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.

MSP-MVS		90.38 5	91.87 1	85.88 94	92.83 80	64.03 213	93.06 126	94.33 59	82.19 43	93.65 3	96.15 44	85.89 1	97.19 92	91.02 45	97.75 1	96.43 31
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++		90.53 4	91.09 5	88.87 16	97.31 4	69.91 43	93.96 82	94.37 57	72.48 218	92.07 10	96.85 21	83.82 2	99.15 2	91.53 41	97.42 4	97.55 4

OPU-MVS				89.97 3	97.52 3	73.15 14	96.89 6				97.00 13	83.82 2	99.15 2	95.72 8	97.63 3	97.62 2

PC_three_1452									80.91 63	94.07 2	96.83 23	83.57 4	99.12 5	95.70 10	97.42 4	97.55 4

DPM-MVS		90.70 3	90.52 9	91.24 1	89.68 165	76.68 2	97.29 1	95.35 17	82.87 35	91.58 17	97.22 7	79.93 5	99.10 9	83.12 118	97.64 2	97.94 1

baseline2		83.68 121	83.42 112	84.48 165	87.37 243	66.00 152	90.06 264	95.93 8	79.71 83	69.08 276	90.39 195	77.92 6	96.28 147	78.91 161	81.38 204	91.16 242

GG-mvs-BLEND				86.53 75	91.91 114	69.67 54	75.02 414	94.75 36		78.67 155	90.85 187	77.91 7	94.56 233	72.25 216	93.74 45	95.36 68

gg-mvs-nofinetune		77.18 249	74.31 271	85.80 99	91.42 128	68.36 81	71.78 419	94.72 37	49.61 418	77.12 171	45.92 447	77.41 8	93.98 264	67.62 265	93.16 55	95.05 88

SED-MVS		89.94 9	90.36 10	88.70 18	96.45 12	69.38 57	96.89 6	94.44 51	71.65 248	92.11 8	97.21 8	76.79 9	99.11 6	92.34 33	95.36 14	97.62 2

test_241102_ONE					96.45 12	69.38 57		94.44 51	71.65 248	92.11 8	97.05 11	76.79 9	99.11 6

test_0728_THIRD									72.48 218	90.55 25	96.93 15	76.24 11	99.08 11	91.53 41	94.99 18	96.43 31

DPE-MVS		88.77 17	89.21 17	87.45 43	96.26 20	67.56 106	94.17 68	94.15 64	68.77 299	90.74 23	97.27 5	76.09 12	98.49 29	90.58 49	94.91 21	96.30 34
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
TSAR-MVS + GP.		87.96 23	88.37 25	86.70 67	93.51 62	65.32 171	95.15 37	93.84 70	78.17 116	85.93 64	94.80 88	75.80 13	98.21 36	89.38 52	88.78 117	96.59 19

DeepPCF-MVS	81.17 1	89.72 10	91.38 4	84.72 150	93.00 76	58.16 349	96.72 9	94.41 53	86.50 9	90.25 29	97.83 1	75.46 14	98.67 25	92.78 30	95.49 13	97.32 6

BP-MVS1		86.54 52	86.68 52	86.13 87	87.80 233	67.18 117	92.97 131	95.62 10	79.92 78	82.84 98	94.14 112	74.95 15	96.46 140	82.91 122	88.96 116	94.74 105

dcpmvs_2		87.37 36	87.55 37	86.85 58	95.04 32	68.20 89	90.36 255	90.66 228	79.37 91	81.20 115	93.67 124	74.73 16	96.55 134	90.88 46	92.00 70	95.82 49

MVSTER		82.47 143	82.05 138	83.74 189	92.68 87	69.01 66	91.90 187	93.21 100	79.83 79	72.14 239	85.71 283	74.72 17	94.72 223	75.72 181	72.49 287	87.50 293

test_241102_TWO								94.41 53	71.65 248	92.07 10	97.21 8	74.58 18	99.11 6	92.34 33	95.36 14	96.59 19

WBMVS		81.67 156	80.98 157	83.72 193	93.07 74	69.40 55	94.33 64	93.05 109	76.84 139	72.05 241	84.14 299	74.49 19	93.88 269	72.76 210	68.09 316	87.88 288

test_one_0601					96.32 18	69.74 51		94.18 62	71.42 259	90.67 24	96.85 21	74.45 20

DELS-MVS		90.05 8	90.09 11	89.94 4	93.14 71	73.88 9	97.01 4	94.40 55	88.32 3	85.71 66	94.91 85	74.11 21	98.91 18	87.26 73	95.94 8	97.03 12
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
patch_mono-2		89.71 11	90.99 6	85.85 97	96.04 24	63.70 225	95.04 42	95.19 22	86.74 8	91.53 19	95.15 78	73.86 22	97.58 64	93.38 25	92.00 70	96.28 37

DVP-MVS		89.41 13	89.73 14	88.45 25	96.40 15	69.99 39	96.64 10	94.52 47	71.92 234	90.55 25	96.93 15	73.77 23	99.08 11	91.91 39	94.90 22	96.29 35
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
test0726					96.40 15	69.99 39	96.76 8	94.33 59	71.92 234	91.89 13	97.11 10	73.77 23

ET-MVSNet_ETH3D		84.01 110	83.15 121	86.58 72	90.78 145	70.89 28	94.74 52	94.62 43	81.44 54	58.19 377	93.64 125	73.64 25	92.35 319	82.66 124	78.66 239	96.50 27

UBG		86.83 45	86.70 50	87.20 48	93.07 74	69.81 47	93.43 115	95.56 13	81.52 50	81.50 110	92.12 160	73.58 26	96.28 147	84.37 105	85.20 160	95.51 60

testing3-2		83.11 131	83.15 121	82.98 219	91.92 112	64.01 214	94.39 63	95.37 16	78.32 113	75.53 188	90.06 213	73.18 27	93.18 284	74.34 195	75.27 266	91.77 227

CSCG		86.87 42	86.26 58	88.72 17	95.05 31	70.79 29	93.83 94	95.33 18	68.48 303	77.63 163	94.35 103	73.04 28	98.45 30	84.92 98	93.71 47	96.92 14

tttt0517		79.50 202	78.53 203	82.41 236	87.22 247	61.43 290	89.75 273	94.76 35	69.29 289	67.91 295	88.06 247	72.92 29	95.63 181	62.91 311	73.90 278	90.16 256

GDP-MVS		85.54 77	85.32 78	86.18 85	87.64 236	67.95 96	92.91 137	92.36 138	77.81 122	83.69 88	94.31 106	72.84 30	96.41 142	80.39 146	85.95 153	94.19 137

MCST-MVS		91.08 1	91.46 3	89.94 4	97.66 2	73.37 10	97.13 2	95.58 11	89.33 1	85.77 65	96.26 40	72.84 30	99.38 1	92.64 31	95.93 9	97.08 11

thisisatest0515		83.41 124	82.49 134	86.16 86	89.46 171	68.26 85	93.54 107	94.70 39	74.31 179	75.75 181	90.92 185	72.62 32	96.52 136	69.64 240	81.50 203	93.71 163

thisisatest0530		81.15 167	80.07 172	84.39 168	88.26 216	65.63 163	91.40 206	94.62 43	71.27 261	70.93 254	89.18 224	72.47 33	96.04 162	65.62 290	76.89 257	91.49 231

myMVS_eth3d28		86.31 59	86.15 62	86.78 63	93.56 58	70.49 33	92.94 134	95.28 19	82.47 39	78.70 154	92.07 162	72.45 34	95.41 193	82.11 128	85.78 155	94.44 125

balanced_conf03		89.08 15	88.84 20	89.81 6	93.66 54	75.15 5	90.61 248	93.43 93	84.06 22	86.20 60	90.17 207	72.42 35	96.98 109	93.09 27	95.92 10	97.29 7

testing11		86.71 50	86.44 55	87.55 40	93.54 60	71.35 21	93.65 101	95.58 11	81.36 57	80.69 123	92.21 159	72.30 36	96.46 140	85.18 94	83.43 180	94.82 103

TSAR-MVS + MP.		88.11 22	88.64 22	86.54 74	91.73 119	68.04 92	90.36 255	93.55 85	82.89 33	91.29 21	92.89 140	72.27 37	96.03 163	87.99 63	94.77 26	95.54 59
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
EPP-MVSNet		81.79 155	81.52 146	82.61 229	88.77 192	60.21 321	93.02 130	93.66 81	68.52 302	72.90 223	90.39 195	72.19 38	94.96 213	74.93 189	79.29 232	92.67 195

CostFormer		82.33 145	81.15 150	85.86 96	89.01 186	68.46 79	82.39 370	93.01 111	75.59 159	80.25 130	81.57 333	72.03 39	94.96 213	79.06 158	77.48 250	94.16 140

HPM-MVS++		89.37 14	89.95 13	87.64 34	95.10 30	68.23 88	95.24 34	94.49 49	82.43 40	88.90 39	96.35 35	71.89 40	98.63 26	88.76 59	96.40 6	96.06 41

testing99		86.01 65	85.47 75	87.63 38	93.62 55	71.25 23	93.47 113	95.23 21	80.42 69	80.60 125	91.95 167	71.73 41	96.50 138	80.02 149	82.22 193	95.13 83

MVSMamba_PlusPlus		84.97 89	83.65 102	88.93 14	90.17 156	74.04 8	87.84 316	92.69 125	62.18 359	81.47 112	87.64 253	71.47 42	96.28 147	84.69 100	94.74 31	96.47 28

CNVR-MVS		90.32 6	90.89 8	88.61 22	96.76 8	70.65 30	96.47 14	94.83 33	84.83 15	89.07 38	96.80 24	70.86 43	99.06 15	92.64 31	95.71 11	96.12 40

IB-MVS	77.80 4	82.18 147	80.46 169	87.35 45	89.14 183	70.28 36	95.59 27	95.17 24	78.85 103	70.19 264	85.82 281	70.66 44	97.67 56	72.19 219	66.52 328	94.09 144
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
testing91		85.93 67	85.31 79	87.78 32	93.59 57	71.47 19	93.50 110	95.08 28	80.26 71	80.53 126	91.93 168	70.43 45	96.51 137	80.32 147	82.13 195	95.37 66

ETVMVS		84.22 106	83.71 100	85.76 101	92.58 90	68.25 87	92.45 162	95.53 15	79.54 86	79.46 140	91.64 175	70.29 46	94.18 250	69.16 248	82.76 188	94.84 99

MM		90.87 2	91.52 2	88.92 15	92.12 101	71.10 27	97.02 3	96.04 6	88.70 2	91.57 18	96.19 42	70.12 47	98.91 18	96.83 2	95.06 17	96.76 15

fmvsm_l_conf0.5_n		87.49 33	88.19 28	85.39 113	86.95 253	64.37 201	94.30 65	88.45 325	80.51 66	92.70 4	96.86 19	69.98 48	97.15 97	95.83 7	88.08 125	94.65 111

baseline1		81.84 154	81.03 155	84.28 173	91.60 122	66.62 137	91.08 227	91.66 180	81.87 46	74.86 197	91.67 174	69.98 48	94.92 216	71.76 222	64.75 345	91.29 240

fmvsm_l_conf0.5_n_a		87.44 35	88.15 29	85.30 119	87.10 250	64.19 208	94.41 60	88.14 335	80.24 74	92.54 5	96.97 14	69.52 50	97.17 93	95.89 6	88.51 120	94.56 114

fmvsm_s_conf0.5_n_9		88.14 19	89.21 17	84.92 134	89.29 176	61.41 291	92.97 131	88.36 327	86.96 6	91.49 20	97.49 3	69.48 51	97.46 71	97.00 1	89.88 105	95.89 47

testing222		85.18 83	84.69 91	86.63 69	92.91 78	69.91 43	92.61 153	95.80 9	80.31 70	80.38 128	92.27 155	68.73 52	95.19 206	75.94 179	83.27 182	94.81 104

alignmvs		87.28 37	86.97 44	88.24 27	91.30 133	71.14 26	95.61 26	93.56 84	79.30 92	87.07 52	95.25 73	68.43 53	96.93 117	87.87 64	84.33 170	96.65 17

PAPM		85.89 69	85.46 76	87.18 49	88.20 220	72.42 15	92.41 163	92.77 120	82.11 44	80.34 129	93.07 135	68.27 54	95.02 209	78.39 166	93.59 49	94.09 144

train_agg		87.21 38	87.42 39	86.60 70	94.18 41	67.28 113	94.16 69	93.51 87	71.87 239	85.52 69	95.33 65	68.19 55	97.27 87	89.09 56	94.90 22	95.25 80

test_8					94.19 40	67.19 115	94.15 71	93.42 94	71.87 239	85.38 72	95.35 64	68.19 55	96.95 114

TEST9					94.18 41	67.28 113	94.16 69	93.51 87	71.75 245	85.52 69	95.33 65	68.01 57	97.27 87

test_prior2							95.10 39		75.40 164	85.25 75	95.61 56	67.94 58		87.47 70	94.77 26

WTY-MVS		86.32 57	85.81 69	87.85 29	92.82 82	69.37 59	95.20 35	95.25 20	82.71 36	81.91 106	94.73 89	67.93 59	97.63 61	79.55 152	82.25 192	96.54 22

APDe-MVS		87.54 30	87.84 32	86.65 68	96.07 23	66.30 145	94.84 50	93.78 71	69.35 288	88.39 41	96.34 36	67.74 60	97.66 59	90.62 48	93.44 51	96.01 44
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
test_fmvsm_n_1920		87.69 29	88.50 23	85.27 122	87.05 252	63.55 232	93.69 99	91.08 209	84.18 21	90.17 31	97.04 12	67.58 61	97.99 41	95.72 8	90.03 102	94.26 133

fmvsm_l_conf0.5_n_9		88.24 18	89.36 16	84.85 139	88.15 221	61.94 275	95.65 25	89.70 275	85.54 11	92.07 10	97.33 4	67.51 62	97.27 87	96.23 5	92.07 69	95.35 69

tpm2		79.80 198	77.95 212	85.34 118	88.28 215	68.26 85	81.56 376	91.42 189	70.11 279	77.59 165	80.50 351	67.40 63	94.26 248	67.34 269	77.35 251	93.51 169

miper_enhance_ethall		78.86 217	77.97 211	81.54 260	88.00 226	65.17 175	91.41 204	89.15 294	75.19 168	68.79 284	83.98 302	67.17 64	92.82 297	72.73 211	65.30 335	86.62 314

