Closed fuy34 closed 3 years ago
Hi,
(1) view weight is used to set different weights for different source images since some pixels may be occluded in some images but not occluded in the others, the idea is widely used in traditional methods (COLMAP, ACMM) and also used in learning-based methods (PVSNet, PVA-MVSNet) (2) feature weight descirbes the similarity, so similar pixels should have higher weight (3) as explained in supplementary sec 1, along the depth dimension, different pixels have different depth hypotheses. So we use a depth weight to balanced their contribution (if the difference is too large, then the contribution is small)
Thank you. These are very helpful!
Hi,
Thank you for releasing the code. I really like this work, and I am trying to understand the code. Here are a few questions.
feature_weight
,depth_weight
, andview_weight
inpatchmatch.py
?feature_weight
andview_weight
seem to be learnable weights given the similarity between center pixel feature and neighbor's feature andref_feature
andsrc_feature
, respectively. Shall we expect the higher weight of similar pixels or opposite?depth_weight
offers higher weights for pixels with similar depth to the center pixel. But why is this needed for the evaluation process?depth_internal_scale
related to theR_k
in the paper? If yes, may I ask what the relationship is?score
inpatchmatch.py
(line 197), why shall we take its exponential after softmax?Please excuse me for the long list. Looking forward to learning more about your work.