gpcv-liujin / rednet Goto Github PK

请问可以提供一下评价WHU数据集的评价指标的代码吗? 非常感谢

Hello, can you upload the Rednet pdf link?

extrinsic
E00 E01 E02 E03
E10 E11 E12 E13
E20 E21 E22 E23
E30 E31 E32 E33

f(pixel) x0(pixel) y0(pixel)

DEPTH_MIN DEPTH_MAX DEPTH_INTERVAL
IMAGE_INDEX 0 0 0 0 WIDTH HEIGHT

What do 0 0 0 0 mean and how to alter proper digits if replaced by our own data?
Thanks.

Hello, I used viewselection.py to correctly generate viewpair.txt. Other configurations are the same as yours. I also used the Tensorflow1.13.1 version, and the cuda version is correct
However, the following errors occurred when the prediction.py program was run. The errors occurred when the pre training weights were imported

Pre-trained model restored from C:/Users/PC2080ti/Desktop/Mulit-View/jishunping/1/REDNet-master/MODEL_FOLDER/model.ckpt-150000
2022-12-18 18:58:03.486554: E tensorflow/core/grappler/optimizers/dependency_optimizer.cc:704] Iteration = 0, topological sort failed with message: The graph couldn't be sorted in topological order.
2022-12-18 18:58:03.493902: E tensorflow/core/grappler/optimizers/dependency_optimizer.cc:704] Iteration = 1, topological sort failed with message: The graph couldn't be sorted in topological order.

I have been trying to download the WHU dataset but I am not able to reach the website. Is the link provided in your readme is down for some reason?

Do you mind checking the link to the pre-trained model? http://gpcv.whu.edu.cn/data/download/MODEL_FOLDER.zip can not be reached.

您好，请问测试了您的测试数据集，输出了深度图之类的，用什么方法来合成三维点云呢？

请问可以提供一下viewpair.txt文件吗？当我运行viewselection.py时出现了错误

Can you please share the links for pretrained models of your experiments in the paper?

请问生成OSGB模型之后， 照片的采集过程是用什么实现的呢？

Could you please point out why I get the error when I run python .Predict.py:

InvalidArgumentError (see above for traceback): ConcatOp : Dimensions of inputs should match: shape[0] = [1,192,384,16] vs. shape[1] = [1,2688,2688,8]
[[node while/conv_gru1/Gates/concat (defined at C:\Abhi\thesis_pjt\liu2020novel\REDNet-master\network.py:656) ]]

Hi! I downloaded the data using the link mentioned in the readme (13G almost) and tried running the code. I could not reproduce the numbers. Rather my numbers are way off. The training is highly unstable and the loss value is very noisy (not going down rather oscillating). I also tried adding RMVSNet to reproduce the numbers on that but wasn't able to do so. I think there is some issue with the data or data loader for WHU dataset. Could you or anyone please verify if you or they are able to reproduce the numbers using the repo?

The link to the dataset seems to be down. Is it possible to upload the dataset somewhere more stable e.g. Google Drive, OneDrive, etc.?

感谢作者的开源数据和代码，在使用自己数据进行测试时，按照readme中的predict中的格式制作数据，发现作者开源数据中外参中的旋转矩阵全为单位阵，这里不太理解，另外还想问下viewselection.py中输入的view.txt是什么

What software do you use to visualize the point cloud in Fig. 7? It seems that the number of points is huge, how do you visualize all points without crashing?

您好，您文章中公开的数据集:WHU MVS/Stereo Dataset(http://gpcv.whu.edu.cn/data/WHU_MVS_Stereo_dataset.html)，
其中用于生产深度图和视差图的模型数据能否公开，现在网上公开Mesh模型的数据集少之又少，不利于Mesh处理算法的研究，请问，你们是否有公开部分Mesh模型的计划呢？