SF-MVS		87.03 40	87.09 42	86.84 59	92.70 86	67.45 111	93.64 102	93.76 74	70.78 272	86.25 58	96.44 32	66.98 65	97.79 50	88.68 60	94.56 34	95.28 76

HY-MVS	76.49 5	84.28 102	83.36 115	87.02 55	92.22 96	67.74 101	84.65 343	94.50 48	79.15 96	82.23 104	87.93 248	66.88 66	96.94 115	80.53 144	82.20 194	96.39 33

EPNet		87.84 27	88.38 24	86.23 84	93.30 65	66.05 150	95.26 33	94.84 32	87.09 5	88.06 42	94.53 94	66.79 67	97.34 80	83.89 110	91.68 76	95.29 74
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
9.14			87.63 34		93.86 48		94.41 60	94.18 62	72.76 213	86.21 59	96.51 30	66.64 68	97.88 47	90.08 50	94.04 39

FIs		79.47 204	79.41 188	79.67 310	85.95 279	59.40 334	91.68 199	93.94 68	78.06 117	68.96 281	88.28 238	66.61 69	91.77 333	66.20 284	74.99 267	87.82 289

NCCC		89.07 16	89.46 15	87.91 28	96.60 10	69.05 65	96.38 15	94.64 42	84.42 19	86.74 55	96.20 41	66.56 70	98.76 24	89.03 58	94.56 34	95.92 46

MVS_0304		90.32 6	90.90 7	88.55 23	94.05 45	70.23 37	97.00 5	93.73 78	87.30 4	92.15 7	96.15 44	66.38 71	98.94 17	96.71 3	94.67 33	96.47 28

reproduce_monomvs		79.49 203	79.11 197	80.64 283	92.91 78	61.47 289	91.17 225	93.28 98	83.09 31	64.04 336	82.38 319	66.19 72	94.57 230	81.19 139	57.71 393	85.88 332

SD-MVS		87.49 33	87.49 38	87.50 42	93.60 56	68.82 71	93.90 86	92.63 131	76.86 138	87.90 44	95.76 52	66.17 73	97.63 61	89.06 57	91.48 80	96.05 42
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
UniMVSNet_NR-MVSNet		78.15 232	77.55 219	79.98 300	84.46 313	60.26 319	92.25 166	93.20 102	77.50 131	68.88 282	86.61 269	66.10 74	92.13 325	66.38 281	62.55 362	87.54 292

CHOSEN 280x420		77.35 247	76.95 233	78.55 326	87.07 251	62.68 257	69.71 425	82.95 397	68.80 298	71.48 250	87.27 261	66.03 75	84.00 410	76.47 176	82.81 186	88.95 272

CANet		89.61 12	89.99 12	88.46 24	94.39 39	69.71 52	96.53 13	93.78 71	86.89 7	89.68 35	95.78 51	65.94 76	99.10 9	92.99 28	93.91 42	96.58 21

segment_acmp												65.94 76

fmvsm_s_conf0.5_n_3		86.88 41	87.99 31	83.58 199	87.26 245	60.74 305	93.21 123	87.94 342	84.22 20	91.70 15	97.27 5	65.91 78	95.02 209	93.95 22	90.42 97	94.99 91

Vis-MVSNet (Re-imp)		79.24 208	79.57 183	78.24 331	88.46 206	52.29 389	90.41 252	89.12 297	74.24 180	69.13 274	91.91 169	65.77 79	90.09 362	59.00 334	88.09 124	92.33 208

FC-MVSNet-test		77.99 236	78.08 209	77.70 334	84.89 303	55.51 375	90.27 258	93.75 77	76.87 137	66.80 314	87.59 254	65.71 80	90.23 359	62.89 312	73.94 276	87.37 297

SMA-MVS		88.14 19	88.29 26	87.67 33	93.21 68	68.72 74	93.85 89	94.03 67	74.18 181	91.74 14	96.67 27	65.61 81	98.42 33	89.24 55	96.08 7	95.88 48
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
test12				87.09 52	94.60 36	68.86 69		92.91 115		82.67 103		65.44 82	97.55 67		93.69 48	94.84 99

fmvsm_l_conf0.5_n_3		87.54 30	88.29 26	85.30 119	86.92 258	62.63 258	95.02 44	90.28 247	84.95 14	90.27 28	96.86 19	65.36 83	97.52 69	94.93 13	90.03 102	95.76 51

test_fmvsmconf_n		86.58 51	87.17 41	84.82 141	85.28 293	62.55 259	94.26 67	89.78 266	83.81 25	87.78 46	96.33 37	65.33 84	96.98 109	94.40 18	87.55 131	94.95 93

旧先验1					91.94 110	60.74 305		91.50 186			94.36 99	65.23 85			91.84 73	94.55 115

1112_ss		80.56 181	79.83 179	82.77 223	88.65 193	60.78 301	92.29 165	88.36 327	72.58 216	72.46 235	94.95 81	65.09 86	93.42 281	66.38 281	77.71 244	94.10 143

MVSFormer		83.75 118	82.88 127	86.37 80	89.24 181	71.18 24	89.07 292	90.69 225	65.80 326	87.13 50	94.34 104	64.99 87	92.67 305	72.83 207	91.80 74	95.27 77

lupinMVS		87.74 28	87.77 33	87.63 38	89.24 181	71.18 24	96.57 12	92.90 116	82.70 37	87.13 50	95.27 71	64.99 87	95.80 169	89.34 53	91.80 74	95.93 45

tpmrst		80.57 180	79.14 196	84.84 140	90.10 157	68.28 84	81.70 374	89.72 273	77.63 129	75.96 180	79.54 365	64.94 89	92.71 302	75.43 183	77.28 253	93.55 167

ZD-MVS					96.63 9	65.50 168		93.50 89	70.74 273	85.26 74	95.19 77	64.92 90	97.29 83	87.51 68	93.01 56

testing3		70.38 332	70.83 317	69.03 402	85.82 284	43.93 433	90.72 242	90.56 232	68.06 306	60.24 364	86.82 268	64.83 91	84.12 406	26.33 443	64.10 352	79.04 410

casdiffmvs_mvg		85.66 74	85.18 81	87.09 52	88.22 219	69.35 60	93.74 98	91.89 164	81.47 51	80.10 131	91.45 177	64.80 92	96.35 145	87.23 74	87.69 129	95.58 57
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
miper_ehance_all_eth		77.60 243	76.44 239	81.09 275	85.70 287	64.41 199	90.65 244	88.64 321	72.31 224	67.37 307	82.52 317	64.77 93	92.64 308	70.67 234	65.30 335	86.24 319

fmvsm_s_conf0.5_n_6		87.50 32	88.72 21	83.84 187	86.89 260	60.04 325	95.05 40	92.17 151	84.80 16	92.27 6	96.37 33	64.62 94	96.54 135	94.43 17	91.86 72	94.94 94

Test_1112_low_res		79.56 201	78.60 202	82.43 233	88.24 218	60.39 317	92.09 175	87.99 339	72.10 232	71.84 243	87.42 257	64.62 94	93.04 286	65.80 288	77.30 252	93.85 160

test2506		83.29 126	82.92 126	84.37 169	88.39 211	63.18 244	92.01 180	91.35 191	77.66 127	78.49 156	91.42 178	64.58 96	95.09 208	73.19 203	89.23 110	94.85 96

DeepC-MVS_fast	79.48 2	87.95 25	88.00 30	87.79 31	95.86 27	68.32 82	95.74 21	94.11 65	83.82 24	83.49 91	96.19 42	64.53 97	98.44 31	83.42 117	94.88 25	96.61 18
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
MG-MVS		87.11 39	86.27 57	89.62 8	97.79 1	76.27 4	94.96 46	94.49 49	78.74 107	83.87 87	92.94 138	64.34 98	96.94 115	75.19 185	94.09 38	95.66 54

fmvsm_s_conf0.5_n_4		86.79 48	87.63 34	84.27 174	86.15 275	61.48 288	94.69 56	91.16 200	83.79 26	90.51 27	96.28 38	64.24 99	98.22 35	95.00 12	86.88 137	93.11 182

casdiffmvs		85.37 79	84.87 87	86.84 59	88.25 217	69.07 64	93.04 128	91.76 171	81.27 58	80.84 122	92.07 162	64.23 100	96.06 161	84.98 97	87.43 133	95.39 64
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
cl22		77.94 238	76.78 234	81.42 262	87.57 237	64.93 183	90.67 243	88.86 312	72.45 220	67.63 301	82.68 316	64.07 101	92.91 295	71.79 220	65.30 335	86.44 315

fmvsm_s_conf0.5_n_8		87.96 23	88.93 19	85.07 129	88.43 208	61.78 278	94.73 55	91.74 172	85.87 10	91.66 16	97.50 2	64.03 102	98.33 34	96.28 4	90.08 101	95.10 85

tpm		78.58 225	77.03 230	83.22 214	85.94 281	64.56 190	83.21 361	91.14 204	78.31 114	73.67 216	79.68 363	64.01 103	92.09 327	66.07 285	71.26 297	93.03 186

CDS-MVSNet		81.43 161	80.74 159	83.52 200	86.26 271	64.45 195	92.09 175	90.65 229	75.83 157	73.95 213	89.81 215	63.97 104	92.91 295	71.27 226	82.82 185	93.20 179
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
MVS_Test		84.16 108	83.20 118	87.05 54	91.56 124	69.82 46	89.99 269	92.05 153	77.77 124	82.84 98	86.57 270	63.93 105	96.09 157	74.91 190	89.18 112	95.25 80

APD-MVS		85.93 67	85.99 66	85.76 101	95.98 26	65.21 174	93.59 105	92.58 133	66.54 321	86.17 61	95.88 50	63.83 106	97.00 105	86.39 83	92.94 57	95.06 87
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
mvs_anonymous		81.36 163	79.99 175	85.46 110	90.39 152	68.40 80	86.88 331	90.61 230	74.41 176	70.31 263	84.67 293	63.79 107	92.32 321	73.13 204	85.70 156	95.67 53

PVSNet_Blended_VisFu		83.97 111	83.50 105	85.39 113	90.02 158	66.59 139	93.77 96	91.73 173	77.43 133	77.08 173	89.81 215	63.77 108	96.97 112	79.67 151	88.21 123	92.60 198

baseline		85.01 87	84.44 93	86.71 66	88.33 214	68.73 73	90.24 260	91.82 170	81.05 62	81.18 116	92.50 147	63.69 109	96.08 160	84.45 104	86.71 144	95.32 72

myMVS_eth3d		72.58 320	72.74 298	72.10 390	87.87 229	49.45 407	88.07 310	89.01 304	72.91 209	63.11 345	88.10 244	63.63 110	85.54 399	32.73 435	69.23 307	81.32 389

CDPH-MVS		85.71 72	85.46 76	86.46 76	94.75 34	67.19 115	93.89 87	92.83 118	70.90 268	83.09 96	95.28 69	63.62 111	97.36 78	80.63 143	94.18 37	94.84 99

HyFIR lowres test		81.03 172	79.56 184	85.43 111	87.81 232	68.11 91	90.18 261	90.01 260	70.65 274	72.95 222	86.06 277	63.61 112	94.50 237	75.01 188	79.75 223	93.67 164

sasdasda		86.85 43	86.25 59	88.66 20	91.80 117	71.92 16	93.54 107	91.71 175	80.26 71	87.55 47	95.25 73	63.59 113	96.93 117	88.18 61	84.34 168	97.11 9

canonicalmvs		86.85 43	86.25 59	88.66 20	91.80 117	71.92 16	93.54 107	91.71 175	80.26 71	87.55 47	95.25 73	63.59 113	96.93 117	88.18 61	84.34 168	97.11 9

c3_l		76.83 258	75.47 254	80.93 279	85.02 301	64.18 209	90.39 253	88.11 336	71.66 247	66.65 316	81.64 331	63.58 115	92.56 309	69.31 246	62.86 359	86.04 325

SteuartSystems-ACMMP		86.82 47	86.90 47	86.58 72	90.42 150	66.38 142	96.09 17	93.87 69	77.73 125	84.01 86	95.66 54	63.39 116	97.94 42	87.40 71	93.55 50	95.42 62
Skip Steuart: Steuart Systems R&D Blog.
test_fmvsmconf0.1_n		85.71 72	86.08 65	84.62 160	80.83 352	62.33 264	93.84 92	88.81 313	83.50 28	87.00 53	96.01 48	63.36 117	96.93 117	94.04 21	87.29 134	94.61 113

EI-MVSNet-Vis-set		83.77 117	83.67 101	84.06 178	92.79 85	63.56 231	91.76 195	94.81 34	79.65 84	77.87 160	94.09 115	63.35 118	97.90 45	79.35 154	79.36 229	90.74 249

UniMVSNet (Re)		77.58 244	76.78 234	79.98 300	84.11 319	60.80 300	91.76 195	93.17 104	76.56 150	69.93 270	84.78 292	63.32 119	92.36 318	64.89 297	62.51 364	86.78 308

PVSNet_BlendedMVS		83.38 125	83.43 110	83.22 214	93.76 50	67.53 108	94.06 74	93.61 82	79.13 97	81.00 120	85.14 288	63.19 120	97.29 83	87.08 77	73.91 277	84.83 349

PVSNet_Blended		86.73 49	86.86 48	86.31 83	93.76 50	67.53 108	96.33 16	93.61 82	82.34 42	81.00 120	93.08 134	63.19 120	97.29 83	87.08 77	91.38 82	94.13 142

NormalMVS		86.39 54	86.66 53	85.60 107	92.12 101	65.95 155	94.88 47	90.83 216	84.69 17	83.67 89	94.10 113	63.16 122	96.91 121	85.31 90	91.15 86	93.93 153

SymmetryMVS		86.32 57	86.39 56	86.12 88	90.52 148	65.95 155	94.88 47	94.58 46	84.69 17	83.67 89	94.10 113	63.16 122	96.91 121	85.31 90	86.59 146	95.51 60

UWE-MVS		80.81 176	81.01 156	80.20 293	89.33 174	57.05 363	91.91 186	94.71 38	75.67 158	75.01 195	89.37 220	63.13 124	91.44 346	67.19 272	82.80 187	92.12 219

