mirror of
https://github.com/nerfstudio-project/nerfstudio.git
synced 2026-11-22 07:35:26 +08:00
misc proposal network modifications (#578)
* misc improvements * cleanup * remove distortion * dist loss * only dist changed now * changes * remove comment
This commit is contained in:
1 parent
5bc011e5fa
commit
81fa5f9ba5
7 files changed
+100
-28
No files matched your search
@@ -34,10 +34,9 @@ from nerfactory.fields.density_field import DensityField
|
||||
from nerfactory.fields.modules.field_heads import FieldHeadNames
|
||||
from nerfactory.fields.modules.spatial_distortions import SceneContraction
|
||||
from nerfactory.models.base import Model, ModelConfig
|
||||
from nerfactory.models.modules.ray_losses import distortion_loss
|
||||
from nerfactory.models.modules.ray_sampler import ProposalNetworkSampler
|
||||
from nerfactory.models.modules.scene_colliders import NearFarCollider
|
||||
from nerfactory.optimizers.loss import MSELoss, interlevel_loss
|
||||
from nerfactory.optimizers.loss import MSELoss, distortion_loss, interlevel_loss
|
||||
from nerfactory.renderers.renderers import (
|
||||
AccumulationRenderer,
|
||||
DepthRenderer,
|
||||
@@ -62,7 +61,7 @@ class ProposalModelConfig(ModelConfig):
|
||||
"""How far along the ray to stop sampling."""
|
||||
randomize_background: bool = True
|
||||
"""Whether to randomize the background color."""
|
||||
num_proposal_samples_per_ray: int = 64
|
||||
num_proposal_samples_per_ray: Tuple[int] = (64,)
|
||||
"""Number of samples per ray for the proposal network."""
|
||||
num_nerf_samples_per_ray: int = 64
|
||||
"""Number of samples per ray for the nerf network."""
|
||||
@@ -72,16 +71,20 @@ class ProposalModelConfig(ModelConfig):
|
||||
"""Use the same proposal network. Otherwise use different ones."""
|
||||
interlevel_loss_mult: float = 1.0
|
||||
"""Proposal loss multiplier."""
|
||||
distortion_loss_mult: float = 0.01
|
||||
distortion_loss_mult: float = 0.001
|
||||
"""Distortion loss multiplier."""
|
||||
use_appearance_conditioning: bool = True
|
||||
"""Whether to use appearance conditioning."""
|
||||
use_proposal_weight_anneal: bool = True
|
||||
"""Whether to use proposal weight annealing."""
|
||||
use_average_appearance_embedding: bool = True
|
||||
"""Whether to use average appearance embedding or zeros for inference."""
|
||||
proposal_weights_anneal_slope: float = 10.0
|
||||
"""Slope of the annealing function for the proposal weights."""
|
||||
proposal_weights_anneal_max_num_iters: int = 1000
|
||||
"""Max num iterations for the annealing function."""
|
||||
use_single_jitter: bool = False
|
||||
"""Whether use single jitter or not for first proposal network."""
|
||||
|
||||
|
||||
class ProposalModel(Model):
|
||||
@@ -102,7 +105,10 @@ class ProposalModel(Model):
|
||||
# Fields
|
||||
if self.config.use_appearance_conditioning:
|
||||
self.field = TCNNCompoundField(
|
||||
self.scene_bounds.aabb, spatial_distortion=scene_contraction, num_images=self.num_train_data
|
||||
self.scene_bounds.aabb,
|
||||
spatial_distortion=scene_contraction,
|
||||
num_images=self.num_train_data,
|
||||
use_average_appearance_embedding=self.config.use_average_appearance_embedding,
|
||||
)
|
||||
else:
|
||||
raise NotImplementedError("Only appearance conditioning is supported.")
|
||||
@@ -127,6 +133,7 @@ class ProposalModel(Model):
|
||||
num_nerf_samples_per_ray=self.config.num_nerf_samples_per_ray,
|
||||
num_proposal_samples_per_ray=self.config.num_proposal_samples_per_ray,
|
||||
num_proposal_network_iterations=self.config.num_proposal_network_iterations,
|
||||
single_jitter=self.config.use_single_jitter,
|
||||
)
|
||||
|
||||
# renderers
|
||||
@@ -197,6 +204,7 @@ class ProposalModel(Model):
|
||||
metrics_dict = {}
|
||||
image = batch["image"].to(self.device)
|
||||
metrics_dict["psnr"] = self.psnr(outputs["rgb"], image)
|
||||
metrics_dict["distortion"] = distortion_loss(outputs["weights_list"], outputs["ray_samples_list"])
|
||||
return metrics_dict
|
||||
|
||||
def get_loss_dict(self, outputs, batch, metrics_dict=None):
|
||||
@@ -206,13 +214,7 @@ class ProposalModel(Model):
|
||||
loss_dict["interlevel_loss"] = self.config.interlevel_loss_mult * interlevel_loss(
|
||||
outputs["weights_list"], outputs["ray_samples_list"]
|
||||
)
|
||||
loss_dict["distortion_loss"] = self.config.distortion_loss_mult * torch.mean(
|
||||
distortion_loss(
|
||||
outputs["ray_samples_list"][-1],
|
||||
weights=outputs["weights_list"][-1],
|
||||
scale_factor=1.0 / (self.config.far_plane - self.config.near_plane),
|
||||
)
|
||||
)
|
||||
loss_dict["distortion_loss"] = self.config.distortion_loss_mult * metrics_dict["distortion"]
|
||||
return loss_dict
|
||||
|
||||
def get_image_metrics_and_images(
|
||||
|
||||
Reference in new issue
Block a user