Yingji Zhong

Difference between GCN_APPRO and GCN_APPRO_MIX

1

It seems that the paper used GCN_APPRO(two sample layer), while the code uses GCN_APPRO_MIX, what is the difference between two methods, does the ultimate result varies a lot?

Hi, I'm training oim loss with resnet50, with batchsize of 1, does it matter with the different batchsize? Moreover, what is the value that oim loss could converge to? I...

Only use the rendering but not raymarching

2

Thanks for the great work! I have several questions about how to use nerfacc, 1. I notice that estimator.sampling(...) returns t_starts of (n_samples, ). Does it mean that all rays...

Hi, thanks for the great work! I tried the grounded sam demo, by using `python grounded_sam_demo.py xxx`. It seems that the output dirs has a mask.json file which only contains...

About Replica dataset

1

Hi, thanks for the great work. I am reading the code, and wondering if the models & data processing of Replica will be available. Thank you.