PAPM_NR		82.97 134	81.84 143	86.37 80	94.10 44	66.76 134	87.66 320	92.84 117	69.96 281	74.07 211	93.57 127	63.10 125	97.50 70	70.66 235	90.58 94	94.85 96

nrg030		80.93 173	79.86 178	84.13 177	83.69 324	68.83 70	93.23 121	91.20 198	75.55 160	75.06 194	88.22 243	63.04 126	94.74 222	81.88 130	66.88 325	88.82 275

fmvsm_s_conf0.5_n		86.39 54	86.91 46	84.82 141	87.36 244	63.54 233	94.74 52	90.02 259	82.52 38	90.14 32	96.92 17	62.93 127	97.84 49	95.28 11	82.26 190	93.07 185

MGCFI-Net		85.59 76	85.73 72	85.17 126	91.41 131	62.44 260	92.87 139	91.31 192	79.65 84	86.99 54	95.14 79	62.90 128	96.12 155	87.13 76	84.13 175	96.96 13

fmvsm_s_conf0.5_n_5		86.38 56	86.94 45	84.71 152	84.67 305	63.29 238	94.04 78	89.99 261	82.88 34	87.85 45	96.03 47	62.89 129	96.36 144	94.15 19	89.95 104	94.48 123

EI-MVSNet-UG-set		83.14 130	82.96 123	83.67 196	92.28 94	63.19 243	91.38 210	94.68 40	79.22 94	76.60 176	93.75 121	62.64 130	97.76 51	78.07 168	78.01 242	90.05 258

DeepC-MVS	77.85 3	85.52 78	85.24 80	86.37 80	88.80 191	66.64 136	92.15 171	93.68 80	81.07 61	76.91 174	93.64 125	62.59 131	98.44 31	85.50 88	92.84 59	94.03 148
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
UWE-MVS-28		76.83 258	77.60 218	74.51 368	84.58 309	50.34 401	88.22 308	94.60 45	74.46 175	66.66 315	88.98 230	62.53 132	85.50 402	57.55 340	80.80 215	87.69 291

EIA-MVS		84.84 91	84.88 86	84.69 153	91.30 133	62.36 263	93.85 89	92.04 154	79.45 87	79.33 143	94.28 108	62.42 133	96.35 145	80.05 148	91.25 85	95.38 65

fmvsm_s_conf0.5_n_a		85.75 71	86.09 64	84.72 150	85.73 286	63.58 230	93.79 95	89.32 285	81.42 55	90.21 30	96.91 18	62.41 134	97.67 56	94.48 16	80.56 217	92.90 191

CS-MVS		85.80 70	86.65 54	83.27 212	92.00 109	58.92 341	95.31 32	91.86 166	79.97 76	84.82 77	95.40 63	62.26 135	95.51 192	86.11 85	92.08 68	95.37 66

MVS_111021_HR		86.19 62	85.80 70	87.37 44	93.17 70	69.79 48	93.99 81	93.76 74	79.08 99	78.88 150	93.99 118	62.25 136	98.15 38	85.93 87	91.15 86	94.15 141

PHI-MVS		86.83 45	86.85 49	86.78 63	93.47 63	65.55 166	95.39 31	95.10 25	71.77 244	85.69 67	96.52 29	62.07 137	98.77 23	86.06 86	95.60 12	96.03 43

MP-MVS		85.02 86	84.97 85	85.17 126	92.60 89	64.27 206	93.24 120	92.27 141	73.13 203	79.63 138	94.43 97	61.90 138	97.17 93	85.00 96	92.56 61	94.06 147
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
jason		86.40 53	86.17 61	87.11 51	86.16 274	70.54 32	95.71 24	92.19 148	82.00 45	84.58 79	94.34 104	61.86 139	95.53 191	87.76 65	90.89 90	95.27 77
jason: jason.
fmvsm_s_conf0.1_n		85.61 75	85.93 67	84.68 154	82.95 335	63.48 235	94.03 80	89.46 279	81.69 48	89.86 33	96.74 25	61.85 140	97.75 52	94.74 15	82.01 197	92.81 193

SPE-MVS-test		86.14 63	87.01 43	83.52 200	92.63 88	59.36 337	95.49 28	91.92 161	80.09 75	85.46 71	95.53 60	61.82 141	95.77 172	86.77 81	93.37 52	95.41 63

PAPR		85.15 84	84.47 92	87.18 49	96.02 25	68.29 83	91.85 190	93.00 113	76.59 149	79.03 146	95.00 80	61.59 142	97.61 63	78.16 167	89.00 115	95.63 55

IS-MVSNet		80.14 191	79.41 188	82.33 237	87.91 227	60.08 324	91.97 184	88.27 332	72.90 211	71.44 251	91.73 173	61.44 143	93.66 276	62.47 315	86.53 148	93.24 176

cl____		76.07 269	74.67 262	80.28 290	85.15 296	61.76 280	90.12 262	88.73 316	71.16 262	65.43 322	81.57 333	61.15 144	92.95 290	66.54 278	62.17 366	86.13 323

DIV-MVS_self_test		76.07 269	74.67 262	80.28 290	85.14 297	61.75 281	90.12 262	88.73 316	71.16 262	65.42 323	81.60 332	61.15 144	92.94 294	66.54 278	62.16 368	86.14 321

EI-MVSNet		78.97 214	78.22 207	81.25 265	85.33 290	62.73 256	89.53 280	93.21 100	72.39 223	72.14 239	90.13 210	60.99 146	94.72 223	67.73 264	72.49 287	86.29 317

IterMVS-LS		76.49 262	75.18 259	80.43 287	84.49 312	62.74 255	90.64 245	88.80 314	72.40 222	65.16 325	81.72 329	60.98 147	92.27 322	67.74 263	64.65 347	86.29 317
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
fmvsm_s_conf0.1_n_a		84.76 93	84.84 88	84.53 162	80.23 365	63.50 234	92.79 141	88.73 316	80.46 67	89.84 34	96.65 28	60.96 148	97.57 66	93.80 23	80.14 219	92.53 202

ETV-MVS		86.01 65	86.11 63	85.70 104	90.21 155	67.02 124	93.43 115	91.92 161	81.21 59	84.13 85	94.07 117	60.93 149	95.63 181	89.28 54	89.81 106	94.46 124

tpm cat1		75.30 285	72.21 306	84.58 161	88.52 199	67.77 100	78.16 402	88.02 338	61.88 365	68.45 290	76.37 390	60.65 150	94.03 262	53.77 354	74.11 274	91.93 225

TAMVS		80.37 186	79.45 187	83.13 217	85.14 297	63.37 236	91.23 220	90.76 224	74.81 173	72.65 227	88.49 233	60.63 151	92.95 290	69.41 244	81.95 198	93.08 184

ZNCC-MVS		85.33 80	85.08 83	86.06 89	93.09 73	65.65 162	93.89 87	93.41 95	73.75 192	79.94 133	94.68 91	60.61 152	98.03 40	82.63 125	93.72 46	94.52 119

fmvsm_s_conf0.5_n_7		85.24 81	86.69 51	80.91 280	84.52 310	60.10 323	93.35 118	90.35 240	83.41 29	86.54 57	96.27 39	60.50 153	90.02 364	94.84 14	90.38 98	92.61 197

viewmanbaseed2359cas		84.89 90	84.26 96	86.78 63	88.50 200	69.77 50	92.69 150	91.13 205	81.11 60	81.54 109	91.98 165	60.35 154	95.73 174	84.47 103	86.56 147	94.84 99

thres100view900		78.37 228	77.01 231	82.46 232	91.89 115	63.21 242	91.19 224	96.33 1	72.28 226	70.45 260	87.89 249	60.31 155	95.32 200	45.16 394	77.58 247	88.83 273

thres600view7		78.00 235	76.66 236	82.03 252	91.93 111	63.69 226	91.30 216	96.33 1	72.43 221	70.46 259	87.89 249	60.31 155	94.92 216	42.64 406	76.64 258	87.48 294

CHOSEN 1792x2688		84.98 88	83.45 109	89.57 11	89.94 160	75.14 6	92.07 177	92.32 139	81.87 46	75.68 183	88.27 239	60.18 157	98.60 27	80.46 145	90.27 100	94.96 92

h-mvs33		83.01 133	82.56 133	84.35 170	89.34 172	62.02 271	92.72 144	93.76 74	81.45 52	82.73 101	92.25 157	60.11 158	97.13 98	87.69 66	62.96 358	93.91 156

hse-mvs2		81.12 170	81.11 154	81.16 268	86.52 266	57.48 358	89.40 283	91.16 200	81.45 52	82.73 101	90.49 193	60.11 158	94.58 228	87.69 66	60.41 385	91.41 234

tfpn200view9		78.79 220	77.43 221	82.88 221	92.21 97	64.49 192	92.05 178	96.28 4	73.48 198	71.75 245	88.26 240	60.07 160	95.32 200	45.16 394	77.58 247	88.83 273

thres400		78.68 222	77.43 221	82.43 233	92.21 97	64.49 192	92.05 178	96.28 4	73.48 198	71.75 245	88.26 240	60.07 160	95.32 200	45.16 394	77.58 247	87.48 294

diffmvs		84.28 102	83.83 99	85.61 106	87.40 242	68.02 93	90.88 233	89.24 288	80.54 65	81.64 108	92.52 146	59.83 162	94.52 236	87.32 72	85.11 161	94.29 132
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
MVS		84.66 95	82.86 128	90.06 2	90.93 140	74.56 7	87.91 314	95.54 14	68.55 301	72.35 238	94.71 90	59.78 163	98.90 20	81.29 138	94.69 32	96.74 16

lecture		84.77 92	84.81 89	84.65 156	92.12 101	62.27 267	94.74 52	92.64 130	68.35 304	85.53 68	95.30 67	59.77 164	97.91 44	83.73 112	91.15 86	93.77 162

thres200		79.66 199	78.33 204	83.66 197	92.54 91	65.82 160	93.06 126	96.31 3	74.90 172	73.30 219	88.66 231	59.67 165	95.61 183	47.84 381	78.67 238	89.56 267

Effi-MVS+		83.82 115	82.76 129	86.99 56	89.56 168	69.40 55	91.35 213	86.12 366	72.59 215	83.22 95	92.81 144	59.60 166	96.01 165	81.76 131	87.80 128	95.56 58

diffmvs_AUTHOR		83.97 111	83.49 106	85.39 113	86.09 276	67.83 98	90.76 238	89.05 302	79.94 77	81.43 113	92.23 158	59.53 167	94.42 239	87.18 75	85.22 159	93.92 155

viewmambaseed2359dif		82.60 142	81.91 142	84.67 155	85.83 283	66.09 149	90.50 249	89.01 304	75.46 161	79.64 137	92.01 164	59.51 168	94.38 241	82.99 121	82.26 190	93.54 168

eth_miper_zixun_eth		75.96 276	74.40 270	80.66 282	84.66 306	63.02 246	89.28 286	88.27 332	71.88 238	65.73 320	81.65 330	59.45 169	92.81 298	68.13 256	60.53 382	86.14 321

ACMMP_NAP		86.05 64	85.80 70	86.80 62	91.58 123	67.53 108	91.79 192	93.49 90	74.93 171	84.61 78	95.30 67	59.42 170	97.92 43	86.13 84	94.92 20	94.94 94

GST-MVS		84.63 96	84.29 95	85.66 105	92.82 82	65.27 172	93.04 128	93.13 106	73.20 201	78.89 147	94.18 111	59.41 171	97.85 48	81.45 134	92.48 63	93.86 159

UA-Net		80.02 194	79.65 182	81.11 271	89.33 174	57.72 353	86.33 336	89.00 308	77.44 132	81.01 119	89.15 225	59.33 172	95.90 166	61.01 322	84.28 172	89.73 264

NR-MVSNet		76.05 272	74.59 265	80.44 286	82.96 333	62.18 269	90.83 235	91.73 173	77.12 135	60.96 360	86.35 272	59.28 173	91.80 332	60.74 323	61.34 377	87.35 298

MP-MVS-pluss		85.24 81	85.13 82	85.56 108	91.42 128	65.59 164	91.54 202	92.51 135	74.56 174	80.62 124	95.64 55	59.15 174	97.00 105	86.94 79	93.80 43	94.07 146
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
reproduce-ours		83.51 122	83.33 116	84.06 178	92.18 99	60.49 313	90.74 240	92.04 154	64.35 336	83.24 92	95.59 58	59.05 175	97.27 87	83.61 113	89.17 113	94.41 130

our_new_method		83.51 122	83.33 116	84.06 178	92.18 99	60.49 313	90.74 240	92.04 154	64.35 336	83.24 92	95.59 58	59.05 175	97.27 87	83.61 113	89.17 113	94.41 130

HFP-MVS		84.73 94	84.40 94	85.72 103	93.75 52	65.01 180	93.50 110	93.19 103	72.19 228	79.22 144	94.93 83	59.04 177	97.67 56	81.55 132	92.21 64	94.49 122

mamv4		65.18 371	67.43 341	58.44 420	77.88 398	49.36 410	69.40 426	70.99 433	48.31 423	57.78 383	85.53 284	59.01 178	51.88 458	73.67 198	64.32 349	74.07 428

MSLP-MVS++		86.27 60	85.91 68	87.35 45	92.01 108	68.97 68	95.04 42	92.70 122	79.04 102	81.50 110	96.50 31	58.98 179	96.78 125	83.49 116	93.93 41	96.29 35

Patchmatch-test		65.86 366	60.94 381	80.62 285	83.75 323	58.83 342	58.91 445	75.26 418	44.50 433	50.95 412	77.09 384	58.81 180	87.90 381	35.13 426	64.03 353	95.12 84

reproduce_model		83.15 129	82.96 123	83.73 191	92.02 105	59.74 329	90.37 254	92.08 152	63.70 343	82.86 97	95.48 61	58.62 181	97.17 93	83.06 119	88.42 121	94.26 133

EPNet_dtu		78.80 219	79.26 193	77.43 339	88.06 223	49.71 405	91.96 185	91.95 160	77.67 126	76.56 177	91.28 182	58.51 182	90.20 360	56.37 343	80.95 207	92.39 205
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
kuosan		60.86 392	60.24 382	62.71 417	81.57 346	46.43 424	75.70 412	85.88 368	57.98 388	48.95 419	69.53 419	58.42 183	76.53 433	28.25 442	35.87 440	65.15 441

test_fmvsmvis_n_1920		83.80 116	83.48 107	84.77 145	82.51 338	63.72 223	91.37 211	83.99 390	81.42 55	77.68 162	95.74 53	58.37 184	97.58 64	93.38 25	86.87 138	93.00 188

