mirror of
https://github.com/nerfstudio-project/nerfstudio.git
synced 2026-11-14 20:03:49 +08:00
352 lines
12 KiB
Python
352 lines
12 KiB
Python
# Copyright 2022 The Plenoptix Team. All rights reserved.
|
|
#
|
|
# Licensed under the Apache License, Version 2.0 (the "License");
|
|
# you may not use this file except in compliance with the License.
|
|
# You may obtain a copy of the License at
|
|
#
|
|
# http://www.apache.org/licenses/LICENSE-2.0
|
|
#
|
|
# Unless required by applicable law or agreed to in writing, software
|
|
# distributed under the License is distributed on an "AS IS" BASIS,
|
|
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
|
# See the License for the specific language governing permissions and
|
|
# limitations under the License.
|
|
|
|
"""
|
|
Some ray datastructures.
|
|
"""
|
|
import random
|
|
from dataclasses import dataclass
|
|
from typing import Optional
|
|
|
|
import torch
|
|
from torchtyping import TensorType
|
|
from pyrad.utils.math import Gaussians, conical_frustum_to_gaussian
|
|
|
|
from pyrad.utils.misc import is_not_none
|
|
|
|
|
|
@dataclass
|
|
class Frustums:
|
|
"""Describes region of space as a frustum.
|
|
|
|
Args:
|
|
origins (TensorType[..., 3]): xyz coordinate for ray origin.
|
|
directions (TensorType[..., 3]): Direction of ray.
|
|
frustum_starts (TensorType[..., num_samples, 1]): Where the frustum starts along a ray.
|
|
frustum_ends (TensorType[..., num_samples, 1]): Where the frustum ends along a ray.
|
|
pixel_area (TensorType[..., 1]): Projected area of pixel a distance 1 away from origin.
|
|
"""
|
|
|
|
origins: TensorType[..., 3]
|
|
directions: TensorType[..., 3]
|
|
frustum_starts: TensorType[..., 1]
|
|
frustum_ends: TensorType[..., 1]
|
|
pixel_area: TensorType[..., 1]
|
|
|
|
def get_positions(self) -> TensorType[..., 3]:
|
|
"""Calulates "center" position of frustum. Not weighted by mass.
|
|
|
|
Returns:
|
|
TensorType[..., 3]: xyz positions.
|
|
"""
|
|
return self.origins + self.directions * (self.frustum_starts + self.frustum_ends) / 2
|
|
|
|
def get_gaussian_blob(self) -> Gaussians:
|
|
"""Calculates of guassian approximation of conical frustum.
|
|
|
|
Resturns:
|
|
Gaussians: Conical frustums approximated by gaussian distribution.
|
|
"""
|
|
# Cone radius is set such that the square pixel_area matches the cone area.
|
|
cone_radius = torch.sqrt(self.pixel_area) / 1.7724538509055159 # r = sqrt(pixel_area / pi)
|
|
return conical_frustum_to_gaussian(
|
|
origins=self.origins,
|
|
directions=self.directions,
|
|
starts=self.frustum_starts,
|
|
ends=self.frustum_ends,
|
|
radius=cone_radius,
|
|
)
|
|
|
|
@classmethod
|
|
def get_mock_frustum(cls) -> "Frustums":
|
|
"""Helper function to generate a placeholder frustum.
|
|
|
|
Returns:
|
|
Frustums: A size 1 frustum with meaningless values.
|
|
"""
|
|
return Frustums(
|
|
origins=torch.ones((1, 3)),
|
|
directions=torch.ones((1, 3)),
|
|
frustum_starts=torch.ones((1, 1)),
|
|
frustum_ends=torch.ones((1, 1)),
|
|
pixel_area=torch.ones((1, 1)),
|
|
)
|
|
|
|
def apply_masks(self, mask: TensorType) -> "Frustums":
|
|
"""Use valid_mask to mask samples.
|
|
|
|
Args:
|
|
mask (TensorType): Frustums to keep
|
|
|
|
Returns:
|
|
Frustum: New set of masked frustums.
|
|
"""
|
|
return Frustums(
|
|
origins=self.origins[mask],
|
|
directions=self.directions[mask],
|
|
frustum_starts=self.frustum_starts[mask],
|
|
frustum_ends=self.frustum_ends[mask],
|
|
pixel_area=self.pixel_area[mask],
|
|
)
|
|
|
|
|
|
@dataclass
|
|
class PointSamples:
|
|
"""Samples in space.
|
|
|
|
Args:
|
|
frustims (Frustums): Frustums along ray.
|
|
directions (TensorType[..., 3]): Unit direction vector.
|
|
camera_indices (TensorType[..., 1]): Camera index.
|
|
valid_mask (TensorType[...]): Rays that are valid.
|
|
"""
|
|
|
|
frustums: Frustums
|
|
camera_indices: TensorType[..., 1] = None
|
|
valid_mask: TensorType[...] = None
|
|
|
|
def apply_masks(self) -> "PointSamples":
|
|
"""Use valid_mask to mask samples.
|
|
|
|
Returns:
|
|
PointSamples: New set of masked samples.
