High-res multi-view results

This table lists the benchmark results for the high-res multi-view scenario. The following metrics are evaluated:

Accuracy [%]: The fraction of the reconstruction which is closer to the ground truth than the evaluation threshold distance (*). Larger is better.
Completeness [%]: The fraction of the ground truth which is closer to the reconstruction than the evaluation threshold distance (*). Larger is better.
F₁ score [%]: The harmonic mean of accuracy and completeness, used to rank methods based on both metrics. Larger is better.
Time [s]: The runtime of the method. Smaller is better.

(*) For exact definitions, detailing how potentially incomplete ground truth is taken into account, see our paper.

The datasets are grouped into different categories, and result averages are computed for a category and method if results of the method are available for all datasets within the category. Note that the category "all" includes both the high-res multi-view and the low-res many-view scenarios.

Methods with suffix _ROB may participate in the Robust Vision Challenge.

Click a dataset result cell to show a visualization of the reconstruction. For training datasets, ground truth and accuracy / completeness visualizations are also available. The visualizations may not work with mobile browsers.

Method	all	high-res multi-view	indoor	outdoor	botani.	boulde.	bridge	door	exhibi.	lectur.	living.	lounge	observ.	old co.	statue	terrac.

test_fmvsm_n_1920		97.55 14	97.89 3	96.53 100	98.41 80	91.73 125	98.01 61	99.02 1	96.37 11	99.30 5	98.92 21	92.39 41	99.79 40	99.16 12	99.46 42	98.08 206

PGM-MVS		96.81 53	96.53 64	97.65 43	99.35 22	93.53 61	97.65 122	98.98 2	92.22 159	97.14 70	98.44 58	91.17 68	99.85 18	94.35 143	99.46 42	99.57 32

MVS_111021_HR		96.68 64	96.58 63	96.99 80	98.46 75	92.31 106	96.20 282	98.90 3	94.30 84	95.86 127	97.74 125	92.33 42	99.38 130	96.04 89	99.42 52	99.28 73

test_fmvsmconf_n		97.49 18	97.56 13	97.29 60	97.44 159	92.37 103	97.91 80	98.88 4	95.83 17	98.92 21	99.05 12	91.45 58	99.80 35	99.12 14	99.46 42	99.69 13

lecture		97.58 13	97.63 10	97.43 54	99.37 16	92.93 82	98.86 7	98.85 5	95.27 32	98.65 31	98.90 23	91.97 49	99.80 35	97.63 36	99.21 77	99.57 32

ACMMP		96.27 81	95.93 84	97.28 62	99.24 30	92.62 94	98.25 36	98.81 6	92.99 133	94.56 164	98.39 62	88.96 98	99.85 18	94.57 141	97.63 157	99.36 68
Qingshan Xu, Weihang Kong, Wenbing Tao, Marc Pollefeys: Multi-Scale Geometric Consistency Guided and Planar Prior Assisted Multi-View Stereo. IEEE Transactions on Pattern Analysis and Machine Intelligence
MVS_111021_LR		96.24 82	96.19 80	96.39 118	98.23 99	91.35 147	96.24 280	98.79 7	93.99 91	95.80 129	97.65 134	89.92 88	99.24 143	95.87 93	99.20 82	98.58 153

patch_mono-2		96.83 52	97.44 21	95.01 206	99.05 41	85.39 342	96.98 206	98.77 8	94.70 64	97.99 45	98.66 41	93.61 19	99.91 1	97.67 35	99.50 36	99.72 12

fmvsm_s_conf0.5_n		96.85 49	97.13 26	96.04 142	98.07 114	90.28 195	97.97 72	98.76 9	94.93 46	98.84 26	99.06 11	88.80 102	99.65 73	99.06 16	98.63 117	98.18 192

fmvsm_l_conf0.5_n		97.65 7	97.75 7	97.34 57	98.21 100	92.75 88	97.83 92	98.73 10	95.04 43	99.30 5	98.84 34	93.34 22	99.78 43	99.32 6	99.13 92	99.50 48

fmvsm_s_conf0.5_n_a		96.75 57	96.93 41	96.20 134	97.64 145	90.72 177	98.00 62	98.73 10	94.55 71	98.91 22	99.08 7	88.22 114	99.63 82	98.91 19	98.37 130	98.25 187

fmvsm_l_conf0.5_n_9		97.59 11	97.79 5	96.97 82	98.28 89	91.49 139	97.61 131	98.71 12	97.10 4	99.70 1	98.93 20	90.95 73	99.77 46	99.35 5	99.53 29	99.65 19

FC-MVSNet-test		93.94 164	93.57 156	95.04 204	95.48 294	91.45 144	98.12 51	98.71 12	93.37 116	90.23 274	96.70 200	87.66 124	97.85 325	91.49 205	90.39 316	95.83 300

UniMVSNet (Re)		93.31 189	92.55 202	95.61 175	95.39 300	93.34 67	97.39 165	98.71 12	93.14 129	90.10 283	94.83 302	87.71 123	98.03 298	91.67 203	83.99 388	95.46 319

fmvsm_l_conf0.5_n_a		97.63 9	97.76 6	97.26 64	98.25 94	92.59 96	97.81 97	98.68 15	94.93 46	99.24 8	98.87 29	93.52 20	99.79 40	99.32 6	99.21 77	99.40 62

FIs		94.09 155	93.70 152	95.27 193	95.70 283	92.03 118	98.10 52	98.68 15	93.36 118	90.39 271	96.70 200	87.63 127	97.94 316	92.25 183	90.50 315	95.84 299

WR-MVS_H		92.00 246	91.35 243	93.95 271	95.09 327	89.47 224	98.04 59	98.68 15	91.46 188	88.34 334	94.68 309	85.86 159	97.56 354	85.77 329	84.24 386	94.82 364

fmvsm_s_conf0.5_n_4		96.75 57	97.07 29	95.79 162	97.76 136	89.57 218	97.66 121	98.66 18	95.36 28	99.03 14	98.90 23	88.39 110	99.73 55	99.17 11	98.66 115	98.08 206

VPA-MVSNet		93.24 191	92.48 207	95.51 181	95.70 283	92.39 102	97.86 85	98.66 18	92.30 156	92.09 232	95.37 277	80.49 269	98.40 252	93.95 149	85.86 359	95.75 308

fmvsm_l_conf0.5_n_3		97.64 8	97.60 11	97.79 30	98.14 107	93.94 52	97.93 78	98.65 20	96.70 6	99.38 3	99.07 10	89.92 88	99.81 30	99.16 12	99.43 49	99.61 26

fmvsm_s_conf0.5_n_3		97.15 31	97.36 23	96.52 102	97.98 120	91.19 155	97.84 89	98.65 20	97.08 5	99.25 7	99.10 5	87.88 121	99.79 40	99.32 6	99.18 84	98.59 152

fmvsm_s_conf0.5_n_8		97.32 25	97.48 20	96.85 83	98.28 89	91.07 163	97.76 102	98.62 22	97.53 2	99.20 10	99.12 4	88.24 113	99.81 30	99.41 3	99.17 85	99.67 14

fmvsm_s_conf0.5_n_2		96.62 65	96.82 50	96.02 144	97.98 120	90.43 187	97.50 146	98.59 23	96.59 8	99.31 4	99.08 7	84.47 185	99.75 52	99.37 4	98.45 127	97.88 219

UniMVSNet_NR-MVSNet		93.37 187	92.67 196	95.47 186	95.34 306	92.83 85	97.17 189	98.58 24	92.98 138	90.13 279	95.80 253	88.37 112	97.85 325	91.71 200	83.93 389	95.73 310

CSCG		96.05 85	95.91 85	96.46 112	99.24 30	90.47 184	98.30 29	98.57 25	89.01 280	93.97 181	97.57 144	92.62 37	99.76 48	94.66 135	99.27 70	99.15 83

fmvsm_s_conf0.5_n_9		97.33 24	97.57 12	96.62 96	98.43 78	90.32 194	97.80 98	98.53 26	97.24 3	99.62 2	99.14 1	88.65 105	99.80 35	99.54 1	99.15 89	99.74 8

fmvsm_s_conf0.5_n_6		97.08 34	97.17 25	96.81 84	97.28 164	91.73 125	97.75 104	98.50 27	94.86 50	99.22 9	98.78 38	89.75 91	99.76 48	99.10 15	99.29 68	98.94 112

MSLP-MVS++		96.94 43	97.06 30	96.59 97	98.72 60	91.86 123	97.67 118	98.49 28	94.66 67	97.24 66	98.41 61	92.31 44	98.94 189	96.61 65	99.46 42	98.96 108

HyFIR lowres test		93.66 176	92.92 184	95.87 154	98.24 95	89.88 209	94.58 356	98.49 28	85.06 377	93.78 184	95.78 257	82.86 220	98.67 227	91.77 198	95.71 214	99.07 94

CHOSEN 1792x2688		94.15 150	93.51 162	96.06 140	98.27 91	89.38 229	95.18 342	98.48 30	85.60 367	93.76 185	97.11 175	83.15 210	99.61 84	91.33 208	98.72 113	99.19 79

fmvsm_s_conf0.5_n_7		96.45 72	96.80 52	95.37 189	97.29 163	88.38 261	97.23 183	98.47 31	95.14 37	98.43 36	99.09 6	87.58 128	99.72 59	98.80 23	99.21 77	98.02 210

fmvsm_s_conf0.5_n_5		97.00 40	96.97 38	97.09 75	97.58 155	92.56 97	97.68 117	98.47 31	94.02 89	98.90 23	98.89 26	88.94 99	99.78 43	99.18 10	99.03 101	98.93 116

PHI-MVS		96.77 55	96.46 71	97.71 41	98.40 81	94.07 48	98.21 43	98.45 33	89.86 252	97.11 72	98.01 98	92.52 39	99.69 67	96.03 90	99.53 29	99.36 68

fmvsm_s_conf0.1_n		96.58 68	96.77 55	96.01 147	96.67 215	90.25 196	97.91 80	98.38 34	94.48 75	98.84 26	99.14 1	88.06 116	99.62 83	98.82 21	98.60 119	98.15 196

PVSNet_BlendedMVS		94.06 156	93.92 146	94.47 240	98.27 91	89.46 226	96.73 231	98.36 35	90.17 244	94.36 169	95.24 285	88.02 117	99.58 92	93.44 161	90.72 311	94.36 384

PVSNet_Blended		94.87 128	94.56 126	95.81 160	98.27 91	89.46 226	95.47 325	98.36 35	88.84 289	94.36 169	96.09 242	88.02 117	99.58 92	93.44 161	98.18 139	98.40 174

3Dnovator	91.36 5	95.19 116	94.44 134	97.44 53	96.56 225	93.36 66	98.65 12	98.36 35	94.12 86	89.25 313	98.06 92	82.20 237	99.77 46	93.41 163	99.32 66	99.18 80

FOURS1					99.55 1	93.34 67	99.29 1	98.35 38	94.98 44	98.49 34

DPE-MVS		97.86 4	97.65 9	98.47 5	99.17 34	95.78 7	97.21 186	98.35 38	95.16 36	98.71 30	98.80 36	95.05 10	99.89 3	96.70 63	99.73 1	99.73 11
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
fmvsm_s_conf0.1_n_a		96.40 74	96.47 68	96.16 136	95.48 294	90.69 178	97.91 80	98.33 40	94.07 87	98.93 18	99.14 1	87.44 135	99.61 84	98.63 24	98.32 132	98.18 192

HFP-MVS		97.14 32	96.92 42	97.83 26	99.42 7	94.12 46	98.52 16	98.32 41	93.21 121	97.18 67	98.29 78	92.08 46	99.83 26	95.63 106	99.59 19	99.54 41

ACMMPR		97.07 36	96.84 46	97.79 30	99.44 6	93.88 53	98.52 16	98.31 42	93.21 121	97.15 69	98.33 72	91.35 62	99.86 9	95.63 106	99.59 19	99.62 23

test_fmvsmvis_n_1920		96.70 60	96.84 46	96.31 123	96.62 217	91.73 125	97.98 66	98.30 43	96.19 12	96.10 117	98.95 18	89.42 92	99.76 48	98.90 20	99.08 96	97.43 246

APDe-MVS		97.82 5	97.73 8	98.08 18	99.15 35	94.82 28	98.81 8	98.30 43	94.76 62	98.30 38	98.90 23	93.77 17	99.68 69	97.93 27	99.69 3	99.75 6
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
test0726					99.45 3	95.36 13	98.31 28	98.29 45	94.92 48	98.99 16	98.92 21	95.08 8

MSP-MVS		97.59 11	97.54 14	97.73 38	99.40 11	93.77 57	98.53 15	98.29 45	95.55 25	98.56 33	97.81 120	93.90 15	99.65 73	96.62 64	99.21 77	99.77 2
Zhenlong Yuan, Cong Liu, Fei Shen, Zhaoxin Li, Jingguo luo, Tianlu Mao and Zhaoqi Wang: MSP-MVS: Multi-granularity Segmentation Prior Guided Multi-View Stereo. AAAI2025
DVP-MVS++		98.06 1	97.99 1	98.28 9	98.67 63	95.39 11	99.29 1	98.28 47	94.78 59	98.93 18	98.87 29	96.04 2	99.86 9	97.45 44	99.58 23	99.59 28

test_0728_SECOND				98.51 4	99.45 3	95.93 5	98.21 43	98.28 47					99.86 9	97.52 40	99.67 6	99.75 6

CP-MVS		97.02 38	96.81 51	97.64 45	99.33 23	93.54 60	98.80 9	98.28 47	92.99 133	96.45 104	98.30 77	91.90 50	99.85 18	95.61 108	99.68 4	99.54 41

test_fmvsmconf0.1_n		97.09 33	97.06 30	97.19 69	95.67 285	92.21 110	97.95 75	98.27 50	95.78 21	98.40 37	99.00 14	89.99 86	99.78 43	99.06 16	99.41 55	99.59 28

SED-MVS		98.05 2	97.99 1	98.24 10	99.42 7	95.30 17	98.25 36	98.27 50	95.13 38	99.19 11	98.89 26	95.54 5	99.85 18	97.52 40	99.66 10	99.56 36

test_241102_TWO								98.27 50	95.13 38	98.93 18	98.89 26	94.99 11	99.85 18	97.52 40	99.65 13	99.74 8

test_241102_ONE					99.42 7	95.30 17		98.27 50	95.09 41	99.19 11	98.81 35	95.54 5	99.65 73

SF-MVS		97.39 21	97.13 26	98.17 15	99.02 44	95.28 19	98.23 40	98.27 50	92.37 155	98.27 39	98.65 43	93.33 23	99.72 59	96.49 69	99.52 31	99.51 45