EC-MVSNet		84.53 97	85.04 84	83.01 218	89.34 172	61.37 292	94.42 59	91.09 207	77.91 120	83.24 92	94.20 110	58.37 184	95.40 194	85.35 89	91.41 81	92.27 214

VNet		86.20 61	85.65 73	87.84 30	93.92 47	69.99 39	95.73 23	95.94 7	78.43 112	86.00 63	93.07 135	58.22 186	97.00 105	85.22 92	84.33 170	96.52 23

TESTMET0.1,1		82.41 144	81.98 141	83.72 193	88.08 222	63.74 220	92.70 146	93.77 73	79.30 92	77.61 164	87.57 255	58.19 187	94.08 255	73.91 197	86.68 145	93.33 175

原ACMM1				84.42 166	93.21 68	64.27 206		93.40 96	65.39 329	79.51 139	92.50 147	58.11 188	96.69 128	65.27 295	93.96 40	92.32 209

sam_mvs1												57.85 189				94.68 108

CR-MVSNet		73.79 303	70.82 319	82.70 226	83.15 331	67.96 94	70.25 422	84.00 388	73.67 196	69.97 268	72.41 407	57.82 190	89.48 368	52.99 357	73.13 281	90.64 251

Patchmtry		67.53 358	63.93 366	78.34 327	82.12 342	64.38 200	68.72 427	84.00 388	48.23 424	59.24 369	72.41 407	57.82 190	89.27 369	46.10 390	56.68 398	81.36 388

patchmatchnet-post											67.62 426	57.62 192	90.25 355

PCF-MVS	73.15 9	79.29 207	77.63 217	84.29 172	86.06 277	65.96 154	87.03 327	91.10 206	69.86 283	69.79 271	90.64 188	57.54 193	96.59 130	64.37 300	82.29 189	90.32 254
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
Fast-Effi-MVS+		81.14 168	80.01 174	84.51 164	90.24 154	65.86 158	94.12 73	89.15 294	73.81 191	75.37 191	88.26 240	57.26 194	94.53 235	66.97 275	84.92 162	93.15 180

miper_lstm_enhance		73.05 309	71.73 312	77.03 345	83.80 322	58.32 348	81.76 372	88.88 310	69.80 284	61.01 359	78.23 373	57.19 195	87.51 390	65.34 294	59.53 387	85.27 346

PatchT		69.11 342	65.37 356	80.32 288	82.07 343	63.68 227	67.96 432	87.62 344	50.86 415	69.37 272	65.18 429	57.09 196	88.53 375	41.59 409	66.60 327	88.74 276

testdata				81.34 264	89.02 185	57.72 353		89.84 265	58.65 386	85.32 73	94.09 115	57.03 197	93.28 282	69.34 245	90.56 95	93.03 186

PatchmatchNet		77.46 245	74.63 264	85.96 92	89.55 169	70.35 35	79.97 393	89.55 277	72.23 227	70.94 253	76.91 386	57.03 197	92.79 300	54.27 351	81.17 205	94.74 105
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
test_yl		84.28 102	83.16 119	87.64 34	94.52 37	69.24 61	95.78 18	95.09 26	69.19 291	81.09 117	92.88 141	57.00 199	97.44 73	81.11 140	81.76 200	96.23 38

DCV-MVSNet		84.28 102	83.16 119	87.64 34	94.52 37	69.24 61	95.78 18	95.09 26	69.19 291	81.09 117	92.88 141	57.00 199	97.44 73	81.11 140	81.76 200	96.23 38

region2R		84.36 100	84.03 98	85.36 117	93.54 60	64.31 204	93.43 115	92.95 114	72.16 231	78.86 151	94.84 87	56.97 201	97.53 68	81.38 136	92.11 67	94.24 135

新几何1				84.73 149	92.32 93	64.28 205		91.46 188	59.56 382	79.77 135	92.90 139	56.95 202	96.57 132	63.40 305	92.91 58	93.34 173

WR-MVS		76.76 260	75.74 252	79.82 306	84.60 307	62.27 267	92.60 154	92.51 135	76.06 154	67.87 298	85.34 286	56.76 203	90.24 358	62.20 316	63.69 357	86.94 306

HPM-MVS		83.25 127	82.95 125	84.17 176	92.25 95	62.88 253	90.91 230	91.86 166	70.30 277	77.12 171	93.96 119	56.75 204	96.28 147	82.04 129	91.34 84	93.34 173
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
sss		82.71 139	82.38 136	83.73 191	89.25 178	59.58 332	92.24 167	94.89 31	77.96 118	79.86 134	92.38 152	56.70 205	97.05 100	77.26 172	80.86 212	94.55 115

ACMMPR		84.37 99	84.06 97	85.28 121	93.56 58	64.37 201	93.50 110	93.15 105	72.19 228	78.85 152	94.86 86	56.69 206	97.45 72	81.55 132	92.20 65	94.02 149

FMVSNet3		77.73 241	76.04 247	82.80 222	91.20 136	68.99 67	91.87 188	91.99 158	73.35 200	67.04 309	83.19 311	56.62 207	92.14 324	59.80 330	69.34 304	87.28 300

Patchmatch-RL test		68.17 352	64.49 363	79.19 319	71.22 423	53.93 383	70.07 424	71.54 431	69.22 290	56.79 387	62.89 434	56.58 208	88.61 372	69.53 243	52.61 408	95.03 90

dongtai		55.18 403	55.46 402	54.34 428	76.03 410	36.88 446	76.07 409	84.61 382	51.28 412	43.41 436	64.61 432	56.56 209	67.81 446	18.09 451	28.50 451	58.32 444

test_post											23.01 457	56.49 210	92.67 305

RPMNet		70.42 331	65.68 352	84.63 159	83.15 331	67.96 94	70.25 422	90.45 233	46.83 427	69.97 268	65.10 430	56.48 211	95.30 203	35.79 425	73.13 281	90.64 251

DU-MVS		76.86 255	75.84 250	79.91 303	82.96 333	60.26 319	91.26 217	91.54 183	76.46 152	68.88 282	86.35 272	56.16 212	92.13 325	66.38 281	62.55 362	87.35 298

Baseline_NR-MVSNet		73.99 300	72.83 296	77.48 338	80.78 354	59.29 338	91.79 192	84.55 383	68.85 297	68.99 279	80.70 347	56.16 212	92.04 328	62.67 313	60.98 379	81.11 391

API-MVS		82.28 146	80.53 167	87.54 41	96.13 22	70.59 31	93.63 103	91.04 213	65.72 328	75.45 189	92.83 143	56.11 214	98.89 21	64.10 301	89.75 109	93.15 180

MTAPA		83.91 113	83.38 114	85.50 109	91.89 115	65.16 176	81.75 373	92.23 142	75.32 166	80.53 126	95.21 76	56.06 215	97.16 96	84.86 99	92.55 62	94.18 138

JIA-IIPM		66.06 365	62.45 375	76.88 349	81.42 349	54.45 382	57.49 448	88.67 319	49.36 419	63.86 338	46.86 446	56.06 215	90.25 355	49.53 369	68.83 310	85.95 328

v148		76.19 267	74.47 269	81.36 263	80.05 367	64.44 196	91.75 197	90.23 250	73.68 195	67.13 308	80.84 346	55.92 217	93.86 272	68.95 251	61.73 373	85.76 336

WR-MVS_H		70.59 329	69.94 326	72.53 384	81.03 350	51.43 394	87.35 324	92.03 157	67.38 314	60.23 365	80.70 347	55.84 218	83.45 414	46.33 389	58.58 392	82.72 375

test_fmvsmconf0.01_n		83.70 120	83.52 103	84.25 175	75.26 411	61.72 282	92.17 170	87.24 350	82.36 41	84.91 76	95.41 62	55.60 219	96.83 124	92.85 29	85.87 154	94.21 136

AUN-MVS		78.37 228	77.43 221	81.17 267	86.60 263	57.45 359	89.46 282	91.16 200	74.11 182	74.40 203	90.49 193	55.52 220	94.57 230	74.73 193	60.43 384	91.48 232

XVS		83.87 114	83.47 108	85.05 130	93.22 66	63.78 218	92.92 135	92.66 127	73.99 184	78.18 157	94.31 106	55.25 221	97.41 75	79.16 156	91.58 78	93.95 151

X-MVStestdata		76.86 255	74.13 277	85.05 130	93.22 66	63.78 218	92.92 135	92.66 127	73.99 184	78.18 157	10.19 462	55.25 221	97.41 75	79.16 156	91.58 78	93.95 151

BH-w/o		80.49 183	79.30 192	84.05 181	90.83 144	64.36 203	93.60 104	89.42 282	74.35 178	69.09 275	90.15 209	55.23 223	95.61 183	64.61 298	86.43 151	92.17 217

CP-MVS		83.71 119	83.40 113	84.65 156	93.14 71	63.84 216	94.59 57	92.28 140	71.03 266	77.41 166	94.92 84	55.21 224	96.19 152	81.32 137	90.70 92	93.91 156

PGM-MVS		83.25 127	82.70 131	84.92 134	92.81 84	64.07 212	90.44 250	92.20 146	71.28 260	77.23 170	94.43 97	55.17 225	97.31 82	79.33 155	91.38 82	93.37 172

tpmvs		72.88 313	69.76 329	82.22 242	90.98 139	67.05 121	78.22 401	88.30 330	63.10 352	64.35 335	74.98 397	55.09 226	94.27 246	43.25 400	69.57 303	85.34 344

v8		75.35 284	73.26 292	81.61 258	80.67 356	66.82 131	89.54 279	89.27 287	71.65 248	63.30 344	80.30 355	54.99 227	94.06 257	67.33 270	62.33 365	83.94 356

sam_mvs												54.91 228

EPMVS		78.49 227	75.98 248	86.02 90	91.21 135	69.68 53	80.23 388	91.20 198	75.25 167	72.48 234	78.11 374	54.65 229	93.69 275	57.66 339	83.04 183	94.69 107

ab-mvs		80.18 190	78.31 205	85.80 99	88.44 207	65.49 169	83.00 365	92.67 126	71.82 242	77.36 167	85.01 289	54.50 230	96.59 130	76.35 178	75.63 264	95.32 72

KD-MVS_2432*1600		69.03 343	66.37 347	77.01 346	85.56 288	61.06 296	81.44 377	90.25 248	67.27 315	58.00 380	76.53 388	54.49 231	87.63 387	48.04 378	35.77 441	82.34 381

miper_refine_blended		69.03 343	66.37 347	77.01 346	85.56 288	61.06 296	81.44 377	90.25 248	67.27 315	58.00 380	76.53 388	54.49 231	87.63 387	48.04 378	35.77 441	82.34 381

DP-MVS Recon		82.73 137	81.65 145	85.98 91	97.31 4	67.06 120	95.15 37	91.99 158	69.08 296	76.50 178	93.89 120	54.48 233	98.20 37	70.76 233	85.66 157	92.69 194

GeoE		78.90 216	77.43 221	83.29 210	88.95 187	62.02 271	92.31 164	86.23 362	70.24 278	71.34 252	89.27 223	54.43 234	94.04 260	63.31 307	80.81 214	93.81 161

XXY-MVS		77.94 238	76.44 239	82.43 233	82.60 337	64.44 196	92.01 180	91.83 169	73.59 197	70.00 267	85.82 281	54.43 234	94.76 220	69.63 241	68.02 318	88.10 287

MDTV_nov1_ep13_2view						59.90 327	80.13 390		67.65 312	72.79 224		54.33 236		59.83 329		92.58 200

fmvsm_s_conf0.5_n_2		85.06 85	85.60 74	83.44 206	86.92 258	60.53 312	94.41 60	87.31 348	83.30 30	88.72 40	96.72 26	54.28 237	97.75 52	94.07 20	84.68 167	92.04 220

IMVS_0403		81.19 166	79.88 177	85.13 128	88.54 195	64.75 185	88.84 297	90.80 219	76.73 144	75.21 192	90.18 201	54.22 238	96.21 151	73.47 199	80.95 207	94.43 126

Test By Simon												54.21 239

MAR-MVS		84.18 107	83.43 110	86.44 77	96.25 21	65.93 157	94.28 66	94.27 61	74.41 176	79.16 145	95.61 56	53.99 240	98.88 22	69.62 242	93.26 54	94.50 121
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
test-LLR		80.10 192	79.56 184	81.72 256	86.93 256	61.17 293	92.70 146	91.54 183	71.51 257	75.62 184	86.94 266	53.83 241	92.38 316	72.21 217	84.76 165	91.60 229

test0.0.03 1		72.76 314	72.71 300	72.88 382	80.25 364	47.99 414	91.22 221	89.45 280	71.51 257	62.51 354	87.66 252	53.83 241	85.06 404	50.16 366	67.84 321	85.58 337

v2v482		77.42 246	75.65 253	82.73 224	80.38 361	67.13 119	91.85 190	90.23 250	75.09 169	69.37 272	83.39 308	53.79 243	94.44 238	71.77 221	65.00 342	86.63 313

SR-MVS		82.81 136	82.58 132	83.50 203	93.35 64	61.16 295	92.23 168	91.28 197	64.48 335	81.27 114	95.28 69	53.71 244	95.86 167	82.87 123	88.77 118	93.49 170

pcd_1.5k_mvsjas		4.46 434	5.95 437	0.00 448	0.00 471	0.00 473	0.00 459	0.00 472	0.00 466	0.00 467	0.00 466	53.55 245	0.00 467	0.00 466	0.00 464	0.00 463

PS-MVSNAJss		77.26 248	76.31 242	80.13 295	80.64 357	59.16 339	90.63 247	91.06 211	72.80 212	68.58 288	84.57 295	53.55 245	93.96 265	72.97 205	71.96 291	87.27 301

PS-MVSNAJ		88.14 19	87.61 36	89.71 7	92.06 104	76.72 1	95.75 20	93.26 99	83.86 23	89.55 36	96.06 46	53.55 245	97.89 46	91.10 43	93.31 53	94.54 117

mPP-MVS		82.96 135	82.44 135	84.52 163	92.83 80	62.92 251	92.76 142	91.85 168	71.52 256	75.61 186	94.24 109	53.48 248	96.99 108	78.97 159	90.73 91	93.64 166

xiu_mvs_v2_base		87.92 26	87.38 40	89.55 12	91.41 131	76.43 3	95.74 21	93.12 107	83.53 27	89.55 36	95.95 49	53.45 249	97.68 54	91.07 44	92.62 60	94.54 117

test_post1							78.95 395				20.70 460	53.05 250	91.50 345	60.43 325

MDTV_nov1_ep13			72.61 301		89.06 184	68.48 78	80.33 386	90.11 254	71.84 241	71.81 244	75.92 394	53.01 251	93.92 267	48.04 378	73.38 279

