# 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. """Data parser for blender dataset""" from __future__ import annotations from dataclasses import dataclass from pathlib import Path import imageio import numpy as np import torch from nerfactory.cameras.cameras import Cameras, CameraType from nerfactory.configs import base as cfg from nerfactory.datamanagers.dataparsers.base import DataParser from nerfactory.datamanagers.structs import DatasetInputs, SceneBounds from nerfactory.utils.colors import get_color from nerfactory.utils.io import get_absolute_path, load_from_json @dataclass class Blender(DataParser): """Blender Dataset Some of this code comes from https://github.com/yenchenlin/nerf-pytorch/blob/master/load_blender.py#L37. """ def __init__(self, config: cfg.BlenderDataParserConfig): super().__init__(config=config) self.data_directory: Path = config.data_directory self.scale_factor: float = config.scale_factor self.alpha_color = config.alpha_color def _generate_dataset_inputs(self, split="train"): if self.alpha_color is not None: alpha_color_tensor = get_color(self.alpha_color) else: alpha_color_tensor = None abs_dir = get_absolute_path(self.data_directory) meta = load_from_json(abs_dir / f"transforms_{split}.json") image_filenames = [] poses = [] for frame in meta["frames"]: fname = abs_dir / 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.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_bounds = SceneBounds(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, ) dataset_inputs = DatasetInputs( image_filenames=image_filenames, cameras=cameras, alpha_color=alpha_color_tensor, scene_bounds=scene_bounds, ) return dataset_inputs