brownvc / deep-synth

Public code release for our SIGGRAPH 2018 paper "Deep Convolutional Priors for Indoor Scene Synthesis"

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Render from specific camera view

zcoo opened this issue · comments

I want to render from a perspective view rather than an orthographic view, could you give an example how to write the parameters? Just like the orthographic view you show below. Sorry that I do not find that in "sstk".
Thank you!

If you want to render from specific camera view (embedded in generated .json files) add the argument --use_scene_camera orthographic

This assumes the .json file contains a block similar to the example below:

"camera": {

"orthographic": {

"left": 29.300252109682454,

"right": 35.35025210968245,

"bottom": 33.97043045231174,

"top": 40.020430452311736,

"far": 2.199999939650297,

"near": 6.749999939650297

}

}