Indoor-SfMLearner

Indoor-SfMLearner copied to clipboard

collapse issues when training

3

Hi, I try to train my model without superpixel planar regularization. But it's likely that the training collapses and the output is all-zero. Have you faced and managed to solve...

gengyuanmax

Hi, is there a chance that someone can share the raw nyuv2 dataset resource? It seems the download link from nyuv2 website may be invalid today? [nyu-v2](https://cs.nyu.edu/~silberman/datasets/nyu_depth_v2.html#raw_parts). And I suspect...

WEIIEW97

shocked by the initial val result

21

Before training, the function val evaluate the initial model on the NYUv2 test set, and the result is abs_rel | sq_rel | rmse | rmse_log | a1 | a2 |...

myalos

Why assume the patch have the same depth?

6

It seems that the keypoints extracted by DSO mainly distribute around the edge of objects, thus the depth variance may be large, so I'm wondering if the same depth assumption...

ghost