eddienewton

I was able to get it working by doing the following: ``` isNanMask = torch.isnan(filtered_cost_volume) filtered_cost_volume[isNanMask] = 0.0 ``` From what I've seen, if a value is NaN, the entire...

@callmeray that's a good idea. FYI, I tested PointMVS with my datasets again. I also had to add the following to the eval_file_logger file: ``` #ensure prob does not have...

@tejaskhot I believe I’m using a P100 with 16GB ram. Are you sure you’re running R-MVSNet and not the older MVSNet? The older version will have problems with memory. I’m...

@YoYo000 thanks for the clarification and makes sense. I wonder if some of the single-image depth refinement algorithms might mimic your refinement technique? For your depth refinement, you’re getting about...

@YoYo000 regarding fusible, I'll post my code this upcoming week. Basically, just going to update the depthfusion.py code to create the normals. Regarding variation refinement, I was trying to test...

@YoYo000 Thanks for the answer. I might be doing the refinement wrong. In my code based off the paper, a gain of 10 is unstable. Was there any data normalization...

@pmoulon excellent and thanks for the quick reply. I was able to get the geometric filter working by adding dummy values for orientation and scale. I also used this code...

@os-gabe looking at the code in function `VoxelDownSampleAndTrace`, the trace matrix always has 8 rows because the trace represents a cube (8 vertices). From what I can discern, the column...

@os-gabe thanks for this! Looks pretty useful actually. I might have to borrow it :)

Hi @raphaelsulzer, thanks for the insight. I got `feat` to work with the colmap input, and was able to run dgnn. When I ran dgnn, I had to disable the...