SteuartSystems-ACMMP		97.62 10	97.53 15	97.87 24	98.39 83	94.25 40	98.43 23	98.27 50	95.34 30	98.11 41	98.56 45	94.53 12	99.71 61	96.57 67	99.62 17	99.65 19
Skip Steuart: Steuart Systems R&D Blog.
test_one_0601					99.32 24	95.20 20		98.25 56	95.13 38	98.48 35	98.87 29	95.16 7

PVSNet_Blended_VisFu		95.27 109	94.91 115	96.38 119	98.20 101	90.86 171	97.27 177	98.25 56	90.21 243	94.18 174	97.27 164	87.48 134	99.73 55	93.53 158	97.77 155	98.55 155

region2R		97.07 36	96.84 46	97.77 34	99.46 2	93.79 55	98.52 16	98.24 58	93.19 124	97.14 70	98.34 69	91.59 57	99.87 7	95.46 112	99.59 19	99.64 21

PS-CasMVS		91.55 266	90.84 267	93.69 288	94.96 331	88.28 264	97.84 89	98.24 58	91.46 188	88.04 345	95.80 253	79.67 285	97.48 362	87.02 309	84.54 383	95.31 333

DU-MVS		92.90 209	92.04 218	95.49 183	94.95 332	92.83 85	97.16 190	98.24 58	93.02 132	90.13 279	95.71 260	83.47 202	97.85 325	91.71 200	83.93 389	95.78 304

9.14			96.75 56		98.93 52		97.73 108	98.23 61	91.28 197	97.88 49	98.44 58	93.00 26	99.65 73	95.76 99	99.47 41

reproduce_model		97.51 17	97.51 17	97.50 50	98.99 48	93.01 78	97.79 100	98.21 62	95.73 22	97.99 45	99.03 13	92.63 36	99.82 28	97.80 29	99.42 52	99.67 14

D2MVS		91.30 283	90.95 261	92.35 336	94.71 347	85.52 338	96.18 284	98.21 62	88.89 287	86.60 374	93.82 358	79.92 281	97.95 314	89.29 258	90.95 308	93.56 399

reproduce-ours		97.53 15	97.51 17	97.60 47	98.97 49	93.31 69	97.71 113	98.20 64	95.80 19	97.88 49	98.98 16	92.91 27	99.81 30	97.68 31	99.43 49	99.67 14

our_new_method		97.53 15	97.51 17	97.60 47	98.97 49	93.31 69	97.71 113	98.20 64	95.80 19	97.88 49	98.98 16	92.91 27	99.81 30	97.68 31	99.43 49	99.67 14

SDMVSNet		94.17 148	93.61 155	95.86 156	98.09 110	91.37 146	97.35 169	98.20 64	93.18 126	91.79 240	97.28 162	79.13 293	98.93 190	94.61 138	92.84 274	97.28 254

XVS		97.18 29	96.96 40	97.81 28	99.38 14	94.03 50	98.59 13	98.20 64	94.85 51	96.59 93	98.29 78	91.70 53	99.80 35	95.66 101	99.40 57	99.62 23

X-MVStestdata		91.71 255	89.67 321	97.81 28	99.38 14	94.03 50	98.59 13	98.20 64	94.85 51	96.59 93	32.69 459	91.70 53	99.80 35	95.66 101	99.40 57	99.62 23

ACMMP_NAP		97.20 28	96.86 44	98.23 11	99.09 36	95.16 22	97.60 132	98.19 69	92.82 145	97.93 48	98.74 40	91.60 56	99.86 9	96.26 73	99.52 31	99.67 14

CP-MVSNet		91.89 251	91.24 250	93.82 280	95.05 328	88.57 254	97.82 94	98.19 69	91.70 177	88.21 340	95.76 258	81.96 242	97.52 360	87.86 284	84.65 377	95.37 329

ZNCC-MVS		96.96 41	96.67 59	97.85 25	99.37 16	94.12 46	98.49 20	98.18 71	92.64 151	96.39 106	98.18 85	91.61 55	99.88 4	95.59 111	99.55 26	99.57 32

SMA-MVS		97.35 22	97.03 35	98.30 8	99.06 40	95.42 10	97.94 76	98.18 71	90.57 235	98.85 25	98.94 19	93.33 23	99.83 26	96.72 61	99.68 4	99.63 22
Yufeng Yin; Xiaoyan Liu; Zichao Zhang: SMA-MVS: Segmentation-Guided Multi-Scale Anchor Deformation Patch Multi-View Stereo. IEEE Transactions on Circuits and Systems for Video Technology
PEN-MVS		91.20 288	90.44 284	93.48 299	94.49 355	87.91 279	97.76 102	98.18 71	91.29 194	87.78 349	95.74 259	80.35 272	97.33 373	85.46 333	82.96 399	95.19 344

DELS-MVS		96.61 66	96.38 75	97.30 59	97.79 134	93.19 74	95.96 295	98.18 71	95.23 33	95.87 126	97.65 134	91.45 58	99.70 66	95.87 93	99.44 48	99.00 103
Christian Sormann, Emanuele Santellani, Mattia Rossi, Andreas Kuhn, Friedrich Fraundorfer: DELS-MVS: Deep Epipolar Line Search for Multi-View Stereo. Winter Conference on Applications of Computer Vision (WACV), 2023
tfpnnormal		89.70 340	88.40 346	93.60 292	95.15 323	90.10 198	97.56 137	98.16 75	87.28 340	86.16 380	94.63 313	77.57 321	98.05 294	74.48 419	84.59 381	92.65 412

VNet		95.89 93	95.45 96	97.21 67	98.07 114	92.94 81	97.50 146	98.15 76	93.87 95	97.52 56	97.61 140	85.29 170	99.53 106	95.81 98	95.27 227	99.16 81

DeepPCF-MVS	93.97 1	96.61 66	97.09 28	95.15 197	98.09 110	86.63 311	96.00 293	98.15 76	95.43 26	97.95 47	98.56 45	93.40 21	99.36 131	96.77 58	99.48 40	99.45 55

SD-MVS		97.41 20	97.53 15	97.06 78	98.57 74	94.46 34	97.92 79	98.14 78	94.82 55	99.01 15	98.55 47	94.18 14	97.41 369	96.94 53	99.64 14	99.32 70
Zhenlong Yuan, Jiakai Cao, Zhaoxin Li, Hao Jiang and Zhaoqi Wang: SD-MVS: Segmentation-driven Deformation Multi-View Stereo with Spherical Refinement and EM optimization. AAAI2024
GST-MVS		96.85 49	96.52 65	97.82 27	99.36 20	94.14 45	98.29 30	98.13 79	92.72 148	96.70 85	98.06 92	91.35 62	99.86 9	94.83 128	99.28 69	99.47 54

UA-Net		95.95 90	95.53 92	97.20 68	97.67 141	92.98 80	97.65 122	98.13 79	94.81 57	96.61 91	98.35 66	88.87 100	99.51 111	90.36 233	97.35 167	99.11 89

QAPM		93.45 185	92.27 212	96.98 81	96.77 210	92.62 94	98.39 25	98.12 81	84.50 385	88.27 338	97.77 123	82.39 234	99.81 30	85.40 334	98.81 109	98.51 160

Vis-MVSNet		95.23 113	94.81 116	96.51 106	97.18 169	91.58 136	98.26 35	98.12 81	94.38 82	94.90 154	98.15 87	82.28 235	98.92 192	91.45 207	98.58 121	99.01 100
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
OpenMVS	89.19 12	92.86 212	91.68 233	96.40 116	95.34 306	92.73 90	98.27 33	98.12 81	84.86 380	85.78 382	97.75 124	78.89 303	99.74 53	87.50 299	98.65 116	96.73 271

TranMVSNet+NR-MVSNet		92.50 221	91.63 234	95.14 198	94.76 343	92.07 115	97.53 143	98.11 84	92.90 142	89.56 301	96.12 237	83.16 209	97.60 352	89.30 257	83.20 398	95.75 308

CPTT-MVS		95.57 103	95.19 106	96.70 87	99.27 28	91.48 141	98.33 27	98.11 84	87.79 325	95.17 149	98.03 95	87.09 141	99.61 84	93.51 159	99.42 52	99.02 97

APD-MVS		96.95 42	96.60 61	98.01 20	99.03 43	94.93 27	97.72 111	98.10 86	91.50 186	98.01 44	98.32 74	92.33 42	99.58 92	94.85 126	99.51 34	99.53 44
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
mPP-MVS		96.86 47	96.60 61	97.64 45	99.40 11	93.44 62	98.50 19	98.09 87	93.27 120	95.95 124	98.33 72	91.04 70	99.88 4	95.20 115	99.57 25	99.60 27

ZD-MVS					99.05 41	94.59 32		98.08 88	89.22 273	97.03 75	98.10 88	92.52 39	99.65 73	94.58 140	99.31 67

MTGPA								98.08 88

MTAPA		97.08 34	96.78 54	97.97 23	99.37 16	94.42 36	97.24 179	98.08 88	95.07 42	96.11 116	98.59 44	90.88 76	99.90 2	96.18 85	99.50 36	99.58 31

CNVR-MVS		97.68 6	97.44 21	98.37 7	98.90 55	95.86 6	97.27 177	98.08 88	95.81 18	97.87 52	98.31 75	94.26 13	99.68 69	97.02 52	99.49 39	99.57 32

DP-MVS Recon		95.68 98	95.12 110	97.37 56	99.19 33	94.19 42	97.03 197	98.08 88	88.35 307	95.09 151	97.65 134	89.97 87	99.48 118	92.08 192	98.59 120	98.44 171

SR-MVS		97.01 39	96.86 44	97.47 52	99.09 36	93.27 71	97.98 66	98.07 93	93.75 98	97.45 58	98.48 55	91.43 60	99.59 89	96.22 76	99.27 70	99.54 41

MCST-MVS		97.18 29	96.84 46	98.20 14	99.30 26	95.35 15	97.12 193	98.07 93	93.54 108	96.08 118	97.69 129	93.86 16	99.71 61	96.50 68	99.39 59	99.55 39

NR-MVSNet		92.34 230	91.27 249	95.53 180	94.95 332	93.05 77	97.39 165	98.07 93	92.65 150	84.46 393	95.71 260	85.00 176	97.77 336	89.71 245	83.52 395	95.78 304

MP-MVS-pluss		96.70 60	96.27 78	97.98 22	99.23 32	94.71 29	96.96 208	98.06 96	90.67 225	95.55 140	98.78 38	91.07 69	99.86 9	96.58 66	99.55 26	99.38 66
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
APD-MVS_3200maxsize		96.81 53	96.71 58	97.12 72	99.01 47	92.31 106	97.98 66	98.06 96	93.11 130	97.44 59	98.55 47	90.93 74	99.55 102	96.06 86	99.25 74	99.51 45

MP-MVS		96.77 55	96.45 72	97.72 39	99.39 13	93.80 54	98.41 24	98.06 96	93.37 116	95.54 142	98.34 69	90.59 80	99.88 4	94.83 128	99.54 28	99.49 50
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
HPM-MVS_fast		96.51 69	96.27 78	97.22 66	99.32 24	92.74 89	98.74 10	98.06 96	90.57 235	96.77 82	98.35 66	90.21 83	99.53 106	94.80 131	99.63 16	99.38 66

HPM-MVS		96.69 62	96.45 72	97.40 55	99.36 20	93.11 76	98.87 6	98.06 96	91.17 204	96.40 105	97.99 99	90.99 71	99.58 92	95.61 108	99.61 18	99.49 50
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
sss		94.51 139	93.80 148	96.64 89	97.07 175	91.97 120	96.32 272	98.06 96	88.94 285	94.50 166	96.78 195	84.60 182	99.27 141	91.90 193	96.02 204	98.68 146

DeepC-MVS	93.07 3	96.06 84	95.66 89	97.29 60	97.96 122	93.17 75	97.30 175	98.06 96	93.92 93	93.38 200	98.66 41	86.83 143	99.73 55	95.60 110	99.22 76	98.96 108
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
NCCC		97.30 26	97.03 35	98.11 17	98.77 58	95.06 25	97.34 170	98.04 103	95.96 13	97.09 73	97.88 110	93.18 25	99.71 61	95.84 97	99.17 85	99.56 36

DeepC-MVS_fast	93.89 2	96.93 44	96.64 60	97.78 32	98.64 69	94.30 37	97.41 160	98.04 103	94.81 57	96.59 93	98.37 64	91.24 65	99.64 81	95.16 117	99.52 31	99.42 61
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
SR-MVS-dyc-post		96.88 46	96.80 52	97.11 74	99.02 44	92.34 104	97.98 66	98.03 105	93.52 111	97.43 61	98.51 50	91.40 61	99.56 100	96.05 87	99.26 72	99.43 59

RE-MVS-def			96.72 57		99.02 44	92.34 104	97.98 66	98.03 105	93.52 111	97.43 61	98.51 50	90.71 78		96.05 87	99.26 72	99.43 59

RPMNet		88.98 346	87.05 360	94.77 224	94.45 357	87.19 295	90.23 432	98.03 105	77.87 432	92.40 218	87.55 439	80.17 276	99.51 111	68.84 439	93.95 260	97.60 239

save fliter					98.91 54	94.28 38	97.02 199	98.02 108	95.35 29

TEST9					98.70 61	94.19 42	96.41 259	98.02 108	88.17 311	96.03 119	97.56 146	92.74 33	99.59 89

train_agg		96.30 80	95.83 88	97.72 39	98.70 61	94.19 42	96.41 259	98.02 108	88.58 298	96.03 119	97.56 146	92.73 34	99.59 89	95.04 119	99.37 63	99.39 64

test_8					98.67 63	94.06 49	96.37 266	98.01 111	88.58 298	95.98 123	97.55 148	92.73 34	99.58 92

agg_prior					98.67 63	93.79 55		98.00 112		95.68 136			99.57 99

test_prior				97.23 65	98.67 63	92.99 79		98.00 112					99.41 126			99.29 71

WR-MVS		92.34 230	91.53 238	94.77 224	95.13 325	90.83 172	96.40 263	97.98 114	91.88 172	89.29 310	95.54 271	82.50 230	97.80 332	89.79 244	85.27 368	95.69 311

HPM-MVS++		97.34 23	96.97 38	98.47 5	99.08 38	96.16 4	97.55 142	97.97 115	95.59 23	96.61 91	97.89 108	92.57 38	99.84 23	95.95 92	99.51 34	99.40 62

CANet		96.39 75	96.02 83	97.50 50	97.62 148	93.38 64	97.02 199	97.96 116	95.42 27	94.86 155	97.81 120	87.38 137	99.82 28	96.88 55	99.20 82	99.29 71

114514_t		93.95 163	93.06 178	96.63 93	99.07 39	91.61 133	97.46 157	97.96 116	77.99 430	93.00 209	97.57 144	86.14 156	99.33 133	89.22 261	99.15 89	98.94 112

IU-MVS					99.42 7	95.39 11		97.94 118	90.40 241	98.94 17				97.41 47	99.66 10	99.74 8

MSC_two_6792asdad				98.86 1	98.67 63	96.94 1		97.93 119					99.86 9	97.68 31	99.67 6	99.77 2

