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.

MM		80.20 7	80.28 8	79.99 2	82.19 79	60.01 46	86.19 17	83.93 55	73.19 1	77.08 31	91.21 15	57.23 33	90.73 10	83.35 1	88.12 35	89.22 5

MVS_0304		78.73 16	78.75 15	78.66 30	80.82 102	57.62 83	85.31 30	81.31 118	70.51 2	74.17 60	91.24 14	54.99 47	89.56 17	82.29 2	88.13 34	88.80 7

CANet		76.46 37	75.93 40	78.06 39	81.29 93	57.53 85	82.35 69	83.31 80	67.78 3	70.09 116	86.34 103	54.92 49	88.90 25	72.68 57	84.55 69	87.76 38

UA-Net		73.13 74	72.93 74	73.76 119	83.58 64	51.66 187	78.75 119	77.66 190	67.75 4	72.61 91	89.42 47	49.82 115	83.29 145	53.61 202	83.14 79	86.32 87

CNVR-MVS		79.84 10	79.97 10	79.45 11	87.90 2	62.17 17	84.37 36	85.03 37	66.96 5	77.58 27	90.06 36	59.47 21	89.13 22	78.67 14	89.73 16	87.03 60

TranMVSNet+NR-MVSNet		70.36 123	70.10 119	71.17 191	78.64 153	42.97 292	76.53 175	81.16 126	66.95 6	68.53 145	85.42 131	51.61 99	83.07 149	52.32 210	69.70 262	87.46 48

3Dnovator+	66.72 4	75.84 45	74.57 54	79.66 9	82.40 76	59.92 48	85.83 22	86.32 16	66.92 7	67.80 162	89.24 51	42.03 204	89.38 19	64.07 119	86.50 56	89.69 2

NCCC		78.58 17	78.31 19	79.39 12	87.51 12	62.61 13	85.20 31	84.42 46	66.73 8	74.67 53	89.38 49	55.30 44	89.18 21	74.19 46	87.34 43	86.38 79

SteuartSystems-ACMMP		79.48 11	79.31 11	79.98 3	83.01 72	62.18 16	87.60 9	85.83 19	66.69 9	78.03 26	90.98 16	54.26 55	90.06 13	78.42 19	89.02 23	87.69 40
Skip Steuart: Steuart Systems R&D Blog.
EPNet		73.09 75	72.16 82	75.90 68	75.95 227	56.28 104	83.05 56	72.39 260	66.53 10	65.27 210	87.00 81	50.40 111	85.47 104	62.48 136	86.32 58	85.94 98
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
UniMVSNet_NR-MVSNet		71.11 107	71.00 102	71.44 180	79.20 137	44.13 279	76.02 188	82.60 93	66.48 11	68.20 149	84.60 145	56.82 35	82.82 160	54.62 193	70.43 243	87.36 55

MSP-MVS		81.06 3	81.40 4	80.02 1	86.21 31	62.73 9	86.09 18	86.83 8	65.51 12	83.81 10	90.51 23	63.71 12	89.23 20	81.51 3	88.44 27	88.09 27
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
HPM-MVS++		79.88 9	80.14 9	79.10 21	88.17 1	64.80 1	86.59 12	83.70 66	65.37 13	78.78 22	90.64 19	58.63 25	87.24 54	79.00 12	90.37 14	85.26 131

NR-MVSNet		69.54 144	68.85 137	71.59 177	78.05 174	43.81 283	74.20 223	80.86 132	65.18 14	62.76 249	84.52 146	52.35 87	83.59 141	50.96 225	70.78 238	87.37 53

MTAPA		76.90 34	76.42 35	78.35 35	86.08 37	63.57 2	74.92 211	80.97 130	65.13 15	75.77 36	90.88 17	48.63 129	86.66 71	77.23 24	88.17 33	84.81 144

DVP-MVS++		81.67 1	82.40 1	79.47 10	87.24 14	59.15 60	88.18 1	87.15 3	65.04 16	84.26 5	91.86 6	67.01 1	90.84 3	79.48 6	91.38 2	88.42 14

test_0728_THIRD									65.04 16	83.82 8	92.00 3	64.69 10	90.75 8	79.48 6	90.63 10	88.09 27

EI-MVSNet-Vis-set		72.42 87	71.59 87	74.91 87	78.47 157	54.02 141	77.05 164	79.33 154	65.03 18	71.68 103	79.35 254	52.75 79	84.89 116	66.46 100	74.23 189	85.83 103

casdiffmvs_mvg		76.14 41	76.30 36	75.66 74	76.46 221	51.83 186	79.67 111	85.08 34	65.02 19	75.84 35	88.58 60	59.42 22	85.08 110	72.75 56	83.93 76	90.08 1
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
test_one_0601					87.58 9	59.30 57		86.84 7	65.01 20	83.80 11	91.86 6	64.03 11

ETV-MVS		74.46 61	73.84 64	76.33 62	79.27 135	55.24 129	79.22 116	85.00 39	64.97 21	72.65 90	79.46 251	53.65 73	87.87 44	67.45 94	82.91 85	85.89 101

WR-MVS		68.47 168	68.47 148	68.44 237	80.20 115	39.84 316	73.75 235	76.07 213	64.68 22	68.11 153	83.63 166	50.39 112	79.14 235	49.78 230	69.66 263	86.34 83

XVS		77.17 31	76.56 34	79.00 23	86.32 29	62.62 11	85.83 22	83.92 56	64.55 23	72.17 98	90.01 40	47.95 136	88.01 40	71.55 65	86.74 52	86.37 81

X-MVStestdata		70.21 126	67.28 175	79.00 23	86.32 29	62.62 11	85.83 22	83.92 56	64.55 23	72.17 98	6.49 408	47.95 136	88.01 40	71.55 65	86.74 52	86.37 81

HQP_MVS		74.31 62	73.73 65	76.06 65	81.41 90	56.31 102	84.22 40	84.01 53	64.52 25	69.27 134	86.10 110	45.26 177	87.21 56	68.16 82	80.58 109	84.65 148

plane_prior2							84.22 40		64.52 25

EI-MVSNet-UG-set		71.92 95	71.06 101	74.52 101	77.98 177	53.56 149	76.62 173	79.16 155	64.40 27	71.18 107	78.95 259	52.19 89	84.66 122	65.47 111	73.57 200	85.32 127

DU-MVS		70.01 129	69.53 126	71.44 180	78.05 174	44.13 279	75.01 208	81.51 108	64.37 28	68.20 149	84.52 146	49.12 126	82.82 160	54.62 193	70.43 243	87.37 53

DVP-MVS		80.84 4	81.64 3	78.42 34	87.75 7	59.07 64	87.85 5	85.03 37	64.26 29	83.82 8	92.00 3	64.82 8	90.75 8	78.66 15	90.61 11	85.45 120
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					87.75 7	59.07 64	87.86 4	86.83 8	64.26 29	84.19 7	91.92 5	64.82 8

test_241102_ONE					87.77 4	58.90 69		86.78 10	64.20 31	85.97 1	91.34 12	66.87 3	90.78 7

SED-MVS		81.56 2	82.30 2	79.32 13	87.77 4	58.90 69	87.82 7	86.78 10	64.18 32	85.97 1	91.84 8	66.87 3	90.83 5	78.63 17	90.87 5	88.23 21

test_241102_TWO								86.73 12	64.18 32	84.26 5	91.84 8	65.19 6	90.83 5	78.63 17	90.70 7	87.65 42

LFMVS		71.78 97	71.59 87	72.32 161	83.40 67	46.38 256	79.75 109	71.08 269	64.18 32	72.80 87	88.64 59	42.58 199	83.72 137	57.41 171	84.49 70	86.86 65

IS-MVSNet		71.57 101	71.00 102	73.27 142	78.86 146	45.63 267	80.22 97	78.69 166	64.14 35	66.46 187	87.36 76	49.30 120	85.60 97	50.26 229	83.71 78	88.59 11

plane_prior3						56.09 108			63.92 36	69.27 134

MP-MVS		78.35 20	78.26 21	78.64 31	86.54 25	63.47 4	86.02 20	83.55 70	63.89 37	73.60 67	90.60 20	54.85 50	86.72 69	77.20 25	88.06 37	85.74 110
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
DELS-MVS		74.76 52	74.46 55	75.65 75	77.84 181	52.25 177	75.59 195	84.17 50	63.76 38	73.15 75	82.79 177	59.58 20	86.80 67	67.24 95	86.04 60	87.89 30
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
OPM-MVS		74.73 53	74.25 57	76.19 64	80.81 103	59.01 67	82.60 66	83.64 67	63.74 39	72.52 92	87.49 74	47.18 151	85.88 92	69.47 74	80.78 105	83.66 183
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
UniMVSNet (Re)		70.63 117	70.20 115	71.89 166	78.55 154	45.29 270	75.94 189	82.92 88	63.68 40	68.16 151	83.59 167	53.89 64	83.49 143	53.97 198	71.12 236	86.89 64

GST-MVS		78.14 22	77.85 24	78.99 25	86.05 38	61.82 22	85.84 21	85.21 29	63.56 41	74.29 59	90.03 38	52.56 81	88.53 30	74.79 42	88.34 29	86.63 75

EC-MVSNet		75.84 45	75.87 42	75.74 72	78.86 146	52.65 168	83.73 50	86.08 17	63.47 42	72.77 88	87.25 80	53.13 76	87.93 42	71.97 61	85.57 63	86.66 73

ZNCC-MVS		78.82 13	78.67 17	79.30 14	86.43 28	62.05 18	86.62 11	86.01 18	63.32 43	75.08 42	90.47 26	53.96 61	88.68 27	76.48 28	89.63 20	87.16 58

DPE-MVS		80.56 5	80.98 5	79.29 15	87.27 13	60.56 41	85.71 26	86.42 14	63.28 44	83.27 13	91.83 10	64.96 7	90.47 11	76.41 29	89.67 18	86.84 66
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
CS-MVS		76.25 40	75.98 39	77.06 50	80.15 118	55.63 120	84.51 35	83.90 58	63.24 45	73.30 70	87.27 79	55.06 46	86.30 85	71.78 62	84.58 68	89.25 4

DeepC-MVS	69.38 2	78.56 18	78.14 22	79.83 7	83.60 63	61.62 23	84.17 42	86.85 6	63.23 46	73.84 65	90.25 32	57.68 29	89.96 14	74.62 43	89.03 22	87.89 30
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
VDD-MVS		72.50 83	72.09 83	73.75 121	81.58 86	49.69 219	77.76 144	77.63 191	63.21 47	73.21 73	89.02 53	42.14 203	83.32 144	61.72 143	82.50 91	88.25 20

plane_prior						56.31 102	83.58 53		63.19 48						80.48 112

ACMMP		76.02 43	75.33 46	78.07 38	85.20 49	61.91 20	85.49 29	84.44 45	63.04 49	69.80 126	89.74 46	45.43 173	87.16 59	72.01 60	82.87 87	85.14 133
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
PEN-MVS		66.60 208	66.45 188	67.04 251	77.11 207	36.56 349	77.03 165	80.42 138	62.95 50	62.51 257	84.03 157	46.69 159	79.07 236	44.22 280	63.08 323	85.51 117

APDe-MVS		80.16 8	80.59 6	78.86 28	86.64 21	60.02 45	88.12 3	86.42 14	62.94 51	82.40 14	92.12 2	59.64 19	89.76 15	78.70 13	88.32 31	86.79 68
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
mPP-MVS		76.54 36	75.93 40	78.34 36	86.47 26	63.50 3	85.74 25	82.28 96	62.90 52	71.77 101	90.26 31	46.61 160	86.55 76	71.71 63	85.66 62	84.97 140

ACMMP_NAP		78.77 15	78.78 14	78.74 29	85.44 45	61.04 31	83.84 49	85.16 32	62.88 53	78.10 24	91.26 13	52.51 82	88.39 31	79.34 8	90.52 13	86.78 69

DeepPCF-MVS	69.58 1	79.03 12	79.00 13	79.13 19	84.92 56	60.32 44	83.03 57	85.33 27	62.86 54	80.17 17	90.03 38	61.76 14	88.95 24	74.21 45	88.67 26	88.12 26

HFP-MVS		78.01 24	77.65 25	79.10 21	86.71 19	62.81 8	86.29 14	84.32 48	62.82 55	73.96 63	90.50 24	53.20 75	88.35 32	74.02 48	87.05 44	86.13 93

