File size: 5,926 Bytes
c608946
 
 
 
 
 
 
 
 
c74a070
c608946
c74a070
c608946
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
c74a070
 
 
 
 
 
 
 
 
c608946
 
 
 
 
 
c74a070
c608946
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
c74a070
c608946
 
 
 
 
c74a070
c608946
 
c74a070
c608946
 
 
 
 
 
 
 
 
 
 
 
 
 
 
c74a070
 
 
 
 
 
c608946
 
c74a070
 
 
 
 
 
c608946
 
 
 
 
 
 
c74a070
c608946
c74a070
 
 
 
c608946
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
import numpy as np
import torch
from roma.utils import *
from PIL import Image
from tqdm import tqdm
import torch.nn.functional as F
import roma
import kornia.geometry.epipolar as kepi


class MegaDepthPoseEstimationBenchmark:
    def __init__(self, data_root="data/megadepth", scene_names=None) -> None:
        if scene_names is None:
            self.scene_names = [
                "0015_0.1_0.3.npz",
                "0015_0.3_0.5.npz",
                "0022_0.1_0.3.npz",
                "0022_0.3_0.5.npz",
                "0022_0.5_0.7.npz",
            ]
        else:
            self.scene_names = scene_names
        self.scenes = [
            np.load(f"{data_root}/{scene}", allow_pickle=True)
            for scene in self.scene_names
        ]
        self.data_root = data_root

    def benchmark(
        self,
        model,
        model_name=None,
        resolution=None,
        scale_intrinsics=True,
        calibrated=True,
    ):
        H, W = model.get_output_resolution()
        with torch.no_grad():
            data_root = self.data_root
            tot_e_t, tot_e_R, tot_e_pose = [], [], []
            thresholds = [5, 10, 20]
            for scene_ind in range(len(self.scenes)):
                import os

                scene_name = os.path.splitext(self.scene_names[scene_ind])[0]
                scene = self.scenes[scene_ind]
                pairs = scene["pair_infos"]
                intrinsics = scene["intrinsics"]
                poses = scene["poses"]
                im_paths = scene["image_paths"]
                pair_inds = range(len(pairs))
                for pairind in tqdm(pair_inds):
                    idx1, idx2 = pairs[pairind][0]
                    K1 = intrinsics[idx1].copy()
                    T1 = poses[idx1].copy()
                    R1, t1 = T1[:3, :3], T1[:3, 3]
                    K2 = intrinsics[idx2].copy()
                    T2 = poses[idx2].copy()
                    R2, t2 = T2[:3, :3], T2[:3, 3]
                    R, t = compute_relative_pose(R1, t1, R2, t2)
                    T1_to_2 = np.concatenate((R, t[:, None]), axis=-1)
                    im_A_path = f"{data_root}/{im_paths[idx1]}"
                    im_B_path = f"{data_root}/{im_paths[idx2]}"
                    dense_matches, dense_certainty = model.match(
                        im_A_path, im_B_path, K1.copy(), K2.copy(), T1_to_2.copy()
                    )
                    sparse_matches, _ = model.sample(
                        dense_matches, dense_certainty, 5000
                    )

                    im_A = Image.open(im_A_path)
                    w1, h1 = im_A.size
                    im_B = Image.open(im_B_path)
                    w2, h2 = im_B.size

                    if scale_intrinsics:
                        scale1 = 1200 / max(w1, h1)
                        scale2 = 1200 / max(w2, h2)
                        w1, h1 = scale1 * w1, scale1 * h1
                        w2, h2 = scale2 * w2, scale2 * h2
                        K1, K2 = K1.copy(), K2.copy()
                        K1[:2] = K1[:2] * scale1
                        K2[:2] = K2[:2] * scale2

                    kpts1 = sparse_matches[:, :2]
                    kpts1 = np.stack(
                        (
                            w1 * (kpts1[:, 0] + 1) / 2,
                            h1 * (kpts1[:, 1] + 1) / 2,
                        ),
                        axis=-1,
                    )
                    kpts2 = sparse_matches[:, 2:]
                    kpts2 = np.stack(
                        (
                            w2 * (kpts2[:, 0] + 1) / 2,
                            h2 * (kpts2[:, 1] + 1) / 2,
                        ),
                        axis=-1,
                    )

                    for _ in range(5):
                        shuffling = np.random.permutation(np.arange(len(kpts1)))
                        kpts1 = kpts1[shuffling]
                        kpts2 = kpts2[shuffling]
                        try:
                            threshold = 0.5
                            if calibrated:
                                norm_threshold = threshold / (
                                    np.mean(np.abs(K1[:2, :2]))
                                    + np.mean(np.abs(K2[:2, :2]))
                                )
                                R_est, t_est, mask = estimate_pose(
                                    kpts1,
                                    kpts2,
                                    K1,
                                    K2,
                                    norm_threshold,
                                    conf=0.99999,
                                )
                            T1_to_2_est = np.concatenate((R_est, t_est), axis=-1)  #
                            e_t, e_R = compute_pose_error(T1_to_2_est, R, t)
                            e_pose = max(e_t, e_R)
                        except Exception as e:
                            print(repr(e))
                            e_t, e_R = 90, 90
                            e_pose = max(e_t, e_R)
                        tot_e_t.append(e_t)
                        tot_e_R.append(e_R)
                        tot_e_pose.append(e_pose)
            tot_e_pose = np.array(tot_e_pose)
            auc = pose_auc(tot_e_pose, thresholds)
            acc_5 = (tot_e_pose < 5).mean()
            acc_10 = (tot_e_pose < 10).mean()
            acc_15 = (tot_e_pose < 15).mean()
            acc_20 = (tot_e_pose < 20).mean()
            map_5 = acc_5
            map_10 = np.mean([acc_5, acc_10])
            map_20 = np.mean([acc_5, acc_10, acc_15, acc_20])
            print(f"{model_name} auc: {auc}")
            return {
                "auc_5": auc[0],
                "auc_10": auc[1],
                "auc_20": auc[2],
                "map_5": map_5,
                "map_10": map_10,
                "map_20": map_20,
            }