No_MVS				98.86 1	98.67 63	96.94 1		97.93 119					99.86 9	97.68 31	99.67 6	99.77 2

fmvsm_s_conf0.1_n_2		96.33 79	96.44 74	96.00 148	97.30 162	90.37 193	97.53 143	97.92 121	96.52 9	99.14 13	99.08 7	83.21 207	99.74 53	99.22 9	98.06 144	97.88 219

Anonymous20231211		90.63 312	89.42 328	94.27 254	98.24 95	89.19 241	98.05 58	97.89 122	79.95 422	88.25 339	94.96 294	72.56 362	98.13 277	89.70 246	85.14 370	95.49 315

原ACMM1				96.38 119	98.59 71	91.09 162		97.89 122	87.41 336	95.22 148	97.68 130	90.25 82	99.54 104	87.95 283	99.12 94	98.49 163

CDPH-MVS		95.97 89	95.38 101	97.77 34	98.93 52	94.44 35	96.35 267	97.88 124	86.98 344	96.65 89	97.89 108	91.99 48	99.47 119	92.26 181	99.46 42	99.39 64

test11								97.88 124

EIA-MVS		95.53 104	95.47 95	95.71 170	97.06 178	89.63 214	97.82 94	97.87 126	93.57 104	93.92 182	95.04 291	90.61 79	98.95 187	94.62 137	98.68 114	98.54 156

CS-MVS		96.86 47	97.06 30	96.26 129	98.16 106	91.16 160	99.09 3	97.87 126	95.30 31	97.06 74	98.03 95	91.72 51	98.71 223	97.10 50	99.17 85	98.90 121

无先验							95.79 306	97.87 126	83.87 393				99.65 73	87.68 293		98.89 125

3Dnovator+	91.43 4	95.40 105	94.48 132	98.16 16	96.90 192	95.34 16	98.48 21	97.87 126	94.65 68	88.53 330	98.02 97	83.69 198	99.71 61	93.18 167	98.96 104	99.44 57

VPNet		92.23 238	91.31 246	94.99 207	95.56 290	90.96 166	97.22 185	97.86 130	92.96 139	90.96 262	96.62 212	75.06 342	98.20 271	91.90 193	83.65 394	95.80 302

test_vis1_n_1920		94.17 148	94.58 125	92.91 320	97.42 160	82.02 389	97.83 92	97.85 131	94.68 65	98.10 42	98.49 52	70.15 381	99.32 135	97.91 28	98.82 108	97.40 248

DVP-MVS		97.91 3	97.81 4	98.22 13	99.45 3	95.36 13	98.21 43	97.85 131	94.92 48	98.73 28	98.87 29	95.08 8	99.84 23	97.52 40	99.67 6	99.48 52
Zhenlong Yuan, Jinguo Luo, Fei Shen, Zhaoxin Li, Cong Liu, Tianlu Mao, Zhaoqi Wang: DVP-MVS: Synergize Depth-Edge and Visibility Prior for Multi-View Stereo. AAAI2025
TSAR-MVS + MP.		97.42 19	97.33 24	97.69 42	99.25 29	94.24 41	98.07 56	97.85 131	93.72 99	98.57 32	98.35 66	93.69 18	99.40 127	97.06 51	99.46 42	99.44 57
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
SPE-MVS-test		96.89 45	97.04 34	96.45 113	98.29 88	91.66 132	99.03 4	97.85 131	95.84 16	96.90 77	97.97 101	91.24 65	98.75 215	96.92 54	99.33 65	98.94 112

test_fmvsmconf0.01_n		96.15 83	95.85 87	97.03 79	92.66 408	91.83 124	97.97 72	97.84 135	95.57 24	97.53 55	99.00 14	84.20 191	99.76 48	98.82 21	99.08 96	99.48 52

GDP-MVS		95.62 100	95.13 108	97.09 75	96.79 204	93.26 72	97.89 83	97.83 136	93.58 103	96.80 79	97.82 118	83.06 214	99.16 155	94.40 142	97.95 150	98.87 127

balanced_conf03		96.84 51	96.89 43	96.68 88	97.63 147	92.22 109	98.17 49	97.82 137	94.44 77	98.23 40	97.36 157	90.97 72	99.22 145	97.74 30	99.66 10	98.61 149

AdaColmap		94.34 143	93.68 153	96.31 123	98.59 71	91.68 131	96.59 250	97.81 138	89.87 251	92.15 228	97.06 178	83.62 201	99.54 104	89.34 256	98.07 143	97.70 232

MVSMamba_PlusPlus		96.51 69	96.48 67	96.59 97	98.07 114	91.97 120	98.14 50	97.79 139	90.43 239	97.34 64	97.52 149	91.29 64	99.19 148	98.12 26	99.64 14	98.60 150

KinetiMVS		95.26 110	94.75 120	96.79 85	96.99 187	92.05 116	97.82 94	97.78 140	94.77 61	96.46 102	97.70 127	80.62 266	99.34 132	92.37 180	98.28 134	98.97 105

mamv4		94.66 136	96.10 82	90.37 389	98.01 117	73.41 439	96.82 221	97.78 140	89.95 250	94.52 165	97.43 153	92.91 27	99.09 168	98.28 25	99.16 88	98.60 150

ETV-MVS		96.02 86	95.89 86	96.40 116	97.16 170	92.44 101	97.47 155	97.77 142	94.55 71	96.48 100	94.51 319	91.23 67	98.92 192	95.65 104	98.19 138	97.82 227

新几何1				97.32 58	98.60 70	93.59 59		97.75 143	81.58 413	95.75 131	97.85 114	90.04 85	99.67 71	86.50 315	99.13 92	98.69 145

旧先验1					98.38 84	93.38 64		97.75 143			98.09 90	92.30 45			99.01 102	99.16 81

EC-MVSNet		96.42 73	96.47 68	96.26 129	97.01 185	91.52 138	98.89 5	97.75 143	94.42 78	96.64 90	97.68 130	89.32 93	98.60 235	97.45 44	99.11 95	98.67 147

EI-MVSNet-Vis-set		96.51 69	96.47 68	96.63 93	98.24 95	91.20 154	96.89 213	97.73 146	94.74 63	96.49 99	98.49 52	90.88 76	99.58 92	96.44 70	98.32 132	99.13 85

PAPM_NR		95.01 119	94.59 124	96.26 129	98.89 56	90.68 179	97.24 179	97.73 146	91.80 173	92.93 214	96.62 212	89.13 96	99.14 160	89.21 262	97.78 154	98.97 105

Anonymous20240529		91.98 247	90.73 274	95.73 168	98.14 107	89.40 228	97.99 63	97.72 148	79.63 424	93.54 193	97.41 155	69.94 383	99.56 100	91.04 215	91.11 304	98.22 189

CHOSEN 280x420		93.12 197	92.72 195	94.34 248	96.71 214	87.27 291	90.29 431	97.72 148	86.61 351	91.34 251	95.29 279	84.29 190	98.41 251	93.25 165	98.94 105	97.35 251

EI-MVSNet-UG-set		96.34 78	96.30 77	96.47 110	98.20 101	90.93 168	96.86 216	97.72 148	94.67 66	96.16 115	98.46 56	90.43 81	99.58 92	96.23 75	97.96 149	98.90 121

LS3D		93.57 180	92.61 200	96.47 110	97.59 151	91.61 133	97.67 118	97.72 148	85.17 375	90.29 273	98.34 69	84.60 182	99.73 55	83.85 357	98.27 135	98.06 208

PAPR		94.18 147	93.42 169	96.48 109	97.64 145	91.42 145	95.55 320	97.71 152	88.99 282	92.34 224	95.82 252	89.19 94	99.11 163	86.14 321	97.38 165	98.90 121

UGNet		94.04 158	93.28 172	96.31 123	96.85 196	91.19 155	97.88 84	97.68 153	94.40 80	93.00 209	96.18 232	73.39 359	99.61 84	91.72 199	98.46 126	98.13 197
Wanjuan Su, Qingshan Xu, Wenbing Tao: Uncertainty-guided Multi-view Stereo Network for Depth Estimation. IEEE Transactions on Circuits and Systems for Video Technology, 2022
testdata				95.46 187	98.18 105	88.90 247		97.66 154	82.73 404	97.03 75	98.07 91	90.06 84	98.85 199	89.67 247	98.98 103	98.64 148

test12				97.65 43	98.46 75	94.26 39		97.66 154		95.52 143		90.89 75	99.46 120		99.25 74	99.22 78

DTE-MVSNet		90.56 313	89.75 319	93.01 316	93.95 370	87.25 292	97.64 126	97.65 156	90.74 220	87.12 362	95.68 263	79.97 280	97.00 386	83.33 358	81.66 405	94.78 371

TAPA-MVS	90.10 7	92.30 233	91.22 252	95.56 177	98.33 86	89.60 216	96.79 224	97.65 156	81.83 410	91.52 246	97.23 167	87.94 119	98.91 194	71.31 434	98.37 130	98.17 195
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
sd_testset		93.10 198	92.45 208	95.05 202	98.09 110	89.21 238	96.89 213	97.64 158	93.18 126	91.79 240	97.28 162	75.35 341	98.65 230	88.99 267	92.84 274	97.28 254

test_cas_vis1_n_1920		94.48 141	94.55 129	94.28 253	96.78 208	86.45 316	97.63 128	97.64 158	93.32 119	97.68 54	98.36 65	73.75 357	99.08 171	96.73 60	99.05 98	97.31 253

NormalMVS		96.36 77	96.11 81	97.12 72	99.37 16	92.90 83	97.99 63	97.63 160	95.92 14	96.57 96	97.93 103	85.34 168	99.50 114	94.99 122	99.21 77	98.97 105

Elysia		94.00 160	93.12 175	96.64 89	96.08 269	92.72 91	97.50 146	97.63 160	91.15 206	94.82 156	97.12 173	74.98 344	99.06 177	90.78 220	98.02 145	98.12 199

StellarMVS		94.00 160	93.12 175	96.64 89	96.08 269	92.72 91	97.50 146	97.63 160	91.15 206	94.82 156	97.12 173	74.98 344	99.06 177	90.78 220	98.02 145	98.12 199

cdsmvs_eth3d_5k		23.24 429	30.99 431	0.00 447	0.00 470	0.00 472	0.00 458	97.63 160	0.00 465	0.00 466	96.88 191	84.38 187	0.00 466	0.00 465	0.00 464	0.00 462

DPM-MVS		95.69 97	94.92 114	98.01 20	98.08 113	95.71 9	95.27 336	97.62 164	90.43 239	95.55 140	97.07 177	91.72 51	99.50 114	89.62 249	98.94 105	98.82 133

sasdasda		96.02 86	95.45 96	97.75 36	97.59 151	95.15 23	98.28 31	97.60 165	94.52 73	96.27 110	96.12 237	87.65 125	99.18 151	96.20 81	94.82 236	98.91 118

canonicalmvs		96.02 86	95.45 96	97.75 36	97.59 151	95.15 23	98.28 31	97.60 165	94.52 73	96.27 110	96.12 237	87.65 125	99.18 151	96.20 81	94.82 236	98.91 118

test222					98.24 95	92.21 110	95.33 331	97.60 165	79.22 426	95.25 146	97.84 116	88.80 102			99.15 89	98.72 142

cascas		91.20 288	90.08 301	94.58 234	94.97 330	89.16 242	93.65 396	97.59 168	79.90 423	89.40 305	92.92 384	75.36 340	98.36 259	92.14 186	94.75 239	96.23 281

h-mvs33		94.15 150	93.52 161	96.04 142	97.81 133	90.22 197	97.62 130	97.58 169	95.19 34	96.74 83	97.45 150	83.67 199	99.61 84	95.85 95	79.73 412	98.29 185

MGCFI-Net		95.94 91	95.40 100	97.56 49	97.59 151	94.62 31	98.21 43	97.57 170	94.41 79	96.17 114	96.16 235	87.54 130	99.17 153	96.19 83	94.73 241	98.91 118

MVSFormer		95.37 106	95.16 107	95.99 149	96.34 247	91.21 152	98.22 41	97.57 170	91.42 190	96.22 112	97.32 158	86.20 154	97.92 319	94.07 146	99.05 98	98.85 129

test_djsdf		93.07 200	92.76 190	94.00 265	93.49 387	88.70 251	98.22 41	97.57 170	91.42 190	90.08 285	95.55 270	82.85 221	97.92 319	94.07 146	91.58 295	95.40 326

OMC-MVS		95.09 118	94.70 121	96.25 132	98.46 75	91.28 148	96.43 257	97.57 170	92.04 168	94.77 160	97.96 102	87.01 142	99.09 168	91.31 209	96.77 186	98.36 178

PS-MVSNAJss		93.74 173	93.51 162	94.44 242	93.91 372	89.28 236	97.75 104	97.56 174	92.50 152	89.94 287	96.54 215	88.65 105	98.18 274	93.83 155	90.90 309	95.86 296

casdiffmvs_mvg		95.81 96	95.57 90	96.51 106	96.87 193	91.49 139	97.50 146	97.56 174	93.99 91	95.13 150	97.92 106	87.89 120	98.78 208	95.97 91	97.33 168	99.26 75
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
jajsoiax		92.42 226	91.89 226	94.03 264	93.33 395	88.50 258	97.73 108	97.53 176	92.00 170	88.85 322	96.50 217	75.62 339	98.11 281	93.88 153	91.56 296	95.48 316

mvs_tets		92.31 232	91.76 229	93.94 273	93.41 392	88.29 263	97.63 128	97.53 176	92.04 168	88.76 325	96.45 219	74.62 349	98.09 286	93.91 151	91.48 297	95.45 321

dcpmvs_2		96.37 76	97.05 33	94.31 251	98.96 51	84.11 363	97.56 137	97.51 178	93.92 93	97.43 61	98.52 49	92.75 32	99.32 135	97.32 49	99.50 36	99.51 45

HQP_MVS		93.78 172	93.43 167	94.82 217	96.21 251	89.99 202	97.74 106	97.51 178	94.85 51	91.34 251	96.64 205	81.32 254	98.60 235	93.02 173	92.23 283	95.86 296

plane_prior5								97.51 178					98.60 235	93.02 173	92.23 283	95.86 296

viewmanbaseed2359cas		95.24 112	95.02 112	95.91 152	96.87 193	89.98 204	96.82 221	97.49 181	92.26 157	95.47 144	97.82 118	86.47 148	98.69 224	94.80 131	97.20 176	99.06 95

reproduce_monomvs		91.30 283	91.10 256	91.92 350	96.82 201	82.48 383	97.01 202	97.49 181	94.64 69	88.35 333	95.27 282	70.53 376	98.10 282	95.20 115	84.60 380	95.19 344