ACMMPR		77.71 25	77.23 28	79.16 17	86.75 18	62.93 7	86.29 14	84.24 49	62.82 55	73.55 68	90.56 22	49.80 116	88.24 34	74.02 48	87.03 45	86.32 87

region2R		77.67 27	77.18 29	79.15 18	86.76 17	62.95 6	86.29 14	84.16 51	62.81 57	73.30 70	90.58 21	49.90 114	88.21 35	73.78 50	87.03 45	86.29 90

casdiffmvs		74.80 51	74.89 52	74.53 100	75.59 233	50.37 205	78.17 133	85.06 36	62.80 58	74.40 56	87.86 70	57.88 27	83.61 140	69.46 75	82.79 89	89.59 3
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
baseline		74.61 58	74.70 53	74.34 104	75.70 229	49.99 214	77.54 150	84.63 44	62.73 59	73.98 62	87.79 73	57.67 30	83.82 136	69.49 73	82.74 90	89.20 6

HPM-MVS		77.28 29	76.85 30	78.54 32	85.00 51	60.81 38	82.91 60	85.08 34	62.57 60	73.09 79	89.97 41	50.90 109	87.48 52	75.30 36	86.85 50	87.33 56
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
DTE-MVSNet		65.58 220	65.34 211	66.31 260	76.06 226	34.79 360	76.43 177	79.38 153	62.55 61	61.66 267	83.83 162	45.60 167	79.15 234	41.64 307	60.88 338	85.00 138

SMA-MVS		80.28 6	80.39 7	79.95 4	86.60 23	61.95 19	86.33 13	85.75 21	62.49 62	82.20 15	92.28 1	56.53 36	89.70 16	79.85 5	91.48 1	88.19 23
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
CP-MVSNet		66.49 211	66.41 192	66.72 253	77.67 186	36.33 352	76.83 172	79.52 150	62.45 63	62.54 255	83.47 171	46.32 161	78.37 244	45.47 275	63.43 320	85.45 120

CP-MVS		77.12 32	76.68 32	78.43 33	86.05 38	63.18 5	87.55 10	83.45 74	62.44 64	72.68 89	90.50 24	48.18 134	87.34 53	73.59 52	85.71 61	84.76 147

PS-CasMVS		66.42 212	66.32 196	66.70 255	77.60 195	36.30 354	76.94 167	79.61 148	62.36 65	62.43 259	83.66 165	45.69 165	78.37 244	45.35 277	63.26 321	85.42 123

3Dnovator	64.47 5	72.49 84	71.39 93	75.79 69	77.70 184	58.99 68	80.66 93	83.15 85	62.24 66	65.46 206	86.59 94	42.38 202	85.52 100	59.59 161	84.72 67	82.85 204

MP-MVS-pluss		78.35 20	78.46 18	78.03 40	84.96 52	59.52 53	82.93 59	85.39 26	62.15 67	76.41 34	91.51 11	52.47 84	86.78 68	80.66 4	89.64 19	87.80 36
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
HQP-NCC					80.66 104		82.31 71		62.10 68	67.85 157

ACMP_Plane					80.66 104		82.31 71		62.10 68	67.85 157

HQP-MVS		73.45 71	72.80 75	75.40 79	80.66 104	54.94 131	82.31 71	83.90 58	62.10 68	67.85 157	85.54 129	45.46 171	86.93 64	67.04 97	80.35 113	84.32 155

CS-MVS-test		75.62 47	75.31 47	76.56 58	80.63 107	55.13 130	83.88 48	85.22 28	62.05 71	71.49 106	86.03 113	53.83 65	86.36 83	67.74 88	86.91 49	88.19 23

VPNet		67.52 187	68.11 155	65.74 273	79.18 138	36.80 347	72.17 256	72.83 257	62.04 72	67.79 163	85.83 122	48.88 128	76.60 277	51.30 221	72.97 213	83.81 173

WR-MVS_H		67.02 199	66.92 184	67.33 250	77.95 178	37.75 336	77.57 147	82.11 99	62.03 73	62.65 252	82.48 188	50.57 110	79.46 225	42.91 296	64.01 313	84.79 145

DeepC-MVS_fast	68.24 3	77.25 30	76.63 33	79.12 20	86.15 34	60.86 36	84.71 33	84.85 41	61.98 74	73.06 80	88.88 55	53.72 69	89.06 23	68.27 79	88.04 38	87.42 50
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
SF-MVS		78.82 13	79.22 12	77.60 44	82.88 74	57.83 80	84.99 32	88.13 2	61.86 75	79.16 20	90.75 18	57.96 26	87.09 62	77.08 26	90.18 15	87.87 32

PGM-MVS		76.77 35	76.06 38	78.88 27	86.14 35	62.73 9	82.55 67	83.74 65	61.71 76	72.45 96	90.34 29	48.48 132	88.13 36	72.32 58	86.85 50	85.78 104

Effi-MVS+		73.31 73	72.54 79	75.62 76	77.87 179	53.64 147	79.62 113	79.61 148	61.63 77	72.02 100	82.61 182	56.44 37	85.97 90	63.99 122	79.07 134	87.25 57

MG-MVS		73.96 66	73.89 63	74.16 109	85.65 42	49.69 219	81.59 83	81.29 120	61.45 78	71.05 108	88.11 63	51.77 96	87.73 47	61.05 149	83.09 80	85.05 137

LPG-MVS_test		72.74 80	71.74 86	75.76 70	80.22 113	57.51 86	82.55 67	83.40 76	61.32 79	66.67 184	87.33 77	39.15 236	86.59 73	67.70 89	77.30 159	83.19 195

LGP-MVS_train				75.76 70	80.22 113	57.51 86		83.40 76	61.32 79	66.67 184	87.33 77	39.15 236	86.59 73	67.70 89	77.30 159	83.19 195

CLD-MVS		73.33 72	72.68 76	75.29 84	78.82 148	53.33 156	78.23 130	84.79 42	61.30 81	70.41 113	81.04 219	52.41 85	87.12 60	64.61 118	82.49 92	85.41 124
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
MVS_111021_HR		74.02 64	73.46 69	75.69 73	83.01 72	60.63 40	77.29 158	78.40 180	61.18 82	70.58 111	85.97 115	54.18 57	84.00 133	67.52 93	82.98 84	82.45 211

FIs		70.82 114	71.43 91	68.98 230	78.33 164	38.14 332	76.96 166	83.59 69	61.02 83	67.33 170	86.73 87	55.07 45	81.64 182	54.61 195	79.22 130	87.14 59

FOURS1					86.12 36	60.82 37	88.18 1	83.61 68	60.87 84	81.50 16

FC-MVSNet-test		69.80 135	70.58 109	67.46 246	77.61 193	34.73 363	76.05 186	83.19 84	60.84 85	65.88 200	86.46 100	54.52 54	80.76 206	52.52 209	78.12 147	86.91 63

v8		70.33 124	69.28 131	73.49 134	73.15 267	50.22 207	78.62 123	80.78 133	60.79 86	66.45 188	82.11 200	49.35 119	84.98 113	63.58 128	68.71 277	85.28 129

CSCG		76.92 33	76.75 31	77.41 46	83.96 62	59.60 51	82.95 58	86.50 13	60.78 87	75.27 39	84.83 138	60.76 15	86.56 75	67.86 86	87.87 41	86.06 95

Vis-MVSNet		72.18 90	71.37 94	74.61 96	81.29 93	55.41 126	80.90 89	78.28 182	60.73 88	69.23 137	88.09 64	44.36 185	82.65 164	57.68 168	81.75 102	85.77 107
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
APD-MVS		78.02 23	78.04 23	77.98 41	86.44 27	60.81 38	85.52 27	84.36 47	60.61 89	79.05 21	90.30 30	55.54 43	88.32 33	73.48 53	87.03 45	84.83 143
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
ACMP	63.53 6	72.30 88	71.20 98	75.59 78	80.28 110	57.54 84	82.74 63	82.84 91	60.58 90	65.24 214	86.18 107	39.25 234	86.03 88	66.95 99	76.79 166	83.22 193
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
testdata1							72.65 246		60.50 91

UGNet		68.81 158	67.39 170	73.06 145	78.33 164	54.47 137	79.77 107	75.40 223	60.45 92	63.22 241	84.40 149	32.71 306	80.91 202	51.71 219	80.56 111	83.81 173
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
h-mvs33		72.71 81	71.49 90	76.40 59	81.99 82	59.58 52	76.92 168	76.74 206	60.40 93	74.81 49	85.95 117	45.54 169	85.76 95	70.41 70	70.61 241	83.86 172

hse-mvs2		71.04 108	69.86 120	74.60 97	79.58 128	57.12 96	73.96 227	75.25 226	60.40 93	74.81 49	81.95 202	45.54 169	82.90 153	70.41 70	66.83 292	83.77 177

EPP-MVSNet		72.16 93	71.31 96	74.71 90	78.68 152	49.70 217	82.10 75	81.65 105	60.40 93	65.94 196	85.84 121	51.74 97	86.37 82	55.93 179	79.55 125	88.07 29

UniMVSNet_ETH3D		67.60 186	67.07 183	69.18 229	77.39 200	42.29 296	74.18 224	75.59 219	60.37 96	66.77 181	86.06 112	37.64 250	78.93 242	52.16 212	73.49 202	86.32 87

test_prior2							81.75 79		60.37 96	75.01 43	89.06 52	56.22 39		72.19 59	88.96 24

SD-MVS		77.70 26	77.62 26	77.93 42	84.47 59	61.88 21	84.55 34	83.87 61	60.37 96	79.89 18	89.38 49	54.97 48	85.58 99	76.12 31	84.94 66	86.33 85
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
VNet		69.68 139	70.19 116	68.16 240	79.73 126	41.63 305	70.53 278	77.38 196	60.37 96	70.69 110	86.63 92	51.08 105	77.09 265	53.61 202	81.69 104	85.75 109

sasdasda		74.67 55	74.98 50	73.71 123	78.94 144	50.56 202	80.23 95	83.87 61	60.30 100	77.15 29	86.56 96	59.65 17	82.00 176	66.01 105	82.12 93	88.58 12

canonicalmvs		74.67 55	74.98 50	73.71 123	78.94 144	50.56 202	80.23 95	83.87 61	60.30 100	77.15 29	86.56 96	59.65 17	82.00 176	66.01 105	82.12 93	88.58 12

v7n		69.01 156	67.36 172	73.98 112	72.51 281	52.65 168	78.54 127	81.30 119	60.26 102	62.67 251	81.62 208	43.61 190	84.49 123	57.01 172	68.70 278	84.79 145

HPM-MVS_fast		74.30 63	73.46 69	76.80 52	84.45 60	59.04 66	83.65 52	81.05 127	60.15 103	70.43 112	89.84 43	41.09 220	85.59 98	67.61 91	82.90 86	85.77 107

VPA-MVSNet		69.02 155	69.47 128	67.69 244	77.42 199	41.00 310	74.04 225	79.68 146	60.06 104	69.26 136	84.81 139	51.06 106	77.58 257	54.44 196	74.43 187	84.48 152

v10		70.21 126	69.02 135	73.81 116	73.51 264	50.92 193	78.74 120	81.39 111	60.05 105	66.39 189	81.83 205	47.58 143	85.41 107	62.80 133	68.86 276	85.09 136

SR-MVS		76.13 42	75.70 43	77.40 48	85.87 40	61.20 29	85.52 27	82.19 97	59.99 106	75.10 41	90.35 28	47.66 141	86.52 77	71.64 64	82.99 82	84.47 153

9.14			78.75 15		83.10 69		84.15 43	88.26 1	59.90 107	78.57 23	90.36 27	57.51 32	86.86 66	77.39 23	89.52 21

v2v482		70.50 120	69.45 129	73.66 126	72.62 277	50.03 212	77.58 146	80.51 137	59.90 107	69.52 128	82.14 198	47.53 144	84.88 118	65.07 114	70.17 250	86.09 94

Baseline_NR-MVSNet		67.05 198	67.56 162	65.50 276	75.65 230	37.70 338	75.42 198	74.65 239	59.90 107	68.14 152	83.15 175	49.12 126	77.20 263	52.23 211	69.78 259	81.60 224

API-MVS		72.17 91	71.41 92	74.45 102	81.95 83	57.22 89	84.03 45	80.38 139	59.89 110	68.40 146	82.33 191	49.64 117	87.83 46	51.87 216	84.16 75	78.30 274

Effi-MVS+-dtu		69.64 141	67.53 165	75.95 67	76.10 225	62.29 15	80.20 98	76.06 214	59.83 111	65.26 213	77.09 287	41.56 212	84.02 132	60.60 152	71.09 237	81.53 225

CANet_DTU		68.18 174	67.71 161	69.59 220	74.83 244	46.24 258	78.66 122	76.85 203	59.60 112	63.45 240	82.09 201	35.25 274	77.41 260	59.88 158	78.76 139	85.14 133

EI-MVSNet		69.27 152	68.44 150	71.73 172	74.47 253	49.39 224	75.20 203	78.45 176	59.60 112	69.16 138	76.51 298	51.29 101	82.50 168	59.86 160	71.45 233	83.30 190