|
|
"""
|
|
if is_not_none(self.valid_mask):
|
|
frustums = self.frustums.apply_masks(self.valid_mask)
|
|
camera_indices = (
|
|
self.camera_indices[self.valid_mask] if is_not_none(self.camera_indices) else self.camera_indices
|
|
)
|
|
return PointSamples(
|
|
frustums=frustums,
|
|
camera_indices=camera_indices,
|
|
)
|
|
return PointSamples(
|
|
frustums=self.frustums,
|
|
camera_indices=self.camera_indices,
|
|
)
|
|
|
|
|
|
@dataclass
|
|
class RaySamples:
|
|
"""Samples along a ray
|
|
|
|
Args:
|
|
frustums (Frustums): Frustums along ray.
|
|
camera_indices (TensorType[..., 1]): Camera index.
|
|
valid_mask (TensorType[...]): Rays that are valid.
|
|
bin_starts (TensorType[..., 1]): frustum starts along ray.
|
|
bin_ends (TensorType[..., 1]): frustum ends along ray.
|
|
deltas )TensorType[..., 1]): "width" of each sample.
|
|
"""
|
|
|
|
frustums: TensorType[..., 3]
|
|
camera_indices: TensorType[..., 1] = None
|
|
valid_mask: TensorType[...] = None
|
|
bin_starts: TensorType[..., 1] = None
|
|
bin_ends: TensorType[..., 1] = None
|
|
deltas: TensorType[..., 1] = None
|
|
|
|
def to_point_samples(self) -> PointSamples:
|
|
"""Convert to PointSamples instance and return."""
|
|
# TODO: make this more interpretable
|
|
return PointSamples(
|
|
frustums=self.frustums,
|
|
camera_indices=self.camera_indices,
|
|
valid_mask=self.valid_mask,
|
|
)
|
|
|
|
def get_weights(self, densities: TensorType[..., "num_samples", 1]) -> TensorType[..., "num_samples"]:
|
|
"""Return weights based on predicted densities
|
|
|
|
Args:
|
|
densities (TensorType[..., "num_samples", 1]): Predicted densities for samples along ray
|
|
|
|
Returns:
|
|
TensorType[..., "num_samples"]: Weights for each sample
|
|
"""
|
|
|
|
delta_density = self.deltas * densities[..., 0]
|
|
alphas = 1 - torch.exp(-delta_density)
|
|
|
|
# mip-nerf version of transmittance calculation:
|
|
transmittance = torch.cumsum(delta_density[..., :-1], dim=-1)
|
|
transmittance = torch.cat(
|
|
[torch.zeros((*transmittance.shape[:1], 1)).to(densities.device), transmittance], axis=-1
|
|
)
|
|
transmittance = torch.exp(-transmittance) # [..., "num_samples"]
|
|
|
|
# most nerf codebases do the following:
|
|
# transmittance = torch.cat(
|
|
# [torch.ones((*alphas.shape[:1], 1)).to(densities.device), 1.0 - alphas + 1e-10], dim=-1
|
|
# )
|
|
# transmittance = torch.cumprod(transmittance, dim=-1)[..., :-1] # [..., "num_samples"]
|
|
|
|
weights = alphas * transmittance # [..., "num_samples"]
|
|
|
|
return weights
|
|
|
|
def set_valid_mask(self, valid_mask: TensorType[..., "num_samples"]) -> None:
|
|
"""Sets valid mask"""
|
|
self.valid_mask = valid_mask
|
|
|
|
|
|
@dataclass
|
|
class RayBundle:
|
|
"""A bundle of ray parameters.
|
|
|
|
Args:
|
|
origins (TensorType[..., 3]): Ray origins (XYZ)
|
|
directions (TensorType[..., 3]): Unit ray direction vector
|
|
pixel_area (TensorType[..., 1]): Projected area of pixel a distance 1 away from origin.
|
|
camera_indices (TensorType[..., 1]): Camera indices
|
|
nears (TensorType[...]): Distance along ray to start sampling
|
|
fars (TensorType[...]): Rays Distance along ray to stop sampling
|
|
valid_mask (TensorType[...]): Rays that are valid
|
|
"""
|
|
|
|
origins: TensorType["num_rays", 3]
|
|
directions: TensorType["num_rays", 3]
|
|
pixel_area: TensorType["num_rays", 1]
|
|
camera_indices: Optional[TensorType["num_rays", 1]] = None
|
|
nears: Optional[TensorType["num_rays"]] = None
|
|
fars: Optional[TensorType["num_rays"]] = None
|
|
valid_mask: Optional[TensorType["num_rays"]] = None
|
|
num_rays_per_chunk: int = None
|
|
|
|
def move_to_device(self, device: torch.device) -> None:
|
|
"""Move bundle data to a device.
|
|
|
|
Args:
|
|
device (torch.device): Device to move tensors to.
|
|
"""
|
|
self.origins = self.origins.to(device)
|
|
self.directions = self.directions.to(device)
|
|
if is_not_none(self.camera_indices):
|
|
self.camera_indices = self.camera_indices.to(device)
|
|
|
|
def set_camera_indices(self, camera_index: int) -> None:
|
|
"""Sets all of the the camera indices to a specific camera index.