PS-MVSNAJ		95.37 106	95.33 103	95.49 183	97.35 161	90.66 180	95.31 333	97.48 183	93.85 96	96.51 98	95.70 262	88.65 105	99.65 73	94.80 131	98.27 135	96.17 285

API-MVS		94.84 129	94.49 131	95.90 153	97.90 128	92.00 119	97.80 98	97.48 183	89.19 274	94.81 158	96.71 198	88.84 101	99.17 153	88.91 269	98.76 112	96.53 274

MG-MVS		95.61 101	95.38 101	96.31 123	98.42 79	90.53 182	96.04 290	97.48 183	93.47 113	95.67 137	98.10 88	89.17 95	99.25 142	91.27 210	98.77 111	99.13 85

MAR-MVS		94.22 146	93.46 164	96.51 106	98.00 119	92.19 113	97.67 118	97.47 186	88.13 315	93.00 209	95.84 250	84.86 180	99.51 111	87.99 282	98.17 140	97.83 226
Zhenyu Xu, Yiguang Liu, Xuelei Shi, Ying Wang, Yunan Zheng: MARMVS: Matching Ambiguity Reduced Multiple View Stereo for Efficient Large Scale Scene Reconstruction. CVPR 2020
CLD-MVS		92.98 204	92.53 204	94.32 249	96.12 266	89.20 239	95.28 334	97.47 186	92.66 149	89.90 288	95.62 266	80.58 267	98.40 252	92.73 178	92.40 281	95.38 328
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
UniMVSNet_ETH3D		91.34 281	90.22 297	94.68 228	94.86 339	87.86 280	97.23 183	97.46 188	87.99 316	89.90 288	96.92 189	66.35 411	98.23 268	90.30 234	90.99 307	97.96 213

nrg030		94.05 157	93.31 171	96.27 128	95.22 317	94.59 32	98.34 26	97.46 188	92.93 140	91.21 260	96.64 205	87.23 140	98.22 269	94.99 122	85.80 360	95.98 295

XVG-OURS		93.72 174	93.35 170	94.80 222	97.07 175	88.61 252	94.79 351	97.46 188	91.97 171	93.99 179	97.86 113	81.74 248	98.88 196	92.64 179	92.67 279	96.92 266

LPG-MVS_test		92.94 207	92.56 201	94.10 259	96.16 261	88.26 265	97.65 122	97.46 188	91.29 194	90.12 281	97.16 170	79.05 296	98.73 218	92.25 183	91.89 291	95.31 333

LGP-MVS_train				94.10 259	96.16 261	88.26 265		97.46 188	91.29 194	90.12 281	97.16 170	79.05 296	98.73 218	92.25 183	91.89 291	95.31 333

MVS		91.71 255	90.44 284	95.51 181	95.20 319	91.59 135	96.04 290	97.45 193	73.44 440	87.36 358	95.60 267	85.42 167	99.10 165	85.97 326	97.46 160	95.83 300

XVG-OURS-SEG-HR		93.86 169	93.55 157	94.81 219	97.06 178	88.53 257	95.28 334	97.45 193	91.68 178	94.08 178	97.68 130	82.41 233	98.90 195	93.84 154	92.47 280	96.98 262

baseline		95.58 102	95.42 99	96.08 138	96.78 208	90.41 188	97.16 190	97.45 193	93.69 102	95.65 138	97.85 114	87.29 138	98.68 226	95.66 101	97.25 174	99.13 85

ab-mvs		93.57 180	92.55 202	96.64 89	97.28 164	91.96 122	95.40 327	97.45 193	89.81 256	93.22 206	96.28 228	79.62 287	99.46 120	90.74 223	93.11 271	98.50 161

xiu_mvs_v2_base		95.32 108	95.29 104	95.40 188	97.22 166	90.50 183	95.44 326	97.44 197	93.70 101	96.46 102	96.18 232	88.59 109	99.53 106	94.79 134	97.81 153	96.17 285

1314		92.81 216	92.03 219	95.14 198	95.33 309	89.52 223	96.04 290	97.44 197	87.72 329	86.25 379	95.33 278	83.84 196	98.79 207	89.26 259	97.05 181	97.11 260

casdiffmvs		95.64 99	95.49 93	96.08 138	96.76 213	90.45 185	97.29 176	97.44 197	94.00 90	95.46 145	97.98 100	87.52 133	98.73 218	95.64 105	97.33 168	99.08 92
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
XXY-MVS		92.16 240	91.23 251	94.95 213	94.75 344	90.94 167	97.47 155	97.43 200	89.14 275	88.90 318	96.43 220	79.71 284	98.24 267	89.56 250	87.68 341	95.67 312

anonymousdsp		92.16 240	91.55 237	93.97 269	92.58 410	89.55 220	97.51 145	97.42 201	89.42 268	88.40 332	94.84 301	80.66 265	97.88 324	91.87 195	91.28 301	94.48 379

Effi-MVS+		94.93 124	94.45 133	96.36 121	96.61 218	91.47 142	96.41 259	97.41 202	91.02 212	94.50 166	95.92 246	87.53 131	98.78 208	93.89 152	96.81 185	98.84 132

RRT-MVS		94.51 139	94.35 136	94.98 209	96.40 242	86.55 314	97.56 137	97.41 202	93.19 124	94.93 153	97.04 179	79.12 294	99.30 139	96.19 83	97.32 170	99.09 91

HQP3-MVS								97.39 204							92.10 288

HQP-MVS		93.19 194	92.74 193	94.54 237	95.86 275	89.33 232	96.65 241	97.39 204	93.55 105	90.14 275	95.87 248	80.95 258	98.50 245	92.13 189	92.10 288	95.78 304

PLC	91.00 6	94.11 154	93.43 167	96.13 137	98.58 73	91.15 161	96.69 237	97.39 204	87.29 339	91.37 250	96.71 198	88.39 110	99.52 110	87.33 302	97.13 179	97.73 230
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
v7n		90.76 305	89.86 312	93.45 301	93.54 384	87.60 286	97.70 116	97.37 207	88.85 288	87.65 351	94.08 349	81.08 257	98.10 282	84.68 343	83.79 393	94.66 376

UnsupCasMVSNet_eth		85.99 382	84.45 386	90.62 385	89.97 428	82.40 386	93.62 397	97.37 207	89.86 252	78.59 430	92.37 394	65.25 419	95.35 420	82.27 371	70.75 438	94.10 390

ACMM	89.79 8	92.96 205	92.50 206	94.35 246	96.30 249	88.71 250	97.58 133	97.36 209	91.40 192	90.53 268	96.65 204	79.77 283	98.75 215	91.24 211	91.64 293	95.59 314
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
xiu_mvs_v1_base_debu		95.01 119	94.76 117	95.75 165	96.58 221	91.71 128	96.25 277	97.35 210	92.99 133	96.70 85	96.63 209	82.67 225	99.44 123	96.22 76	97.46 160	96.11 291

xiu_mvs_v1_base		95.01 119	94.76 117	95.75 165	96.58 221	91.71 128	96.25 277	97.35 210	92.99 133	96.70 85	96.63 209	82.67 225	99.44 123	96.22 76	97.46 160	96.11 291

xiu_mvs_v1_base_debi		95.01 119	94.76 117	95.75 165	96.58 221	91.71 128	96.25 277	97.35 210	92.99 133	96.70 85	96.63 209	82.67 225	99.44 123	96.22 76	97.46 160	96.11 291

diffmvs		95.25 111	95.13 108	95.63 173	96.43 241	89.34 231	95.99 294	97.35 210	92.83 144	96.31 108	97.37 156	86.44 149	98.67 227	96.26 73	97.19 177	98.87 127
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
WTY-MVS		94.71 135	94.02 144	96.79 85	97.71 139	92.05 116	96.59 250	97.35 210	90.61 231	94.64 162	96.93 186	86.41 150	99.39 128	91.20 212	94.71 242	98.94 112

mamba_test_0407		94.54 138	94.12 143	95.80 161	96.79 204	90.38 190	96.79 224	97.29 215	91.24 198	93.68 186	97.60 141	85.03 174	98.67 227	92.14 186	96.51 194	98.35 180

mamba_0404		94.73 134	94.31 138	95.98 150	97.05 180	90.90 170	97.01 202	97.29 215	91.24 198	94.17 175	97.60 141	85.03 174	98.76 212	92.14 186	97.30 171	98.29 185

F-COLMAP		93.58 178	92.98 182	95.37 189	98.40 81	88.98 245	97.18 188	97.29 215	87.75 328	90.49 269	97.10 176	85.21 171	99.50 114	86.70 312	96.72 189	97.63 234

VortexMVS		92.88 211	92.64 197	93.58 294	96.58 221	87.53 287	96.93 210	97.28 218	92.78 147	89.75 293	94.99 292	82.73 224	97.76 337	94.60 139	88.16 336	95.46 319

XVG-ACMP-BASELINE		90.93 301	90.21 298	93.09 314	94.31 363	85.89 331	95.33 331	97.26 219	91.06 211	89.38 306	95.44 276	68.61 394	98.60 235	89.46 252	91.05 305	94.79 369

PCF-MVS	89.48 11	91.56 265	89.95 309	96.36 121	96.60 219	92.52 99	92.51 416	97.26 219	79.41 425	88.90 318	96.56 214	84.04 195	99.55 102	77.01 410	97.30 171	97.01 261
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
ACMP	89.59 10	92.62 220	92.14 215	94.05 262	96.40 242	88.20 268	97.36 168	97.25 221	91.52 185	88.30 336	96.64 205	78.46 308	98.72 222	91.86 196	91.48 297	95.23 340
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
icg_test_0407_2		93.58 178	93.46 164	93.94 273	96.19 255	86.16 325	93.73 391	97.24 222	91.54 181	93.50 195	97.04 179	85.64 164	96.91 389	90.68 225	95.59 218	98.76 135

icg_test_0407		93.94 164	93.75 150	94.49 239	96.19 255	86.16 325	96.35 267	97.24 222	91.54 181	93.50 195	97.04 179	85.64 164	98.54 242	90.68 225	95.59 218	98.76 135

ICG_test_0404		92.44 224	91.92 224	94.00 265	96.19 255	86.16 325	93.84 388	97.24 222	91.54 181	88.17 342	97.04 179	76.96 326	97.09 380	90.68 225	95.59 218	98.76 135

icg_test_0403		93.98 162	93.79 149	94.55 236	96.19 255	86.16 325	96.35 267	97.24 222	91.54 181	93.59 190	97.04 179	85.86 159	98.73 218	90.68 225	95.59 218	98.76 135

OPM-MVS		93.28 190	92.76 190	94.82 217	94.63 350	90.77 175	96.65 241	97.18 226	93.72 99	91.68 244	97.26 165	79.33 291	98.63 232	92.13 189	92.28 282	95.07 347
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
PatchMatch-RL		92.90 209	92.02 220	95.56 177	98.19 103	90.80 173	95.27 336	97.18 226	87.96 317	91.86 239	95.68 263	80.44 270	98.99 185	84.01 352	97.54 159	96.89 267

alignmvs		95.87 95	95.23 105	97.78 32	97.56 157	95.19 21	97.86 85	97.17 228	94.39 81	96.47 101	96.40 222	85.89 158	99.20 147	96.21 80	95.11 232	98.95 111

MVS_Test		94.89 126	94.62 123	95.68 171	96.83 199	89.55 220	96.70 235	97.17 228	91.17 204	95.60 139	96.11 241	87.87 122	98.76 212	93.01 175	97.17 178	98.72 142

Fast-Effi-MVS+		93.46 184	92.75 192	95.59 176	96.77 210	90.03 199	96.81 223	97.13 230	88.19 310	91.30 254	94.27 337	86.21 153	98.63 232	87.66 294	96.46 200	98.12 199

EI-MVSNet		93.03 202	92.88 186	93.48 299	95.77 281	86.98 300	96.44 255	97.12 231	90.66 227	91.30 254	97.64 137	86.56 145	98.05 294	89.91 240	90.55 313	95.41 323

MVSTER		93.20 193	92.81 189	94.37 245	96.56 225	89.59 217	97.06 196	97.12 231	91.24 198	91.30 254	95.96 244	82.02 241	98.05 294	93.48 160	90.55 313	95.47 318

viewmambaseed2359dif		94.28 144	94.14 141	94.71 227	96.21 251	86.97 301	95.93 297	97.11 233	89.00 281	95.00 152	97.70 127	86.02 157	98.59 239	93.71 157	96.59 193	98.57 154

test_yl		94.78 132	94.23 139	96.43 114	97.74 137	91.22 150	96.85 217	97.10 234	91.23 201	95.71 133	96.93 186	84.30 188	99.31 137	93.10 168	95.12 230	98.75 139

DCV-MVSNet		94.78 132	94.23 139	96.43 114	97.74 137	91.22 150	96.85 217	97.10 234	91.23 201	95.71 133	96.93 186	84.30 188	99.31 137	93.10 168	95.12 230	98.75 139

LTVRE_ROB	88.41 13	90.99 297	89.92 311	94.19 255	96.18 259	89.55 220	96.31 273	97.09 236	87.88 320	85.67 383	95.91 247	78.79 304	98.57 240	81.50 374	89.98 318	94.44 382
Andreas Kuhn, Heiko HirschmÃ¼ller, Daniel Scharstein, Helmut Mayer: A TV Prior for High-Quality Scalable Multi-View Stereo Reconstruction. International Journal of Computer Vision 2016
test_fmvs1_n		92.73 218	92.88 186	92.29 340	96.08 269	81.05 397	97.98 66	97.08 237	90.72 222	96.79 81	98.18 85	63.07 423	98.45 249	97.62 38	98.42 129	97.36 249

v10		91.04 295	90.23 295	93.49 298	94.12 366	88.16 271	97.32 173	97.08 237	88.26 309	88.29 337	94.22 342	82.17 238	97.97 306	86.45 316	84.12 387	94.33 385

mamba_0408		93.70 175	92.99 179	95.83 158	96.79 204	90.38 190	88.69 441	97.07 239	90.96 214	93.68 186	97.31 160	84.97 177	98.76 212	90.95 216	96.51 194	98.35 180

mamba_test_0407_2		93.51 183	92.99 179	95.05 202	96.79 204	90.38 190	88.69 441	97.07 239	90.96 214	93.68 186	97.31 160	84.97 177	96.42 400	90.95 216	96.51 194	98.35 180

v144192		91.06 294	90.28 291	93.39 302	93.66 381	87.23 294	96.83 220	97.07 239	87.43 335	89.69 296	94.28 336	81.48 251	98.00 301	87.18 306	84.92 376	94.93 355

v1192		91.07 293	90.23 295	93.58 294	93.70 378	87.82 282	96.73 231	97.07 239	87.77 326	89.58 299	94.32 334	80.90 262	97.97 306	86.52 314	85.48 363	94.95 351

v8		91.29 285	90.53 283	93.57 296	94.15 365	88.12 272	97.34 170	97.06 243	88.99 282	88.32 335	94.26 339	83.08 212	98.01 300	87.62 296	83.92 391	94.57 378

mvs_anonymous		93.82 170	93.74 151	94.06 261	96.44 240	85.41 340	95.81 304	97.05 244	89.85 254	90.09 284	96.36 224	87.44 135	97.75 339	93.97 148	96.69 190	99.02 97