FA-MVS(test-final)		79.12 210	77.23 227	84.81 144	90.54 147	63.98 215	81.35 379	91.71 175	71.09 265	74.85 198	82.94 312	52.85 252	97.05 100	67.97 260	81.73 202	93.41 171

test222					89.77 163	61.60 285	89.55 278	89.42 282	56.83 397	77.28 169	92.43 151	52.76 253			91.14 89	93.09 183

fmvsm_s_conf0.1_n_2		84.40 98	84.78 90	83.27 212	85.25 294	60.41 315	94.13 72	85.69 372	83.05 32	87.99 43	96.37 33	52.75 254	97.68 54	93.75 24	84.05 176	91.71 228

v1144		76.73 261	74.88 261	82.27 239	80.23 365	66.60 138	91.68 199	90.21 252	73.69 194	69.06 277	81.89 326	52.73 255	94.40 240	69.21 247	65.23 339	85.80 333

v10		74.77 293	72.54 303	81.46 261	80.33 363	66.71 135	89.15 291	89.08 300	70.94 267	63.08 347	79.86 360	52.52 256	94.04 260	65.70 289	62.17 366	83.64 359

CLD-MVS		82.73 137	82.35 137	83.86 186	87.90 228	67.65 104	95.45 29	92.18 149	85.06 13	72.58 229	92.27 155	52.46 257	95.78 170	84.18 106	79.06 234	88.16 286
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
TranMVSNet+NR-MVSNet		75.86 277	74.52 268	79.89 304	82.44 339	60.64 310	91.37 211	91.37 190	76.63 148	67.65 300	86.21 275	52.37 258	91.55 340	61.84 318	60.81 380	87.48 294

VPA-MVSNet		79.03 212	78.00 210	82.11 250	85.95 279	64.48 194	93.22 122	94.66 41	75.05 170	74.04 212	84.95 290	52.17 259	93.52 278	74.90 191	67.04 324	88.32 285

APD-MVS_3200maxsize		81.64 158	81.32 148	82.59 231	92.36 92	58.74 343	91.39 208	91.01 214	63.35 347	79.72 136	94.62 93	51.82 260	96.14 154	79.71 150	87.93 126	92.89 192

dp		75.01 289	72.09 307	83.76 188	89.28 177	66.22 148	79.96 394	89.75 268	71.16 262	67.80 299	77.19 383	51.81 261	92.54 310	50.39 364	71.44 296	92.51 203

mvsmamba		81.55 159	80.72 160	84.03 182	91.42 128	66.93 129	83.08 362	89.13 296	78.55 111	67.50 302	87.02 265	51.79 262	90.07 363	87.48 69	90.49 96	95.10 85

v144192		76.05 272	74.03 278	82.12 247	79.50 373	66.55 140	91.39 208	89.71 274	72.30 225	68.17 291	81.33 338	51.75 263	94.03 262	67.94 261	64.19 350	85.77 334

BH-untuned		78.68 222	77.08 229	83.48 204	89.84 161	63.74 220	92.70 146	88.59 322	71.57 254	66.83 313	88.65 232	51.75 263	95.39 195	59.03 333	84.77 164	91.32 238

HQP2-MVS												51.63 265

HQP-MVS		81.14 168	80.64 163	82.64 228	87.54 238	63.66 228	94.06 74	91.70 178	79.80 80	74.18 204	90.30 198	51.63 265	95.61 183	77.63 170	78.90 235	88.63 277

icg_test_0407_2		80.38 185	79.22 194	83.88 185	88.54 195	64.75 185	86.79 332	90.80 219	76.73 144	73.95 213	90.18 201	51.55 267	92.45 314	73.47 199	80.95 207	94.43 126

IMVS_0407		80.80 177	79.39 190	85.00 133	88.54 195	64.75 185	88.40 305	90.80 219	76.73 144	73.95 213	90.18 201	51.55 267	95.81 168	73.47 199	80.95 207	94.43 126

dmvs_testset		65.55 369	66.45 345	62.86 416	79.87 368	22.35 462	76.55 406	71.74 429	77.42 134	55.85 389	87.77 251	51.39 269	80.69 428	31.51 441	65.92 332	85.55 339

V42		76.46 263	74.55 267	82.19 244	79.14 379	67.82 99	90.26 259	89.42 282	73.75 192	68.63 287	81.89 326	51.31 270	94.09 254	71.69 223	64.84 343	84.66 350

RRT-MVS		82.61 141	81.16 149	86.96 57	91.10 137	68.75 72	87.70 319	92.20 146	76.97 136	72.68 225	87.10 264	51.30 271	96.41 142	83.56 115	87.84 127	95.74 52

SR-MVS-dyc-post		81.06 171	80.70 161	82.15 245	92.02 105	58.56 346	90.90 231	90.45 233	62.76 354	78.89 147	94.46 95	51.26 272	95.61 183	78.77 163	86.77 142	92.28 211

CL-MVSNet_self_test		69.92 335	68.09 339	75.41 357	73.25 418	55.90 373	90.05 265	89.90 263	69.96 281	61.96 357	76.54 387	51.05 273	87.64 386	49.51 370	50.59 413	82.70 377

TransMVSNet (Re)		70.07 334	67.66 340	77.31 342	80.62 358	59.13 340	91.78 194	84.94 379	65.97 325	60.08 366	80.44 352	50.78 274	91.87 330	48.84 373	45.46 423	80.94 393

HQP_MVS		80.34 187	79.75 181	82.12 247	86.94 254	62.42 261	93.13 124	91.31 192	78.81 105	72.53 230	89.14 226	50.66 275	95.55 189	76.74 173	78.53 240	88.39 283

plane_prior6					87.23 246	62.32 265						50.66 275

SD_0403		73.79 303	73.48 287	74.69 365	85.33 290	45.56 428	83.80 351	85.57 373	76.55 151	62.96 348	88.45 234	50.62 277	87.59 389	48.80 374	79.28 233	90.92 247

ACMMP		81.49 160	80.67 162	83.93 184	91.71 120	62.90 252	92.13 172	92.22 145	71.79 243	71.68 247	93.49 129	50.32 278	96.96 113	78.47 165	84.22 174	91.93 225
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		82.02 152	81.52 146	83.51 202	88.42 209	62.88 253	89.77 272	88.93 309	76.78 141	75.55 187	93.10 132	50.31 279	95.38 196	83.82 111	87.02 136	92.26 215

1314		80.70 178	78.95 198	85.94 93	87.77 235	67.56 106	87.91 314	92.55 134	72.17 230	67.44 303	93.09 133	50.27 280	97.04 103	71.68 224	87.64 130	93.23 177

CP-MVSNet		70.50 330	69.91 327	72.26 387	80.71 355	51.00 398	87.23 326	90.30 245	67.84 309	59.64 367	82.69 315	50.23 281	82.30 422	51.28 360	59.28 388	83.46 364

guyue		81.23 165	80.57 166	83.21 216	86.64 261	61.85 276	92.52 160	92.78 119	78.69 108	74.92 196	89.42 219	50.07 282	95.35 197	80.79 142	79.31 231	92.42 204

LCM-MVSNet-Re		72.93 311	71.84 310	76.18 354	88.49 204	48.02 413	80.07 391	70.17 434	73.96 187	52.25 404	80.09 359	49.98 283	88.24 379	67.35 268	84.23 173	92.28 211

Vis-MVSNet		80.92 174	79.98 176	83.74 189	88.48 205	61.80 277	93.44 114	88.26 334	73.96 187	77.73 161	91.76 171	49.94 284	94.76 220	65.84 287	90.37 99	94.65 111
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
v1192		75.98 274	73.92 280	82.15 245	79.73 369	66.24 147	91.22 221	89.75 268	72.67 214	68.49 289	81.42 336	49.86 285	94.27 246	67.08 273	65.02 341	85.95 328

test-mter		79.96 195	79.38 191	81.72 256	86.93 256	61.17 293	92.70 146	91.54 183	73.85 189	75.62 184	86.94 266	49.84 286	92.38 316	72.21 217	84.76 165	91.60 229

MonoMVSNet		76.99 253	75.08 260	82.73 224	83.32 329	63.24 240	86.47 335	86.37 358	79.08 99	66.31 317	79.30 367	49.80 287	91.72 334	79.37 153	65.70 333	93.23 177

VortexMVS		77.62 242	76.44 239	81.13 269	88.58 194	63.73 222	91.24 219	91.30 196	77.81 122	65.76 319	81.97 325	49.69 288	93.72 273	76.40 177	65.26 338	85.94 330

cdsmvs_eth3d_5k		19.86 429	26.47 428	0.00 448	0.00 471	0.00 473	0.00 459	93.45 91	0.00 466	0.00 467	95.27 71	49.56 289	0.00 467	0.00 466	0.00 464	0.00 463

3Dnovator+	73.60 7	82.10 151	80.60 165	86.60 70	90.89 142	66.80 133	95.20 35	93.44 92	74.05 183	67.42 304	92.49 149	49.46 290	97.65 60	70.80 232	91.68 76	95.33 70

MVP-Stereo		77.12 251	76.23 244	79.79 307	81.72 345	66.34 144	89.29 285	90.88 215	70.56 275	62.01 356	82.88 313	49.34 291	94.13 252	65.55 292	93.80 43	78.88 412
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
RE-MVS-def			80.48 168		92.02 105	58.56 346	90.90 231	90.45 233	62.76 354	78.89 147	94.46 95	49.30 292		78.77 163	86.77 142	92.28 211

OMC-MVS		78.67 224	77.91 213	80.95 278	85.76 285	57.40 360	88.49 303	88.67 319	73.85 189	72.43 236	92.10 161	49.29 293	94.55 234	72.73 211	77.89 243	90.91 248

VPNet		78.82 218	77.53 220	82.70 226	84.52 310	66.44 141	93.93 84	92.23 142	80.46 67	72.60 228	88.38 237	49.18 294	93.13 285	72.47 215	63.97 355	88.55 280

CVMVSNet		74.04 299	74.27 272	73.33 378	85.33 290	43.94 432	89.53 280	88.39 326	54.33 405	70.37 261	90.13 210	49.17 295	84.05 408	61.83 319	79.36 229	91.99 221

v1921920		75.63 282	73.49 286	82.06 251	79.38 374	66.35 143	91.07 229	89.48 278	71.98 233	67.99 292	81.22 341	49.16 296	93.90 268	66.56 277	64.56 348	85.92 331

pm-mvs1		72.89 312	71.09 316	78.26 330	79.10 380	57.62 355	90.80 236	89.30 286	67.66 311	62.91 350	81.78 328	49.11 297	92.95 290	60.29 327	58.89 390	84.22 354

pmmvs4		73.92 301	71.81 311	80.25 292	79.17 377	65.24 173	87.43 323	87.26 349	67.64 313	63.46 342	83.91 303	48.96 298	91.53 344	62.94 310	65.49 334	83.96 355

TAPA-MVS	70.22 12	74.94 290	73.53 285	79.17 320	90.40 151	52.07 390	89.19 290	89.61 276	62.69 356	70.07 265	92.67 145	48.89 299	94.32 242	38.26 420	79.97 220	91.12 243
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
3Dnovator	73.91 6	82.69 140	80.82 158	88.31 26	89.57 167	71.26 22	92.60 154	94.39 56	78.84 104	67.89 297	92.48 150	48.42 300	98.52 28	68.80 253	94.40 36	95.15 82

CPTT-MVS		79.59 200	79.16 195	80.89 281	91.54 126	59.80 328	92.10 174	88.54 324	60.42 375	72.96 221	93.28 131	48.27 301	92.80 299	78.89 162	86.50 149	90.06 257

GBi-Net		75.65 280	73.83 281	81.10 272	88.85 188	65.11 177	90.01 266	90.32 241	70.84 269	67.04 309	80.25 356	48.03 302	91.54 341	59.80 330	69.34 304	86.64 310

test1		75.65 280	73.83 281	81.10 272	88.85 188	65.11 177	90.01 266	90.32 241	70.84 269	67.04 309	80.25 356	48.03 302	91.54 341	59.80 330	69.34 304	86.64 310

FMVSNet2		76.07 269	74.01 279	82.26 241	88.85 188	67.66 103	91.33 214	91.61 181	70.84 269	65.98 318	82.25 321	48.03 302	92.00 329	58.46 335	68.73 312	87.10 303

SSM_0407		79.09 211	77.21 228	84.75 148	88.50 200	66.98 125	89.21 288	87.03 351	67.99 307	74.12 208	89.32 221	47.98 305	95.29 204	71.23 227	79.52 224	91.98 222

SSM_0404		79.46 205	77.65 215	84.91 136	88.37 213	67.04 122	89.59 274	87.03 351	67.99 307	75.45 189	89.32 221	47.98 305	95.34 199	71.23 227	81.90 199	92.34 207

LFMVS		84.34 101	82.73 130	89.18 13	94.76 33	73.25 11	94.99 45	91.89 164	71.90 236	82.16 105	93.49 129	47.98 305	97.05 100	82.55 126	84.82 163	97.25 8

SDMVSNet		80.26 188	78.88 199	84.40 167	89.25 178	67.63 105	85.35 339	93.02 110	76.77 142	70.84 255	87.12 262	47.95 308	96.09 157	85.04 95	74.55 268	89.48 268

QAPM		79.95 196	77.39 225	87.64 34	89.63 166	71.41 20	93.30 119	93.70 79	65.34 331	67.39 306	91.75 172	47.83 309	98.96 16	57.71 338	89.81 106	92.54 201

HPM-MVS_fast		80.25 189	79.55 186	82.33 237	91.55 125	59.95 326	91.32 215	89.16 293	65.23 332	74.71 201	93.07 135	47.81 310	95.74 173	74.87 192	88.23 122	91.31 239

CANet_DTU		84.09 109	83.52 103	85.81 98	90.30 153	66.82 131	91.87 188	89.01 304	85.27 12	86.09 62	93.74 122	47.71 311	96.98 109	77.90 169	89.78 108	93.65 165

mamba_0408		76.22 266	73.37 288	84.77 145	88.50 200	66.98 125	58.80 446	86.18 364	69.12 294	74.12 208	89.01 228	47.50 312	95.35 197	67.57 266	79.52 224	91.98 222

