_target_: sam3d_objects.model.backbone.tdfy_dit.models.structured_latent_vae.decoder_gs.SLatGaussianDecoderTdfyWrapper
resolution: 64
model_channels: 768
latent_channels: 8
num_blocks: 12
num_heads: 12
mlp_ratio: 4
attn_mode: swin
window_size: 8
representation_config:
  lr:
    _xyz: 1.0
    _features_dc: 1.0
    _opacity: 1.0
    _scaling: 1.0
    _rotation: 0.1
  perturb_offset: true
  voxel_size: 1.5
  num_gaussians: 32
  2d_filter_kernel_size: 0.1
  3d_filter_kernel_size: 0.0009
  scaling_bias: 0.004
  opacity_bias: 0.1
  scaling_activation: softplus
use_fp16: true