IterMVS-LS		92.29 234	91.94 223	93.34 304	96.25 250	86.97 301	96.57 253	97.05 244	90.67 225	89.50 304	94.80 304	86.59 144	97.64 347	89.91 240	86.11 358	95.40 326
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
v1921920		90.85 303	90.03 306	93.29 306	93.55 383	86.96 303	96.74 230	97.04 246	87.36 337	89.52 303	94.34 331	80.23 275	97.97 306	86.27 317	85.21 369	94.94 353

CDS-MVSNet		94.14 153	93.54 158	95.93 151	96.18 259	91.46 143	96.33 271	97.04 246	88.97 284	93.56 191	96.51 216	87.55 129	97.89 323	89.80 243	95.95 206	98.44 171
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
SSC-MVS3.2		89.74 339	89.26 332	91.19 374	95.16 320	80.29 408	94.53 358	97.03 248	91.79 174	88.86 321	94.10 346	69.94 383	97.82 329	85.29 335	86.66 354	95.45 321

v1144		91.37 278	90.60 279	93.68 289	93.89 373	88.23 267	96.84 219	97.03 248	88.37 306	89.69 296	94.39 326	82.04 240	97.98 303	87.80 286	85.37 365	94.84 361

v1240		90.70 309	89.85 313	93.23 308	93.51 386	86.80 304	96.61 247	97.02 250	87.16 342	89.58 299	94.31 335	79.55 288	97.98 303	85.52 332	85.44 364	94.90 358

EPP-MVSNet		95.22 114	95.04 111	95.76 163	97.49 158	89.56 219	98.67 11	97.00 251	90.69 223	94.24 172	97.62 139	89.79 90	98.81 205	93.39 164	96.49 198	98.92 117

V42		91.58 264	90.87 263	93.73 284	94.05 369	88.50 258	97.32 173	96.97 252	88.80 294	89.71 294	94.33 332	82.54 229	98.05 294	89.01 266	85.07 372	94.64 377

test_fmvs1		93.21 192	93.53 159	92.25 343	96.55 227	81.20 396	97.40 164	96.96 253	90.68 224	96.80 79	98.04 94	69.25 389	98.40 252	97.58 39	98.50 122	97.16 259

FMVSNet2		91.31 282	90.08 301	94.99 207	96.51 233	92.21 110	97.41 160	96.95 254	88.82 291	88.62 327	94.75 306	73.87 353	97.42 368	85.20 338	88.55 333	95.35 330

ACMH	87.59 16	90.53 314	89.42 328	93.87 278	96.21 251	87.92 277	97.24 179	96.94 255	88.45 304	83.91 403	96.27 229	71.92 365	98.62 234	84.43 346	89.43 324	95.05 349
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
GBi-Net		91.35 279	90.27 292	94.59 230	96.51 233	91.18 157	97.50 146	96.93 256	88.82 291	89.35 307	94.51 319	73.87 353	97.29 375	86.12 322	88.82 328	95.31 333

test1		91.35 279	90.27 292	94.59 230	96.51 233	91.18 157	97.50 146	96.93 256	88.82 291	89.35 307	94.51 319	73.87 353	97.29 375	86.12 322	88.82 328	95.31 333

FMVSNet3		91.78 253	90.69 277	95.03 205	96.53 230	92.27 108	97.02 199	96.93 256	89.79 257	89.35 307	94.65 312	77.01 324	97.47 363	86.12 322	88.82 328	95.35 330

FMVSNet1		89.88 334	88.31 347	94.59 230	95.41 299	91.18 157	97.50 146	96.93 256	86.62 350	87.41 356	94.51 319	65.94 416	97.29 375	83.04 361	87.43 344	95.31 333

GeoE		93.89 167	93.28 172	95.72 169	96.96 190	89.75 212	98.24 39	96.92 260	89.47 265	92.12 230	97.21 168	84.42 186	98.39 257	87.71 289	96.50 197	99.01 100

SymmetryMVS		95.94 91	95.54 91	97.15 70	97.85 130	92.90 83	97.99 63	96.91 261	95.92 14	96.57 96	97.93 103	85.34 168	99.50 114	94.99 122	96.39 201	99.05 96

miper_enhance_ethall		91.54 268	91.01 259	93.15 312	95.35 305	87.07 299	93.97 380	96.90 262	86.79 348	89.17 314	93.43 378	86.55 146	97.64 347	89.97 239	86.93 349	94.74 373

eth_miper_zixun_eth		91.02 296	90.59 280	92.34 338	95.33 309	84.35 359	94.10 377	96.90 262	88.56 300	88.84 323	94.33 332	84.08 193	97.60 352	88.77 272	84.37 385	95.06 348

TAMVS		94.01 159	93.46 164	95.64 172	96.16 261	90.45 185	96.71 234	96.89 264	89.27 272	93.46 198	96.92 189	87.29 138	97.94 316	88.70 274	95.74 212	98.53 157

miper_ehance_all_eth		91.59 262	91.13 255	92.97 318	95.55 291	86.57 312	94.47 361	96.88 265	87.77 326	88.88 320	94.01 351	86.22 152	97.54 356	89.49 251	86.93 349	94.79 369

v2v482		91.59 262	90.85 266	93.80 281	93.87 374	88.17 270	96.94 209	96.88 265	89.54 262	89.53 302	94.90 298	81.70 249	98.02 299	89.25 260	85.04 374	95.20 341

CNLPA		94.28 144	93.53 159	96.52 102	98.38 84	92.55 98	96.59 250	96.88 265	90.13 247	91.91 236	97.24 166	85.21 171	99.09 168	87.64 295	97.83 152	97.92 216

PAPM		91.52 269	90.30 290	95.20 195	95.30 312	89.83 210	93.38 402	96.85 268	86.26 358	88.59 328	95.80 253	84.88 179	98.15 276	75.67 415	95.93 207	97.63 234

c3_l		91.38 276	90.89 262	92.88 322	95.58 289	86.30 319	94.68 353	96.84 269	88.17 311	88.83 324	94.23 340	85.65 163	97.47 363	89.36 255	84.63 378	94.89 359

pm-mvs1		90.72 308	89.65 323	93.96 270	94.29 364	89.63 214	97.79 100	96.82 270	89.07 277	86.12 381	95.48 275	78.61 306	97.78 334	86.97 310	81.67 404	94.46 380

test_vis1_n		92.37 229	92.26 213	92.72 328	94.75 344	82.64 379	98.02 60	96.80 271	91.18 203	97.77 53	97.93 103	58.02 433	98.29 265	97.63 36	98.21 137	97.23 257

CMPMVS	62.92 21	85.62 387	84.92 382	87.74 411	89.14 433	73.12 441	94.17 375	96.80 271	73.98 437	73.65 439	94.93 296	66.36 410	97.61 351	83.95 354	91.28 301	92.48 417
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
MS-PatchMatch		90.27 321	89.77 317	91.78 359	94.33 361	84.72 356	95.55 320	96.73 273	86.17 360	86.36 378	95.28 281	71.28 370	97.80 332	84.09 351	98.14 141	92.81 409

Effi-MVS+-dtu		93.08 199	93.21 174	92.68 331	96.02 272	83.25 373	97.14 192	96.72 274	93.85 96	91.20 261	93.44 375	83.08 212	98.30 264	91.69 202	95.73 213	96.50 276

TSAR-MVS + GP.		96.69 62	96.49 66	97.27 63	98.31 87	93.39 63	96.79 224	96.72 274	94.17 85	97.44 59	97.66 133	92.76 31	99.33 133	96.86 57	97.76 156	99.08 92

1112_ss		93.37 187	92.42 209	96.21 133	97.05 180	90.99 164	96.31 273	96.72 274	86.87 347	89.83 291	96.69 202	86.51 147	99.14 160	88.12 279	93.67 265	98.50 161

PVSNet	86.66 18	92.24 237	91.74 232	93.73 284	97.77 135	83.69 370	92.88 411	96.72 274	87.91 319	93.00 209	94.86 300	78.51 307	99.05 180	86.53 313	97.45 164	98.47 166

miper_lstm_enhance		90.50 317	90.06 305	91.83 355	95.33 309	83.74 367	93.86 386	96.70 278	87.56 333	87.79 348	93.81 359	83.45 204	96.92 388	87.39 300	84.62 379	94.82 364

v148		90.99 297	90.38 286	92.81 325	93.83 375	85.80 332	96.78 228	96.68 279	89.45 267	88.75 326	93.93 355	82.96 218	97.82 329	87.83 285	83.25 396	94.80 367

ACMH+	87.92 14	90.20 325	89.18 334	93.25 307	96.48 236	86.45 316	96.99 205	96.68 279	88.83 290	84.79 392	96.22 231	70.16 380	98.53 243	84.42 347	88.04 337	94.77 372

CANet_DTU		94.37 142	93.65 154	96.55 99	96.46 239	92.13 114	96.21 281	96.67 281	94.38 82	93.53 194	97.03 184	79.34 290	99.71 61	90.76 222	98.45 127	97.82 227

cl____		90.96 300	90.32 288	92.89 321	95.37 303	86.21 322	94.46 363	96.64 282	87.82 322	88.15 343	94.18 343	82.98 216	97.54 356	87.70 290	85.59 361	94.92 357

HY-MVS	89.66 9	93.87 168	92.95 183	96.63 93	97.10 174	92.49 100	95.64 317	96.64 282	89.05 279	93.00 209	95.79 256	85.77 162	99.45 122	89.16 265	94.35 244	97.96 213

Test_1112_low_res		92.84 214	91.84 227	95.85 157	97.04 182	89.97 206	95.53 322	96.64 282	85.38 370	89.65 298	95.18 286	85.86 159	99.10 165	87.70 290	93.58 270	98.49 163

DIV-MVS_self_test		90.97 299	90.33 287	92.88 322	95.36 304	86.19 324	94.46 363	96.63 285	87.82 322	88.18 341	94.23 340	82.99 215	97.53 358	87.72 287	85.57 362	94.93 355

Fast-Effi-MVS+-dtu		92.29 234	91.99 221	93.21 310	95.27 313	85.52 338	97.03 197	96.63 285	92.09 166	89.11 316	95.14 288	80.33 273	98.08 287	87.54 298	94.74 240	96.03 294

UnsupCasMVSNet_bld		82.13 403	79.46 408	90.14 392	88.00 441	82.47 384	90.89 429	96.62 287	78.94 427	75.61 434	84.40 445	56.63 436	96.31 402	77.30 407	66.77 446	91.63 427

cl22		91.21 287	90.56 282	93.14 313	96.09 268	86.80 304	94.41 365	96.58 288	87.80 324	88.58 329	93.99 353	80.85 263	97.62 350	89.87 242	86.93 349	94.99 350

jason		94.84 129	94.39 135	96.18 135	95.52 292	90.93 168	96.09 288	96.52 289	89.28 271	96.01 122	97.32 158	84.70 181	98.77 211	95.15 118	98.91 107	98.85 129
jason: jason.
tt0805		91.09 292	90.07 304	94.16 257	95.61 287	88.31 262	97.56 137	96.51 290	89.56 261	89.17 314	95.64 265	67.08 408	98.38 258	91.07 214	88.44 334	95.80 302

AUN-MVS		91.76 254	90.75 272	94.81 219	97.00 186	88.57 254	96.65 241	96.49 291	89.63 259	92.15 228	96.12 237	78.66 305	98.50 245	90.83 218	79.18 415	97.36 249

hse-mvs2		93.45 185	92.99 179	94.81 219	97.02 184	88.59 253	96.69 237	96.47 292	95.19 34	96.74 83	96.16 235	83.67 199	98.48 248	95.85 95	79.13 416	97.35 251

SD_0403		90.01 329	90.02 307	89.96 395	95.65 286	76.76 429	95.76 308	96.46 293	90.58 234	86.59 375	96.29 227	82.12 239	94.78 424	73.00 429	93.76 263	98.35 180

EG-PatchMatch MVS		87.02 369	85.44 374	91.76 361	92.67 407	85.00 350	96.08 289	96.45 294	83.41 400	79.52 426	93.49 372	57.10 435	97.72 341	79.34 398	90.87 310	92.56 414

KD-MVS_self_test		85.95 383	84.95 381	88.96 405	89.55 432	79.11 423	95.13 343	96.42 295	85.91 363	84.07 401	90.48 417	70.03 382	94.82 423	80.04 390	72.94 435	92.94 407

pmmvs6		87.81 361	86.19 369	92.69 330	91.32 420	86.30 319	97.34 170	96.41 296	80.59 421	84.05 402	94.37 328	67.37 403	97.67 344	84.75 342	79.51 414	94.09 392

PMMVS		92.86 212	92.34 210	94.42 244	94.92 335	86.73 307	94.53 358	96.38 297	84.78 382	94.27 171	95.12 290	83.13 211	98.40 252	91.47 206	96.49 198	98.12 199

RPSCF		90.75 306	90.86 264	90.42 388	96.84 197	76.29 432	95.61 318	96.34 298	83.89 391	91.38 249	97.87 111	76.45 330	98.78 208	87.16 307	92.23 283	96.20 283

BP-MVS1		95.89 93	95.49 93	97.08 77	96.67 215	93.20 73	98.08 54	96.32 299	94.56 70	96.32 107	97.84 116	84.07 194	99.15 157	96.75 59	98.78 110	98.90 121

MSDG		91.42 274	90.24 294	94.96 212	97.15 172	88.91 246	93.69 394	96.32 299	85.72 366	86.93 371	96.47 218	80.24 274	98.98 186	80.57 387	95.05 233	96.98 262

WBMVS		90.69 311	89.99 308	92.81 325	96.48 236	85.00 350	95.21 341	96.30 301	89.46 266	89.04 317	94.05 350	72.45 363	97.82 329	89.46 252	87.41 346	95.61 313

OurMVSNet-221017-0		90.51 316	90.19 299	91.44 367	93.41 392	81.25 394	96.98 206	96.28 302	91.68 178	86.55 376	96.30 226	74.20 352	97.98 303	88.96 268	87.40 347	95.09 346

MVP-Stereo		90.74 307	90.08 301	92.71 329	93.19 397	88.20 268	95.86 301	96.27 303	86.07 361	84.86 391	94.76 305	77.84 319	97.75 339	83.88 356	98.01 147	92.17 424
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
lupinMVS		94.99 123	94.56 126	96.29 127	96.34 247	91.21 152	95.83 303	96.27 303	88.93 286	96.22 112	96.88 191	86.20 154	98.85 199	95.27 114	99.05 98	98.82 133