IterMVS-LS		69.22 154	68.48 146	71.43 182	74.44 255	49.40 223	76.23 181	77.55 192	59.60 112	65.85 201	81.59 211	51.28 102	81.58 185	59.87 159	69.90 257	83.30 190
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
MGCFI-Net		72.45 85	73.34 71	69.81 217	77.77 183	43.21 289	75.84 192	81.18 124	59.59 115	75.45 38	86.64 90	57.74 28	77.94 250	63.92 123	81.90 98	88.30 18

VDDNet		71.81 96	71.33 95	73.26 143	82.80 75	47.60 247	78.74 120	75.27 225	59.59 115	72.94 82	89.40 48	41.51 214	83.91 134	58.75 165	82.99 82	88.26 19

alignmvs		73.86 67	73.99 61	73.45 136	78.20 167	50.50 204	78.57 125	82.43 94	59.40 117	76.57 32	86.71 89	56.42 38	81.23 193	65.84 108	81.79 99	88.62 10

MVS_Test		72.45 85	72.46 80	72.42 160	74.88 242	48.50 235	76.28 180	83.14 86	59.40 117	72.46 94	84.68 140	55.66 42	81.12 194	65.98 107	79.66 122	87.63 43

TSAR-MVS + MP.		78.44 19	78.28 20	78.90 26	84.96 52	61.41 26	84.03 45	83.82 64	59.34 119	79.37 19	89.76 45	59.84 16	87.62 50	76.69 27	86.74 52	87.68 41
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
MSLP-MVS++		73.77 68	73.47 68	74.66 93	83.02 71	59.29 58	82.30 74	81.88 101	59.34 119	71.59 104	86.83 83	45.94 164	83.65 139	65.09 113	85.22 65	81.06 239

PAPM_NR		72.63 82	71.80 85	75.13 85	81.72 85	53.42 154	79.91 104	83.28 82	59.14 121	66.31 191	85.90 119	51.86 94	86.06 86	57.45 170	80.62 107	85.91 100

testing91		64.46 235	63.80 226	66.47 257	78.43 159	40.06 314	67.63 301	69.59 282	59.06 122	63.18 243	78.05 269	34.05 286	76.99 267	48.30 246	75.87 175	82.37 213

save fliter					86.17 33	61.30 28	83.98 47	79.66 147	59.00 123

v148		68.24 173	67.19 181	71.40 183	70.43 313	47.77 244	75.76 193	77.03 201	58.91 124	67.36 169	80.10 238	48.60 131	81.89 178	60.01 156	66.52 295	84.53 150

TransMVSNet (Re)		64.72 230	64.33 220	65.87 272	75.22 238	38.56 328	74.66 217	75.08 235	58.90 125	61.79 265	82.63 181	51.18 103	78.07 249	43.63 289	55.87 359	80.99 241

Anonymous202405211		66.84 203	65.99 202	69.40 224	80.19 116	42.21 298	71.11 272	71.31 268	58.80 126	67.90 155	86.39 102	29.83 328	79.65 222	49.60 236	78.78 138	86.33 85

test2506		65.33 225	64.61 218	67.50 245	79.46 131	34.19 367	74.43 221	51.92 374	58.72 127	66.75 182	88.05 66	25.99 357	80.92 201	51.94 215	84.25 72	87.39 51

ECVR-MVS		67.72 184	67.51 166	68.35 238	79.46 131	36.29 355	74.79 214	66.93 302	58.72 127	67.19 172	88.05 66	36.10 267	81.38 188	52.07 213	84.25 72	87.39 51

test1111		67.21 191	67.14 182	67.42 247	79.24 136	34.76 362	73.89 232	65.65 311	58.71 129	66.96 177	87.95 69	36.09 268	80.53 208	52.03 214	83.79 77	86.97 61

LCM-MVSNet-Re		61.88 264	61.35 257	63.46 291	74.58 251	31.48 380	61.42 342	58.14 353	58.71 129	53.02 348	79.55 249	43.07 194	76.80 271	45.69 268	77.96 149	82.11 219

testing99		64.05 238	63.29 235	66.34 259	78.17 171	39.76 318	67.33 306	68.00 295	58.60 131	63.03 246	78.10 268	32.57 311	76.94 269	48.22 247	75.58 179	82.34 214

v1144		70.42 122	69.31 130	73.76 119	73.22 265	50.64 198	77.83 142	81.43 110	58.58 132	69.40 132	81.16 216	47.53 144	85.29 109	64.01 121	70.64 239	85.34 126

TSAR-MVS + GP.		74.90 50	74.15 58	77.17 49	82.00 81	58.77 72	81.80 78	78.57 169	58.58 132	74.32 58	84.51 148	55.94 41	87.22 55	67.11 96	84.48 71	85.52 116

BH-RMVSNet		68.81 158	67.42 169	72.97 146	80.11 119	52.53 172	74.26 222	76.29 209	58.48 134	68.38 147	84.20 151	42.59 198	83.83 135	46.53 260	75.91 174	82.56 206

APD-MVS_3200maxsize		74.96 49	74.39 56	76.67 54	82.20 78	58.24 77	83.67 51	83.29 81	58.41 135	73.71 66	90.14 33	45.62 166	85.99 89	69.64 72	82.85 88	85.78 104

OMC-MVS		71.40 105	70.60 107	73.78 117	76.60 217	53.15 158	79.74 110	79.78 144	58.37 136	68.75 141	86.45 101	45.43 173	80.60 207	62.58 134	77.73 151	87.58 46

nrg030		72.96 77	73.01 73	72.84 149	75.41 236	50.24 206	80.02 99	82.89 90	58.36 137	74.44 55	86.73 87	58.90 24	80.83 203	65.84 108	74.46 185	87.44 49

K. test v3		60.47 274	57.11 289	70.56 202	73.74 263	48.22 238	75.10 207	62.55 333	58.27 138	53.62 344	76.31 301	27.81 343	81.59 184	47.42 251	39.18 389	81.88 222

FA-MVS(test-final)		69.82 134	68.48 146	73.84 115	78.44 158	50.04 211	75.58 197	78.99 159	58.16 139	67.59 166	82.14 198	42.66 197	85.63 96	56.60 174	76.19 172	85.84 102

MVS_111021_LR		69.50 146	68.78 140	71.65 175	78.38 160	59.33 56	74.82 213	70.11 277	58.08 140	67.83 161	84.68 140	41.96 205	76.34 282	65.62 110	77.54 152	79.30 267

SR-MVS-dyc-post		74.57 59	73.90 62	76.58 57	83.49 65	59.87 49	84.29 37	81.36 113	58.07 141	73.14 76	90.07 34	44.74 180	85.84 93	68.20 80	81.76 100	84.03 163

RE-MVS-def			73.71 66		83.49 65	59.87 49	84.29 37	81.36 113	58.07 141	73.14 76	90.07 34	43.06 195		68.20 80	81.76 100	84.03 163

SDMVSNet		68.03 176	68.10 156	67.84 242	77.13 205	48.72 233	65.32 321	79.10 156	58.02 143	65.08 217	82.55 184	47.83 138	73.40 294	63.92 123	73.92 193	81.41 227

sd_testset		64.46 235	64.45 219	64.51 286	77.13 205	42.25 297	62.67 335	72.11 263	58.02 143	65.08 217	82.55 184	41.22 219	69.88 315	47.32 253	73.92 193	81.41 227

GeoE		71.01 109	70.15 117	73.60 131	79.57 129	52.17 178	78.93 118	78.12 183	58.02 143	67.76 165	83.87 161	52.36 86	82.72 162	56.90 173	75.79 176	85.92 99

ZD-MVS					86.64 21	60.38 43		82.70 92	57.95 146	78.10 24	90.06 36	56.12 40	88.84 26	74.05 47	87.00 48

EIA-MVS		71.78 97	70.60 107	75.30 83	79.85 123	53.54 150	77.27 159	83.26 83	57.92 147	66.49 186	79.39 252	52.07 91	86.69 70	60.05 155	79.14 133	85.66 112

test_yl		69.69 137	69.13 132	71.36 184	78.37 162	45.74 263	74.71 215	80.20 141	57.91 148	70.01 121	83.83 162	42.44 200	82.87 156	54.97 189	79.72 119	85.48 118

DCV-MVSNet		69.69 137	69.13 132	71.36 184	78.37 162	45.74 263	74.71 215	80.20 141	57.91 148	70.01 121	83.83 162	42.44 200	82.87 156	54.97 189	79.72 119	85.48 118

dcpmvs_2		74.55 60	75.23 48	72.48 156	82.34 77	53.34 155	77.87 139	81.46 109	57.80 150	75.49 37	86.81 84	62.22 13	77.75 255	71.09 67	82.02 96	86.34 83

mvsmamba		71.15 106	69.54 125	75.99 66	77.61 193	53.46 152	81.95 77	75.11 231	57.73 151	66.95 178	85.96 116	37.14 259	87.56 51	67.94 84	75.49 181	86.97 61

Fast-Effi-MVS+-dtu		67.37 189	65.33 212	73.48 135	72.94 272	57.78 82	77.47 152	76.88 202	57.60 152	61.97 262	76.85 291	39.31 232	80.49 211	54.72 192	70.28 248	82.17 218

v1192		69.97 131	68.68 142	73.85 114	73.19 266	50.94 191	77.68 145	81.36 113	57.51 153	68.95 140	80.85 226	45.28 176	85.33 108	62.97 132	70.37 245	85.27 130

ACMH+	57.40 11	66.12 214	64.06 221	72.30 162	77.79 182	52.83 166	80.39 94	78.03 184	57.30 154	57.47 307	82.55 184	27.68 344	84.17 127	45.54 271	69.78 259	79.90 257

diffmvs		70.69 116	70.43 110	71.46 179	69.45 328	48.95 229	72.93 243	78.46 175	57.27 155	71.69 102	83.97 160	51.48 100	77.92 252	70.70 69	77.95 150	87.53 47
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
BH-untuned		68.27 171	67.29 174	71.21 188	79.74 125	53.22 157	76.06 185	77.46 195	57.19 156	66.10 193	81.61 209	45.37 175	83.50 142	45.42 276	76.68 168	76.91 297

thres100view900		63.28 247	62.41 245	65.89 271	77.31 202	38.66 327	72.65 246	69.11 289	57.07 157	62.45 258	81.03 220	37.01 263	79.17 231	31.84 359	73.25 208	79.83 259

DP-MVS Recon		72.15 94	70.73 106	76.40 59	86.57 24	57.99 79	81.15 88	82.96 87	57.03 158	66.78 180	85.56 126	44.50 183	88.11 37	51.77 218	80.23 116	83.10 199

thres600view7		63.30 246	62.27 246	66.41 258	77.18 204	38.87 325	72.35 253	69.11 289	56.98 159	62.37 260	80.96 222	37.01 263	79.00 240	31.43 366	73.05 212	81.36 230

V42		68.65 162	67.35 173	72.56 154	68.93 334	50.18 208	72.90 244	79.47 151	56.92 160	69.45 131	80.26 235	46.29 162	82.99 150	64.07 119	67.82 284	84.53 150

MCST-MVS		77.48 28	77.45 27	77.54 45	86.67 20	58.36 76	83.22 55	86.93 5	56.91 161	74.91 47	88.19 62	59.15 23	87.68 48	73.67 51	87.45 42	86.57 76

GA-MVS		65.53 221	63.70 228	71.02 195	70.87 308	48.10 239	70.48 279	74.40 241	56.69 162	64.70 225	76.77 292	33.66 293	81.10 195	55.42 188	70.32 247	83.87 171

v144192		69.71 136	68.51 145	73.33 141	73.10 268	50.13 209	77.54 150	80.64 134	56.65 163	68.57 144	80.55 229	46.87 158	84.96 115	62.98 131	69.66 263	84.89 142

tfpn200view9		63.18 249	62.18 248	66.21 263	76.85 212	39.62 319	71.96 260	69.44 285	56.63 164	62.61 253	79.83 241	37.18 256	79.17 231	31.84 359	73.25 208	79.83 259

thres400		63.31 245	62.18 248	66.72 253	76.85 212	39.62 319	71.96 260	69.44 285	56.63 164	62.61 253	79.83 241	37.18 256	79.17 231	31.84 359	73.25 208	81.36 230

GBi-Net		67.21 191	66.55 186	69.19 226	77.63 188	43.33 286	77.31 155	77.83 187	56.62 166	65.04 219	82.70 178	41.85 207	80.33 213	47.18 255	72.76 215	83.92 168

test1		67.21 191	66.55 186	69.19 226	77.63 188	43.33 286	77.31 155	77.83 187	56.62 166	65.04 219	82.70 178	41.85 207	80.33 213	47.18 255	72.76 215	83.92 168

FMVSNet2		66.93 201	66.31 197	68.79 233	77.63 188	42.98 291	76.11 183	77.47 193	56.62 166	65.22 216	82.17 196	41.85 207	80.18 219	47.05 258	72.72 218	83.20 194