|
|
|
|
Args:
|
|
camera_index (int): Camera index.
|
|
"""
|
|
self.camera_indices = torch.ones_like(self.origins[..., 0]).long() * camera_index
|
|
|
|
def __len__(self):
|
|
num_rays = torch.numel(self.origins) // self.origins.shape[-1]
|
|
return num_rays
|
|
|
|
def sample(self, num_rays: int) -> "RayBundle":
|
|
"""Returns a RayBundle as a subset of rays.
|
|
|
|
Args:
|
|
num_rays (int): Number of rays in output RayBundle
|
|
|
|
Returns:
|
|
RayBundle: RayBundle with subset of rays.
|
|
"""
|
|
assert num_rays <= len(self)
|
|
indices = random.sample(range(len(self)), k=num_rays)
|
|
return RayBundle(
|
|
origins=self.origins[indices],
|
|
directions=self.directions[indices],
|
|
pixel_area=self.pixel_area[indices],
|
|
camera_indices=self.camera_indices[indices],
|
|
)
|
|
|
|
def get_masked_ray_bundle(self, valid_mask: TensorType) -> "RayBundle":
|
|
"""Return a masked instance of the ray bundle.
|
|
|
|
Args:
|
|
valid_mask (TensorType): Mask of rays to keep.
|
|
|
|
Returns:
|
|
RayBundle: RayBundle of masked rays.
|
|
"""
|
|
return RayBundle(
|
|
origins=self.origins[valid_mask],
|
|
directions=self.directions[valid_mask],
|
|
pixel_area=self.pixel_area[valid_mask],
|
|
camera_indices=self.camera_indices[valid_mask] if is_not_none(self.camera_indices) else None,
|
|
nears=self.nears[valid_mask] if is_not_none(self.nears) else None,
|
|
fars=self.fars[valid_mask] if is_not_none(self.fars) else None,
|
|
valid_mask=self.valid_mask[valid_mask] if is_not_none(self.valid_mask) else None,
|
|
)
|
|
|
|
def get_row_major_sliced_ray_bundle(self, start_idx: int, end_idx: int) -> "RayBundle":
|
|
"""Flattens RayBundle and extracts chunk given start and end indicies.
|
|
|
|
Args:
|
|
start_idx (int): Start index of RayBundle chunk.
|
|
end_idx (int): End index of RayBundle chunk.
|
|
|
|
Returns:
|
|
RayBundle: Flattened RayBundle with end_idx-start_idx rays.
|
|
|
|
"""
|
|
camera_indices = (
|
|
self.camera_indices.view(-1)[start_idx:end_idx] if not isinstance(self.camera_indices, type(None)) else None
|
|
)
|
|
return RayBundle(
|
|
origins=self.origins.view(-1, 3)[start_idx:end_idx],
|
|
directions=self.directions.view(-1, 3)[start_idx:end_idx],
|
|
pixel_area=self.pixel_area.view(-1, 1)[start_idx:end_idx],
|
|
camera_indices=camera_indices,
|
|
)
|
|
|
|
def get_ray_samples(
|
|
self, bin_starts: TensorType["num_rays", "num_samples"], bin_ends: TensorType["num_rays", "num_samples"]
|
|
) -> RaySamples:
|
|
"""Produces samples for each ray by projection points along the ray direction.
|
|
|
|
|
|
Args:
|
|
bin_starts (TensorType["num_rays", "num_samples"]): Distance from origin to start of bin.
|
|
bin_ends (TensorType["num_rays", "num_samples"]): Distance from origin to end of bin.
|
|
|
|
Returns:
|
|
RaySamples: Samples projected along ray.
|
|
"""
|
|
device = self.origins.device
|
|
num_samples = bin_starts.shape[-1]
|
|
|
|
valid_mask = torch.ones((bin_starts.shape), dtype=torch.bool, device=device)
|
|
|
|
dists = bin_ends - bin_starts # [N_rays, N_samples]
|
|
deltas = dists * torch.norm(self.directions[:, None, :], dim=-1)
|
|
|
|
if is_not_none(self.camera_indices):
|
|
camera_indices = self.camera_indices.unsqueeze(1).repeat(1, num_samples)
|
|
else:
|
|
camera_indices = None
|
|
|
|
frustums = Frustums(
|
|
origins=self.origins.unsqueeze(1).repeat(1, num_samples, 1),
|
|
directions=self.directions.unsqueeze(1).repeat(1, num_samples, 1),
|
|
frustum_starts=bin_starts[:, :, None].to(device),
|
|
frustum_ends=bin_ends[:, :, None].to(device),
|
|
pixel_area=self.pixel_area.unsqueeze(1).repeat(1, num_samples, 1).to(device),
|
|
)
|
|
|
|
ray_samples = RaySamples(
|
|
frustums=frustums,
|
|
camera_indices=camera_indices,
|
|
valid_mask=valid_mask,
|
|
bin_starts=bin_starts,
|
|
bin_ends=bin_ends,
|
|
deltas=deltas,
|
|
)
|
|
|
|
return ray_samples
|