SSM_04072		74.86 292	73.37 288	79.35 317	88.50 200	66.98 125	58.80 446	86.18 364	69.12 294	74.12 208	89.01 228	47.50 312	79.09 431	67.57 266	79.52 224	91.98 222

v1240		75.21 287	72.98 295	81.88 253	79.20 376	66.00 152	90.75 239	89.11 298	71.63 252	67.41 305	81.22 341	47.36 314	93.87 270	65.46 293	64.72 346	85.77 334

PEN-MVS		69.46 340	68.56 334	72.17 389	79.27 375	49.71 405	86.90 330	89.24 288	67.24 318	59.08 372	82.51 318	47.23 315	83.54 413	48.42 376	57.12 394	83.25 367

KinetiMVS		81.43 161	80.11 171	85.38 116	86.60 263	65.47 170	92.90 138	93.54 86	75.33 165	77.31 168	90.39 195	46.81 316	96.75 126	71.65 225	86.46 150	93.93 153

dmvs_re		76.93 254	75.36 256	81.61 258	87.78 234	60.71 307	80.00 392	87.99 339	79.42 88	69.02 278	89.47 218	46.77 317	94.32 242	63.38 306	74.45 271	89.81 261

CNLPA		74.31 296	72.30 305	80.32 288	91.49 127	61.66 283	90.85 234	80.72 403	56.67 398	63.85 339	90.64 188	46.75 318	90.84 349	53.79 353	75.99 263	88.47 282

114514_t		79.17 209	77.67 214	83.68 195	95.32 29	65.53 167	92.85 140	91.60 182	63.49 345	67.92 294	90.63 190	46.65 319	95.72 179	67.01 274	83.54 179	89.79 262

PS-CasMVS		69.86 337	69.13 332	72.07 391	80.35 362	50.57 400	87.02 328	89.75 268	67.27 315	59.19 371	82.28 320	46.58 320	82.24 423	50.69 363	59.02 389	83.39 366

DTE-MVSNet		68.46 349	67.33 343	71.87 393	77.94 396	49.00 411	86.16 337	88.58 323	66.36 323	58.19 377	82.21 322	46.36 321	83.87 411	44.97 397	55.17 401	82.73 374

test1111		80.84 175	80.02 173	83.33 207	87.87 229	60.76 303	92.62 152	86.86 355	77.86 121	75.73 182	91.39 180	46.35 322	94.70 226	72.79 209	88.68 119	94.52 119

ECVR-MVS		81.29 164	80.38 170	84.01 183	88.39 211	61.96 273	92.56 159	86.79 356	77.66 127	76.63 175	91.42 178	46.34 323	95.24 205	74.36 194	89.23 110	94.85 96

PMMVS		81.98 153	82.04 139	81.78 254	89.76 164	56.17 369	91.13 226	90.69 225	77.96 118	80.09 132	93.57 127	46.33 324	94.99 212	81.41 135	87.46 132	94.17 139

OPM-MVS		79.00 213	78.09 208	81.73 255	83.52 327	63.83 217	91.64 201	90.30 245	76.36 153	71.97 242	89.93 214	46.30 325	95.17 207	75.10 186	77.70 245	86.19 320
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
BH-RMVSNet		79.46 205	77.65 215	84.89 137	91.68 121	65.66 161	93.55 106	88.09 337	72.93 208	73.37 218	91.12 184	46.20 326	96.12 155	56.28 344	85.61 158	92.91 190

FE-MVS		75.97 275	73.02 294	84.82 141	89.78 162	65.56 165	77.44 404	91.07 210	64.55 334	72.66 226	79.85 361	46.05 327	96.69 128	54.97 348	80.82 213	92.21 216

AstraMVS		80.66 179	79.79 180	83.28 211	85.07 300	61.64 284	92.19 169	90.58 231	79.40 89	74.77 199	90.18 201	45.93 328	95.61 183	83.04 120	76.96 256	92.60 198

TR-MVS		78.77 221	77.37 226	82.95 220	90.49 149	60.88 299	93.67 100	90.07 255	70.08 280	74.51 202	91.37 181	45.69 329	95.70 180	60.12 328	80.32 218	92.29 210

IterMVS-SCA-FT		71.55 325	69.97 325	76.32 352	81.48 347	60.67 309	87.64 321	85.99 367	66.17 324	59.50 368	78.88 368	45.53 330	83.65 412	62.58 314	61.93 369	84.63 353

SCA		75.82 278	72.76 297	85.01 132	86.63 262	70.08 38	81.06 381	89.19 291	71.60 253	70.01 266	77.09 384	45.53 330	90.25 355	60.43 325	73.27 280	94.68 108

IterMVS		72.65 319	70.83 317	78.09 332	82.17 341	62.96 248	87.64 321	86.28 360	71.56 255	60.44 363	78.85 369	45.42 332	86.66 394	63.30 308	61.83 370	84.65 351
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
Syy-MVS		69.65 338	69.52 330	70.03 398	87.87 229	43.21 434	88.07 310	89.01 304	72.91 209	63.11 345	88.10 244	45.28 333	85.54 399	22.07 448	69.23 307	81.32 389

WB-MVSnew		77.14 250	76.18 246	80.01 299	86.18 273	63.24 240	91.26 217	94.11 65	71.72 246	73.52 217	87.29 260	45.14 334	93.00 288	56.98 341	79.42 227	83.80 358

Effi-MVS+-dtu		76.14 268	75.28 258	78.72 325	83.22 330	55.17 377	89.87 270	87.78 343	75.42 163	67.98 293	81.43 335	45.08 335	92.52 311	75.08 187	71.63 292	88.48 281

XVG-OURS-SEG-HR		74.70 294	73.08 293	79.57 313	78.25 392	57.33 361	80.49 384	87.32 346	63.22 349	68.76 285	90.12 212	44.89 336	91.59 338	70.55 236	74.09 275	89.79 262

v7n		71.31 326	68.65 333	79.28 318	76.40 406	60.77 302	86.71 333	89.45 280	64.17 339	58.77 375	78.24 372	44.59 337	93.54 277	57.76 337	61.75 372	83.52 362

pmmvs5		73.35 306	71.52 313	78.86 324	78.64 387	60.61 311	91.08 227	86.90 353	67.69 310	63.32 343	83.64 304	44.33 338	90.53 352	62.04 317	66.02 330	85.46 341

OpenMVS	70.45 11	78.54 226	75.92 249	86.41 79	85.93 282	71.68 18	92.74 143	92.51 135	66.49 322	64.56 330	91.96 166	43.88 339	98.10 39	54.61 349	90.65 93	89.44 270

AdaColmap		78.94 215	77.00 232	84.76 147	96.34 17	65.86 158	92.66 151	87.97 341	62.18 359	70.56 257	92.37 153	43.53 340	97.35 79	64.50 299	82.86 184	91.05 244

tfpnnormal		70.10 333	67.36 342	78.32 328	83.45 328	60.97 298	88.85 296	92.77 120	64.85 333	60.83 361	78.53 370	43.52 341	93.48 279	31.73 438	61.70 374	80.52 398

mvsany_test1		68.77 345	68.56 334	69.39 400	73.57 417	45.88 427	80.93 382	60.88 448	59.65 381	71.56 248	90.26 200	43.22 342	75.05 435	74.26 196	62.70 361	87.25 302

test_djsdf		73.76 305	72.56 302	77.39 340	77.00 404	53.93 383	89.07 292	90.69 225	65.80 326	63.92 337	82.03 324	43.14 343	92.67 305	72.83 207	68.53 313	85.57 338

GA-MVS		78.33 230	76.23 244	84.65 156	83.65 325	66.30 145	91.44 203	90.14 253	76.01 155	70.32 262	84.02 301	42.50 344	94.72 223	70.98 230	77.00 255	92.94 189

PLC	68.80 14	75.23 286	73.68 284	79.86 305	92.93 77	58.68 344	90.64 245	88.30 330	60.90 372	64.43 334	90.53 191	42.38 345	94.57 230	56.52 342	76.54 259	86.33 316
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
D2MVS		73.80 302	72.02 308	79.15 322	79.15 378	62.97 247	88.58 302	90.07 255	72.94 207	59.22 370	78.30 371	42.31 346	92.70 304	65.59 291	72.00 290	81.79 386

SSC-MVS3.2		74.92 291	73.32 291	79.74 309	86.53 265	60.31 318	89.03 295	92.70 122	78.61 110	68.98 280	83.34 309	41.93 347	92.23 323	52.77 358	65.97 331	86.69 309

Fast-Effi-MVS+-dtu		75.04 288	73.37 288	80.07 296	80.86 351	59.52 333	91.20 223	85.38 374	71.90 236	65.20 324	84.84 291	41.46 348	92.97 289	66.50 280	72.96 283	87.73 290

sd_testset		77.08 252	75.37 255	82.20 243	89.25 178	62.11 270	82.06 371	89.09 299	76.77 142	70.84 255	87.12 262	41.43 349	95.01 211	67.23 271	74.55 268	89.48 268

LuminaMVS		78.14 233	76.66 236	82.60 230	80.82 353	64.64 189	89.33 284	90.45 233	68.25 305	74.73 200	85.51 285	41.15 350	94.14 251	78.96 160	80.69 216	89.04 271

MS-PatchMatch		77.90 240	76.50 238	82.12 247	85.99 278	69.95 42	91.75 197	92.70 122	73.97 186	62.58 353	84.44 297	41.11 351	95.78 170	63.76 304	92.17 66	80.62 397

our_test_3		68.29 351	64.69 360	79.11 323	78.92 381	64.85 184	88.40 305	85.06 377	60.32 377	52.68 402	76.12 392	40.81 352	89.80 367	44.25 399	55.65 399	82.67 379

XVG-OURS		74.25 297	72.46 304	79.63 311	78.45 390	57.59 357	80.33 386	87.39 345	63.86 341	68.76 285	89.62 217	40.50 353	91.72 334	69.00 250	74.25 273	89.58 265

IMVS_0404		78.11 234	76.29 243	83.59 198	88.54 195	64.75 185	84.63 344	90.80 219	76.73 144	61.16 358	90.18 201	40.17 354	91.58 339	73.47 199	80.95 207	94.43 126

VDD-MVS		83.06 132	81.81 144	86.81 61	90.86 143	67.70 102	95.40 30	91.50 186	75.46 161	81.78 107	92.34 154	40.09 355	97.13 98	86.85 80	82.04 196	95.60 56

DP-MVS		69.90 336	66.48 344	80.14 294	95.36 28	62.93 249	89.56 277	76.11 412	50.27 417	57.69 384	85.23 287	39.68 356	95.73 174	33.35 430	71.05 298	81.78 387

ppachtmachnet_test		67.72 355	63.70 367	79.77 308	78.92 381	66.04 151	88.68 300	82.90 398	60.11 379	55.45 390	75.96 393	39.19 357	90.55 351	39.53 415	52.55 409	82.71 376

ADS-MVSNet2		66.90 361	63.44 369	77.26 343	88.06 223	60.70 308	68.01 430	75.56 416	57.57 389	64.48 331	69.87 417	38.68 358	84.10 407	40.87 411	67.89 319	86.97 304

ADS-MVSNet		68.54 348	64.38 365	81.03 276	88.06 223	66.90 130	68.01 430	84.02 387	57.57 389	64.48 331	69.87 417	38.68 358	89.21 370	40.87 411	67.89 319	86.97 304

test_cas_vis1_n_1920		80.45 184	80.61 164	79.97 302	78.25 392	57.01 365	94.04 78	88.33 329	79.06 101	82.81 100	93.70 123	38.65 360	91.63 337	90.82 47	79.81 221	91.27 241

LPG-MVS_test		75.82 278	74.58 266	79.56 314	84.31 316	59.37 335	90.44 250	89.73 271	69.49 286	64.86 326	88.42 235	38.65 360	94.30 244	72.56 213	72.76 284	85.01 347

LGP-MVS_train				79.56 314	84.31 316	59.37 335		89.73 271	69.49 286	64.86 326	88.42 235	38.65 360	94.30 244	72.56 213	72.76 284	85.01 347

VDDNet		80.50 182	78.26 206	87.21 47	86.19 272	69.79 48	94.48 58	91.31 192	60.42 375	79.34 142	90.91 186	38.48 363	96.56 133	82.16 127	81.05 206	95.27 77

ACMP	71.68 10	75.58 283	74.23 273	79.62 312	84.97 302	59.64 330	90.80 236	89.07 301	70.39 276	62.95 349	87.30 259	38.28 364	93.87 270	72.89 206	71.45 295	85.36 343
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
test_vis1_n_1920		81.66 157	82.01 140	80.64 283	82.24 340	55.09 378	94.76 51	86.87 354	81.67 49	84.40 81	94.63 92	38.17 365	94.67 227	91.98 38	83.34 181	92.16 218

UGNet		79.87 197	78.68 200	83.45 205	89.96 159	61.51 286	92.13 172	90.79 223	76.83 140	78.85 152	86.33 274	38.16 366	96.17 153	67.93 262	87.17 135	92.67 195
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
anonymousdsp		71.14 327	69.37 331	76.45 351	72.95 419	54.71 380	84.19 348	88.88 310	61.92 364	62.15 355	79.77 362	38.14 367	91.44 346	68.90 252	67.45 322	83.21 368

xiu_mvs_v1_base_debu		82.16 148	81.12 151	85.26 123	86.42 267	68.72 74	92.59 156	90.44 237	73.12 204	84.20 82	94.36 99	38.04 368	95.73 174	84.12 107	86.81 139	91.33 235

xiu_mvs_v1_base		82.16 148	81.12 151	85.26 123	86.42 267	68.72 74	92.59 156	90.44 237	73.12 204	84.20 82	94.36 99	38.04 368	95.73 174	84.12 107	86.81 139	91.33 235

xiu_mvs_v1_base_debi		82.16 148	81.12 151	85.26 123	86.42 267	68.72 74	92.59 156	90.44 237	73.12 204	84.20 82	94.36 99	38.04 368	95.73 174	84.12 107	86.81 139	91.33 235

PVSNet_0	68.08 15	71.81 322	68.32 338	82.27 239	84.68 304	62.31 266	88.68 300	90.31 244	75.84 156	57.93 382	80.65 350	37.85 371	94.19 249	69.94 239	29.05 450	90.31 255

Anonymous20231206		67.53 358	65.78 350	72.79 383	74.95 412	47.59 416	88.23 307	87.32 346	61.75 369	58.07 379	77.29 381	37.79 372	87.29 392	42.91 402	63.71 356	83.48 363