DPM-MVS		75.47 48	75.00 49	76.88 51	81.38 92	59.16 59	79.94 102	85.71 22	56.59 169	72.46 94	86.76 85	56.89 34	87.86 45	66.36 101	88.91 25	83.64 185

v1921920		69.47 147	68.17 154	73.36 140	73.06 269	50.10 210	77.39 153	80.56 135	56.58 170	68.59 142	80.37 231	44.72 181	84.98 113	62.47 137	69.82 258	85.00 138

FMVSNet1		66.70 206	65.87 203	69.19 226	77.49 197	43.33 286	77.31 155	77.83 187	56.45 171	64.60 227	82.70 178	38.08 248	80.33 213	46.08 264	72.31 223	83.92 168

v1240		69.24 153	67.91 157	73.25 144	73.02 271	49.82 215	77.21 160	80.54 136	56.43 172	68.34 148	80.51 230	43.33 193	84.99 111	62.03 141	69.77 261	84.95 141

testing222		62.29 259	61.31 258	65.25 281	77.87 179	38.53 329	68.34 296	66.31 308	56.37 173	63.15 245	77.58 283	28.47 338	76.18 285	37.04 328	76.65 169	81.05 240

CDPH-MVS		76.31 38	75.67 44	78.22 37	85.35 48	59.14 62	81.31 86	84.02 52	56.32 174	74.05 61	88.98 54	53.34 74	87.92 43	69.23 76	88.42 28	87.59 45

Vis-MVSNet (Re-imp)		63.69 242	63.88 224	63.14 295	74.75 246	31.04 381	71.16 270	63.64 326	56.32 174	59.80 284	84.99 136	44.51 182	75.46 286	39.12 317	80.62 107	82.92 201

AdaColmap		69.99 130	68.66 143	73.97 113	84.94 54	57.83 80	82.63 65	78.71 165	56.28 176	64.34 228	84.14 153	41.57 211	87.06 63	46.45 261	78.88 135	77.02 293

PS-MVSNAJss		72.24 89	71.21 97	75.31 82	78.50 155	55.93 112	81.63 80	82.12 98	56.24 177	70.02 120	85.68 125	47.05 153	84.34 126	65.27 112	74.41 188	85.67 111

c3_l		68.33 170	67.56 162	70.62 201	70.87 308	46.21 259	74.47 220	78.80 163	56.22 178	66.19 192	78.53 266	51.88 93	81.40 187	62.08 138	69.04 272	84.25 157

Fast-Effi-MVS+		70.28 125	69.12 134	73.73 122	78.50 155	51.50 188	75.01 208	79.46 152	56.16 179	68.59 142	79.55 249	53.97 60	84.05 129	53.34 204	77.53 153	85.65 113

PHI-MVS		75.87 44	75.36 45	77.41 46	80.62 108	55.91 113	84.28 39	85.78 20	56.08 180	73.41 69	86.58 95	50.94 108	88.54 29	70.79 68	89.71 17	87.79 37

baseline1		63.81 241	63.87 225	63.62 290	76.29 222	36.36 350	71.78 262	67.29 299	56.05 181	64.23 233	82.95 176	47.11 152	74.41 291	47.30 254	61.85 332	80.10 255

train_agg		76.27 39	76.15 37	76.64 55	85.58 43	61.59 24	81.62 81	81.26 121	55.86 182	74.93 45	88.81 56	53.70 70	84.68 120	75.24 38	88.33 30	83.65 184

test_8					85.40 46	60.96 34	81.54 84	81.18 124	55.86 182	74.81 49	88.80 58	53.70 70	84.45 124

bld_raw_dy_0_64		74.00 65	73.69 67	74.93 86	80.28 110	50.00 213	77.56 148	85.20 31	55.84 184	72.52 92	84.05 156	53.90 63	86.60 72	67.59 92	86.28 59	88.18 25

FMVSNet3		66.32 213	65.61 208	68.46 236	76.48 220	42.34 295	74.98 210	77.15 200	55.83 185	65.04 219	81.16 216	39.91 225	80.14 220	47.18 255	72.76 215	82.90 203

PAPR		71.72 100	70.82 104	74.41 103	81.20 97	51.17 189	79.55 114	83.33 79	55.81 186	66.93 179	84.61 144	50.95 107	86.06 86	55.79 182	79.20 131	86.00 96

eth_miper_zixun_eth		67.63 185	66.28 198	71.67 174	71.60 294	48.33 237	73.68 236	77.88 185	55.80 187	65.91 197	78.62 264	47.35 150	82.88 155	59.45 162	66.25 296	83.81 173

ACMH	55.70 15	65.20 227	63.57 230	70.07 210	78.07 173	52.01 183	79.48 115	79.69 145	55.75 188	56.59 313	80.98 221	27.12 349	80.94 199	42.90 297	71.58 231	77.25 291
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
IB-MVS	56.42 12	65.40 224	62.73 242	73.40 139	74.89 241	52.78 167	73.09 242	75.13 230	55.69 189	58.48 301	73.73 324	32.86 301	86.32 84	50.63 226	70.11 251	81.10 238
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
CL-MVSNet_self_test		61.53 267	60.94 264	63.30 293	68.95 333	36.93 346	67.60 302	72.80 258	55.67 190	59.95 281	76.63 294	45.01 179	72.22 301	39.74 315	62.09 331	80.74 245

iter_conf05		73.64 69	73.08 72	75.33 81	78.05 174	50.61 199	79.76 108	84.74 43	55.66 191	72.19 97	85.10 135	53.98 59	87.65 49	68.56 78	79.69 121	87.73 39

mamv4		74.72 54	74.09 59	76.61 56	79.86 122	53.06 162	79.89 105	85.13 33	55.66 191	72.81 85	85.24 134	53.83 65	88.07 38	67.77 87	86.63 55	88.71 9

TEST9					85.58 43	61.59 24	81.62 81	81.26 121	55.65 193	74.93 45	88.81 56	53.70 70	84.68 120

thres200		62.20 260	61.16 262	65.34 279	75.38 237	39.99 315	69.60 288	69.29 287	55.64 194	61.87 264	76.99 288	37.07 262	78.96 241	31.28 367	73.28 207	77.06 292

pm-mvs1		65.24 226	64.97 216	66.04 268	72.38 283	39.40 322	72.62 248	75.63 218	55.53 195	62.35 261	83.18 174	47.45 146	76.47 280	49.06 240	66.54 294	82.24 215

testing11		62.81 252	61.90 251	65.54 275	78.38 160	40.76 311	67.59 303	66.78 304	55.48 196	60.13 277	77.11 286	31.67 317	76.79 272	45.53 272	74.45 186	79.06 268

ACMM	61.98 7	70.80 115	69.73 122	74.02 111	80.59 109	58.59 74	82.68 64	82.02 100	55.46 197	67.18 173	84.39 150	38.51 241	83.17 148	60.65 151	76.10 173	80.30 251
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
Anonymous20240529		69.91 132	69.02 135	72.56 154	80.19 116	47.65 245	77.56 148	80.99 129	55.45 198	69.88 124	86.76 85	39.24 235	82.18 174	54.04 197	77.10 163	87.85 33

tt0805		67.77 183	67.24 179	69.34 225	74.87 243	40.08 313	77.36 154	81.37 112	55.31 199	66.33 190	84.65 142	37.35 254	82.55 167	55.65 185	72.28 224	85.39 125

CPTT-MVS		72.78 79	72.08 84	74.87 89	84.88 57	61.41 26	84.15 43	77.86 186	55.27 200	67.51 168	88.08 65	41.93 206	81.85 179	69.04 77	80.01 117	81.35 232

XVG-OURS		68.76 161	67.37 171	72.90 148	74.32 258	57.22 89	70.09 284	78.81 162	55.24 201	67.79 163	85.81 124	36.54 266	78.28 246	62.04 140	75.74 177	83.19 195

tfpnnormal		62.47 255	61.63 254	64.99 283	74.81 245	39.01 324	71.22 268	73.72 250	55.22 202	60.21 276	80.09 239	41.26 218	76.98 268	30.02 372	68.09 282	78.97 271

MVSMamba_pp		74.64 57	74.07 60	76.35 61	79.76 124	53.09 161	79.97 101	85.21 29	55.21 203	72.81 85	85.37 133	53.93 62	87.17 58	67.93 85	86.46 57	88.80 7

cl____		67.18 194	66.26 199	69.94 212	70.20 316	45.74 263	73.30 238	76.83 204	55.10 204	65.27 210	79.57 248	47.39 148	80.53 208	59.41 164	69.22 270	83.53 187

DIV-MVS_self_test		67.18 194	66.26 199	69.94 212	70.20 316	45.74 263	73.29 239	76.83 204	55.10 204	65.27 210	79.58 247	47.38 149	80.53 208	59.43 163	69.22 270	83.54 186

PC_three_1452									55.09 206	84.46 4	89.84 43	66.68 5	89.41 18	74.24 44	91.38 2	88.42 14

EPNet_dtu		61.90 263	61.97 250	61.68 303	72.89 273	39.78 317	75.85 191	65.62 312	55.09 206	54.56 334	79.36 253	37.59 251	67.02 329	39.80 314	76.95 164	78.25 275
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
PVSNet_Blended_VisFu		71.45 104	70.39 111	74.65 94	82.01 80	58.82 71	79.93 103	80.35 140	55.09 206	65.82 202	82.16 197	49.17 123	82.64 165	60.34 153	78.62 142	82.50 210

cl22		67.47 188	66.45 188	70.54 203	69.85 324	46.49 255	73.85 233	77.35 197	55.07 209	65.51 205	77.92 273	47.64 142	81.10 195	61.58 146	69.32 266	84.01 165

miper_ehance_all_eth		68.03 176	67.24 179	70.40 205	70.54 311	46.21 259	73.98 226	78.68 167	55.07 209	66.05 194	77.80 277	52.16 90	81.31 190	61.53 147	69.32 266	83.67 181

PS-MVSNAJ		70.51 119	69.70 123	72.93 147	81.52 87	55.79 116	74.92 211	79.00 158	55.04 211	69.88 124	78.66 261	47.05 153	82.19 173	61.61 144	79.58 123	80.83 243

xiu_mvs_v2_base		70.52 118	69.75 121	72.84 149	81.21 96	55.63 120	75.11 205	78.92 160	54.92 212	69.96 123	79.68 246	47.00 157	82.09 175	61.60 145	79.37 126	80.81 244

MAR-MVS		71.51 102	70.15 117	75.60 77	81.84 84	59.39 55	81.38 85	82.90 89	54.90 213	68.08 154	78.70 260	47.73 139	85.51 101	51.68 220	84.17 74	81.88 222
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
XVG-OURS-SEG-HR		68.81 158	67.47 168	72.82 151	74.40 256	56.87 99	70.59 277	79.04 157	54.77 214	66.99 176	86.01 114	39.57 230	78.21 247	62.54 135	73.33 206	83.37 189

testing3		56.54 300	55.92 302	58.41 322	77.52 196	27.93 389	69.72 287	56.36 362	54.75 215	58.63 299	77.80 277	20.88 375	71.75 304	25.31 387	62.25 329	75.53 307

Anonymous20231211		69.28 151	68.47 148	71.73 172	80.28 110	47.18 251	79.98 100	82.37 95	54.61 216	67.24 171	84.01 158	39.43 231	82.41 171	55.45 187	72.83 214	85.62 114

SixPastTwentyTwo		61.65 266	58.80 278	70.20 208	75.80 228	47.22 250	75.59 195	69.68 280	54.61 216	54.11 338	79.26 255	27.07 350	82.96 151	43.27 291	49.79 376	80.41 249

test_0402		63.25 248	61.01 263	69.96 211	80.00 120	54.37 139	76.86 171	72.02 264	54.58 218	58.71 296	80.79 228	35.00 277	84.36 125	26.41 385	64.71 307	71.15 355

tttt0517		67.83 182	65.66 207	74.33 105	76.69 214	50.82 195	77.86 140	73.99 248	54.54 219	64.64 226	82.53 187	35.06 276	85.50 102	55.71 183	69.91 256	86.67 72

BH-w/o		66.85 202	65.83 204	69.90 215	79.29 133	52.46 174	74.66 217	76.65 207	54.51 220	64.85 223	78.12 267	45.59 168	82.95 152	43.26 292	75.54 180	74.27 323

AUN-MVS		68.45 169	66.41 192	74.57 99	79.53 130	57.08 97	73.93 230	75.23 227	54.44 221	66.69 183	81.85 204	37.10 261	82.89 154	62.07 139	66.84 291	83.75 178