BH-untuned		92.94 207	92.62 199	93.92 277	97.22 166	86.16 325	96.40 263	96.25 305	90.06 248	89.79 292	96.17 234	83.19 208	98.35 260	87.19 305	97.27 173	97.24 256

CL-MVSNet_self_test		86.31 378	85.15 378	89.80 397	88.83 436	81.74 392	93.93 383	96.22 306	86.67 349	85.03 389	90.80 415	78.09 315	94.50 425	74.92 418	71.86 437	93.15 405

IS-MVSNet		94.90 125	94.52 130	96.05 141	97.67 141	90.56 181	98.44 22	96.22 306	93.21 121	93.99 179	97.74 125	85.55 166	98.45 249	89.98 238	97.86 151	99.14 84

FA-MVS(test-final)		93.52 182	92.92 184	95.31 192	96.77 210	88.54 256	94.82 350	96.21 308	89.61 260	94.20 173	95.25 284	83.24 206	99.14 160	90.01 237	96.16 203	98.25 187

GA-MVS		91.38 276	90.31 289	94.59 230	94.65 349	87.62 285	94.34 368	96.19 309	90.73 221	90.35 272	93.83 356	71.84 366	97.96 310	87.22 304	93.61 268	98.21 190

LuminaMVS		94.89 126	94.35 136	96.53 100	95.48 294	92.80 87	96.88 215	96.18 310	92.85 143	95.92 125	96.87 193	81.44 252	98.83 202	96.43 71	97.10 180	97.94 215

IterMVS-SCA-FT		90.31 319	89.81 315	91.82 356	95.52 292	84.20 362	94.30 371	96.15 311	90.61 231	87.39 357	94.27 337	75.80 336	96.44 399	87.34 301	86.88 353	94.82 364

IterMVS		90.15 327	89.67 321	91.61 363	95.48 294	83.72 368	94.33 369	96.12 312	89.99 249	87.31 360	94.15 345	75.78 338	96.27 403	86.97 310	86.89 352	94.83 362
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
DP-MVS		92.76 217	91.51 241	96.52 102	98.77 58	90.99 164	97.38 167	96.08 313	82.38 406	89.29 310	97.87 111	83.77 197	99.69 67	81.37 380	96.69 190	98.89 125

pmmvs4		90.93 301	89.85 313	94.17 256	93.34 394	90.79 174	94.60 355	96.02 314	84.62 383	87.45 354	95.15 287	81.88 246	97.45 365	87.70 290	87.87 339	94.27 389

ppachtmachnet_test		88.35 356	87.29 355	91.53 364	92.45 413	83.57 371	93.75 390	95.97 315	84.28 386	85.32 388	94.18 343	79.00 302	96.93 387	75.71 414	84.99 375	94.10 390

Anonymous20240521		86.42 376	85.44 374	89.34 403	90.33 425	79.79 414	96.73 231	95.92 316	83.71 396	83.25 407	91.36 412	63.92 421	96.01 404	78.39 402	85.36 366	92.22 422

ITE_SJBPF				92.43 334	95.34 306	85.37 343		95.92 316	91.47 187	87.75 350	96.39 223	71.00 372	97.96 310	82.36 370	89.86 320	93.97 395

test_fmvs2		89.77 338	89.93 310	89.31 404	93.68 380	76.37 431	97.64 126	95.90 318	89.84 255	91.49 247	96.26 230	58.77 431	97.10 379	94.65 136	91.13 303	94.46 380

USDC		88.94 347	87.83 352	92.27 341	94.66 348	84.96 352	93.86 386	95.90 318	87.34 338	83.40 405	95.56 269	67.43 402	98.19 273	82.64 369	89.67 322	93.66 398

COLMAP_ROB	87.81 15	90.40 318	89.28 331	93.79 282	97.95 123	87.13 298	96.92 211	95.89 320	82.83 403	86.88 373	97.18 169	73.77 356	99.29 140	78.44 401	93.62 267	94.95 351
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
VDD-MVS		93.82 170	93.08 177	96.02 144	97.88 129	89.96 207	97.72 111	95.85 321	92.43 153	95.86 127	98.44 58	68.42 398	99.39 128	96.31 72	94.85 234	98.71 144

VDDNet		93.05 201	92.07 216	96.02 144	96.84 197	90.39 189	98.08 54	95.85 321	86.22 359	95.79 130	98.46 56	67.59 401	99.19 148	94.92 125	94.85 234	98.47 166

mvsmamba		94.57 137	94.14 141	95.87 154	97.03 183	89.93 208	97.84 89	95.85 321	91.34 193	94.79 159	96.80 194	80.67 264	98.81 205	94.85 126	98.12 142	98.85 129

Vis-MVSNet (Re-imp)		94.15 150	93.88 147	94.95 213	97.61 149	87.92 277	98.10 52	95.80 324	92.22 159	93.02 208	97.45 150	84.53 184	97.91 322	88.24 278	97.97 148	99.02 97

MM		97.29 27	96.98 37	98.23 11	98.01 117	95.03 26	98.07 56	95.76 325	97.78 1	97.52 56	98.80 36	88.09 115	99.86 9	99.44 2	99.37 63	99.80 1

KD-MVS_2432*1600		84.81 393	82.64 396	91.31 369	91.07 422	85.34 344	91.22 424	95.75 326	85.56 368	83.09 408	90.21 420	67.21 404	95.89 406	77.18 408	62.48 450	92.69 410

miper_refine_blended		84.81 393	82.64 396	91.31 369	91.07 422	85.34 344	91.22 424	95.75 326	85.56 368	83.09 408	90.21 420	67.21 404	95.89 406	77.18 408	62.48 450	92.69 410

FE-MVS		92.05 245	91.05 257	95.08 201	96.83 199	87.93 276	93.91 385	95.70 328	86.30 356	94.15 176	94.97 293	76.59 328	99.21 146	84.10 350	96.86 183	98.09 205

tpm cat1		88.36 355	87.21 358	91.81 357	95.13 325	80.55 403	92.58 415	95.70 328	74.97 436	87.45 354	91.96 405	78.01 318	98.17 275	80.39 389	88.74 331	96.72 272

our_test_3		88.78 351	87.98 351	91.20 373	92.45 413	82.53 381	93.61 398	95.69 330	85.77 365	84.88 390	93.71 361	79.99 279	96.78 395	79.47 395	86.24 355	94.28 388

BH-w/o		92.14 242	91.75 230	93.31 305	96.99 187	85.73 335	95.67 312	95.69 330	88.73 296	89.26 312	94.82 303	82.97 217	98.07 291	85.26 337	96.32 202	96.13 290

CR-MVSNet		90.82 304	89.77 317	93.95 271	94.45 357	87.19 295	90.23 432	95.68 332	86.89 346	92.40 218	92.36 397	80.91 260	97.05 382	81.09 384	93.95 260	97.60 239

Patchmtry		88.64 353	87.25 356	92.78 327	94.09 367	86.64 308	89.82 436	95.68 332	80.81 418	87.63 352	92.36 397	80.91 260	97.03 383	78.86 399	85.12 371	94.67 375

testing91		91.90 250	91.02 258	94.53 238	96.54 228	86.55 314	95.86 301	95.64 334	91.77 175	91.89 237	93.47 374	69.94 383	98.86 197	90.23 236	93.86 262	98.18 192

BH-RMVSNet		92.72 219	91.97 222	94.97 211	97.16 170	87.99 275	96.15 286	95.60 335	90.62 230	91.87 238	97.15 172	78.41 309	98.57 240	83.16 359	97.60 158	98.36 178

PVSNet_0	82.17 19	85.46 388	83.64 391	90.92 377	95.27 313	79.49 419	90.55 430	95.60 335	83.76 395	83.00 410	89.95 422	71.09 371	97.97 306	82.75 367	60.79 452	95.31 333

guyue		95.17 117	94.96 113	95.82 159	96.97 189	89.65 213	97.56 137	95.58 337	94.82 55	95.72 132	97.42 154	82.90 219	98.84 201	96.71 62	96.93 182	98.96 108

SCA		91.84 252	91.18 254	93.83 279	95.59 288	84.95 353	94.72 352	95.58 337	90.82 217	92.25 226	93.69 363	75.80 336	98.10 282	86.20 319	95.98 205	98.45 168

MonoMVSNet		91.92 248	91.77 228	92.37 335	92.94 401	83.11 375	97.09 195	95.55 339	92.91 141	90.85 264	94.55 316	81.27 256	96.52 398	93.01 175	87.76 340	97.47 245

AllTest		90.23 323	88.98 337	93.98 267	97.94 124	86.64 308	96.51 254	95.54 340	85.38 370	85.49 385	96.77 196	70.28 378	99.15 157	80.02 391	92.87 272	96.15 288

TestCases				93.98 267	97.94 124	86.64 308		95.54 340	85.38 370	85.49 385	96.77 196	70.28 378	99.15 157	80.02 391	92.87 272	96.15 288

mmtdpeth		89.70 340	88.96 338	91.90 352	95.84 280	84.42 358	97.46 157	95.53 342	90.27 242	94.46 168	90.50 416	69.74 387	98.95 187	97.39 48	69.48 441	92.34 418

tpmvs		89.83 337	89.15 335	91.89 353	94.92 335	80.30 407	93.11 407	95.46 343	86.28 357	88.08 344	92.65 387	80.44 270	98.52 244	81.47 376	89.92 319	96.84 268

pmmvs5		89.86 336	88.87 341	92.82 324	92.86 403	86.23 321	96.26 276	95.39 344	84.24 387	87.12 362	94.51 319	74.27 351	97.36 372	87.61 297	87.57 342	94.86 360

PatchmatchNet		91.91 249	91.35 243	93.59 293	95.38 301	84.11 363	93.15 406	95.39 344	89.54 262	92.10 231	93.68 365	82.82 222	98.13 277	84.81 341	95.32 226	98.52 158
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
tpmrst		91.44 273	91.32 245	91.79 358	95.15 323	79.20 422	93.42 401	95.37 346	88.55 301	93.49 197	93.67 366	82.49 231	98.27 266	90.41 231	89.34 325	97.90 217

Anonymous20231206		87.09 368	86.14 370	89.93 396	91.22 421	80.35 405	96.11 287	95.35 347	83.57 398	84.16 397	93.02 382	73.54 358	95.61 414	72.16 431	86.14 357	93.84 397

MIMVSNet1		84.93 391	83.05 393	90.56 386	89.56 431	84.84 355	95.40 327	95.35 347	83.91 390	80.38 422	92.21 402	57.23 434	93.34 437	70.69 437	82.75 402	93.50 400

TDRefinement		86.53 372	84.76 384	91.85 354	82.23 453	84.25 360	96.38 265	95.35 347	84.97 379	84.09 400	94.94 295	65.76 417	98.34 263	84.60 345	74.52 431	92.97 406

TR-MVS		91.48 272	90.59 280	94.16 257	96.40 242	87.33 288	95.67 312	95.34 350	87.68 330	91.46 248	95.52 272	76.77 327	98.35 260	82.85 364	93.61 268	96.79 270

EPNet_dtu		91.71 255	91.28 248	92.99 317	93.76 377	83.71 369	96.69 237	95.28 351	93.15 128	87.02 367	95.95 245	83.37 205	97.38 371	79.46 396	96.84 184	97.88 219
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
FMVSNet5		87.29 365	85.79 372	91.78 359	94.80 342	87.28 290	95.49 324	95.28 351	84.09 389	83.85 404	91.82 406	62.95 424	94.17 429	78.48 400	85.34 367	93.91 396

MDTV_nov1_ep13			90.76 270		95.22 317	80.33 406	93.03 409	95.28 351	88.14 314	92.84 215	93.83 356	81.34 253	98.08 287	82.86 362	94.34 245

LF4IMVS		87.94 359	87.25 356	89.98 394	92.38 415	80.05 413	94.38 366	95.25 354	87.59 332	84.34 394	94.74 307	64.31 420	97.66 346	84.83 340	87.45 343	92.23 421

TransMVSNet (Re)		88.94 347	87.56 353	93.08 315	94.35 360	88.45 260	97.73 108	95.23 355	87.47 334	84.26 396	95.29 279	79.86 282	97.33 373	79.44 397	74.44 432	93.45 402

test20.03		86.14 381	85.40 376	88.35 406	90.12 426	80.06 412	95.90 300	95.20 356	88.59 297	81.29 417	93.62 368	71.43 369	92.65 441	71.26 435	81.17 407	92.34 418

new-patchmatchnet		83.18 399	81.87 402	87.11 414	86.88 444	75.99 433	93.70 392	95.18 357	85.02 378	77.30 433	88.40 432	65.99 415	93.88 434	74.19 423	70.18 439	91.47 431

MDA-MVSNet_test_wron		85.87 385	84.23 388	90.80 383	92.38 415	82.57 380	93.17 404	95.15 358	82.15 407	67.65 445	92.33 400	78.20 311	95.51 417	77.33 405	79.74 411	94.31 387

YYNet1		85.87 385	84.23 388	90.78 384	92.38 415	82.46 385	93.17 404	95.14 359	82.12 408	67.69 443	92.36 397	78.16 314	95.50 418	77.31 406	79.73 412	94.39 383

Baseline_NR-MVSNet		91.20 288	90.62 278	92.95 319	93.83 375	88.03 274	97.01 202	95.12 360	88.42 305	89.70 295	95.13 289	83.47 202	97.44 366	89.66 248	83.24 397	93.37 403

thres200		92.23 238	91.39 242	94.75 226	97.61 149	89.03 244	96.60 249	95.09 361	92.08 167	93.28 203	94.00 352	78.39 310	99.04 183	81.26 383	94.18 251	96.19 284

ADS-MVSNet		89.89 333	88.68 343	93.53 297	95.86 275	84.89 354	90.93 427	95.07 362	83.23 401	91.28 257	91.81 407	79.01 300	97.85 325	79.52 393	91.39 299	97.84 224

pmmvs-eth3d		86.22 379	84.45 386	91.53 364	88.34 440	87.25 292	94.47 361	95.01 363	83.47 399	79.51 427	89.61 425	69.75 386	95.71 411	83.13 360	76.73 425	91.64 426

Anonymous202405211		92.07 244	90.83 268	95.76 163	98.19 103	88.75 249	97.58 133	95.00 364	86.00 362	93.64 189	97.45 150	66.24 413	99.53 106	90.68 225	92.71 277	99.01 100

