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 82	60.01 49	86.19 17	83.93 54	73.19 1	77.08 34	91.21 17	57.23 33	90.73 10	83.35 1	88.12 34	89.22 6

MVS_0304		78.45 18	78.28 19	78.98 26	80.73 107	57.91 83	84.68 35	81.64 107	68.35 2	75.77 39	90.38 29	53.98 59	90.26 13	81.30 3	87.68 42	88.77 11

CANet		76.46 40	75.93 44	78.06 39	81.29 97	57.53 88	82.35 72	83.31 80	67.78 3	70.09 118	86.34 110	54.92 50	88.90 25	72.68 58	84.55 67	87.76 38

UA-Net		73.13 75	72.93 75	73.76 121	83.58 66	51.66 192	78.75 121	77.66 193	67.75 4	72.61 93	89.42 50	49.82 114	83.29 148	53.61 209	83.14 80	86.32 86

CNVR-MVS		79.84 10	79.97 10	79.45 11	87.90 2	62.17 17	84.37 39	85.03 36	66.96 5	77.58 29	90.06 39	59.47 21	89.13 22	78.67 14	89.73 16	87.03 59

TranMVSNet+NR-MVSNet		70.36 125	70.10 122	71.17 194	78.64 155	42.97 299	76.53 177	81.16 127	66.95 6	68.53 147	85.42 136	51.61 96	83.07 152	52.32 217	69.70 267	87.46 47

3Dnovator+	66.72 4	75.84 49	74.57 59	79.66 9	82.40 79	59.92 51	85.83 22	86.32 16	66.92 7	67.80 165	89.24 54	42.03 206	89.38 19	64.07 122	86.50 57	89.69 3

NCCC		78.58 16	78.31 18	79.39 12	87.51 12	62.61 13	85.20 30	84.42 45	66.73 8	74.67 58	89.38 52	55.30 46	89.18 21	74.19 46	87.34 44	86.38 78

SteuartSystems-ACMMP		79.48 11	79.31 11	79.98 3	83.01 75	62.18 16	87.60 9	85.83 19	66.69 9	78.03 26	90.98 18	54.26 56	90.06 14	78.42 19	89.02 23	87.69 39
Skip Steuart: Steuart Systems R&D Blog.
EPNet		73.09 76	72.16 83	75.90 71	75.95 232	56.28 107	83.05 59	72.39 265	66.53 10	65.27 212	87.00 87	50.40 110	85.47 105	62.48 139	86.32 58	85.94 97
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
UniMVSNet_NR-MVSNet		71.11 109	71.00 104	71.44 183	79.20 139	44.13 285	76.02 190	82.60 94	66.48 11	68.20 151	84.60 148	56.82 36	82.82 163	54.62 199	70.43 247	87.36 54

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 25	63.71 12	89.23 20	81.51 2	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 65	65.37 13	78.78 22	90.64 21	58.63 25	87.24 54	79.00 12	90.37 14	85.26 132

NR-MVSNet		69.54 146	68.85 139	71.59 180	78.05 177	43.81 290	74.20 227	80.86 134	65.18 14	62.76 254	84.52 149	52.35 84	83.59 144	50.96 232	70.78 242	87.37 52

MTAPA		76.90 34	76.42 38	78.35 35	86.08 37	63.57 2	74.92 214	80.97 132	65.13 15	75.77 39	90.88 19	48.63 129	86.66 73	77.23 24	88.17 33	84.81 147

DVP-MVS++		81.67 1	82.40 1	79.47 10	87.24 14	59.15 63	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 16

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 89	71.59 88	74.91 88	78.47 159	54.02 146	77.05 165	79.33 157	65.03 18	71.68 104	79.35 258	52.75 76	84.89 118	66.46 102	74.23 193	85.83 102

casdiffmvs_mvg		76.14 45	76.30 39	75.66 77	76.46 226	51.83 191	79.67 111	85.08 33	65.02 19	75.84 38	88.58 63	59.42 22	85.08 111	72.75 57	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 60		86.84 7	65.01 20	83.80 11	91.86 6	64.03 11

ETV-MVS		74.46 64	73.84 67	76.33 67	79.27 137	55.24 132	79.22 117	85.00 38	64.97 21	72.65 92	79.46 254	53.65 70	87.87 44	67.45 95	82.91 86	85.89 100

WR-MVS		68.47 170	68.47 150	68.44 240	80.20 118	39.84 324	73.75 239	76.07 216	64.68 22	68.11 156	83.63 168	50.39 111	79.14 238	49.78 237	69.66 268	86.34 82

XVS		77.17 31	76.56 36	79.00 23	86.32 29	62.62 11	85.83 22	83.92 55	64.55 23	72.17 98	90.01 43	47.95 136	88.01 40	71.55 70	86.74 53	86.37 80

X-MVStestdata		70.21 128	67.28 177	79.00 23	86.32 29	62.62 11	85.83 22	83.92 55	64.55 23	72.17 98	6.49 420	47.95 136	88.01 40	71.55 70	86.74 53	86.37 80

HQP_MVS		74.31 65	73.73 68	76.06 69	81.41 94	56.31 105	84.22 43	84.01 52	64.52 25	69.27 136	86.10 117	45.26 178	87.21 58	68.16 87	80.58 111	84.65 151

plane_prior2							84.22 43		64.52 25

EI-MVSNet-UG-set		71.92 97	71.06 103	74.52 102	77.98 180	53.56 155	76.62 174	79.16 158	64.40 27	71.18 109	78.95 263	52.19 86	84.66 125	65.47 113	73.57 204	85.32 128

DU-MVS		70.01 131	69.53 128	71.44 183	78.05 177	44.13 285	75.01 210	81.51 110	64.37 28	68.20 151	84.52 149	49.12 126	82.82 163	54.62 199	70.43 247	87.37 52