LTVRE_ROB	55.42 16	63.15 250	61.23 261	68.92 231	76.57 218	47.80 242	59.92 351	76.39 208	54.35 222	58.67 297	82.46 189	29.44 332	81.49 186	42.12 301	71.14 235	77.46 286
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_fmvsmconf_n		73.01 76	72.59 77	74.27 107	71.28 303	55.88 114	78.21 132	75.56 220	54.31 223	74.86 48	87.80 72	54.72 51	80.23 217	78.07 21	78.48 143	86.70 70

test_fmvsmconf0.01_n		72.17 91	71.50 89	74.16 109	67.96 340	55.58 123	78.06 136	74.67 238	54.19 224	74.54 54	88.23 61	50.35 113	80.24 216	78.07 21	77.46 155	86.65 74

test_fmvsmconf0.1_n		72.81 78	72.33 81	74.24 108	69.89 323	55.81 115	78.22 131	75.40 223	54.17 225	75.00 44	88.03 68	53.82 67	80.23 217	78.08 20	78.34 146	86.69 71

ETVMVS		59.51 282	58.81 276	61.58 305	77.46 198	34.87 359	64.94 326	59.35 348	54.06 226	61.08 272	76.67 293	29.54 329	71.87 303	32.16 355	74.07 191	78.01 282

ab-mvs		66.65 207	66.42 191	67.37 248	76.17 224	41.73 302	70.41 281	76.14 212	53.99 227	65.98 195	83.51 169	49.48 118	76.24 283	48.60 243	73.46 204	84.14 161

IU-MVS					87.77 4	59.15 60		85.53 25	53.93 228	84.64 3				79.07 11	90.87 5	88.37 17

XVG-ACMP-BASELINE		64.36 237	62.23 247	70.74 199	72.35 284	52.45 175	70.80 276	78.45 176	53.84 229	59.87 282	81.10 218	16.24 382	79.32 228	55.64 186	71.76 228	80.47 247

FE-MVS		65.91 216	63.33 234	73.63 129	77.36 201	51.95 185	72.62 248	75.81 215	53.70 230	65.31 208	78.96 258	28.81 337	86.39 81	43.93 285	73.48 203	82.55 207

thisisatest0530		67.92 180	65.78 205	74.33 105	76.29 222	51.03 190	76.89 169	74.25 245	53.67 231	65.59 204	81.76 206	35.15 275	85.50 102	55.94 178	72.47 219	86.47 78

PVSNet_BlendedMVS		68.56 167	67.72 159	71.07 194	77.03 209	50.57 200	74.50 219	81.52 106	53.66 232	64.22 234	79.72 245	49.13 124	82.87 156	55.82 180	73.92 193	79.77 262

patch_mono-2		69.85 133	71.09 100	66.16 264	79.11 141	54.80 135	71.97 259	74.31 243	53.50 233	70.90 109	84.17 152	57.63 31	63.31 343	66.17 102	82.02 96	80.38 250

EG-PatchMatch MVS		64.71 231	62.87 239	70.22 206	77.68 185	53.48 151	77.99 137	78.82 161	53.37 234	56.03 318	77.41 285	24.75 364	84.04 130	46.37 262	73.42 205	73.14 329

DP-MVS		65.68 218	63.66 229	71.75 171	84.93 55	56.87 99	80.74 92	73.16 255	53.06 235	59.09 293	82.35 190	36.79 265	85.94 91	32.82 353	69.96 255	72.45 337

TR-MVS		66.59 210	65.07 215	71.17 191	79.18 138	49.63 221	73.48 237	75.20 229	52.95 236	67.90 155	80.33 234	39.81 228	83.68 138	43.20 293	73.56 201	80.20 252

ET-MVSNet_ETH3D		67.96 179	65.72 206	74.68 92	76.67 215	55.62 122	75.11 205	74.74 236	52.91 237	60.03 279	80.12 237	33.68 292	82.64 165	61.86 142	76.34 170	85.78 104

QAPM		70.05 128	68.81 139	73.78 117	76.54 219	53.43 153	83.23 54	83.48 71	52.89 238	65.90 198	86.29 104	41.55 213	86.49 79	51.01 223	78.40 145	81.42 226

OpenMVS	61.03 9	68.85 157	67.56 162	72.70 153	74.26 259	53.99 142	81.21 87	81.34 117	52.70 239	62.75 250	85.55 128	38.86 239	84.14 128	48.41 245	83.01 81	79.97 256

pmmvs6		63.69 242	62.82 241	66.27 262	70.63 310	39.27 323	73.13 241	75.47 222	52.69 240	59.75 286	82.30 192	39.71 229	77.03 266	47.40 252	64.35 312	82.53 208

IterMVS		62.79 253	61.27 259	67.35 249	69.37 329	52.04 182	71.17 269	68.24 294	52.63 241	59.82 283	76.91 290	37.32 255	72.36 298	52.80 208	63.19 322	77.66 284
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
mvs_tets		68.18 174	66.36 194	73.63 129	75.61 232	55.35 128	80.77 91	78.56 170	52.48 242	64.27 231	84.10 155	27.45 346	81.84 180	63.45 130	70.56 242	83.69 180

jajsoiax		68.25 172	66.45 188	73.66 126	75.62 231	55.49 125	80.82 90	78.51 172	52.33 243	64.33 229	84.11 154	28.28 340	81.81 181	63.48 129	70.62 240	83.67 181

TAMVS		66.78 205	65.27 213	71.33 187	79.16 140	53.67 146	73.84 234	69.59 282	52.32 244	65.28 209	81.72 207	44.49 184	77.40 261	42.32 300	78.66 141	82.92 201

iter_conf05_11		73.52 70	72.59 77	76.30 63	80.93 101	51.97 184	78.62 123	83.48 71	52.20 245	71.53 105	85.93 118	54.01 58	88.55 28	61.08 148	85.56 64	88.39 16

CDS-MVSNet		66.80 204	65.37 210	71.10 193	78.98 143	53.13 160	73.27 240	71.07 270	52.15 246	64.72 224	80.23 236	43.56 191	77.10 264	45.48 274	78.88 135	83.05 200
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
PVSNet_Blended		68.59 163	67.72 159	71.19 189	77.03 209	50.57 200	72.51 251	81.52 106	51.91 247	64.22 234	77.77 280	49.13 124	82.87 156	55.82 180	79.58 123	80.14 254

mvs_anonymous		68.03 176	67.51 166	69.59 220	72.08 288	44.57 277	71.99 258	75.23 227	51.67 248	67.06 175	82.57 183	54.68 52	77.94 250	56.56 175	75.71 178	86.26 91

xiu_mvs_v1_base_debu		68.58 164	67.28 175	72.48 156	78.19 168	57.19 91	75.28 200	75.09 232	51.61 249	70.04 117	81.41 213	32.79 302	79.02 237	63.81 125	77.31 156	81.22 234

xiu_mvs_v1_base		68.58 164	67.28 175	72.48 156	78.19 168	57.19 91	75.28 200	75.09 232	51.61 249	70.04 117	81.41 213	32.79 302	79.02 237	63.81 125	77.31 156	81.22 234

xiu_mvs_v1_base_debi		68.58 164	67.28 175	72.48 156	78.19 168	57.19 91	75.28 200	75.09 232	51.61 249	70.04 117	81.41 213	32.79 302	79.02 237	63.81 125	77.31 156	81.22 234

MVSTER		67.16 196	65.58 209	71.88 167	70.37 315	49.70 217	70.25 283	78.45 176	51.52 252	69.16 138	80.37 231	38.45 242	82.50 168	60.19 154	71.46 232	83.44 188

CNLPA		65.43 222	64.02 222	69.68 218	78.73 151	58.07 78	77.82 143	70.71 273	51.49 253	61.57 269	83.58 168	38.23 246	70.82 307	43.90 286	70.10 252	80.16 253

原ACMM1				74.69 91	85.39 47	59.40 54		83.42 75	51.47 254	70.27 115	86.61 93	48.61 130	86.51 78	53.85 200	87.96 39	78.16 276

miper_enhance_ethall		67.11 197	66.09 201	70.17 209	69.21 331	45.98 261	72.85 245	78.41 179	51.38 255	65.65 203	75.98 306	51.17 104	81.25 191	60.82 150	69.32 266	83.29 192

MSDG		61.81 265	59.23 273	69.55 223	72.64 276	52.63 170	70.45 280	75.81 215	51.38 255	53.70 341	76.11 302	29.52 330	81.08 197	37.70 323	65.79 300	74.93 315

test20.03		53.87 320	54.02 319	53.41 352	61.47 374	28.11 388	61.30 343	59.21 349	51.34 257	52.09 350	77.43 284	33.29 297	58.55 363	29.76 373	60.27 343	73.58 328

MVSFormer		71.50 103	70.38 112	74.88 88	78.76 149	57.15 94	82.79 61	78.48 173	51.26 258	69.49 129	83.22 172	43.99 188	83.24 146	66.06 103	79.37 126	84.23 158

test_djsdf		69.45 148	67.74 158	74.58 98	74.57 252	54.92 133	82.79 61	78.48 173	51.26 258	65.41 207	83.49 170	38.37 243	83.24 146	66.06 103	69.25 269	85.56 115

dmvs_testset		50.16 337	51.90 327	44.94 370	66.49 350	11.78 410	61.01 348	51.50 375	51.17 260	50.30 362	67.44 364	39.28 233	60.29 354	22.38 390	57.49 352	62.76 375

PAPM		67.92 180	66.69 185	71.63 176	78.09 172	49.02 227	77.09 163	81.24 123	51.04 261	60.91 273	83.98 159	47.71 140	84.99 111	40.81 308	79.32 129	80.90 242

Syy-MVS		56.00 307	56.23 300	55.32 339	74.69 248	26.44 395	65.52 316	57.49 357	50.97 262	56.52 314	72.18 331	39.89 226	68.09 322	24.20 388	64.59 310	71.44 351

myMVS_eth3d		54.86 316	54.61 311	55.61 338	74.69 248	27.31 392	65.52 316	57.49 357	50.97 262	56.52 314	72.18 331	21.87 373	68.09 322	27.70 380	64.59 310	71.44 351

miper_lstm_enhance		62.03 262	60.88 265	65.49 277	66.71 348	46.25 257	56.29 367	75.70 217	50.68 264	61.27 270	75.48 312	40.21 224	68.03 324	56.31 177	65.25 303	82.18 216

gg-mvs-nofinetune		57.86 292	56.43 298	62.18 301	72.62 277	35.35 358	66.57 307	56.33 363	50.65 265	57.64 306	57.10 386	30.65 320	76.36 281	37.38 325	78.88 135	74.82 317

TAPA-MVS	59.36 10	66.60 208	65.20 214	70.81 197	76.63 216	48.75 231	76.52 176	80.04 143	50.64 266	65.24 214	84.93 137	39.15 236	78.54 243	36.77 330	76.88 165	85.14 133
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
dmvs_re		56.77 299	56.83 294	56.61 333	69.23 330	41.02 307	58.37 356	64.18 322	50.59 267	57.45 308	71.42 339	35.54 272	58.94 361	37.23 326	67.45 287	69.87 364

MVP-Stereo		65.41 223	63.80 226	70.22 206	77.62 192	55.53 124	76.30 179	78.53 171	50.59 267	56.47 316	78.65 262	39.84 227	82.68 163	44.10 284	72.12 226	72.44 338
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
PCF-MVS	61.88 8	70.95 111	69.49 127	75.35 80	77.63 188	55.71 117	76.04 187	81.81 103	50.30 269	69.66 127	85.40 132	52.51 82	84.89 116	51.82 217	80.24 115	85.45 120
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
baseline2		63.42 244	61.26 260	69.89 216	72.55 279	47.62 246	71.54 263	68.38 293	50.11 270	54.82 330	75.55 311	43.06 195	80.96 198	48.13 248	67.16 290	81.11 237

test-LLR		58.15 290	58.13 286	58.22 324	68.57 335	44.80 273	65.46 318	57.92 354	50.08 271	55.44 322	69.82 352	32.62 308	57.44 367	49.66 234	73.62 198	72.41 339

test0.0.03 1		53.32 325	53.59 322	52.50 356	62.81 369	29.45 384	59.51 352	54.11 370	50.08 271	54.40 336	74.31 321	32.62 308	55.92 376	30.50 370	63.95 315	72.15 344

fmvsm_s_conf0.5_n		69.58 142	68.84 138	71.79 170	72.31 286	52.90 164	77.90 138	62.43 336	49.97 273	72.85 84	85.90 119	52.21 88	76.49 278	75.75 33	70.26 249	85.97 97

