tnt datasets church demo result is bad.

[qq297110281]

any one try the tnt datasets's church demo? the result (50k iters) is not good.

here is my train paramters:

Training with 1 GPUs. Using random seed 0 Make folder logs/church

• checkpoint:
  • save_epoch: 9999999999
  • save_iter: 20000
  • save_latest_iter: 9999999999
  • save_period: 9999999999
  • strict_resume: True
• cudnn:
  • benchmark: True
  • deterministic: False
• data:
  • name: dummy
  • num_images: None
  • num_workers: 4
  • preload: True
  • readjust:
    • center: [0.0, 0.0, 0.0]
    • scale: 1.0
  • root: datasets/church
  • train:
    • batch_size: 2
    • image_size: [1086, 1960]
    • subset: None
  • type: projects.neuralangelo.data
  • use_multi_epoch_loader: True
  • val:
    • batch_size: 1
    • image_size: [300, 541]
    • max_viz_samples: 16
    • subset: 1
• image_save_iter: 9999999999
• inference_args:
• local_rank: 0
• logdir: logs/church
• logging_iter: 9999999999999
• max_epoch: 9999999999
• max_iter: 500000
• metrics_epoch: None
• metrics_iter: None
• model:
  • appear_embed:
    • dim: 8
    • enabled: False
  • background:
    • enabled: False
    • encoding:
      • levels: 10
      • type: fourier
    • encoding_view:
      • levels: 3
      • type: spherical
    • mlp:
      • activ: relu
      • activ_density: softplus
      • activ_density_params:
      • activ_params:
      • hidden_dim: 256
      • hidden_dim_rgb: 128
      • num_layers: 8
      • num_layers_rgb: 2
      • skip: [4]
      • skip_rgb: []
    • view_dep: True
    • white: False
  • object:
    • rgb:
      • encoding_view:
      • levels: 3
      • type: spherical
      • mlp:
      • activ: relu_
      • activ_params:
      • hidden_dim: 256
      • num_layers: 4
      • skip: []
      • weight_norm: True
      • mode: idr
    • s_var:
      • anneal_end: 0.1
      • init_val: 3.0
    • sdf:
      • encoding:
      • coarse2fine:
        • enabled: True
        • init_active_level: 8
        • step: 5000
      • hashgrid:
        • dict_size: 20
        • dim: 4
        • max_logres: 11
        • min_logres: 5
        • range: [-2, 2]
      • levels: 16
      • type: hashgrid
      • gradient:
      • mode: numerical
      • taps: 4
      • mlp:
      • activ: softplus
      • activ_params:
        • beta: 100
      • geometric_init: True
      • hidden_dim: 256
      • inside_out: True
      • num_layers: 1
      • out_bias: 0.5
      • skip: []
      • weight_norm: True
  • render:
    • num_sample_hierarchy: 4
    • num_samples:
      • background: 0
      • coarse: 64
      • fine: 16
    • rand_rays: 512
    • stratified: True
  • type: projects.neuralangelo.model
• nvtx_profile: False
• optim:
  • fused_opt: False
  • params:
    • lr: 0.001
    • weight_decay: 0.01
  • sched:
    • gamma: 10.0
    • iteration_mode: True
    • step_size: 9999999999
    • two_steps: [300000, 400000]
    • type: two_steps_with_warmup
    • warm_up_end: 5000
  • type: AdamW
• pretrained_weight: None
• source_filename: projects/neuralangelo/configs/custom/church.yaml
• speed_benchmark: False
• test_data:
  • name: dummy
  • num_workers: 0
  • test:
    • batch_size: 1
    • is_lmdb: False
    • roots: None
  • type: imaginaire.datasets.images
• timeout_period: 9999999
• trainer:
  • amp_config:
    • backoff_factor: 0.5
    • enabled: False
    • growth_factor: 2.0
    • growth_interval: 2000
    • init_scale: 65536.0
  • ddp_config:
    • find_unused_parameters: False
    • static_graph: True
  • depth_vis_scale: 0.5
  • ema_config:
    • beta: 0.9999
    • enabled: False
    • load_ema_checkpoint: False
    • start_iteration: 0
  • grad_accum_iter: 1
  • image_to_tensorboard: False
  • init:
    • gain: None
    • type: none
  • loss_weight:
    • curvature: 0.0005
    • eikonal: 0.1
    • render: 1.0
  • type: projects.neuralangelo.trainer
• validation_iter: 5000
• wandb_image_iter: 10000
• wandb_scalar_iter: 100 cudnn benchmark: True cudnn deterministic: False Setup trainer. Using random seed 0 model parameter count: 53,029,160 Initialize model weights using type: none, gain: None Using random seed 0 Allow TensorFloat32 operations on supported devices

[mli0603]

Hi @qq297110281

The Church scene does not come with the poses due to data corruption from TnT. Therefore, we did not report Church scene results for reproducibility. Nonetheless, I also experimented with the Church scene and I have found that COLMAP simply cannot recover the correct trajectory due to similarities/ambiguities of the chairs. Many poses end up opposite of where cameras are looking at. I would inspect your colmap results before running the Church scene.

Let us know if you have made progress!

[hlpan]

model: appear_embed: dim: 8 enabled: False

maybe you should enable the appearence embeding by setting:

model: appear_embed: dim: 32 enabled: True