DTU dataset train/test overlap

[sxyu]

Hello, I am not very familiar with this work, so perhaps I am just being ignorant. However, I observed that some scenes e.g. scan_1 are present in both the training and test DTU data. Is this intended? Thanks, A

[YoYo000]

Training and testing sets should always be separated code:

def gen_dtu_mvs_path(dtu_data_folder, mode='training'):
    """ generate data paths for dtu dataset """
    sample_list = []

    # parse camera pairs
    cluster_file_path = dtu_data_folder + '/Cameras/pair.txt'
    cluster_list = open(cluster_file_path).read().split()

    # 3 sets
    training_set = [2, 6, 7, 8, 14, 16, 18, 19, 20, 22, 30, 31, 36, 39, 41, 42, 44,
                    45, 46, 47, 50, 51, 52, 53, 55, 57, 58, 60, 61, 63, 64, 65, 68, 69, 70, 71, 72,
                    74, 76, 83, 84, 85, 87, 88, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100,
                    101, 102, 103, 104, 105, 107, 108, 109, 111, 112, 113, 115, 116, 119, 120,
                    121, 122, 123, 124, 125, 126, 127, 128]
    validation_set = [3, 5, 17, 21, 28, 35, 37, 38, 40, 43, 56, 59, 66, 67, 82, 86, 106, 117]
    evaluation_set = [1, 4, 9, 10, 11, 12, 13, 15, 23, 24, 29, 32, 33, 34, 48, 49, 62, 75, 77,
                      110, 114, 118]

    # for each dataset
    data_set = []
    if mode == 'training':
        data_set = training_set
    elif mode == 'validation':
        data_set = validation_set
    elif mode == 'evaluation':
        data_set = evaluation_set

[sxyu]

Thank you for the clarification!