黎自鸿 comments

Results 9 comments of


                                            黎自鸿

测试数据太大，能不能提供一部分（The test data is too large, can you provide part of it）

请问是怎么组织的哈，我下的dtu只有一个文件，但是cfg文件里面测试训练的路径是dtu/dtu2文件，是怎么做的数据处理呢？

Please optimize texture saving so that save_obj_with_mtl is faster than generating the video

Hello,it seems like you do a lot of test .Did you run the train.py?i don,t know how to build filtered_obj_name.json,i wonder if you can give me some guidance,thankyou

How to render image from Objaverse

thank you !!but when i try to run the code in the [a_blender_render.txt],it seems to have some error ,like this : OSError: /home/yw/yw2/LZH/PaperCode/objaverse-xl/objaverse-xl-main/scripts/rendering/4.0/python/lib/python3.10/site-packages/libextern_draco.so: cannot open shared object file: No such...

Finish writing the rendering script ！！！！ Look！！

谢谢！！可以认识一下您吗？感觉您太厉害了！！

could you provide the rendering scripts to evalutate ?

@Costwen 您好，我想问一下您是怎么渲染的图像哈，可以请教一下代码怎么写的吗，被这个问题困扰好久了，希望能交流一下

Train on nerf of stage 1 with custom dataset

@hopeliu20160622 hello,how did you render your datasets with 32 views?Use python code？i am interested in it .！！

Training CUDA Out Of Memory error

@Kev1MSL hello,i am trying to run the training process,but i don't know how to construct the dataset ,can i have a look at the structure of dataset?thank you very much...

No module named 'igl.pyigl'

感谢您的回复！！！对我帮助很大。我在Linux上成功运行了您的代码，并且生成的图片的效果真的很棒。然而我发现在changlog中提到可以将模型导出成obj文件，但是在生成的结果好像没有发现，想问一下如果想导出的结果为obj，需要进行一些什么设置呢

No module named 'igl.pyigl'

谢谢您的答复！我近期又仔细看了一下您放上来的代码，发现代码一直在跑的是coarse阶段，是不是后面的细化阶段的代码是没有在发布的工程里面的呢，还是我得用别的指令去运行呢，