YANG-SOBER comments

Results 4 comments of


                                            YANG-SOBER

Why is there a big gap between the reproducing results and the paper results?

Hi Yikang, thanks for your work, I have tried your **released dtu checkpoints** and updated fusion parameters of **gipuma** on the **DTU evaluation set**, the results are **0.3603** (accuracy), **0.2714**...

Why is there a big gap between the reproducing results and the paper results?

> > Hi Yikang, thanks for your work, I have tried your **released dtu checkpoints** and updated fusion parameters of **gipuma** on the **DTU evaluation set**, the results are **0.3603**...

Why is there a big gap between the reproducing results and the paper results?

> > > > Hi Yikang, thanks for your work, I have tried your **released dtu checkpoints** and updated fusion parameters of **gipuma** on the **DTU evaluation set**, the results...

The evaluation results on DTU evaluation set are different between paper and released checkpoints

After set the `align_corners=True` in the `F.grid_sample()`, the result is 0.3685 (acc) and 0.2785 (comp), the other difference will be attributed to the gipuma (fusible). The compilation of which is...