Yao Yao
Thanks! One suggestion for improve the accuracy. The disparity of scene flow is relatively large and most stereo pair would have a maximum disp of ~200. In this case if...
The depth-wise pixel is measured by the depth interval. For example, the depth interval of the view is 2.5mm, the GT depth is 100mm, and the estimated depth is 110mm....
The image centering is moved to line 272 in train.py. inference_mem() is a memory-efficient function that, only one copy of the feature volume is kept in the memory during the...
你是用dtu数据集进行训练的吗，有没有对图像大小进行过改变呢
I use 640 x 480 in my training
@eddienewton The variational refinement can significantly reduce the noise level. Another thing is the depth map fusion. In the provided code I use Fusibile for fusion implementation. However, recently I...
> @eddienewton Can you share how you managed to run with `1600x1200x256`? What GPU did you use? I was unable to fit the full resolution in memory even with a...
@eddienewton I think single-image depth refinement can help reduce the noise, however, eventually it looks something like "smoothing" on the depth map. Personally I believe more on the photo-consistency based...
@eddienewton we solve the pixelwise depth gradient independently and the gain is set to 10.0.
@xiaochi97 Have you solved the download problem?