COLMAP_ROB	52.97 17	61.27 271	58.81 276	68.64 234	74.63 250	52.51 173	78.42 128	73.30 253	49.92 274	50.96 354	81.51 212	23.06 367	79.40 226	31.63 363	65.85 298	74.01 326
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
fmvsm_s_conf0.5_n_a		69.54 144	68.74 141	71.93 165	72.47 282	53.82 144	78.25 129	62.26 338	49.78 275	73.12 78	86.21 106	52.66 80	76.79 272	75.02 39	68.88 274	85.18 132

tpmvs		58.47 286	56.95 292	63.03 297	70.20 316	41.21 306	67.90 300	67.23 300	49.62 276	54.73 332	70.84 343	34.14 285	76.24 283	36.64 334	61.29 336	71.64 347

fmvsm_s_conf0.1_n		69.41 149	68.60 144	71.83 168	71.07 305	52.88 165	77.85 141	62.44 335	49.58 277	72.97 81	86.22 105	51.68 98	76.48 279	75.53 34	70.10 252	86.14 92

thisisatest0515		65.83 217	63.50 231	72.82 151	73.75 262	49.50 222	71.32 266	73.12 256	49.39 278	63.82 236	76.50 300	34.95 278	84.84 119	53.20 206	75.49 181	84.13 162

fmvsm_s_conf0.1_n_a		69.32 150	68.44 150	71.96 164	70.91 307	53.78 145	78.12 134	62.30 337	49.35 279	73.20 74	86.55 98	51.99 92	76.79 272	74.83 41	68.68 279	85.32 127

HY-MVS	56.14 13	64.55 234	63.89 223	66.55 256	74.73 247	41.02 307	69.96 285	74.43 240	49.29 280	61.66 267	80.92 223	47.43 147	76.68 276	44.91 279	71.69 229	81.94 220

MIMVSNet1		55.17 314	54.31 316	57.77 329	70.03 320	32.01 378	65.68 314	64.81 316	49.19 281	46.75 371	76.00 303	25.53 360	64.04 341	28.65 377	62.13 330	77.26 290

SCA		60.49 273	58.38 282	66.80 252	74.14 261	48.06 240	63.35 332	63.23 329	49.13 282	59.33 292	72.10 333	37.45 252	74.27 292	44.17 281	62.57 326	78.05 278

test_fmvsmvis_n_1920		70.84 112	70.38 112	72.22 163	71.16 304	55.39 127	75.86 190	72.21 262	49.03 283	73.28 72	86.17 108	51.83 95	77.29 262	75.80 32	78.05 148	83.98 166

testgi		51.90 329	52.37 326	50.51 362	60.39 382	23.55 402	58.42 355	58.15 352	49.03 283	51.83 351	79.21 256	22.39 368	55.59 377	29.24 376	62.64 325	72.40 341

MIMVSNet		57.35 294	57.07 290	58.22 324	74.21 260	37.18 341	62.46 336	60.88 345	48.88 285	55.29 325	75.99 305	31.68 316	62.04 348	31.87 358	72.35 221	75.43 309

gm-plane-assit					71.40 300	41.72 304			48.85 286		73.31 326		82.48 170	48.90 241

fmvsm_l_conf0.5_n		70.99 110	70.82 104	71.48 178	71.45 296	54.40 138	77.18 161	70.46 275	48.67 287	75.17 40	86.86 82	53.77 68	76.86 270	76.33 30	77.51 154	83.17 198

UWE-MVS		60.18 275	59.78 270	61.39 308	77.67 186	33.92 370	69.04 294	63.82 324	48.56 288	64.27 231	77.64 282	27.20 348	70.40 312	33.56 350	76.24 171	79.83 259

cascas		65.98 215	63.42 232	73.64 128	77.26 203	52.58 171	72.26 255	77.21 199	48.56 288	61.21 271	74.60 319	32.57 311	85.82 94	50.38 228	76.75 167	82.52 209

PLC	56.13 14	65.09 228	63.21 236	70.72 200	81.04 99	54.87 134	78.57 125	77.47 193	48.51 290	55.71 319	81.89 203	33.71 291	79.71 221	41.66 305	70.37 245	77.58 285
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
LS3D		64.71 231	62.50 244	71.34 186	79.72 127	55.71 117	79.82 106	74.72 237	48.50 291	56.62 312	84.62 143	33.59 294	82.34 172	29.65 374	75.23 183	75.97 301

anonymousdsp		67.00 200	64.82 217	73.57 132	70.09 319	56.13 107	76.35 178	77.35 197	48.43 292	64.99 222	80.84 227	33.01 299	80.34 212	64.66 116	67.64 286	84.23 158

无先验							79.66 112	74.30 244	48.40 293				80.78 205	53.62 201		79.03 270

114514_t		70.83 113	69.56 124	74.64 95	86.21 31	54.63 136	82.34 70	81.81 103	48.22 294	63.01 247	85.83 122	40.92 221	87.10 61	57.91 167	79.79 118	82.18 216

tpm		57.34 295	58.16 284	54.86 342	71.80 293	34.77 361	67.47 305	56.04 366	48.20 295	60.10 278	76.92 289	37.17 258	53.41 383	40.76 309	65.01 304	76.40 300

test_fmvsm_n_1920		71.73 99	71.14 99	73.50 133	72.52 280	56.53 101	75.60 194	76.16 210	48.11 296	77.22 28	85.56 126	53.10 77	77.43 259	74.86 40	77.14 161	86.55 77

MDA-MVSNet-bldmvs		53.87 320	50.81 332	63.05 296	66.25 352	48.58 234	56.93 365	63.82 324	48.09 297	41.22 383	70.48 348	30.34 323	68.00 325	34.24 345	45.92 381	72.57 335

XXY-MVS		60.68 272	61.67 253	57.70 330	70.43 313	38.45 330	64.19 329	66.47 305	48.05 298	63.22 241	80.86 225	49.28 121	60.47 352	45.25 278	67.28 289	74.19 324

F-COLMAP		63.05 251	60.87 266	69.58 222	76.99 211	53.63 148	78.12 134	76.16 210	47.97 299	52.41 349	81.61 209	27.87 342	78.11 248	40.07 311	66.66 293	77.00 294

fmvsm_l_conf0.5_n_a		70.50 120	70.27 114	71.18 190	71.30 302	54.09 140	76.89 169	69.87 278	47.90 300	74.37 57	86.49 99	53.07 78	76.69 275	75.41 35	77.11 162	82.76 205

Patchmatch-RL test		58.16 289	55.49 305	66.15 265	67.92 341	48.89 230	60.66 349	51.07 378	47.86 301	59.36 289	62.71 380	34.02 288	72.27 300	56.41 176	59.40 345	77.30 288

D2MVS		62.30 258	60.29 268	68.34 239	66.46 351	48.42 236	65.70 313	73.42 252	47.71 302	58.16 303	75.02 315	30.51 321	77.71 256	53.96 199	71.68 230	78.90 272

ANet_high		41.38 354	37.47 361	53.11 353	39.73 407	24.45 400	56.94 364	69.69 279	47.65 303	26.04 399	52.32 389	12.44 389	62.38 347	21.80 391	10.61 408	72.49 336

CostFormer		64.04 239	62.51 243	68.61 235	71.88 291	45.77 262	71.30 267	70.60 274	47.55 304	64.31 230	76.61 296	41.63 210	79.62 224	49.74 232	69.00 273	80.42 248

PatchmatchNet		59.84 278	58.24 283	64.65 285	73.05 270	46.70 254	69.42 290	62.18 339	47.55 304	58.88 295	71.96 335	34.49 282	69.16 317	42.99 295	63.60 317	78.07 277
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
KD-MVS_self_test		55.22 313	53.89 320	59.21 316	57.80 387	27.47 391	57.75 361	74.32 242	47.38 306	50.90 355	70.00 351	28.45 339	70.30 313	40.44 310	57.92 350	79.87 258

ITE_SJBPF				62.09 302	66.16 353	44.55 278		64.32 320	47.36 307	55.31 324	80.34 233	19.27 376	62.68 346	36.29 338	62.39 328	79.04 269

KD-MVS_2432*1600		53.45 322	51.50 330	59.30 313	62.82 367	37.14 342	55.33 368	71.79 266	47.34 308	55.09 327	70.52 346	21.91 371	70.45 310	35.72 340	42.97 384	70.31 360

miper_refine_blended		53.45 322	51.50 330	59.30 313	62.82 367	37.14 342	55.33 368	71.79 266	47.34 308	55.09 327	70.52 346	21.91 371	70.45 310	35.72 340	42.97 384	70.31 360

OurMVSNet-221017-0		61.37 270	58.63 280	69.61 219	72.05 289	48.06 240	73.93 230	72.51 259	47.23 310	54.74 331	80.92 223	21.49 374	81.24 192	48.57 244	56.22 358	79.53 264

tpmrst		58.24 288	58.70 279	56.84 332	66.97 345	34.32 365	69.57 289	61.14 344	47.17 311	58.58 300	71.60 338	41.28 217	60.41 353	49.20 238	62.84 324	75.78 304

PVSNet	50.76 19	58.40 287	57.39 288	61.42 306	75.53 234	44.04 281	61.43 341	63.45 327	47.04 312	56.91 310	73.61 325	27.00 351	64.76 339	39.12 317	72.40 220	75.47 308

WB-MVSnew		59.66 280	59.69 271	59.56 312	75.19 240	35.78 357	69.34 291	64.28 321	46.88 313	61.76 266	75.79 307	40.61 222	65.20 338	32.16 355	71.21 234	77.70 283

FMVSNet5		55.86 308	54.93 308	58.66 321	71.05 306	36.35 351	64.18 330	62.48 334	46.76 314	50.66 359	74.73 318	25.80 358	64.04 341	33.11 351	65.57 301	75.59 306

jason		69.65 140	68.39 152	73.43 138	78.27 166	56.88 98	77.12 162	73.71 251	46.53 315	69.34 133	83.22 172	43.37 192	79.18 230	64.77 115	79.20 131	84.23 158
jason: jason.
MS-PatchMatch		62.42 256	61.46 256	65.31 280	75.21 239	52.10 179	72.05 257	74.05 247	46.41 316	57.42 309	74.36 320	34.35 284	77.57 258	45.62 270	73.67 197	66.26 372

1112_ss		64.00 240	63.36 233	65.93 270	79.28 134	42.58 294	71.35 265	72.36 261	46.41 316	60.55 275	77.89 275	46.27 163	73.28 295	46.18 263	69.97 254	81.92 221

lupinMVS		69.57 143	68.28 153	73.44 137	78.76 149	57.15 94	76.57 174	73.29 254	46.19 318	69.49 129	82.18 194	43.99 188	79.23 229	64.66 116	79.37 126	83.93 167

testdata				64.66 284	81.52 87	52.93 163		65.29 314	46.09 319	73.88 64	87.46 75	38.08 248	66.26 334	53.31 205	78.48 143	74.78 318

UnsupCasMVSNet_eth		53.16 327	52.47 325	55.23 340	59.45 383	33.39 373	59.43 353	69.13 288	45.98 320	50.35 361	72.32 330	29.30 333	58.26 365	42.02 303	44.30 382	74.05 325

AllTest		57.08 297	54.65 310	64.39 287	71.44 297	49.03 225	69.92 286	67.30 297	45.97 321	47.16 368	79.77 243	17.47 377	67.56 326	33.65 347	59.16 346	76.57 298

TestCases				64.39 287	71.44 297	49.03 225		67.30 297	45.97 321	47.16 368	79.77 243	17.47 377	67.56 326	33.65 347	59.16 346	76.57 298

WTY-MVS		59.75 279	60.39 267	57.85 328	72.32 285	37.83 335	61.05 347	64.18 322	45.95 323	61.91 263	79.11 257	47.01 156	60.88 351	42.50 299	69.49 265	74.83 316

IterMVS-SCA-FT		62.49 254	61.52 255	65.40 278	71.99 290	50.80 196	71.15 271	69.63 281	45.71 324	60.61 274	77.93 272	37.45 252	65.99 335	55.67 184	63.50 319	79.42 265

WB-MVS		43.26 349	43.41 350	42.83 374	63.32 366	10.32 412	58.17 358	45.20 390	45.42 325	40.44 386	67.26 367	34.01 289	58.98 360	11.96 403	24.88 397	59.20 378

旧先验2							76.08 184		45.32 326	76.55 33			65.56 337	58.75 165

OpenMVS_ROB	52.78 18	60.03 276	58.14 285	65.69 274	70.47 312	44.82 272	75.33 199	70.86 272	45.04 327	56.06 317	76.00 303	26.89 352	79.65 222	35.36 342	67.29 288	72.60 334

TinyColmap		54.14 317	51.72 328	61.40 307	66.84 347	41.97 299	66.52 308	68.51 292	44.81 328	42.69 382	75.77 308	11.66 391	72.94 296	31.96 357	56.77 356	69.27 368

MDTV_nov1_ep13			57.00 291		72.73 275	38.26 331	65.02 325	64.73 318	44.74 329	55.46 321	72.48 329	32.61 310	70.47 309	37.47 324	67.75 285

新几何1				70.76 198	85.66 41	61.13 30		66.43 306	44.68 330	70.29 114	86.64 90	41.29 216	75.23 287	49.72 233	81.75 102	75.93 302

