nbv_reconstruction/utils/data_load.py

import os
import numpy as np
import json
import cv2
import trimesh

class DataLoadUtil:
    
    @staticmethod
    def get_path(root, scene_name, frame_idx):
        path = os.path.join(root, scene_name, f"{frame_idx}")
        return path
    
    @staticmethod
    def get_label_path(root, scene_name):
        path = os.path.join(root,scene_name, f"label.json")
        return path
    
    @staticmethod
    def get_sampled_model_points_path(root, scene_name):
        path = os.path.join(root,scene_name, f"sampled_model_points.txt")
        return path
    
    @staticmethod
    def get_scene_seq_length(root, scene_name):
        camera_params_path = os.path.join(root, scene_name, "camera_params")
        return len(os.listdir(camera_params_path))
    
    @staticmethod
    def load_downsampled_world_model_points(root, scene_name):
        model_path = DataLoadUtil.get_sampled_model_points_path(root, scene_name)
        model_points = np.loadtxt(model_path)
        return model_points

    @staticmethod
    def save_downsampled_world_model_points(root, scene_name, model_points):
        model_path = DataLoadUtil.get_sampled_model_points_path(root, scene_name)
        np.savetxt(model_path, model_points)
    
    @staticmethod
    def load_original_model_points(model_dir, object_name):
        model_path = os.path.join(model_dir, object_name, "mesh.obj")
        mesh = trimesh.load(model_path)
        return mesh.vertices
    
    @staticmethod
    def load_scene_info(root, scene_name):
        scene_info_path = os.path.join(root, scene_name, "scene_info.json")
        with open(scene_info_path, "r") as f:
            scene_info = json.load(f)
        return scene_info
    
    @staticmethod
    def load_target_object_pose(root, scene_name):
        scene_info = DataLoadUtil.load_scene_info(root, scene_name)
        target_name = scene_info["target_name"]
        transformation = scene_info[target_name]
        location = transformation["location"]
        rotation_euler = transformation["rotation_euler"]
        pose_mat = trimesh.transformations.euler_matrix(*rotation_euler)
        pose_mat[:3, 3] = location
        return pose_mat
    
    @staticmethod
    def load_depth(path):
        depth_path = os.path.join(os.path.dirname(path), "depth", os.path.basename(path) + ".png")
        depth = cv2.imread(depth_path, cv2.IMREAD_UNCHANGED)
        depth = depth.astype(np.float32) / 65535.0
        min_depth = 0.01
        max_depth = 5.0
        depth_meters = min_depth + (max_depth - min_depth) * depth
        return depth_meters
    
    @staticmethod
    def load_label(path):
        with open(path, 'r') as f:
            label_data = json.load(f)
        return label_data
    
    @staticmethod
    def load_rgb(path):
        rgb_path = os.path.join(os.path.dirname(path), "rgb", os.path.basename(path) + ".png")
        rgb_image = cv2.imread(rgb_path, cv2.IMREAD_COLOR)
        return rgb_image
    
    @staticmethod
    def load_seg(path):
        mask_path = os.path.join(os.path.dirname(path), "mask", os.path.basename(path) + ".png")
        mask_image = cv2.imread(mask_path, cv2.IMREAD_GRAYSCALE)
        return mask_image
    
    @staticmethod
    def cam_pose_transformation(cam_pose_before):
        offset = np.asarray([
            [1, 0, 0, 0],
            [0, -1, 0, 0],
            [0, 0, -1, 0],
            [0, 0, 0, 1]])  
        cam_pose_after =  cam_pose_before @ offset
        return cam_pose_after
    
    @staticmethod
    def load_cam_info(path):
        camera_params_path = os.path.join(os.path.dirname(path), "camera_params", os.path.basename(path) + ".json")
        with open(camera_params_path, 'r') as f:
            label_data = json.load(f)
        cam_to_world = np.asarray(label_data["extrinsic"])
        cam_to_world = DataLoadUtil.cam_pose_transformation(cam_to_world)
        cam_intrinsic = np.asarray(label_data["intrinsic"])
        return {
            "cam_to_world": cam_to_world,
            "cam_intrinsic": cam_intrinsic
        }

    @staticmethod
    def get_target_point_cloud(depth, cam_intrinsic, cam_extrinsic, mask, target_mask_label=255):
        h, w = depth.shape
        i, j = np.meshgrid(np.arange(w), np.arange(h), indexing='xy')
        
        z = depth
        x = (i - cam_intrinsic[0, 2]) * z / cam_intrinsic[0, 0]
        y = (j - cam_intrinsic[1, 2]) * z / cam_intrinsic[1, 1]
        
        points_camera = np.stack((x, y, z), axis=-1).reshape(-1, 3)
        mask = mask.reshape(-1)

        target_mask = mask == target_mask_label
        target_points_camera = points_camera[target_mask]
        target_points_camera_aug = np.concatenate([target_points_camera, np.ones((target_points_camera.shape[0], 1))], axis=-1)
        
        target_points_world = np.dot(cam_extrinsic, target_points_camera_aug.T).T[:, :3]
        return {
            "points_world": target_points_world,
            "points_camera": target_points_camera
        }
    
        
    @staticmethod
    def get_point_cloud_world_from_path(path):
        cam_info = DataLoadUtil.load_cam_info(path)
        depth = DataLoadUtil.load_depth(path)
        mask = DataLoadUtil.load_seg(path)
        point_cloud = DataLoadUtil.get_target_point_cloud(depth, cam_info['cam_intrinsic'], cam_info['cam_to_world'], mask)
        return point_cloud['points_world']
    
    @staticmethod
    def get_point_cloud_list_from_seq(root, scene_name, num_frames):
        point_cloud_list = []
        for frame_idx in range(num_frames):
            path = DataLoadUtil.get_path(root, scene_name, frame_idx)
            point_cloud = DataLoadUtil.get_point_cloud_world_from_path(path)
            point_cloud_list.append(point_cloud)
        return point_cloud_list