ACMM	69.62 13	74.34 295	72.73 299	79.17 320	84.25 318	57.87 351	90.36 255	89.93 262	63.17 351	65.64 321	86.04 278	37.79 372	94.10 253	65.89 286	71.52 294	85.55 339
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
cascas		78.18 231	75.77 251	85.41 112	87.14 249	69.11 63	92.96 133	91.15 203	66.71 320	70.47 258	86.07 276	37.49 374	96.48 139	70.15 238	79.80 222	90.65 250

LS3D		69.17 341	66.40 346	77.50 337	91.92 112	56.12 370	85.12 340	80.37 405	46.96 425	56.50 388	87.51 256	37.25 375	93.71 274	32.52 437	79.40 228	82.68 378

MDA-MVSNet_test_wron		63.78 380	60.16 383	74.64 366	78.15 394	60.41 315	83.49 354	84.03 386	56.17 401	39.17 441	71.59 413	37.22 376	83.24 417	42.87 404	48.73 415	80.26 401

YYNet1		63.76 381	60.14 384	74.62 367	78.06 395	60.19 322	83.46 356	83.99 390	56.18 400	39.25 440	71.56 414	37.18 377	83.34 415	42.90 403	48.70 416	80.32 400

FMVSNet5		68.04 353	65.66 353	75.18 361	84.43 314	57.89 350	83.54 353	86.26 361	61.83 366	53.64 399	73.30 402	37.15 378	85.08 403	48.99 372	61.77 371	82.56 380

test20.03		63.83 378	62.65 374	67.38 409	70.58 428	39.94 441	86.57 334	84.17 385	63.29 348	51.86 406	77.30 380	37.09 379	82.47 420	38.87 419	54.13 405	79.73 404

PVSNet	73.49 8	80.05 193	78.63 201	84.31 171	90.92 141	64.97 181	92.47 161	91.05 212	79.18 95	72.43 236	90.51 192	37.05 380	94.06 257	68.06 259	86.00 152	93.90 158

EU-MVSNet		64.01 377	63.01 371	67.02 410	74.40 415	38.86 445	83.27 358	86.19 363	45.11 431	54.27 394	81.15 344	36.91 381	80.01 430	48.79 375	57.02 395	82.19 384

Anonymous20231211		73.08 307	70.39 323	81.13 269	90.62 146	63.33 237	91.40 206	90.06 257	51.84 411	64.46 333	80.67 349	36.49 382	94.07 256	63.83 303	64.17 351	85.98 327

FMVSNet1		72.71 316	69.91 327	81.10 272	83.60 326	65.11 177	90.01 266	90.32 241	63.92 340	63.56 341	80.25 356	36.35 383	91.54 341	54.46 350	66.75 326	86.64 310

Anonymous20240529		76.84 257	74.15 276	84.88 138	91.02 138	64.95 182	93.84 92	91.09 207	53.57 406	73.00 220	87.42 257	35.91 384	97.32 81	69.14 249	72.41 289	92.36 206

WB-MVS		46.23 411	44.94 413	50.11 431	62.13 444	21.23 464	76.48 407	55.49 450	45.89 429	35.78 442	61.44 439	35.54 385	72.83 439	9.96 458	21.75 453	56.27 446

CMPMVS	48.56 21	66.77 362	64.41 364	73.84 375	70.65 427	50.31 402	77.79 403	85.73 371	45.54 430	44.76 431	82.14 323	35.40 386	90.14 361	63.18 309	74.54 270	81.07 392
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
pmmvs6		67.57 357	64.76 359	76.00 355	72.82 421	53.37 385	88.71 299	86.78 357	53.19 407	57.58 385	78.03 375	35.33 387	92.41 315	55.56 346	54.88 403	82.21 383

PatchMatch-RL		72.06 321	69.98 324	78.28 329	89.51 170	55.70 374	83.49 354	83.39 395	61.24 370	63.72 340	82.76 314	34.77 388	93.03 287	53.37 356	77.59 246	86.12 324

LTVRE_ROB	59.60 19	66.27 364	63.54 368	74.45 369	84.00 321	51.55 393	67.08 434	83.53 392	58.78 385	54.94 392	80.31 354	34.54 389	93.23 283	40.64 413	68.03 317	78.58 416
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
SSC-MVS		44.51 413	43.35 415	47.99 435	61.01 447	18.90 466	74.12 415	54.36 451	43.42 438	34.10 446	60.02 440	34.42 390	70.39 442	9.14 460	19.57 454	54.68 447

Elysia		76.45 264	74.17 274	83.30 208	80.43 359	64.12 210	89.58 275	90.83 216	61.78 367	72.53 230	85.92 279	34.30 391	94.81 218	68.10 257	84.01 177	90.97 245

StellarMVS		76.45 264	74.17 274	83.30 208	80.43 359	64.12 210	89.58 275	90.83 216	61.78 367	72.53 230	85.92 279	34.30 391	94.81 218	68.10 257	84.01 177	90.97 245

UniMVSNet_ETH3D		72.74 315	70.53 322	79.36 316	78.62 388	56.64 367	85.01 341	89.20 290	63.77 342	64.84 328	84.44 297	34.05 393	91.86 331	63.94 302	70.89 299	89.57 266

F-COLMAP		70.66 328	68.44 336	77.32 341	86.37 270	55.91 372	88.00 312	86.32 359	56.94 396	57.28 386	88.07 246	33.58 394	92.49 312	51.02 361	68.37 314	83.55 360

pmmvs-eth3d		65.53 370	62.32 376	75.19 360	69.39 431	59.59 331	82.80 366	83.43 393	62.52 357	51.30 410	72.49 405	32.86 395	87.16 393	55.32 347	50.73 412	78.83 413

MDA-MVSNet-bldmvs		61.54 388	57.70 392	73.05 380	79.53 372	57.00 366	83.08 362	81.23 400	57.57 389	34.91 445	72.45 406	32.79 396	86.26 397	35.81 424	41.95 429	75.89 425

MIMVSNet		71.64 323	68.44 336	81.23 266	81.97 344	64.44 196	73.05 416	88.80 314	69.67 285	64.59 329	74.79 399	32.79 396	87.82 383	53.99 352	76.35 260	91.42 233

UnsupCasMVSNet_eth		65.79 367	63.10 370	73.88 374	70.71 426	50.29 403	81.09 380	89.88 264	72.58 216	49.25 418	74.77 400	32.57 398	87.43 391	55.96 345	41.04 431	83.90 357

N_pmnet		50.55 407	49.11 409	54.88 426	77.17 403	4.02 470	84.36 345	2.00 468	48.59 420	45.86 427	68.82 420	32.22 399	82.80 419	31.58 439	51.38 411	77.81 421

test_0402		64.54 374	61.09 380	74.92 364	84.10 320	60.75 304	87.95 313	79.71 407	52.03 409	52.41 403	77.20 382	32.21 400	91.64 336	23.14 446	61.03 378	72.36 434

DSMNet-mixed		56.78 400	54.44 404	63.79 414	63.21 441	29.44 457	64.43 437	64.10 444	42.12 441	51.32 409	71.60 412	31.76 401	75.04 436	36.23 422	65.20 340	86.87 307

MSDG		69.54 339	65.73 351	80.96 277	85.11 299	63.71 224	84.19 348	83.28 396	56.95 395	54.50 393	84.03 300	31.50 402	96.03 163	42.87 404	69.13 309	83.14 370

RPSCF		64.24 376	61.98 378	71.01 396	76.10 408	45.00 429	75.83 411	75.94 413	46.94 426	58.96 373	84.59 294	31.40 403	82.00 424	47.76 383	60.33 386	86.04 325

tt0805		73.07 308	70.73 320	80.07 296	78.37 391	57.05 363	87.78 317	92.18 149	61.23 371	67.04 309	86.49 271	31.35 404	94.58 228	65.06 296	67.12 323	88.57 279

jajsoiax		73.05 309	71.51 314	77.67 335	77.46 401	54.83 379	88.81 298	90.04 258	69.13 293	62.85 351	83.51 306	31.16 405	92.75 301	70.83 231	69.80 300	85.43 342

MVS-HIRNet		60.25 394	55.55 401	74.35 370	84.37 315	56.57 368	71.64 420	74.11 420	34.44 444	45.54 429	42.24 452	31.11 406	89.81 365	40.36 414	76.10 262	76.67 424

SixPastTwentyTwo		64.92 372	61.78 379	74.34 371	78.74 385	49.76 404	83.42 357	79.51 408	62.86 353	50.27 413	77.35 379	30.92 407	90.49 353	45.89 391	47.06 418	82.78 372

mmtdpeth		68.33 350	66.37 347	74.21 373	82.81 336	51.73 391	84.34 346	80.42 404	67.01 319	71.56 248	68.58 421	30.52 408	92.35 319	75.89 180	36.21 439	78.56 417

KD-MVS_self_test		60.87 391	58.60 389	67.68 407	66.13 437	39.93 442	75.63 413	84.70 380	57.32 393	49.57 416	68.45 422	29.55 409	82.87 418	48.09 377	47.94 417	80.25 402

mvs_tets		72.71 316	71.11 315	77.52 336	77.41 402	54.52 381	88.45 304	89.76 267	68.76 300	62.70 352	83.26 310	29.49 410	92.71 302	70.51 237	69.62 302	85.34 344

Anonymous202405211		77.96 237	75.33 257	85.87 95	93.73 53	64.52 191	94.85 49	85.36 375	62.52 357	76.11 179	90.18 201	29.43 411	97.29 83	68.51 255	77.24 254	95.81 50

K. test v3		63.09 382	59.61 386	73.53 377	76.26 407	49.38 409	83.27 358	77.15 411	64.35 336	47.77 423	72.32 409	28.73 412	87.79 384	49.93 368	36.69 438	83.41 365

UnsupCasMVSNet_bld		61.60 387	57.71 391	73.29 379	68.73 432	51.64 392	78.61 397	89.05 302	57.20 394	46.11 424	61.96 437	28.70 413	88.60 373	50.08 367	38.90 436	79.63 405

lessismore_v0				73.72 376	72.93 420	47.83 415		61.72 447		45.86 427	73.76 401	28.63 414	89.81 365	47.75 384	31.37 446	83.53 361

MVStest1		51.35 406	46.89 410	64.74 412	65.06 439	51.10 397	67.33 433	72.58 425	30.20 448	35.30 443	74.82 398	27.70 415	69.89 443	24.44 445	24.57 452	73.22 430

new-patchmatchnet		59.30 397	56.48 399	67.79 406	65.86 438	44.19 430	82.47 369	81.77 399	59.94 380	43.65 435	66.20 428	27.67 416	81.68 425	39.34 416	41.40 430	77.50 422

ACMH	63.93 17	68.62 346	64.81 358	80.03 298	85.22 295	63.25 239	87.72 318	84.66 381	60.83 373	51.57 408	79.43 366	27.29 417	94.96 213	41.76 407	64.84 343	81.88 385
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
OurMVSNet-221017-0		64.68 373	62.17 377	72.21 388	76.08 409	47.35 417	80.67 383	81.02 401	56.19 399	51.60 407	79.66 364	27.05 418	88.56 374	53.60 355	53.63 406	80.71 396

ACMH+	65.35 16	67.65 356	64.55 361	76.96 348	84.59 308	57.10 362	88.08 309	80.79 402	58.59 387	53.00 401	81.09 345	26.63 419	92.95 290	46.51 387	61.69 375	80.82 394

OpenMVS_ROB	61.12 18	66.39 363	62.92 372	76.80 350	76.51 405	57.77 352	89.22 287	83.41 394	55.48 402	53.86 397	77.84 376	26.28 420	93.95 266	34.90 427	68.76 311	78.68 415

tt0320		61.85 385	57.45 394	75.03 362	77.49 400	57.60 356	82.74 367	73.65 422	43.65 437	53.65 398	68.18 423	25.47 421	88.66 371	45.56 393	46.68 420	78.81 414

test_fmvs1		74.07 298	73.69 283	75.22 359	78.91 383	47.34 418	89.06 294	74.69 419	63.68 344	79.41 141	91.59 176	24.36 422	87.77 385	85.22 92	76.26 261	90.55 253

COLMAP_ROB	57.96 20	62.98 383	59.65 385	72.98 381	81.44 348	53.00 387	83.75 352	75.53 417	48.34 422	48.81 420	81.40 337	24.14 423	90.30 354	32.95 432	60.52 383	75.65 426
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
MIMVSNet1		60.16 395	57.33 395	68.67 403	69.71 429	44.13 431	78.92 396	84.21 384	55.05 403	44.63 432	71.85 411	23.91 424	81.54 426	32.63 436	55.03 402	80.35 399

testgi		64.48 375	62.87 373	69.31 401	71.24 422	40.62 439	85.49 338	79.92 406	65.36 330	54.18 395	83.49 307	23.74 425	84.55 405	41.60 408	60.79 381	82.77 373

tt0320-xc		61.51 389	56.89 397	75.37 358	78.50 389	58.61 345	82.61 368	71.27 432	44.31 434	53.17 400	68.03 425	23.38 426	88.46 376	47.77 382	43.00 428	79.03 411

ITE_SJBPF				70.43 397	74.44 414	47.06 421		77.32 410	60.16 378	54.04 396	83.53 305	23.30 427	84.01 409	43.07 401	61.58 376	80.21 403

sc_t1		63.81 379	59.39 387	77.10 344	77.62 399	56.03 371	84.32 347	73.56 423	46.66 428	58.22 376	73.06 403	23.28 428	90.62 350	50.93 362	46.84 419	84.64 352

mvs5depth		61.03 390	57.65 393	71.18 394	67.16 435	47.04 422	72.74 417	77.49 409	57.47 392	60.52 362	72.53 404	22.84 429	88.38 377	49.15 371	38.94 435	78.11 420

EG-PatchMatch MVS		68.55 347	65.41 355	77.96 333	78.69 386	62.93 249	89.86 271	89.17 292	60.55 374	50.27 413	77.73 378	22.60 430	94.06 257	47.18 385	72.65 286	76.88 423

tmp_tt		22.26 428	23.75 430	17.80 444	5.23 468	12.06 469	35.26 455	39.48 462	2.82 462	18.94 453	44.20 451	22.23 431	24.64 463	36.30 421	9.31 460	16.69 457

USDC		67.43 360	64.51 362	76.19 353	77.94 396	55.29 376	78.38 399	85.00 378	73.17 202	48.36 421	80.37 353	21.23 432	92.48 313	52.15 359	64.02 354	80.81 395

