Shuran Song

You can reference the following function to generate your own testing example. ```matlab_code/perpareDataTest.m ``` This function provides an example of how to generate your own testing data without ground truth...

The depth map is saved in a way that it shifts 3 bits to make the depth in PNG format more pleasing to human eyes. Therefore we need to shift...

The images are saved as 16 bit png. I'm not sure whether the line ``` cv::Mat depth_image = cv::imread(filenamePng.c_str(), CV_LOAD_IMAGE_ANYCOLOR | CV_LOAD_IMAGE_ANYDEPTH);``` handled it correctly.

Please check this [issue](https://github.com/shurans/sscnet/issues/16)

.bin file in the test is just an empty volume with a camera pose computed using https://github.com/shurans/sscnet/blob/master/matlab_code/utils/rectify.m, which is different from the demo where the camera pose and volume comes...

@JamesTonG321 You don't need to train in total 400000 iterations some point after 10000 iterations the loss may stop decrease and can take the snapshot and test it to see...

The bigger one contains ground truth volume which can be used for training. The smaller one is empty volume, which is used when you don't have ground truth volume and...

@JamesTonG321 During testing, the network won't use the ground truth volume in the bin data it just uses the camera parameters in the ".bin" file. Therefore it is ok to...

For this project, we didn't use color images. You can generate your own RGB-D images use the [SUNCG toolbox.](https://github.com/shurans/sscnet/#generating-training-data-from-suncg) Here is another [project](http://3dvision.princeton.edu/projects/2016/PBRS/), where you can download many precompute RGB-D...

@lsc19940810 For this project, we didn't use color images. The depth maps are generated with an older version of SUNCG, which has been updated significantly since then. Therefore to get...