SparseNeuS_demo_v1/confs/one2345_lod0_val_demo.conf

# - for the lod1 geometry network, using adaptive cost for sparse cost regularization network
#- for lod1 rendering network, using depth-adaptive render

general {

  base_exp_dir = exp/lod0 # !!! where you store the results and checkpoints to be used
  recording = [
    ./,
    ./data
    ./ops
    ./models
    ./loss
  ]
}

dataset {
  trainpath = ../
  valpath = ../ # !!! where you store the validation data
  testpath = ../

  imgScale_train = 1.0
  imgScale_test = 1.0
  nviews = 5
  clean_image = True
  importance_sample = True
  test_ref_views = [23]

  # test dataset
  test_n_views = 2
  test_img_wh = [256, 256]
  test_clip_wh = [0, 0]
  test_scan_id = scan110
  train_img_idx = [49, 50, 52, 53, 54, 56, 58] #[21, 22, 23, 24, 25]  #
  test_img_idx = [51, 55, 57]  #[32, 33, 34]  #

  test_dir_comment = train
}

train {
  learning_rate = 2e-4
  learning_rate_milestone = [100000, 150000, 200000]
  learning_rate_factor = 0.5
  end_iter = 200000
  save_freq = 5000
  val_freq = 1
  val_mesh_freq = 1
  report_freq = 100

  N_rays = 512

  validate_resolution_level = 4
  anneal_start = 0
  anneal_end = 25000
  anneal_start_lod1 = 0
  anneal_end_lod1 = 15000

  use_white_bkgd = True

  # Loss
  # ! for training the lod1 network, don't use this regularization in first 10k steps; then use the regularization
  sdf_igr_weight = 0.1
  sdf_sparse_weight = 0.02  # 0.002 for lod1 network;  0.02 for lod0 network
  sdf_decay_param = 100   # cannot be too large, which decide the tsdf range
  fg_bg_weight = 0.01  # first 0.01
  bg_ratio = 0.3

  if_fix_lod0_networks = False
}

model {
  num_lods = 1

  sdf_network_lod0 {
    lod = 0,
    ch_in = 56,  # the channel num of fused pyramid features
    voxel_size = 0.02105263,  # 0.02083333, should be 2/95
    vol_dims = [96, 96, 96],
    hidden_dim = 128,
    cost_type = variance_mean
    d_pyramid_feature_compress = 16,
    regnet_d_out = 16,
    num_sdf_layers = 4,
    # position embedding
    multires = 6
  }


  sdf_network_lod1 {
    lod = 1,
    ch_in = 56,  # the channel num of fused pyramid features
    voxel_size = 0.0104712, #0.01041667, should be 2/191
    vol_dims = [192, 192, 192],
    hidden_dim = 128,
    cost_type = variance_mean
    d_pyramid_feature_compress = 8,
    regnet_d_out = 16,
    num_sdf_layers = 4,

    # position embedding
    multires = 6
  }


  variance_network {
    init_val = 0.2
  }

  variance_network_lod1 {
    init_val = 0.2
  }

  rendering_network {
    in_geometry_feat_ch = 16
    in_rendering_feat_ch = 56
    anti_alias_pooling = True
  }

  rendering_network_lod1 {
    in_geometry_feat_ch = 16 # default 8
    in_rendering_feat_ch = 56
    anti_alias_pooling = True

  }


  trainer {
    n_samples_lod0 = 64
    n_importance_lod0 = 64
    n_samples_lod1 = 64
    n_importance_lod1 = 64
    n_outside = 0  # 128 if render_outside_uniform_sampling
    perturb = 1.0
    alpha_type = div
  }
}