George Tang

Consistently Low Acc for Jester Pretrained models

1

Hi, The pretrained Jester models give around 50% acc at best. I tried MobileNetV2, MobileNet, and ShuffleNet. Any tips? Thanks

Bring back QuaternionCoeffOrder

1

## 🚀 Feature Bring back QuaternionCoeffOrder ## Motivation It was pretty useful to have conversions between XYZW and WXYZ for example for parsing files and converting to kornia and back...

camera distance question

2

What camera distance should I set render to get the original image, assuming I set height and width to be the same as the original image and leave all other...

Poor performance on duplicate objects

1

Hello! Really good work. I was benchmarking your method wrt to Replica (i set the batch size to 4096 and segment loss to 0.75 as they did in Panopli; i...

Hi, I might have missed it, but where can I find the individual performance of the replica and scannet scenes? Thanks!

Issue with training

1

Hello, thank you for this great work! for this line running on an itw dataset: loss_semantics = (self.loss_semantics(output_semantics, probs) * confs).mean() gives the error: RuntimeError: 0D or 1D target tensor...

DepthRenderer method='median' is not differentiable

1

https://github.com/nerfstudio-project/nerfstudio/blob/702886b213a5942b64250b3c4dc632e62237a511/nerfstudio/model_components/renderers.py#L330 requires_grad=False while for expected its True Seems like it will create a lot of "why is this not learning issues" downstream. Perhaps an improvement would be to raise a...