PRNet-Depth-Generation icon indicating copy to clipboard operation
PRNet-Depth-Generation copied to clipboard

A implementaion of depth generation based on [PRNet](https://github.com/YadiraF/PRNet), which was used in the paper ***Exploiting Temporal and Depth Information for Multi-frame Face Anti-spoofing***

Results 9 PRNet-Depth-Generation issues
Sort by recently updated
recently updated
newest added

nice, it is a good job.but,when i run it ,some quetions occers.as shown below: ![Uploading 2.png…]() ![1](https://user-images.githubusercontent.com/31872115/88537503-473ebe00-d040-11ea-8f47-8795875b4b19.png)

![image](https://user-images.githubusercontent.com/76394313/127089290-60ba1e91-d621-49d0-8a15-c3fbb6d4aa79.png) I had this problem. There is enough GPU memory. Has anyone solved this problem?

Thank you for your job! When I try to generate a pose face image, the following image appears: ![DELSU3((Z1I8D1TBY(R0}53](https://user-images.githubusercontent.com/56471955/89708816-1437eb00-d9ad-11ea-8f82-bc8c709904bc.png) How to solve the black area of depth map?

Nice. You have done a great job. But I have a question about the depth map. In the original paper, the values of depth map are normalized to [0:1]. But,...

![image](https://user-images.githubusercontent.com/25198185/97962311-d7cf2c00-1def-11eb-985f-1fc7c9254d99.png) 裁剪的人脸宽高不一致,请问size为什么用二者的平均,不是直接用宽和高?

The passed save_path is not a valid checkpoint: ./Data/net-data/256_256_resfcn256_weight

The thing is dosn't matter you put replay image, printed photo or mask photo, it still generates depth model with no difference from real face

Hello! I would really like to try the approach that you described in your article. But at first glance, the code presented on the repository is a slightly modified official...

The result generated from your code is different from PRNet souce code https://github.com/YadiraF/PRNet) I just test trump.jpg, the result of depth image is difficult.