MDA-MVSNet-bldmvs		85.00 390	82.95 395	91.17 375	93.13 399	83.33 372	94.56 357	95.00 364	84.57 384	65.13 449	92.65 387	70.45 377	95.85 408	73.57 426	77.49 421	94.33 385

ambc				86.56 417	83.60 450	70.00 444	85.69 448	94.97 366		80.60 421	88.45 431	37.42 452	96.84 392	82.69 368	75.44 429	92.86 408

testgi		87.97 358	87.21 358	90.24 391	92.86 403	80.76 398	96.67 240	94.97 366	91.74 176	85.52 384	95.83 251	62.66 426	94.47 427	76.25 412	88.36 335	95.48 316

myMVS_eth3d28		91.52 269	90.97 260	93.17 311	96.91 191	83.24 374	95.61 318	94.96 368	92.24 158	91.98 234	93.28 379	69.31 388	98.40 252	88.71 273	95.68 215	97.88 219

dp		88.90 349	88.26 349	90.81 381	94.58 353	76.62 430	92.85 412	94.93 369	85.12 376	90.07 286	93.07 381	75.81 335	98.12 280	80.53 388	87.42 345	97.71 231

test_fmvs3		83.21 398	83.02 394	83.78 421	86.77 445	68.34 447	96.76 229	94.91 370	86.49 352	84.14 399	89.48 426	36.04 453	91.73 443	91.86 196	80.77 409	91.26 433

test_0402		86.46 375	84.79 383	91.45 366	95.02 329	85.55 337	96.29 275	94.89 371	80.90 415	82.21 413	93.97 354	68.21 399	97.29 375	62.98 444	88.68 332	91.51 429

tfpn200view9		92.38 228	91.52 239	94.95 213	97.85 130	89.29 234	97.41 160	94.88 372	92.19 163	93.27 204	94.46 324	78.17 312	99.08 171	81.40 377	94.08 255	96.48 277

CVMVSNet		91.23 286	91.75 230	89.67 398	95.77 281	74.69 434	96.44 255	94.88 372	85.81 364	92.18 227	97.64 137	79.07 295	95.58 416	88.06 281	95.86 210	98.74 141

thres400		92.42 226	91.52 239	95.12 200	97.85 130	89.29 234	97.41 160	94.88 372	92.19 163	93.27 204	94.46 324	78.17 312	99.08 171	81.40 377	94.08 255	96.98 262

tt0320		85.39 389	83.12 392	92.19 345	93.44 391	85.79 333	96.19 283	94.87 375	71.19 443	82.92 411	91.76 409	58.43 432	96.81 393	81.03 385	78.26 420	93.98 394

EPNet		95.20 115	94.56 126	97.14 71	92.80 405	92.68 93	97.85 88	94.87 375	96.64 7	92.46 217	97.80 122	86.23 151	99.65 73	93.72 156	98.62 118	99.10 90
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
testing99		91.62 260	90.72 275	94.32 249	96.48 236	86.11 330	95.81 304	94.76 377	91.55 180	91.75 242	93.44 375	68.55 396	98.82 203	90.43 230	93.69 264	98.04 209

sc_t1		86.48 374	84.10 390	93.63 290	93.45 390	85.76 334	96.79 224	94.71 378	73.06 441	86.45 377	94.35 329	55.13 439	97.95 314	84.38 348	78.55 419	97.18 258

SixPastTwentyTwo		89.15 345	88.54 345	90.98 376	93.49 387	80.28 409	96.70 235	94.70 379	90.78 218	84.15 398	95.57 268	71.78 367	97.71 342	84.63 344	85.07 372	94.94 353

thres100view900		92.43 225	91.58 236	94.98 209	97.92 126	89.37 230	97.71 113	94.66 380	92.20 161	93.31 202	94.90 298	78.06 316	99.08 171	81.40 377	94.08 255	96.48 277

thres600view7		92.49 223	91.60 235	95.18 196	97.91 127	89.47 224	97.65 122	94.66 380	92.18 165	93.33 201	94.91 297	78.06 316	99.10 165	81.61 373	94.06 259	96.98 262

PatchT		88.87 350	87.42 354	93.22 309	94.08 368	85.10 348	89.51 437	94.64 382	81.92 409	92.36 221	88.15 435	80.05 278	97.01 385	72.43 430	93.65 266	97.54 242

baseline1		92.82 215	91.90 225	95.55 179	97.20 168	90.77 175	97.19 187	94.58 383	92.20 161	92.36 221	96.34 225	84.16 192	98.21 270	89.20 263	83.90 392	97.68 233

AstraMVS		94.82 131	94.64 122	95.34 191	96.36 246	88.09 273	97.58 133	94.56 384	94.98 44	95.70 135	97.92 106	81.93 245	98.93 190	96.87 56	95.88 208	98.99 104

UBG		91.55 266	90.76 270	93.94 273	96.52 232	85.06 349	95.22 339	94.54 385	90.47 238	91.98 234	92.71 386	72.02 364	98.74 217	88.10 280	95.26 228	98.01 211

Gipuma		67.86 419	65.41 421	75.18 434	92.66 408	73.45 438	66.50 455	94.52 386	53.33 454	57.80 455	66.07 455	30.81 455	89.20 447	48.15 453	78.88 418	62.90 455
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
testing11		91.68 258	90.75 272	94.47 240	96.53 230	86.56 313	95.76 308	94.51 387	91.10 210	91.24 259	93.59 369	68.59 395	98.86 197	91.10 213	94.29 247	98.00 212

CostFormer		91.18 291	90.70 276	92.62 332	94.84 340	81.76 391	94.09 378	94.43 388	84.15 388	92.72 216	93.77 360	79.43 289	98.20 271	90.70 224	92.18 286	97.90 217

tpm2		89.96 330	89.21 333	92.23 344	94.91 337	81.25 394	93.78 389	94.42 389	80.62 420	91.56 245	93.44 375	76.44 331	97.94 316	85.60 331	92.08 290	97.49 243

testing3-2		92.10 243	92.05 217	92.27 341	97.71 139	79.56 416	97.42 159	94.41 390	93.53 109	93.22 206	95.49 273	69.16 390	99.11 163	93.25 165	94.22 249	98.13 197

MVS_0304		96.74 59	96.31 76	98.02 19	96.87 193	94.65 30	97.58 133	94.39 391	96.47 10	97.16 68	98.39 62	87.53 131	99.87 7	98.97 18	99.41 55	99.55 39

JIA-IIPM		88.26 357	87.04 361	91.91 351	93.52 385	81.42 393	89.38 438	94.38 392	80.84 417	90.93 263	80.74 447	79.22 292	97.92 319	82.76 366	91.62 294	96.38 280

dmvs_re		90.21 324	89.50 326	92.35 336	95.47 298	85.15 346	95.70 311	94.37 393	90.94 216	88.42 331	93.57 370	74.63 348	95.67 413	82.80 365	89.57 323	96.22 282

Patchmatch-test		89.42 343	87.99 350	93.70 287	95.27 313	85.11 347	88.98 439	94.37 393	81.11 414	87.10 365	93.69 363	82.28 235	97.50 361	74.37 421	94.76 238	98.48 165

LCM-MVSNet		72.55 412	69.39 416	82.03 423	70.81 463	65.42 452	90.12 434	94.36 395	55.02 453	65.88 447	81.72 446	24.16 461	89.96 444	74.32 422	68.10 444	90.71 436

ADS-MVSNet2		89.45 342	88.59 344	92.03 348	95.86 275	82.26 387	90.93 427	94.32 396	83.23 401	91.28 257	91.81 407	79.01 300	95.99 405	79.52 393	91.39 299	97.84 224

mvs5depth		86.53 372	85.08 379	90.87 378	88.74 438	82.52 382	91.91 420	94.23 397	86.35 355	87.11 364	93.70 362	66.52 409	97.76 337	81.37 380	75.80 427	92.31 420

EU-MVSNet		88.72 352	88.90 340	88.20 408	93.15 398	74.21 436	96.63 246	94.22 398	85.18 374	87.32 359	95.97 243	76.16 333	94.98 422	85.27 336	86.17 356	95.41 323

tt0320-xc		84.83 392	82.33 400	92.31 339	93.66 381	86.20 323	96.17 285	94.06 399	71.26 442	82.04 415	92.22 401	55.07 440	96.72 396	81.49 375	75.04 430	94.02 393

MIMVSNet		88.50 354	86.76 364	93.72 286	94.84 340	87.77 283	91.39 422	94.05 400	86.41 354	87.99 346	92.59 390	63.27 422	95.82 410	77.44 404	92.84 274	97.57 241

OpenMVS_ROB	81.14 20	84.42 395	82.28 401	90.83 379	90.06 427	84.05 365	95.73 310	94.04 401	73.89 439	80.17 425	91.53 411	59.15 430	97.64 347	66.92 442	89.05 327	90.80 435

TinyColmap		86.82 370	85.35 377	91.21 371	94.91 337	82.99 377	93.94 382	94.02 402	83.58 397	81.56 416	94.68 309	62.34 427	98.13 277	75.78 413	87.35 348	92.52 416

ETVMVS		90.52 315	89.14 336	94.67 229	96.81 203	87.85 281	95.91 299	93.97 403	89.71 258	92.34 224	92.48 392	65.41 418	97.96 310	81.37 380	94.27 248	98.21 190

IB-MVS	87.33 17	89.91 331	88.28 348	94.79 223	95.26 316	87.70 284	95.12 344	93.95 404	89.35 270	87.03 366	92.49 391	70.74 375	99.19 148	89.18 264	81.37 406	97.49 243
Christian Sormann, Mattia Rossi, Andreas Kuhn and Friedrich Fraundorfer: IB-MVS: An Iterative Algorithm for Deep Multi-View Stereo based on Binary Decisions. BMVC 2021
Syy-MVS		87.13 367	87.02 362	87.47 412	95.16 320	73.21 440	95.00 346	93.93 405	88.55 301	86.96 368	91.99 403	75.90 334	94.00 431	61.59 446	94.11 252	95.20 341

myMVS_eth3d		87.18 366	86.38 367	89.58 399	95.16 320	79.53 417	95.00 346	93.93 405	88.55 301	86.96 368	91.99 403	56.23 437	94.00 431	75.47 417	94.11 252	95.20 341

testing222		90.31 319	88.96 338	94.35 246	96.54 228	87.29 289	95.50 323	93.84 407	90.97 213	91.75 242	92.96 383	62.18 428	98.00 301	82.86 362	94.08 255	97.76 229

test_f		80.57 405	79.62 407	83.41 422	83.38 451	67.80 449	93.57 399	93.72 408	80.80 419	77.91 432	87.63 438	33.40 454	92.08 442	87.14 308	79.04 417	90.34 437

LCM-MVSNet-Re		92.50 221	92.52 205	92.44 333	96.82 201	81.89 390	96.92 211	93.71 409	92.41 154	84.30 395	94.60 314	85.08 173	97.03 383	91.51 204	97.36 166	98.40 174

tpm		90.25 322	89.74 320	91.76 361	93.92 371	79.73 415	93.98 379	93.54 410	88.28 308	91.99 233	93.25 380	77.51 322	97.44 366	87.30 303	87.94 338	98.12 199

ET-MVSNet_ETH3D		91.49 271	90.11 300	95.63 173	96.40 242	91.57 137	95.34 330	93.48 411	90.60 233	75.58 435	95.49 273	80.08 277	96.79 394	94.25 144	89.76 321	98.52 158

LFMVS		93.60 177	92.63 198	96.52 102	98.13 109	91.27 149	97.94 76	93.39 412	90.57 235	96.29 109	98.31 75	69.00 391	99.16 155	94.18 145	95.87 209	99.12 88

MVStest1		82.38 402	80.04 406	89.37 401	87.63 443	82.83 378	95.03 345	93.37 413	73.90 438	73.50 440	94.35 329	62.89 425	93.25 439	73.80 424	65.92 447	92.04 425

Patchmatch-RL test		87.38 364	86.24 368	90.81 381	88.74 438	78.40 426	88.12 446	93.17 414	87.11 343	82.17 414	89.29 427	81.95 243	95.60 415	88.64 275	77.02 422	98.41 173

ttmdpeth		85.91 384	84.76 384	89.36 402	89.14 433	80.25 410	95.66 315	93.16 415	83.77 394	83.39 406	95.26 283	66.24 413	95.26 421	80.65 386	75.57 428	92.57 413

test-LLR		91.42 274	91.19 253	92.12 346	94.59 351	80.66 400	94.29 372	92.98 416	91.11 208	90.76 266	92.37 394	79.02 298	98.07 291	88.81 270	96.74 187	97.63 234

test-mter		90.19 326	89.54 325	92.12 346	94.59 351	80.66 400	94.29 372	92.98 416	87.68 330	90.76 266	92.37 394	67.67 400	98.07 291	88.81 270	96.74 187	97.63 234

WB-MVSnew		89.88 334	89.56 324	90.82 380	94.57 354	83.06 376	95.65 316	92.85 418	87.86 321	90.83 265	94.10 346	79.66 286	96.88 390	76.34 411	94.19 250	92.54 415

testing3		87.67 362	86.88 363	90.05 393	96.14 264	80.71 399	97.10 194	92.85 418	90.15 246	87.54 353	94.55 316	55.70 438	94.10 430	73.77 425	94.10 254	95.35 330

test_method		66.11 420	64.89 422	69.79 437	72.62 461	35.23 469	65.19 456	92.83 420	20.35 459	65.20 448	88.08 436	43.14 450	82.70 454	73.12 428	63.46 449	91.45 432

test0.0.03 1		89.37 344	88.70 342	91.41 368	92.47 412	85.63 336	95.22 339	92.70 421	91.11 208	86.91 372	93.65 367	79.02 298	93.19 440	78.00 403	89.18 326	95.41 323

new_pmnet		82.89 400	81.12 405	88.18 409	89.63 430	80.18 411	91.77 421	92.57 422	76.79 434	75.56 436	88.23 434	61.22 429	94.48 426	71.43 433	82.92 400	89.87 438

mvsany_test1		93.93 166	93.98 145	93.78 283	94.94 334	86.80 304	94.62 354	92.55 423	88.77 295	96.85 78	98.49 52	88.98 97	98.08 287	95.03 120	95.62 217	96.46 279

thisisatest0515		92.29 234	91.30 247	95.25 194	96.60 219	88.90 247	94.36 367	92.32 424	87.92 318	93.43 199	94.57 315	77.28 323	99.00 184	89.42 254	95.86 210	97.86 223

thisisatest0530		93.03 202	92.21 214	95.49 183	97.07 175	89.11 243	97.49 154	92.19 425	90.16 245	94.09 177	96.41 221	76.43 332	99.05 180	90.38 232	95.68 215	98.31 184

tttt0517		92.96 205	92.33 211	94.87 216	97.11 173	87.16 297	97.97 72	92.09 426	90.63 229	93.88 183	97.01 185	76.50 329	99.06 177	90.29 235	95.45 224	98.38 176

K. test v3		87.64 363	86.75 365	90.32 390	93.02 400	79.48 420	96.61 247	92.08 427	90.66 227	80.25 424	94.09 348	67.21 404	96.65 397	85.96 327	80.83 408	94.83 362

TESTMET0.1,1		90.06 328	89.42 328	91.97 349	94.41 359	80.62 402	94.29 372	91.97 428	87.28 340	90.44 270	92.47 393	68.79 392	97.67 344	88.50 277	96.60 192	97.61 238

