Haoyu Guo

我们是用单张12G显卡训练的。你的pytorch版本是多少？建议使用1.6，参考：#8

Hi @keloee I met the same problem, have you solved it?

Hi, Thanks for your interest! I'm not sure what the reason is. Do you use the conda envrionment file we provide? And is this bug reproducible?

Hi! @qihangGH I met the same problem, test views are of much lower PSNR than training views. Have you solved it?

> @ghy0324 No, I haven't. @qihangGH @apchenstu I found that it works after modifying `fea2denseAct` in config file from `softplus` to `relu`, but I haven't figured out the reason.

> Thank you for your interest in our dataset! Does #37 answer your question (baseline between the cameras), or are you looking for the XYZ and rotation of camera for...

Congratulations on the acceptance to ECCV 2022! Looking forward to your code!

@Pamogar @Charlescai123 @IvanGarcia7 Hi! I also have this requirement, have you successfully run inference on your point cloud?

> Has the problem been solved, bros? @tangze5258 You may refer to [this version](https://github.com/cvg/Mask3D).

> My apologies for the delay, I tried to dig this out but it has proven difficult to get this information since it is stored in some proprietary Unreal format....