Patchmtry		57.16 296	56.47 297	59.23 315	69.17 332	34.58 364	62.98 333	63.15 330	44.53 331	56.83 311	74.84 316	35.83 270	68.71 319	40.03 312	60.91 337	74.39 322

ppachtmachnet_test		58.06 291	55.38 306	66.10 267	69.51 326	48.99 228	68.01 299	66.13 309	44.50 332	54.05 339	70.74 344	32.09 315	72.34 299	36.68 333	56.71 357	76.99 296

PatchT		53.17 326	53.44 323	52.33 357	68.29 339	25.34 399	58.21 357	54.41 369	44.46 333	54.56 334	69.05 358	33.32 296	60.94 350	36.93 329	61.76 334	70.73 358

EPMVS		53.96 318	53.69 321	54.79 343	66.12 354	31.96 379	62.34 338	49.05 381	44.42 334	55.54 320	71.33 341	30.22 324	56.70 370	41.65 306	62.54 327	75.71 305

pmmvs4		61.48 269	59.39 272	67.76 243	71.57 295	53.86 143	71.42 264	65.34 313	44.20 335	59.46 288	77.92 273	35.90 269	74.71 289	43.87 287	64.87 306	74.71 319

dp		51.89 330	51.60 329	52.77 355	68.44 338	32.45 377	62.36 337	54.57 368	44.16 336	49.31 363	67.91 360	28.87 336	56.61 372	33.89 346	54.89 361	69.24 369

PatchMatch-RL		56.25 305	54.55 312	61.32 309	77.06 208	56.07 109	65.57 315	54.10 371	44.13 337	53.49 347	71.27 342	25.20 361	66.78 330	36.52 336	63.66 316	61.12 376

our_test_3		56.49 301	54.42 313	62.68 299	69.51 326	45.48 268	66.08 311	61.49 342	44.11 338	50.73 358	69.60 355	33.05 298	68.15 321	38.38 320	56.86 354	74.40 321

USDC		56.35 304	54.24 317	62.69 298	64.74 359	40.31 312	65.05 324	73.83 249	43.93 339	47.58 366	77.71 281	15.36 385	75.05 288	38.19 322	61.81 333	72.70 333

PM-MVS		52.33 328	50.19 336	58.75 320	62.10 372	45.14 271	65.75 312	40.38 397	43.60 340	53.52 345	72.65 328	9.16 399	65.87 336	50.41 227	54.18 364	65.24 374

pmmvs-eth3d		58.81 285	56.31 299	66.30 261	67.61 342	52.42 176	72.30 254	64.76 317	43.55 341	54.94 329	74.19 322	28.95 334	72.60 297	43.31 290	57.21 353	73.88 327

SSC-MVS		41.96 353	41.99 353	41.90 375	62.46 371	9.28 414	57.41 363	44.32 393	43.38 342	38.30 391	66.45 370	32.67 307	58.42 364	10.98 404	21.91 400	57.99 382

new-patchmatchnet		47.56 344	47.73 344	47.06 365	58.81 385	9.37 413	48.78 384	59.21 349	43.28 343	44.22 378	68.66 359	25.67 359	57.20 369	31.57 365	49.35 377	74.62 320

Test_1112_low_res		62.32 257	61.77 252	64.00 289	79.08 142	39.53 321	68.17 297	70.17 276	43.25 344	59.03 294	79.90 240	44.08 186	71.24 306	43.79 288	68.42 280	81.25 233

RPMNet		61.53 267	58.42 281	70.86 196	69.96 321	52.07 180	65.31 322	81.36 113	43.20 345	59.36 289	70.15 350	35.37 273	85.47 104	36.42 337	64.65 308	75.06 311

tpm2		62.07 261	60.10 269	67.99 241	72.79 274	43.86 282	71.05 274	66.85 303	43.14 346	62.77 248	75.39 313	38.32 244	80.80 204	41.69 304	68.88 274	79.32 266

JIA-IIPM		51.56 331	47.68 345	63.21 294	64.61 360	50.73 197	47.71 386	58.77 351	42.90 347	48.46 365	51.72 390	24.97 362	70.24 314	36.06 339	53.89 365	68.64 370

1314		64.61 233	63.21 236	68.80 232	71.87 292	47.46 248	73.95 228	78.39 181	42.88 348	59.97 280	76.60 297	38.11 247	79.39 227	54.84 191	72.32 222	79.55 263

HyFIR lowres test		65.67 219	63.01 238	73.67 125	79.97 121	55.65 119	69.07 293	75.52 221	42.68 349	63.53 239	77.95 271	40.43 223	81.64 182	46.01 265	71.91 227	83.73 179

CR-MVSNet		59.91 277	57.90 287	65.96 269	69.96 321	52.07 180	65.31 322	63.15 330	42.48 350	59.36 289	74.84 316	35.83 270	70.75 308	45.50 273	64.65 308	75.06 311

test222					83.14 68	58.68 73	72.57 250	63.45 327	41.78 351	67.56 167	86.12 109	37.13 260			78.73 140	74.98 314

TDRefinement		53.44 324	50.72 333	61.60 304	64.31 362	46.96 252	70.89 275	65.27 315	41.78 351	44.61 377	77.98 270	11.52 393	66.36 333	28.57 378	51.59 370	71.49 350

sss		56.17 306	56.57 296	54.96 341	66.93 346	36.32 353	57.94 359	61.69 341	41.67 353	58.64 298	75.32 314	38.72 240	56.25 374	42.04 302	66.19 297	72.31 342

PVSNet_0	43.31 20	47.46 345	45.64 348	52.92 354	67.60 343	44.65 275	54.06 372	54.64 367	41.59 354	46.15 373	58.75 383	30.99 319	58.66 362	32.18 354	24.81 398	55.46 386

MVS		67.37 189	66.33 195	70.51 204	75.46 235	50.94 191	73.95 228	81.85 102	41.57 355	62.54 255	78.57 265	47.98 135	85.47 104	52.97 207	82.05 95	75.14 310

Anonymous20240521		55.30 311	54.41 314	57.96 327	60.92 381	41.73 302	71.09 273	71.06 271	41.18 356	48.65 364	73.31 326	16.93 379	59.25 359	42.54 298	64.01 313	72.90 331

Anonymous20231206		55.10 315	55.30 307	54.48 344	69.81 325	33.94 369	62.91 334	62.13 340	41.08 357	55.18 326	75.65 309	32.75 305	56.59 373	30.32 371	67.86 283	72.91 330

MDA-MVSNet_test_wron		50.71 336	48.95 338	56.00 337	61.17 376	41.84 300	51.90 378	56.45 360	40.96 358	44.79 376	67.84 361	30.04 326	55.07 380	36.71 332	50.69 373	71.11 356

YYNet1		50.73 335	48.96 337	56.03 336	61.10 377	41.78 301	51.94 377	56.44 361	40.94 359	44.84 375	67.80 362	30.08 325	55.08 379	36.77 330	50.71 372	71.22 353

dongtai		34.52 363	34.94 363	33.26 384	61.06 378	16.00 409	52.79 376	23.78 410	40.71 360	39.33 390	48.65 398	16.91 380	48.34 391	12.18 402	19.05 402	35.44 401

CHOSEN 1792x2688		65.08 229	62.84 240	71.82 169	81.49 89	56.26 105	66.32 310	74.20 246	40.53 361	63.16 244	78.65 262	41.30 215	77.80 254	45.80 267	74.09 190	81.40 229

pmmvs5		56.47 302	55.68 304	58.86 319	61.41 375	36.71 348	66.37 309	62.75 332	40.38 362	53.70 341	76.62 295	34.56 280	67.05 328	40.02 313	65.27 302	72.83 332

test_vis1_n_1920		58.86 284	59.06 275	58.25 323	63.76 363	43.14 290	67.49 304	66.36 307	40.22 363	65.89 199	71.95 336	31.04 318	59.75 357	59.94 157	64.90 305	71.85 346

MDTV_nov1_ep13_2view						25.89 397	61.22 344		40.10 364	51.10 353		32.97 300		38.49 319		78.61 273

tpm cat1		59.25 283	56.95 292	66.15 265	72.19 287	46.96 252	68.09 298	65.76 310	40.03 365	57.81 305	70.56 345	38.32 244	74.51 290	38.26 321	61.50 335	77.00 294

test-mter		56.42 303	55.82 303	58.22 324	68.57 335	44.80 273	65.46 318	57.92 354	39.94 366	55.44 322	69.82 352	21.92 370	57.44 367	49.66 234	73.62 198	72.41 339

UnsupCasMVSNet_bld		50.07 338	48.87 339	53.66 349	60.97 380	33.67 371	57.62 362	64.56 319	39.47 367	47.38 367	64.02 378	27.47 345	59.32 358	34.69 344	43.68 383	67.98 371

TESTMET0.1,1		55.28 312	54.90 309	56.42 334	66.56 349	43.67 284	65.46 318	56.27 364	39.18 368	53.83 340	67.44 364	24.21 365	55.46 378	48.04 249	73.11 211	70.13 362

ADS-MVSNet2		51.33 333	48.76 340	59.07 318	66.02 355	44.60 276	50.90 380	59.76 347	36.90 369	50.74 356	66.18 372	26.38 353	63.11 344	27.17 381	54.76 362	69.50 366

ADS-MVSNet		48.48 342	47.77 343	50.63 361	66.02 355	29.92 383	50.90 380	50.87 380	36.90 369	50.74 356	66.18 372	26.38 353	52.47 385	27.17 381	54.76 362	69.50 366

RPSCF		55.80 309	54.22 318	60.53 311	65.13 358	42.91 293	64.30 328	57.62 356	36.84 371	58.05 304	82.28 193	28.01 341	56.24 375	37.14 327	58.61 348	82.44 212

test_cas_vis1_n_1920		56.91 298	56.71 295	57.51 331	59.13 384	45.40 269	63.58 331	61.29 343	36.24 372	67.14 174	71.85 337	29.89 327	56.69 371	57.65 169	63.58 318	70.46 359

Patchmatch-test		49.08 340	48.28 342	51.50 360	64.40 361	30.85 382	45.68 390	48.46 384	35.60 373	46.10 374	72.10 333	34.47 283	46.37 394	27.08 383	60.65 341	77.27 289

CHOSEN 280x420		47.83 343	46.36 347	52.24 359	67.37 344	49.78 216	38.91 398	43.11 395	35.00 374	43.27 381	63.30 379	28.95 334	49.19 390	36.53 335	60.80 339	57.76 383

N_pmnet		39.35 358	40.28 356	36.54 381	63.76 363	1.62 418	49.37 383	0.76 417	34.62 375	43.61 380	66.38 371	26.25 355	42.57 398	26.02 386	51.77 369	65.44 373

kuosan		29.62 370	30.82 369	26.02 389	52.99 390	16.22 408	51.09 379	22.71 411	33.91 376	33.99 393	40.85 399	15.89 383	33.11 406	7.59 410	18.37 403	28.72 403

PMMVS		53.96 318	53.26 324	56.04 335	62.60 370	50.92 193	61.17 345	56.09 365	32.81 377	53.51 346	66.84 369	34.04 287	59.93 356	44.14 283	68.18 281	57.27 384

CMPMVS	42.80 21	57.81 293	55.97 301	63.32 292	60.98 379	47.38 249	64.66 327	69.50 284	32.06 378	46.83 370	77.80 277	29.50 331	71.36 305	48.68 242	73.75 196	71.21 354
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
CVMVSNet		59.63 281	59.14 274	61.08 310	74.47 253	38.84 326	75.20 203	68.74 291	31.15 379	58.24 302	76.51 298	32.39 313	68.58 320	49.77 231	65.84 299	75.81 303

FPMVS		42.18 352	41.11 355	45.39 367	58.03 386	41.01 309	49.50 382	53.81 372	30.07 380	33.71 394	64.03 376	11.69 390	52.08 388	14.01 398	55.11 360	43.09 395

EU-MVSNet		55.61 310	54.41 314	59.19 317	65.41 357	33.42 372	72.44 252	71.91 265	28.81 381	51.27 352	73.87 323	24.76 363	69.08 318	43.04 294	58.20 349	75.06 311

test_vis1_n		49.89 339	48.69 341	53.50 351	53.97 388	37.38 340	61.53 340	47.33 387	28.54 382	59.62 287	67.10 368	13.52 387	52.27 386	49.07 239	57.52 351	70.84 357

test_fmvs1_n		51.37 332	50.35 335	54.42 346	52.85 391	37.71 337	61.16 346	51.93 373	28.15 383	63.81 237	69.73 354	13.72 386	53.95 381	51.16 222	60.65 341	71.59 348

