Zeeshan Khan Suri

Would you please be kind enough to share your quantitative results for the ResNet18 backbone Depth model with velocity supervision? Thank you

How to interpret the reconstructed ray?

2

https://github.com/TRI-ML/packnet-sfm/blob/2698f1fb27785275ef847f3dbbd550cf8fff1799/packnet_sfm/geometry/camera.py#L132-L138 How to interpret the output of the reconstruct function which lifts the depthmap onto 3D using inverse intrinsic matrix? I see that it outputs a ray of size [Bx3xwxh]....

resolves #319

RuntimeError: Input type (c10::Half) and bias type (float) should be the same

3

Error when trying to run training ```bash File "/dinov2/dinov2/layers/patch_embed.py", line 75, in forward x = self.proj(x) # B C H W File "/dinov2/dinov2/models/vision_transformer.py", line 211, in prepare_tokens_with_masks x = self.patch_embed(x)...

Unable to replicate downstream depth result on KITTI

4

I evaluate the pretrained dinov2 with different decoder heads on KITTI Eigen Split in order to replicate the paper's numbers. I found the results much worse. Here's what I did....

RandomOrder transform now accepts torch.Tensor and works well with torch.seed

3

Changed the `RandomOrder `transform to use `torch.randperm` and thus make it Scriptable

Has anyone compared this library with [Pytorch3D](https://pytorch3d.readthedocs.io/en/latest/modules/transforms.html). I'm wondering what makes lietorch better? The accompanying paper compares with Pytorch though.

Dataset License?

1

Congrats on the remarkable work. The repo mentions MIT License. Is the dataset also published under the same?

Dear authors, Great work. Please add license. Please also check for and respect licenses from which this repo was derived from ( pixelNeRF, monodepth2). Thanks