Kadir Yilmaz

Results 7 issues of Kadir Yilmaz

I have looked at all issues but I could not find a related one. When I run with loop closure detection enabled, it does not detect any loops. I uploaded...

Hello, I am evaluating ROVIO algorithm in VIO mode. In the paper it is stated that in EuRoC MH_01 data they achieve 0.178m RMSE, and in V2_01 they achieve 0.064...

In the paper, you say that you mask the point cloud similar to MAE but I could not find the details. In MAE image is divided into patches that contain...

I checked and could not find a generative or expand_coordinates flag. Do you provide 3D generative transposed convolution operation that allows creating new possible coordinates as in Minkowski Engine: https://github.com/NVIDIA/MinkowskiEngine/blob/b71caef9b45ab32c02d2c1b5f48f13c1eb5df526/MinkowskiEngine/MinkowskiConvolution.py#L539...

I checked torchsparse.nn.Conv3d and could not find generative or expand_coordinates flag. Do you provide 3D generative transposed convolution operation that allows to create new possible coordinates as in Minkowski Engine:...

enhancement

From my understanding, in the original Spatiotemporal Segmentation paper MinkowskiNet42 (Res16UNet34C) has LAYERS = (2, 3, 4, 6, 2, 2, 2, 2). However, your SparseResUNet42 implementation has LAYERS = (2,...

Hi, I'm interested in using the Aria Synthetic Environments dataset for 3D scene understanding. I was wondering whether you used the provided semidense_points.csv.gz files as point clouds in your Sonata...