LF4IMVS		42.95 350	42.26 352	45.04 368	48.30 398	32.50 376	54.80 370	48.49 383	28.03 384	40.51 385	70.16 349	9.24 398	43.89 397	31.63 363	49.18 378	58.72 380

test_fmvs1		51.32 334	50.48 334	53.81 348	53.57 389	37.51 339	60.63 350	51.16 376	28.02 385	63.62 238	69.23 357	16.41 381	53.93 382	51.01 223	60.70 340	69.99 363

MVS-HIRNet		45.52 346	44.48 349	48.65 364	68.49 337	34.05 368	59.41 354	44.50 392	27.03 386	37.96 392	50.47 394	26.16 356	64.10 340	26.74 384	59.52 344	47.82 393

PMVS	28.69 22	36.22 361	33.29 366	45.02 369	36.82 409	35.98 356	54.68 371	48.74 382	26.31 387	21.02 402	51.61 391	2.88 411	60.10 355	9.99 407	47.58 379	38.99 400
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
pmmvs3		44.92 347	41.95 354	53.86 347	52.58 393	43.55 285	62.11 339	46.90 389	26.05 388	40.63 384	60.19 382	11.08 396	57.91 366	31.83 362	46.15 380	60.11 377

test_fmvs2		48.69 341	47.49 346	52.29 358	48.63 397	33.06 375	57.76 360	48.05 385	25.71 389	59.76 285	69.60 355	11.57 392	52.23 387	49.45 237	56.86 354	71.58 349

PMMVS2		27.40 371	25.91 374	31.87 386	39.46 408	6.57 415	31.17 401	28.52 406	23.96 390	20.45 403	48.94 397	4.20 407	37.94 402	16.51 395	19.97 401	51.09 388

Gipuma		34.77 362	31.91 367	43.33 372	62.05 373	37.87 333	20.39 403	67.03 301	23.23 391	18.41 404	25.84 404	4.24 405	62.73 345	14.71 397	51.32 371	29.38 402
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
test_vis1_rt		41.35 355	39.45 357	47.03 366	46.65 400	37.86 334	47.76 385	38.65 398	23.10 392	44.21 379	51.22 392	11.20 395	44.08 396	39.27 316	53.02 367	59.14 379

new_pmnet		34.13 364	34.29 365	33.64 383	52.63 392	18.23 407	44.43 393	33.90 403	22.81 393	30.89 396	53.18 388	10.48 397	35.72 405	20.77 392	39.51 388	46.98 394

mvsany_test1		39.38 357	38.16 360	43.02 373	49.05 395	34.28 366	44.16 394	25.94 408	22.74 394	46.57 372	62.21 381	23.85 366	41.16 401	33.01 352	35.91 392	53.63 387

LCM-MVSNet		40.30 356	35.88 362	53.57 350	42.24 402	29.15 385	45.21 392	60.53 346	22.23 395	28.02 397	50.98 393	3.72 408	61.78 349	31.22 368	38.76 390	69.78 365

test_fmvs3		44.30 348	42.55 351	49.55 363	42.83 401	27.15 394	53.03 374	44.93 391	22.03 396	53.69 343	64.94 375	4.21 406	49.63 389	47.47 250	49.82 375	71.88 345

APD_test1		37.39 360	34.94 363	44.72 371	48.88 396	33.19 374	52.95 375	44.00 394	19.49 397	27.28 398	58.59 384	3.18 410	52.84 384	18.92 393	41.17 387	48.14 392

mvsany_test3		32.62 365	30.57 370	38.77 379	36.16 410	24.20 401	38.10 399	20.63 412	19.14 398	40.36 387	57.43 385	5.06 403	36.63 404	29.59 375	28.66 396	55.49 385

E-PMN		23.77 372	22.73 376	26.90 387	42.02 403	20.67 404	42.66 395	35.70 401	17.43 399	10.28 409	25.05 405	6.42 401	42.39 399	10.28 406	14.71 405	17.63 404

EMVS		22.97 373	21.84 377	26.36 388	40.20 406	19.53 406	41.95 396	34.64 402	17.09 400	9.73 410	22.83 406	7.29 400	42.22 400	9.18 408	13.66 406	17.32 405

test_vis3_rt		32.09 366	30.20 371	37.76 380	35.36 411	27.48 390	40.60 397	28.29 407	16.69 401	32.52 395	40.53 400	1.96 412	37.40 403	33.64 349	42.21 386	48.39 390

test_f		31.86 367	31.05 368	34.28 382	32.33 413	21.86 403	32.34 400	30.46 405	16.02 402	39.78 389	55.45 387	4.80 404	32.36 407	30.61 369	37.66 391	48.64 389

DSMNet-mixed		39.30 359	38.72 358	41.03 376	51.22 394	19.66 405	45.53 391	31.35 404	15.83 403	39.80 388	67.42 366	22.19 369	45.13 395	22.43 389	52.69 368	58.31 381

testf1		31.46 368	28.89 372	39.16 377	41.99 404	28.78 386	46.45 388	37.56 399	14.28 404	21.10 400	48.96 395	1.48 414	47.11 392	13.63 399	34.56 393	41.60 396

APD_test2		31.46 368	28.89 372	39.16 377	41.99 404	28.78 386	46.45 388	37.56 399	14.28 404	21.10 400	48.96 395	1.48 414	47.11 392	13.63 399	34.56 393	41.60 396

MVE	17.77 23	21.41 374	17.77 379	32.34 385	34.34 412	25.44 398	16.11 404	24.11 409	11.19 406	13.22 406	31.92 402	1.58 413	30.95 408	10.47 405	17.03 404	40.62 399
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
DeepMVS_CX				12.03 392	17.97 414	10.91 411		10.60 415	7.46 407	11.07 408	28.36 403	3.28 409	11.29 411	8.01 409	9.74 410	13.89 406

wuyk23d		13.32 377	12.52 380	15.71 391	47.54 399	26.27 396	31.06 402	1.98 416	4.93 408	5.18 411	1.94 411	0.45 416	18.54 410	6.81 411	12.83 407	2.33 408

test_method		19.68 375	18.10 378	24.41 390	13.68 415	3.11 417	12.06 406	42.37 396	2.00 409	11.97 407	36.38 401	5.77 402	29.35 409	15.06 396	23.65 399	40.76 398

tmp_tt		9.43 378	11.14 381	4.30 393	2.38 416	4.40 416	13.62 405	16.08 414	0.39 410	15.89 405	13.06 407	15.80 384	5.54 412	12.63 401	10.46 409	2.95 407

EGC-MVSNET		42.47 351	38.48 359	54.46 345	74.33 257	48.73 232	70.33 282	51.10 377	0.03 411	0.18 412	67.78 363	13.28 388	66.49 332	18.91 394	50.36 374	48.15 391

testmvs		4.52 381	6.03 384	0.01 395	0.01 417	0.00 420	53.86 373	0.00 418	0.01 412	0.04 413	0.27 412	0.00 418	0.00 413	0.04 412	0.00 411	0.03 410

test123		4.73 380	6.30 383	0.02 394	0.01 417	0.01 419	56.36 366	0.00 418	0.01 412	0.04 413	0.21 413	0.01 417	0.00 413	0.03 413	0.00 411	0.04 409

test_blank		0.00 383	0.00 386	0.00 396	0.00 419	0.00 420	0.00 407	0.00 418	0.00 414	0.00 415	0.00 414	0.00 418	0.00 413	0.00 414	0.00 411	0.00 411

uanet_test		0.00 383	0.00 386	0.00 396	0.00 419	0.00 420	0.00 407	0.00 418	0.00 414	0.00 415	0.00 414	0.00 418	0.00 413	0.00 414	0.00 411	0.00 411

DCPMVS		0.00 383	0.00 386	0.00 396	0.00 419	0.00 420	0.00 407	0.00 418	0.00 414	0.00 415	0.00 414	0.00 418	0.00 413	0.00 414	0.00 411	0.00 411

cdsmvs_eth3d_5k		17.50 376	23.34 375	0.00 396	0.00 419	0.00 420	0.00 407	78.63 168	0.00 414	0.00 415	82.18 194	49.25 122	0.00 413	0.00 414	0.00 411	0.00 411

pcd_1.5k_mvsjas		3.92 382	5.23 385	0.00 396	0.00 419	0.00 420	0.00 407	0.00 418	0.00 414	0.00 415	0.00 414	47.05 153	0.00 413	0.00 414	0.00 411	0.00 411

sosnet-low-res		0.00 383	0.00 386	0.00 396	0.00 419	0.00 420	0.00 407	0.00 418	0.00 414	0.00 415	0.00 414	0.00 418	0.00 413	0.00 414	0.00 411	0.00 411

sosnet		0.00 383	0.00 386	0.00 396	0.00 419	0.00 420	0.00 407	0.00 418	0.00 414	0.00 415	0.00 414	0.00 418	0.00 413	0.00 414	0.00 411	0.00 411

uncertanet		0.00 383	0.00 386	0.00 396	0.00 419	0.00 420	0.00 407	0.00 418	0.00 414	0.00 415	0.00 414	0.00 418	0.00 413	0.00 414	0.00 411	0.00 411

Regformer		0.00 383	0.00 386	0.00 396	0.00 419	0.00 420	0.00 407	0.00 418	0.00 414	0.00 415	0.00 414	0.00 418	0.00 413	0.00 414	0.00 411	0.00 411

ab-mvs-re		6.49 379	8.65 382	0.00 396	0.00 419	0.00 420	0.00 407	0.00 418	0.00 414	0.00 415	77.89 275	0.00 418	0.00 413	0.00 414	0.00 411	0.00 411

uanet		0.00 383	0.00 386	0.00 396	0.00 419	0.00 420	0.00 407	0.00 418	0.00 414	0.00 415	0.00 414	0.00 418	0.00 413	0.00 414	0.00 411	0.00 411

WAC-MVS						27.31 392								27.77 379

MSC_two_6792asdad				79.95 4	87.24 14	61.04 31		85.62 23					90.96 1	79.31 9	90.65 8	87.85 33

No_MVS				79.95 4	87.24 14	61.04 31		85.62 23					90.96 1	79.31 9	90.65 8	87.85 33

eth-test2					0.00 419

eth-test					0.00 419

OPU-MVS				79.83 7	87.54 11	60.93 35	87.82 7				89.89 42	67.01 1	90.33 12	73.16 54	91.15 4	88.23 21

test_0728_SECOND				79.19 16	87.82 3	59.11 63	87.85 5	87.15 3					90.84 3	78.66 15	90.61 11	87.62 44

GSMVS																78.05 278

test_part2					87.58 9	60.47 42				83.42 12

sam_mvs1												34.74 279				78.05 278

sam_mvs												33.43 295

ambc				65.13 282	63.72 365	37.07 344	47.66 387	78.78 164		54.37 337	71.42 339	11.24 394	80.94 199	45.64 269	53.85 366	77.38 287

MTGPA								80.97 130

test_post1							68.67 295				3.64 409	32.39 313	69.49 316	44.17 281

test_post											3.55 410	33.90 290	66.52 331

patchmatchnet-post											64.03 376	34.50 281	74.27 292

GG-mvs-BLEND				62.34 300	71.36 301	37.04 345	69.20 292	57.33 359		54.73 332	65.48 374	30.37 322	77.82 253	34.82 343	74.93 184	72.17 343

MTMP							86.03 19	17.08 413

test9_res														75.28 37	88.31 32	83.81 173

agg_prior2														73.09 55	87.93 40	84.33 154

agg_prior					85.04 50	59.96 47		81.04 128		74.68 52			84.04 130

test_prior4						62.51 14	82.08 76

test_prior				76.69 53	84.20 61	57.27 88		84.88 40					86.43 80			86.38 79

新几何2							76.12 182

旧先验1					83.04 70	53.15 158		67.52 296			87.85 71	44.08 186			80.76 106	78.03 281

原ACMM2							79.02 117

testdata2													72.18 302	46.95 259

segment_acmp												54.23 56

test12				77.76 43	84.52 58	58.41 75		83.36 78		72.93 83		54.61 53	88.05 39		88.12 35	86.81 67

plane_prior7					81.41 90	55.96 111

plane_prior6					81.20 97	56.24 106						45.26 177

plane_prior5								84.01 53					87.21 56	68.16 82	80.58 109	84.65 148

plane_prior4											86.10 110

plane_prior1					81.27 95

n2								0.00 418

nn								0.00 418

door-mid								47.19 388

lessismore_v0				69.91 214	71.42 299	47.80 242		50.90 379		50.39 360	75.56 310	27.43 347	81.33 189	45.91 266	34.10 395	80.59 246

test11								83.47 73

door								47.60 386

HQP5-MVS						54.94 131

BP-MVS														67.04 97

HQP4-MVS										67.85 157			86.93 64			84.32 155

HQP3-MVS								83.90 58							80.35 113

HQP2-MVS												45.46 171

NP-MVS					80.98 100	56.05 110					85.54 129

ACMMP++_ref															74.07 191

ACMMP++															72.16 225

Test By Simon												48.33 133

High-resolution multi-view benchmark