Anonymous20240521		62.09 384	59.08 388	71.10 395	67.19 434	48.72 412	83.91 350	85.23 376	50.38 416	47.84 422	71.22 416	20.74 433	85.51 401	46.47 388	58.75 391	79.06 409

test_vis1_n		71.63 324	70.73 320	74.31 372	69.63 430	47.29 419	86.91 329	72.11 427	63.21 350	75.18 193	90.17 207	20.40 434	85.76 398	84.59 102	74.42 272	89.87 260

XVG-ACMP-BASELINE		68.04 353	65.53 354	75.56 356	74.06 416	52.37 388	78.43 398	85.88 368	62.03 362	58.91 374	81.21 343	20.38 435	91.15 348	60.69 324	68.18 315	83.16 369

test_fmvs1_n		72.69 318	71.92 309	74.99 363	71.15 424	47.08 420	87.34 325	75.67 414	63.48 346	78.08 159	91.17 183	20.16 436	87.87 382	84.65 101	75.57 265	90.01 259

AllTest		61.66 386	58.06 390	72.46 385	79.57 370	51.42 395	80.17 389	68.61 437	51.25 413	45.88 425	81.23 339	19.86 437	86.58 395	38.98 417	57.01 396	79.39 406

TestCases				72.46 385	79.57 370	51.42 395		68.61 437	51.25 413	45.88 425	81.23 339	19.86 437	86.58 395	38.98 417	57.01 396	79.39 406

test_vis1_rt		59.09 398	57.31 396	64.43 413	68.44 433	46.02 426	83.05 364	48.63 457	51.96 410	49.57 416	63.86 433	16.30 439	80.20 429	71.21 229	62.79 360	67.07 440

pmmvs3		55.51 401	51.50 407	67.53 408	57.90 449	50.93 399	80.37 385	73.66 421	40.63 442	44.15 434	64.75 431	16.30 439	78.97 432	44.77 398	40.98 433	72.69 432

test_fmvs2		65.78 368	64.84 357	68.60 404	66.54 436	41.71 436	83.27 358	69.81 435	54.38 404	67.91 295	84.54 296	15.35 441	81.22 427	75.65 182	66.16 329	82.88 371

TDRefinement		55.28 402	51.58 406	66.39 411	59.53 448	46.15 425	76.23 408	72.80 424	44.60 432	42.49 437	76.28 391	15.29 442	82.39 421	33.20 431	43.75 425	70.62 436

new_pmnet		49.31 408	46.44 411	57.93 421	62.84 442	40.74 438	68.47 429	62.96 446	36.48 443	35.09 444	57.81 441	14.97 443	72.18 440	32.86 434	46.44 421	60.88 443

TinyColmap		60.32 393	56.42 400	72.00 392	78.78 384	53.18 386	78.36 400	75.64 415	52.30 408	41.59 439	75.82 395	14.76 444	88.35 378	35.84 423	54.71 404	74.46 427

EGC-MVSNET		42.35 414	38.09 417	55.11 425	74.57 413	46.62 423	71.63 421	55.77 449	0.04 463	0.24 464	62.70 435	14.24 445	74.91 437	17.59 452	46.06 422	43.80 449

LF4IMVS		54.01 404	52.12 405	59.69 419	62.41 443	39.91 443	68.59 428	68.28 439	42.96 439	44.55 433	75.18 396	14.09 446	68.39 445	41.36 410	51.68 410	70.78 435

ttmdpeth		53.34 405	49.96 408	63.45 415	62.07 445	40.04 440	72.06 418	65.64 442	42.54 440	51.88 405	77.79 377	13.94 447	76.48 434	32.93 433	30.82 449	73.84 429

PM-MVS		59.40 396	56.59 398	67.84 405	63.63 440	41.86 435	76.76 405	63.22 445	59.01 384	51.07 411	72.27 410	11.72 448	83.25 416	61.34 320	50.28 414	78.39 418

mvsany_test3		48.86 409	46.35 412	56.41 422	46.00 457	31.67 453	62.26 439	47.25 458	43.71 436	45.54 429	68.15 424	10.84 449	64.44 454	57.95 336	35.44 443	73.13 431

ambc				69.61 399	61.38 446	41.35 437	49.07 453	85.86 370		50.18 415	66.40 427	10.16 450	88.14 380	45.73 392	44.20 424	79.32 408

FPMVS		45.64 412	43.10 416	53.23 429	51.42 454	36.46 447	64.97 436	71.91 428	29.13 449	27.53 449	61.55 438	9.83 451	65.01 452	16.00 455	55.58 400	58.22 445

ANet_high		40.27 418	35.20 421	55.47 424	34.74 465	34.47 450	63.84 438	71.56 430	48.42 421	18.80 454	41.08 453	9.52 452	64.45 453	20.18 449	8.66 461	67.49 439

test_method		38.59 419	35.16 422	48.89 433	54.33 450	21.35 463	45.32 454	53.71 452	7.41 460	28.74 448	51.62 444	8.70 453	52.87 457	33.73 428	32.89 445	72.47 433

EMVS		23.76 427	23.20 431	25.46 443	41.52 463	16.90 468	60.56 442	38.79 464	14.62 458	8.99 462	20.24 461	7.35 454	45.82 461	7.25 462	9.46 459	13.64 459

test_f		46.58 410	43.45 414	55.96 423	45.18 458	32.05 452	61.18 440	49.49 456	33.39 445	42.05 438	62.48 436	7.00 455	65.56 450	47.08 386	43.21 427	70.27 437

test_fmvs3		56.82 399	54.86 403	62.69 418	53.59 451	35.47 448	75.87 410	65.64 442	43.91 435	55.10 391	71.43 415	6.91 456	74.40 438	68.64 254	52.63 407	78.20 419

E-PMN		24.61 425	24.00 429	26.45 442	43.74 460	18.44 467	60.86 441	39.66 461	15.11 457	9.53 461	22.10 458	6.52 457	46.94 460	8.31 461	10.14 458	13.98 458

DeepMVS_CX				34.71 441	51.45 453	24.73 461		28.48 467	31.46 447	17.49 457	52.75 443	5.80 458	42.60 462	18.18 450	19.42 455	36.81 454

Gipuma		34.91 421	31.44 424	45.30 436	70.99 425	39.64 444	19.85 458	72.56 426	20.10 454	16.16 458	21.47 459	5.08 459	71.16 441	13.07 456	43.70 426	25.08 456
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
APD_test1		40.50 416	37.31 419	50.09 432	51.88 452	35.27 449	59.45 444	52.59 453	21.64 452	26.12 450	57.80 442	4.56 460	66.56 448	22.64 447	39.09 434	48.43 448

LCM-MVSNet		40.54 415	35.79 420	54.76 427	36.92 464	30.81 454	51.41 451	69.02 436	22.07 451	24.63 451	45.37 448	4.56 460	65.81 449	33.67 429	34.50 444	67.67 438

PMMVS2		37.93 420	33.61 423	50.92 430	46.31 456	24.76 460	60.55 443	50.05 454	28.94 450	20.93 452	47.59 445	4.41 462	65.13 451	25.14 444	18.55 456	62.87 442

test_vis3_rt		40.46 417	37.79 418	48.47 434	44.49 459	33.35 451	66.56 435	32.84 465	32.39 446	29.65 447	39.13 455	3.91 463	68.65 444	50.17 365	40.99 432	43.40 450

testf1		32.77 422	29.47 425	42.67 438	41.89 461	30.81 454	52.07 449	43.45 459	15.45 455	18.52 455	44.82 449	2.12 464	58.38 455	16.05 453	30.87 447	38.83 451

APD_test2		32.77 422	29.47 425	42.67 438	41.89 461	30.81 454	52.07 449	43.45 459	15.45 455	18.52 455	44.82 449	2.12 464	58.38 455	16.05 453	30.87 447	38.83 451

PMVS	26.43 22	31.84 424	28.16 427	42.89 437	25.87 467	27.58 458	50.92 452	49.78 455	21.37 453	14.17 459	40.81 454	2.01 466	66.62 447	9.61 459	38.88 437	34.49 455
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
MVE	24.84 23	24.35 426	19.77 432	38.09 440	34.56 466	26.92 459	26.57 456	38.87 463	11.73 459	11.37 460	27.44 456	1.37 467	50.42 459	11.41 457	14.60 457	36.93 453
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
wuyk23d		11.30 430	10.95 433	12.33 445	48.05 455	19.89 465	25.89 457	1.92 469	3.58 461	3.12 463	1.37 463	0.64 468	15.77 464	6.23 463	7.77 462	1.35 460

test123		6.92 433	9.21 436	0.08 446	0.03 470	0.05 471	81.65 375	0.01 471	0.02 465	0.14 466	0.85 465	0.03 469	0.02 465	0.12 465	0.00 464	0.16 461

testmvs		7.23 432	9.62 435	0.06 447	0.04 469	0.02 472	84.98 342	0.02 470	0.03 464	0.18 465	1.21 464	0.01 470	0.02 465	0.14 464	0.01 463	0.13 462

mmdepth		0.00 435	0.00 438	0.00 448	0.00 471	0.00 473	0.00 459	0.00 472	0.00 466	0.00 467	0.00 466	0.00 471	0.00 467	0.00 466	0.00 464	0.00 463

monomultidepth		0.00 435	0.00 438	0.00 448	0.00 471	0.00 473	0.00 459	0.00 472	0.00 466	0.00 467	0.00 466	0.00 471	0.00 467	0.00 466	0.00 464	0.00 463

test_blank		0.00 435	0.00 438	0.00 448	0.00 471	0.00 473	0.00 459	0.00 472	0.00 466	0.00 467	0.00 466	0.00 471	0.00 467	0.00 466	0.00 464	0.00 463

uanet_test		0.00 435	0.00 438	0.00 448	0.00 471	0.00 473	0.00 459	0.00 472	0.00 466	0.00 467	0.00 466	0.00 471	0.00 467	0.00 466	0.00 464	0.00 463

DCPMVS		0.00 435	0.00 438	0.00 448	0.00 471	0.00 473	0.00 459	0.00 472	0.00 466	0.00 467	0.00 466	0.00 471	0.00 467	0.00 466	0.00 464	0.00 463

sosnet-low-res		0.00 435	0.00 438	0.00 448	0.00 471	0.00 473	0.00 459	0.00 472	0.00 466	0.00 467	0.00 466	0.00 471	0.00 467	0.00 466	0.00 464	0.00 463

sosnet		0.00 435	0.00 438	0.00 448	0.00 471	0.00 473	0.00 459	0.00 472	0.00 466	0.00 467	0.00 466	0.00 471	0.00 467	0.00 466	0.00 464	0.00 463

uncertanet		0.00 435	0.00 438	0.00 448	0.00 471	0.00 473	0.00 459	0.00 472	0.00 466	0.00 467	0.00 466	0.00 471	0.00 467	0.00 466	0.00 464	0.00 463

Regformer		0.00 435	0.00 438	0.00 448	0.00 471	0.00 473	0.00 459	0.00 472	0.00 466	0.00 467	0.00 466	0.00 471	0.00 467	0.00 466	0.00 464	0.00 463

ab-mvs-re		7.91 431	10.55 434	0.00 448	0.00 471	0.00 473	0.00 459	0.00 472	0.00 466	0.00 467	94.95 81	0.00 471	0.00 467	0.00 466	0.00 464	0.00 463

uanet		0.00 435	0.00 438	0.00 448	0.00 471	0.00 473	0.00 459	0.00 472	0.00 466	0.00 467	0.00 466	0.00 471	0.00 467	0.00 466	0.00 464	0.00 463

WAC-MVS						49.45 407								31.56 440

FOURS1					93.95 46	61.77 279	93.96 82	91.92 161	62.14 361	86.57 56

MSC_two_6792asdad				89.60 9	97.31 4	73.22 12		95.05 29					99.07 13	92.01 36	94.77 26	96.51 24

No_MVS				89.60 9	97.31 4	73.22 12		95.05 29					99.07 13	92.01 36	94.77 26	96.51 24

eth-test2					0.00 471

eth-test					0.00 471

IU-MVS					96.46 11	69.91 43		95.18 23	80.75 64	95.28 1				92.34 33	95.36 14	96.47 28

save fliter					93.84 49	67.89 97	95.05 40	92.66 127	78.19 115

test_0728_SECOND				88.70 18	96.45 12	70.43 34	96.64 10	94.37 57					99.15 2	91.91 39	94.90 22	96.51 24

GSMVS																94.68 108

test_part2					96.29 19	68.16 90				90.78 22

MTGPA								92.23 142

MTMP							93.77 96	32.52 466

gm-plane-assit					88.42 209	67.04 122			78.62 109		91.83 170		97.37 77	76.57 175

test9_res														89.41 51	94.96 19	95.29 74

agg_prior2														86.41 82	94.75 30	95.33 70

agg_prior					94.16 43	66.97 128		93.31 97		84.49 80			96.75 126

test_prior4						67.18 117	93.92 85

test_prior				86.42 78	94.71 35	67.35 112		93.10 108					96.84 123			95.05 88

旧先验2							92.00 183		59.37 383	87.54 49			93.47 280	75.39 184

新几何2							91.41 204

无先验							92.71 145	92.61 132	62.03 362				97.01 104	66.63 276		93.97 150

原ACMM2							92.01 180

testdata2													96.09 157	61.26 321

testdata1							89.21 288		77.55 130

plane_prior7					86.94 254	61.51 286

plane_prior5								91.31 192					95.55 189	76.74 173	78.53 240	88.39 283

plane_prior4											89.14 226

plane_prior3						61.95 274			79.09 98	72.53 230

plane_prior2							93.13 124		78.81 105

plane_prior1					87.15 248

plane_prior						62.42 261	93.85 89		79.38 90						78.80 237

n2								0.00 472

nn								0.00 472

door-mid								66.01 441

test11								93.01 111

door								66.57 440

HQP5-MVS						63.66 228

HQP-NCC					87.54 238		94.06 74		79.80 80	74.18 204

ACMP_Plane					87.54 238		94.06 74		79.80 80	74.18 204

BP-MVS														77.63 170

HQP4-MVS										74.18 204			95.61 183			88.63 277

HQP3-MVS								91.70 178							78.90 235

NP-MVS					87.41 241	63.04 245					90.30 198

ACMMP++_ref															71.63 292

ACMMP++															69.72 301

High-resolution multi-view benchmark