.02, with no unit, as the L2 distance from the reconstructed edge point to the ground truth point.)

2. For generating the 3D GT edges from the DTU dataset, the supp says that the dense point cloud is projected to the images and then cross-comparing these projections with 2D edges observations to mark 3D edges. Are the "cross-comparing" done manually? If not, what strategies/algorithms did you use? In addition, the supp says, (Section B.3) "To ensure accuracy in the ground-truth edge points, we manually set thresholds for each scan and meticulously remove any floating points." What threshold and floating points are you referring to here?

3. For the metrics, what are the definitions of "Accuracy" and "Completeness"? The paper says that it follows the NEF and the LiMAP papers for the metrics but I do not find them from both papers. Maybe it's a typo as I find the definitions in the NEAT paper, Section F of supp. Also, do you have an explicit definition of what an "edge direction consistency" is?

4. In Table 1, are the reported numbers the average of all selected 82 CAD models? Do you use all 50 images per CAD model?

Is this repo support arbitrary mesh as input? What should I do if I want to test new .obj file?
Thanks!