# Copyright 2022 the Regents of the University of California, Nerfstudio Team and contributors. 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.
"""Data parser for blender dataset"""
from __future__ import annotations
from dataclasses import dataclass, field
from pathlib import Path
from typing import Optional, Type
import imageio
import numpy as np
import open3d as o3d
import torch
from nerfstudio.cameras.cameras import Cameras, CameraType
from nerfstudio.data.dataparsers.base_dataparser import DataParser, DataParserConfig, DataparserOutputs
from nerfstudio.data.scene_box import SceneBox
from nerfstudio.utils.colors import get_color
from nerfstudio.utils.io import load_from_json
[docs]@dataclass
class BlenderDataParserConfig(DataParserConfig):
"""Blender dataset parser config"""
_target: Type = field(default_factory=lambda: Blender)
"""target class to instantiate"""
data: Path = Path("data/blender/lego")
"""Directory specifying location of data."""
scale_factor: float = 1.0
"""How much to scale the camera origins by."""
alpha_color: Optional[str] = "white"
"""alpha color of background, when set to None, InputDataset that consumes DataparserOutputs will not attempt
to blend with alpha_colors using image's alpha channel data. Thus rgba image will be directly used in training. """
ply_path: Optional[Path] = None
"""Path to PLY file to load 3D points from, defined relative to the dataset directory. This is helpful for
Gaussian splatting and generally unused otherwise. If `None`, points are initialized randomly."""
[docs]@dataclass
class Blender(DataParser):
"""Blender Dataset
Some of this code comes from https://github.com/yenchenlin/nerf-pytorch/blob/master/load_blender.py#L37.
"""
config: BlenderDataParserConfig
def __init__(self, config: BlenderDataParserConfig):
super().__init__(config=config)
self.data: Path = config.data
self.scale_factor: float = config.scale_factor
self.alpha_color = config.alpha_color
if self.alpha_color is not None:
self.alpha_color_tensor = get_color(self.alpha_color)
else:
self.alpha_color_tensor = None
def _generate_dataparser_outputs(self, split="train"):
meta = load_from_json(self.data / f"transforms_{split}.json")
image_filenames = []
poses = []
for frame in meta["frames"]:
fname = self.data / Path(frame["file_path"].replace("./", "") + ".png")
image_filenames.append(fname)
poses.append(np.array(frame["transform_matrix"]))
poses = np.array(poses).astype(np.float32)
img_0 = imageio.v2.imread(image_filenames[0])
image_height, image_width = img_0.shape[:2]
camera_angle_x = float(meta["camera_angle_x"])
focal_length = 0.5 * image_width / np.tan(0.5 * camera_angle_x)
cx = image_width / 2.0
cy = image_height / 2.0
camera_to_world = torch.from_numpy(poses[:, :3]) # camera to world transform
# in x,y,z order
camera_to_world[..., 3] *= self.scale_factor
scene_box = SceneBox(aabb=torch.tensor([[-1.5, -1.5, -1.5], [1.5, 1.5, 1.5]], dtype=torch.float32))
cameras = Cameras(
camera_to_worlds=camera_to_world,
fx=focal_length,
fy=focal_length,
cx=cx,
cy=cy,
camera_type=CameraType.PERSPECTIVE,
)
metadata = {}
if self.config.ply_path is not None:
metadata.update(self._load_3D_points(self.config.data / self.config.ply_path))
dataparser_outputs = DataparserOutputs(
image_filenames=image_filenames,
cameras=cameras,
alpha_color=self.alpha_color_tensor,
scene_box=scene_box,
dataparser_scale=self.scale_factor,
metadata=metadata,
)
return dataparser_outputs
def _load_3D_points(self, ply_file_path: Path):
pcd = o3d.io.read_point_cloud(str(ply_file_path))
points3D = torch.from_numpy(np.asarray(pcd.points, dtype=np.float32) * self.config.scale_factor)
points3D_rgb = torch.from_numpy((np.asarray(pcd.colors) * 255).astype(np.uint8))
out = {
"points3D_xyz": points3D,
"points3D_rgb": points3D_rgb,
}
return out