Parameters to render SRN dataset

[psguo]

Hi! Could you share some key parameters (listed below) used to render the same Chairs/Cars dataset presented in SRN paper?

1. sphere radius (distance to object)
2. light properties (like how many, direction, intensity, etc.)
3. other relevant parameters if necessary

[ventusff]

This is also what I'm looking for! Especially for the scaling parameters/settings.

Done some tedious research to align shapenet v2 models with original SRN datasets, but there are some weird scaling issues that I can not make right. Need to know the original scaling parameter of SRN chairs_train datasets.

• I'm aware that when the models are imported into blender's scene, their bounding boxes are centered at the origin.

• The alignment only works fine for renderings using the scripts and parameters provided in the repo, but not for original SRN datasets' renderings.

• Below are some example results:

• :heavy_check_mark: Render chairs using parameters written in the scripts & align with shapenet v2 model (pointclouds)

• :x: Align shapenet v2 model (pointclouds) with SRN chairs_train

• :x: Align shapenet v2 model (pointclouds) with SRN chairs_train_2.0

[ventusff]

@psguo As for the sphere radius, it can be infered from the poses. For example, for chairs_train, np.linalg.norm(c2w[...,:3,3], axis=-1) is constant at 1.3, so the sphere radius is 1.3. And similarly for chairs_train_2.0, the sphere radius is 2.0

[ventusff]

UPDATE: I've found how the shapenet models are scaled to render the original SRN datasets!!!!!!!

• Quick answer: after the models are imported, I believe Dr. Sitzmann scales them again so that the maximum value of the bounding boxes size equals 1.

• Now the shapenet models are perfectly aligned with the SRN renderings.

• Detailed steps to make shapenet v2's normalized models to be aligned with SRN's renderings dataset:

  • ('model' stands for vertices or pointclouds of the model)
  • First, offset the model, so that the center of the bounding box is at the origin. This could be done using the model_normalized.json provided in the shapenet v2 dataset, with: model = model + (centroid - center) / norm(diag), where:
    • centroid stands for the mean point of the model's vertices, and can be directly read from the json
    • diag stands for the diagonal vector of the bounding box and can be calculated with 'max'-'min' from the json
    • center stands for the center of the bounding box, and can be calculated with ('max'+'min')/2 from the json
  • Secondly, rescale the model, so that the max value of the bouding box size equals 1.
    • model = model / ( max(diag) / norm(diag) )
  • Finally, rotate the model, with the left rotation matrix: np.array([ [1, 0, 0], [0, 0, -1], [0, 1, 0] ])

• Below are some example results:

I found it out by tring to think in his situation about how he would scale the models to make the renderings better to train.

[amanikiruga]

For the lighting parameters. I changed them around to get something similar to SRN at least for the cars category:

lamp1 = bpy.data.lamps['Lamp']
lamp1.type = 'SUN'
lamp1.shadow_method = 'NOSHADOW'
lamp1.use_specular = False
lamp1.energy = 1.33
lamp1_obj = bpy.data.objects['Lamp']
lamp1_obj.rotation_euler = (math.radians(90), 0, math.radians(180)) # pointing from the top 

bpy.ops.object.lamp_add(type='SUN')
lamp2 = bpy.data.lamps['Sun']
lamp2.shadow_method = 'NOSHADOW'
lamp2.use_specular = False
lamp2.energy = 0.1
bpy.data.objects['Sun'].rotation_euler = (math.radians(0), 0, 0)

bpy.ops.object.lamp_add(type='SUN')
lamp2 = bpy.data.lamps['Sun.001']
lamp2.shadow_method = 'NOSHADOW'
lamp2.use_specular = False
lamp2.energy = 0.1
bpy.data.objects['Sun.001'].rotation_euler = (math.radians(0), 90, 0)

bpy.ops.object.lamp_add(type='SUN')
lamp2 = bpy.data.lamps['Sun.002']
lamp2.shadow_method = 'NOSHADOW'
lamp2.use_specular = False
lamp2.energy = 0.1
bpy.data.objects['Sun.002'].rotation_euler = (math.radians(0), 180, 0)

bpy.ops.object.lamp_add(type='SUN')
lamp2 = bpy.data.lamps['Sun.003']
lamp2.shadow_method = 'NOSHADOW'
lamp2.use_specular = False
lamp2.energy = 0.1
bpy.data.objects['Sun.003'].rotation_euler = (math.radians(0),270, 0)