mirror of
https://github.com/nerfstudio-project/nerfstudio.git
synced 2026-11-14 20:03:49 +08:00
113 lines
3.7 KiB
Python
113 lines
3.7 KiB
Python
# Copyright 2022 The Nerfstudio 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.
|
|
|
|
"""Data parser for blender dataset"""
|
|
from __future__ import annotations
|
|
|
|
from dataclasses import dataclass, field
|
|
from pathlib import Path
|
|
from typing import Type
|
|
|
|
import imageio
|
|
import numpy as np
|
|
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
|
|
|
|
|
|
@dataclass
|
|
class DNeRFDataParserConfig(DataParserConfig):
|
|
"""D-NeRF dataset parser config"""
|
|
|
|
_target: Type = field(default_factory=lambda: DNeRF)
|
|
"""target class to instantiate"""
|
|
data: Path = Path("data/dnerf/lego")
|
|
"""Directory specifying location of data."""
|
|
scale_factor: float = 1.0
|
|
"""How much to scale the camera origins by."""
|
|
alpha_color: str = "white"
|
|
"""alpha color of background"""
|
|
|
|
|
|
@dataclass
|
|
class DNeRF(DataParser):
|
|
"""DNeRF Dataset"""
|
|
|
|
config: DNeRFDataParserConfig
|
|
|
|
def __init__(self, config: DNeRFDataParserConfig):
|
|
super().__init__(config=config)
|
|
self.data: Path = config.data
|
|
self.scale_factor: float = config.scale_factor
|
|
self.alpha_color = config.alpha_color
|
|
|
|
def _generate_dataparser_outputs(self, split="train"):
|
|
if self.alpha_color is not None:
|
|
alpha_color_tensor = get_color(self.alpha_color)
|
|
else:
|
|
alpha_color_tensor = None
|
|
|
|
meta = load_from_json(self.data / f"transforms_{split}.json")
|
|
image_filenames = []
|
|
poses = []
|
|
times = []
|
|
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"]))
|
|
times.append(frame["time"])
|
|
poses = np.array(poses).astype(np.float32)
|
|
times = torch.tensor(times, dtype=torch.float32)
|
|
|
|
img_0 = imageio.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,
|
|
times=times,
|
|
)
|
|
|
|
dataparser_outputs = DataparserOutputs(
|
|
image_filenames=image_filenames,
|
|
cameras=cameras,
|
|
alpha_color=alpha_color_tensor,
|
|
scene_box=scene_box,
|
|
dataparser_scale=self.scale_factor,
|
|
)
|
|
|
|
return dataparser_outputs
|