xiemeilong

``` private static LocalDate getLocalDate(ResultSet r, int i) throws SQLException { Timestamp ts = r.getTimestamp(i); return ts == null ? null : ts.toLocalDateTime().toLocalDate(); } ``` ParseException throwed. `Caused by: java.text.ParseException:...

Add support of spatial data types

6

Will pony support spatial data types?

When I called the refine_keypoints_from_db function on a dataset of over 9,000 images, my server ran out of memory (384 GB) and had to be restarted. Is this normal behavior...

Why is there such a big difference in the results between the models trained with nerfacto and neus-facto?

23

**Describe the bug** `ns-train neus-facto --pipeline.model.sdf-field.inside-outside False --pipeline.model.sdf-field.bias 0.3 --pipeline.model.background-model grid --pipeline.model.eikonal-loss-mult 0.0001 nerfstudio-data --data data/nerfstudio/tangtousimple`   But the result generated through the under command is rendered almost identical...

The more GPUs, the slower the training speed

4

**Describe the bug** 4 4090 GPUs , train-num-rays-per-batch 512 eval-num-rays-per-batch 128 ``` ns-train bakedangelo --machine.num-gpus 4 --pipeline.model.level-init 8 --trainer.steps-per-eval-image 5000 --pipeline.datamanager.train-num-rays-per-batch 512 --pipeline.datamanager.eval-num-rays-per-batch 128 --pipeline.model.sdf-field.use-appearance-embedding True --pipeline.model.background-color white --pipeline.model.sdf-field.bias 0.1...

Bad quality using official Neuralangelo compared to sdfstudio Implementation

8

I obtained very good results using neuralangelo in sdfstudio, but for the same image data, the results obtained using the official neuralangelo implementation were like this.  results using neuralangelo...

Can this well-performing, initialization-free BA be used in Colmap?

1

The solver achieves state-of-the-art results in terms of speed and accuracy. [povar](https://github.com/tum-vision/povar)