search

jiahaopang / crl

Implementation of the paper "Cascade Residual Learning: A Two-stage Convolutional Neural Network for Stereo Matching"
Apache License 2.0
99 stars 30 forks source link

two problems~ #1

Open Lvhhhh opened 7 years ago

Lvhhhh commented 7 years ago

thanks for the codes. the idea that using ResNet to rectify the results is wonderful! i have two problems.

  1. in 'correlation 1d layer', have you try to set the "single_direction" -1 ? due to the samples all have the positive disparity. i do the test and find the result does not achieve expectation.
  2. have you try to generate the 'cost_volume' using caffe? i found it is very hard using caffe. if you do a success trial . Please let me know! Thx~