-
Please check the name, according to the 65th line of scannetv2_inst.py
-
I modified `projects/configs/denoise/petrv2_vovnet_gridmask_p4_800x320_dn.py` to generate a config file using ResNet-50DCN as backbone. After training, I got a lower performance compared to the paper:…
-
Hi, I find that there is default setting of `depth_W` and `depth_H` in `options.py`. I would like to ask that if I use NerfingMVS on my custom dataset which has a totally different resolution from Sca…
-
Very cool!
* I think it would cleaner and easier to switch from format to format if the selection of, for example, `ImagenetDataModule` vs `ImagenetFfcvDataModule` should be automatic and/or select…
-
LoFTR uses only **15,300**=153*100 image training pairs from MegaDepth.
While DKM iteratively sample **150,000** pairs each iteration from **10,661,614** total traning pairs in **53** iterations.
-
Hi, I find it hard to understand what is going on with the data chunks generation process in the file below. https://github.com/daveredrum/Pointnet2.ScanNet/blob/f4adc43779aaaefd6138d37183a94185d07188…
-
I tried to train the model on ScanNet v2 dataset, and found out that the dataset loading process does not match with the dataset format.
Here are what I found:
1.
When I extract rgb and depth fi…
-
Hi, thanks for sharing the amazing work!
I am curious about the number of scenes you used for training for the reconstruction task on the Scannet and 7-Scenes datasets . Did you train the model o…
-
**Describe the bug**
Unable to set args for fields of type `Union`, when the field is nested deep within the config tree (I'm trying to add custom configs for the base MLP). I assume it's a mistake w…
-
Thanks for sharing the code.
However, when I run per-scene optimization, CUDA is out of memory even if I set the batch size to 1.
The code is listed below:
```
CUDA_VISIBLE_DEVICES=2,3,4 pyt…