3DTopia / OpenLRM

An open-source impl. of Large Reconstruction Models
Apache License 2.0
976 stars 56 forks source link

Hello, I am very interested in your research and also feel that it is an excellent paper.I have a few questions about Triplane. #49

Open bjy12 opened 5 months ago

bjy12 commented 5 months ago

According to the paper, after passing the image through the Encoder, three feature maps of size 32x32 are obtained. After upsampling, the feature map size is 64x64, and PointFeatures are obtained through the Triplane Decoder. I would like to know what determines the number of PointFeatures input into the MLP and what the image size is after rendering.