PM-MVS		83.48 397	81.86 403	88.31 407	87.83 442	77.59 428	93.43 400	91.75 429	86.91 345	80.63 420	89.91 423	44.42 449	95.84 409	85.17 339	76.73 425	91.50 430

baseline2		91.63 259	90.86 264	93.94 273	94.33 361	86.32 318	95.92 298	91.64 430	89.37 269	86.94 370	94.69 308	81.62 250	98.69 224	88.64 275	94.57 243	96.81 269

APD_test1		79.31 407	77.70 410	84.14 420	89.11 435	69.07 446	92.36 419	91.50 431	69.07 445	73.87 438	92.63 389	39.93 451	94.32 428	70.54 438	80.25 410	89.02 440

FPMVS		71.27 413	69.85 415	75.50 433	74.64 458	59.03 458	91.30 423	91.50 431	58.80 450	57.92 454	88.28 433	29.98 457	85.53 453	53.43 451	82.84 401	81.95 446

door								91.13 433

door-mid								91.06 434

EGC-MVSNET		68.77 418	63.01 424	86.07 419	92.49 411	82.24 388	93.96 381	90.96 435	0.71 464	2.62 465	90.89 414	53.66 441	93.46 435	57.25 449	84.55 382	82.51 445

mvsany_test3		83.59 396	82.44 399	87.03 415	83.80 448	73.82 437	93.70 392	90.92 436	86.42 353	82.51 412	90.26 419	46.76 448	95.71 411	90.82 219	76.76 424	91.57 428

pmmvs3		79.97 406	77.50 411	87.39 413	82.80 452	79.38 421	92.70 414	90.75 437	70.69 444	78.66 429	87.47 440	51.34 444	93.40 436	73.39 427	69.65 440	89.38 439

UWE-MVS		89.91 331	89.48 327	91.21 371	95.88 274	78.23 427	94.91 349	90.26 438	89.11 276	92.35 223	94.52 318	68.76 393	97.96 310	83.95 354	95.59 218	97.42 247

DSMNet-mixed		86.34 377	86.12 371	87.00 416	89.88 429	70.43 442	94.93 348	90.08 439	77.97 431	85.42 387	92.78 385	74.44 350	93.96 433	74.43 420	95.14 229	96.62 273

MVS-HIRNet		82.47 401	81.21 404	86.26 418	95.38 301	69.21 445	88.96 440	89.49 440	66.28 447	80.79 419	74.08 452	68.48 397	97.39 370	71.93 432	95.47 223	92.18 423

WB-MVS		76.77 409	76.63 412	77.18 428	85.32 446	56.82 460	94.53 358	89.39 441	82.66 405	71.35 441	89.18 428	75.03 343	88.88 448	35.42 457	66.79 445	85.84 442

test1111		93.19 194	92.82 188	94.30 252	97.58 155	84.56 357	98.21 43	89.02 442	93.53 109	94.58 163	98.21 82	72.69 360	99.05 180	93.06 171	98.48 125	99.28 73

SSC-MVS		76.05 410	75.83 413	76.72 432	84.77 447	56.22 461	94.32 370	88.96 443	81.82 411	70.52 442	88.91 429	74.79 347	88.71 449	33.69 458	64.71 448	85.23 443

ECVR-MVS		93.19 194	92.73 194	94.57 235	97.66 143	85.41 340	98.21 43	88.23 444	93.43 114	94.70 161	98.21 82	72.57 361	99.07 175	93.05 172	98.49 123	99.25 76

EPMVS		90.70 309	89.81 315	93.37 303	94.73 346	84.21 361	93.67 395	88.02 445	89.50 264	92.38 220	93.49 372	77.82 320	97.78 334	86.03 325	92.68 278	98.11 204

ANet_high		63.94 422	59.58 425	77.02 429	61.24 465	66.06 450	85.66 449	87.93 446	78.53 429	42.94 457	71.04 454	25.42 460	80.71 456	52.60 452	30.83 458	84.28 444

PMMVS2		70.19 414	66.92 418	80.01 424	76.35 457	65.67 451	86.22 447	87.58 447	64.83 449	62.38 450	80.29 449	26.78 459	88.49 451	63.79 443	54.07 454	85.88 441

lessismore_v0				90.45 387	91.96 418	79.09 424		87.19 448		80.32 423	94.39 326	66.31 412	97.55 355	84.00 353	76.84 423	94.70 374

PMVS	53.92 22	58.58 423	55.40 426	68.12 438	51.00 466	48.64 463	78.86 452	87.10 449	46.77 455	35.84 461	74.28 451	8.76 465	86.34 452	42.07 455	73.91 433	69.38 452
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
UWE-MVS-28		86.81 371	86.41 366	88.02 410	92.87 402	74.60 435	95.38 329	86.70 450	88.17 311	87.28 361	94.67 311	70.83 374	93.30 438	67.45 440	94.31 246	96.17 285

test_vis1_rt		86.16 380	85.06 380	89.46 400	93.47 389	80.46 404	96.41 259	86.61 451	85.22 373	79.15 428	88.64 430	52.41 443	97.06 381	93.08 170	90.57 312	90.87 434

testf1		69.31 416	66.76 419	76.94 430	78.61 455	61.93 454	88.27 444	86.11 452	55.62 451	59.69 451	85.31 443	20.19 463	89.32 445	57.62 447	69.44 442	79.58 447

APD_test2		69.31 416	66.76 419	76.94 430	78.61 455	61.93 454	88.27 444	86.11 452	55.62 451	59.69 451	85.31 443	20.19 463	89.32 445	57.62 447	69.44 442	79.58 447

gg-mvs-nofinetune		87.82 360	85.61 373	94.44 242	94.46 356	89.27 237	91.21 426	84.61 454	80.88 416	89.89 290	74.98 450	71.50 368	97.53 358	85.75 330	97.21 175	96.51 275

dmvs_testset		81.38 404	82.60 398	77.73 427	91.74 419	51.49 462	93.03 409	84.21 455	89.07 277	78.28 431	91.25 413	76.97 325	88.53 450	56.57 450	82.24 403	93.16 404

GG-mvs-BLEND				93.62 291	93.69 379	89.20 239	92.39 418	83.33 456		87.98 347	89.84 424	71.00 372	96.87 391	82.08 372	95.40 225	94.80 367

MTMP							97.86 85	82.03 457

DeepMVS_CX				74.68 435	90.84 424	64.34 453		81.61 458	65.34 448	67.47 446	88.01 437	48.60 447	80.13 457	62.33 445	73.68 434	79.58 447

E-PMN		53.28 424	52.56 428	55.43 441	74.43 459	47.13 464	83.63 451	76.30 459	42.23 456	42.59 458	62.22 457	28.57 458	74.40 458	31.53 459	31.51 457	44.78 456

test2506		91.60 261	90.78 269	94.04 263	97.66 143	83.81 366	98.27 33	75.53 460	93.43 114	95.23 147	98.21 82	67.21 404	99.07 175	93.01 175	98.49 123	99.25 76

EMVS		52.08 426	51.31 429	54.39 442	72.62 461	45.39 466	83.84 450	75.51 461	41.13 457	40.77 459	59.65 458	30.08 456	73.60 459	28.31 461	29.90 459	44.18 457

test_vis3_rt		72.73 411	70.55 414	79.27 425	80.02 454	68.13 448	93.92 384	74.30 462	76.90 433	58.99 453	73.58 453	20.29 462	95.37 419	84.16 349	72.80 436	74.31 450

MVE	50.73 23	53.25 425	48.81 430	66.58 440	65.34 464	57.50 459	72.49 454	70.94 463	40.15 458	39.28 460	63.51 456	6.89 467	73.48 460	38.29 456	42.38 456	68.76 454
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
tmp_tt		51.94 427	53.82 427	46.29 443	33.73 467	45.30 467	78.32 453	67.24 464	18.02 460	50.93 456	87.05 441	52.99 442	53.11 462	70.76 436	25.29 460	40.46 458

kuosan		65.27 421	64.66 423	67.11 439	83.80 448	61.32 457	88.53 443	60.77 465	68.22 446	67.67 444	80.52 448	49.12 446	70.76 461	29.67 460	53.64 455	69.26 453

dongtai		69.99 415	69.33 417	71.98 436	88.78 437	61.64 456	89.86 435	59.93 466	75.67 435	74.96 437	85.45 442	50.19 445	81.66 455	43.86 454	55.27 453	72.63 451

N_pmnet		78.73 408	78.71 409	78.79 426	92.80 405	46.50 465	94.14 376	43.71 467	78.61 428	80.83 418	91.66 410	74.94 346	96.36 401	67.24 441	84.45 384	93.50 400

wuyk23d		25.11 428	24.57 432	26.74 444	73.98 460	39.89 468	57.88 457	9.80 468	12.27 461	10.39 462	6.97 464	7.03 466	36.44 463	25.43 462	17.39 461	3.89 461

testmvs		13.36 430	16.33 433	4.48 446	5.04 468	2.26 471	93.18 403	3.28 469	2.70 462	8.24 463	21.66 460	2.29 469	2.19 464	7.58 463	2.96 462	9.00 460

test123		13.04 431	15.66 434	5.18 445	4.51 469	3.45 470	92.50 417	1.81 470	2.50 463	7.58 464	20.15 461	3.67 468	2.18 465	7.13 464	1.07 463	9.90 459

mmdepth		0.00 434	0.00 437	0.00 447	0.00 470	0.00 472	0.00 458	0.00 471	0.00 465	0.00 466	0.00 465	0.00 470	0.00 466	0.00 465	0.00 464	0.00 462

monomultidepth		0.00 434	0.00 437	0.00 447	0.00 470	0.00 472	0.00 458	0.00 471	0.00 465	0.00 466	0.00 465	0.00 470	0.00 466	0.00 465	0.00 464	0.00 462

test_blank		0.00 434	0.00 437	0.00 447	0.00 470	0.00 472	0.00 458	0.00 471	0.00 465	0.00 466	0.00 465	0.00 470	0.00 466	0.00 465	0.00 464	0.00 462

uanet_test		0.00 434	0.00 437	0.00 447	0.00 470	0.00 472	0.00 458	0.00 471	0.00 465	0.00 466	0.00 465	0.00 470	0.00 466	0.00 465	0.00 464	0.00 462

DCPMVS		0.00 434	0.00 437	0.00 447	0.00 470	0.00 472	0.00 458	0.00 471	0.00 465	0.00 466	0.00 465	0.00 470	0.00 466	0.00 465	0.00 464	0.00 462

pcd_1.5k_mvsjas		7.39 433	9.85 436	0.00 447	0.00 470	0.00 472	0.00 458	0.00 471	0.00 465	0.00 466	0.00 465	88.65 105	0.00 466	0.00 465	0.00 464	0.00 462

sosnet-low-res		0.00 434	0.00 437	0.00 447	0.00 470	0.00 472	0.00 458	0.00 471	0.00 465	0.00 466	0.00 465	0.00 470	0.00 466	0.00 465	0.00 464	0.00 462

sosnet		0.00 434	0.00 437	0.00 447	0.00 470	0.00 472	0.00 458	0.00 471	0.00 465	0.00 466	0.00 465	0.00 470	0.00 466	0.00 465	0.00 464	0.00 462

uncertanet		0.00 434	0.00 437	0.00 447	0.00 470	0.00 472	0.00 458	0.00 471	0.00 465	0.00 466	0.00 465	0.00 470	0.00 466	0.00 465	0.00 464	0.00 462

Regformer		0.00 434	0.00 437	0.00 447	0.00 470	0.00 472	0.00 458	0.00 471	0.00 465	0.00 466	0.00 465	0.00 470	0.00 466	0.00 465	0.00 464	0.00 462

n2								0.00 471

nn								0.00 471

ab-mvs-re		8.06 432	10.74 435	0.00 447	0.00 470	0.00 472	0.00 458	0.00 471	0.00 465	0.00 466	96.69 202	0.00 470	0.00 466	0.00 465	0.00 464	0.00 462

uanet		0.00 434	0.00 437	0.00 447	0.00 470	0.00 472	0.00 458	0.00 471	0.00 465	0.00 466	0.00 465	0.00 470	0.00 466	0.00 465	0.00 464	0.00 462

WAC-MVS						79.53 417								75.56 416

PC_three_1452									90.77 219	98.89 24	98.28 80	96.24 1	98.35 260	95.76 99	99.58 23	99.59 28

eth-test2					0.00 470

eth-test					0.00 470

OPU-MVS				98.55 3	98.82 57	96.86 3	98.25 36				98.26 81	96.04 2	99.24 143	95.36 113	99.59 19	99.56 36

test_0728_THIRD									94.78 59	98.73 28	98.87 29	95.87 4	99.84 23	97.45 44	99.72 2	99.77 2

GSMVS																98.45 168

test_part2					99.28 27	95.74 8				98.10 42

sam_mvs1												82.76 223				98.45 168

sam_mvs												81.94 244

test_post1							92.81 413				16.58 463	80.53 268	97.68 343	86.20 319

test_post											17.58 462	81.76 247	98.08 287

patchmatchnet-post											90.45 418	82.65 228	98.10 282

gm-plane-assit					93.22 396	78.89 425			84.82 381		93.52 371		98.64 231	87.72 287

test9_res														94.81 130	99.38 60	99.45 55

agg_prior2														93.94 150	99.38 60	99.50 48

test_prior4						93.66 58	96.42 258

test_prior2							96.35 267		92.80 146	96.03 119	97.59 143	92.01 47		95.01 121	99.38 60

旧先验2							95.94 296		81.66 412	97.34 64			98.82 203	92.26 181

新几何2							95.79 306

原ACMM2							95.67 312

testdata2													99.67 71	85.96 327

segment_acmp												92.89 30

testdata1							95.26 338		93.10 131

plane_prior7					96.21 251	89.98 204

plane_prior6					96.10 267	90.00 200						81.32 254

plane_prior4											96.64 205

plane_prior3						90.00 200			94.46 76	91.34 251

plane_prior2							97.74 106		94.85 51

plane_prior1					96.14 264

plane_prior						89.99 202	97.24 179		94.06 88						92.16 287

HQP5-MVS						89.33 232

HQP-NCC					95.86 275		96.65 241		93.55 105	90.14 275

ACMP_Plane					95.86 275		96.65 241		93.55 105	90.14 275

BP-MVS														92.13 189

HQP4-MVS										90.14 275			98.50 245			95.78 304

HQP2-MVS												80.95 258

NP-MVS					95.99 273	89.81 211					95.87 248

MDTV_nov1_ep13_2view						70.35 443	93.10 408		83.88 392	93.55 192		82.47 232		86.25 318		98.38 176

ACMMP++_ref															90.30 317

ACMMP++															91.02 306

Test By Simon												88.73 104

High-resolution multi-view benchmark