DVP-MVS		80.84 4	81.64 3	78.42 34	87.75 7	59.07 67	87.85 5	85.03 36	64.26 29	83.82 8	92.00 3	64.82 8	90.75 8	78.66 15	90.61 11	85.45 121
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 67	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 72		86.78 10	64.20 31	85.97 1	91.34 15	66.87 3	90.78 7

SED-MVS		81.56 2	82.30 2	79.32 13	87.77 4	58.90 72	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 22

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 41

LFMVS		71.78 99	71.59 88	72.32 164	83.40 70	46.38 261	79.75 109	71.08 274	64.18 32	72.80 89	88.64 62	42.58 201	83.72 140	57.41 177	84.49 70	86.86 64

IS-MVSNet		71.57 103	71.00 104	73.27 145	78.86 148	45.63 272	80.22 100	78.69 169	64.14 35	66.46 189	87.36 81	49.30 120	85.60 98	50.26 236	83.71 79	88.59 13

plane_prior3						56.09 111			63.92 36	69.27 136

MP-MVS		78.35 20	78.26 21	78.64 31	86.54 25	63.47 4	86.02 20	83.55 69	63.89 37	73.60 71	90.60 22	54.85 51	86.72 71	77.20 25	88.06 36	85.74 109
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
DELS-MVS		74.76 57	74.46 60	75.65 78	77.84 184	52.25 183	75.59 197	84.17 49	63.76 38	73.15 79	82.79 180	59.58 20	86.80 69	67.24 96	86.04 59	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 58	74.25 62	76.19 68	80.81 106	59.01 70	82.60 69	83.64 66	63.74 39	72.52 94	87.49 77	47.18 152	85.88 93	69.47 80	80.78 107	83.66 186
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
UniMVSNet (Re)		70.63 119	70.20 118	71.89 169	78.55 156	45.29 275	75.94 191	82.92 88	63.68 40	68.16 154	83.59 169	53.89 62	83.49 146	53.97 205	71.12 240	86.89 63

GST-MVS		78.14 22	77.85 24	78.99 25	86.05 38	61.82 22	85.84 21	85.21 30	63.56 41	74.29 64	90.03 41	52.56 78	88.53 29	74.79 42	88.34 29	86.63 74

EC-MVSNet		75.84 49	75.87 46	75.74 75	78.86 148	52.65 174	83.73 53	86.08 17	63.47 42	72.77 90	87.25 85	53.13 73	87.93 42	71.97 66	85.57 62	86.66 72

ZNCC-MVS		78.82 13	78.67 16	79.30 14	86.43 28	62.05 18	86.62 11	86.01 18	63.32 43	75.08 46	90.47 28	53.96 61	88.68 27	76.48 28	89.63 20	87.16 57

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 65
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
CS-MVS		76.25 44	75.98 43	77.06 53	80.15 121	55.63 123	84.51 38	83.90 57	63.24 45	73.30 74	87.27 84	55.06 48	86.30 86	71.78 67	84.58 66	89.25 5

DeepC-MVS	69.38 2	78.56 17	78.14 22	79.83 7	83.60 65	61.62 23	84.17 45	86.85 6	63.23 46	73.84 69	90.25 35	57.68 29	89.96 15	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 85	72.09 84	73.75 123	81.58 90	49.69 222	77.76 146	77.63 194	63.21 47	73.21 77	89.02 56	42.14 205	83.32 147	61.72 146	82.50 92	88.25 21

plane_prior						56.31 105	83.58 56		63.19 48						80.48 114

ACMMP		76.02 47	75.33 51	78.07 38	85.20 49	61.91 20	85.49 29	84.44 44	63.04 49	69.80 128	89.74 49	45.43 174	87.16 60	72.01 64	82.87 88	85.14 134
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		66.60 211	66.45 191	67.04 254	77.11 211	36.56 357	77.03 166	80.42 141	62.95 50	62.51 262	84.03 159	46.69 160	79.07 239	44.22 287	63.08 328	85.51 116

APDe-MVS		80.16 8	80.59 6	78.86 29	86.64 21	60.02 48	88.12 3	86.42 14	62.94 51	82.40 14	92.12 2	59.64 19	89.76 16	78.70 13	88.32 31	86.79 67
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
mPP-MVS		76.54 39	75.93 44	78.34 36	86.47 26	63.50 3	85.74 25	82.28 97	62.90 52	71.77 102	90.26 34	46.61 161	86.55 77	71.71 68	85.66 61	84.97 143

ACMMP_NAP		78.77 15	78.78 14	78.74 30	85.44 45	61.04 31	83.84 52	85.16 31	62.88 53	78.10 24	91.26 16	52.51 79	88.39 30	79.34 8	90.52 13	86.78 68

DeepPCF-MVS	69.58 1	79.03 12	79.00 13	79.13 19	84.92 56	60.32 46	83.03 60	85.33 28	62.86 54	80.17 17	90.03 41	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 47	62.82 55	73.96 67	90.50 26	53.20 72	88.35 31	74.02 48	87.05 45	86.13 92

ACMMPR		77.71 25	77.23 28	79.16 17	86.75 18	62.93 7	86.29 14	84.24 48	62.82 55	73.55 72	90.56 24	49.80 115	88.24 33	74.02 48	87.03 46	86.32 86

region2R		77.67 27	77.18 29	79.15 18	86.76 17	62.95 6	86.29 14	84.16 50	62.81 57	73.30 74	90.58 23	49.90 113	88.21 34	73.78 50	87.03 46	86.29 89

casdiffmvs		74.80 56	74.89 57	74.53 101	75.59 238	50.37 209	78.17 135	85.06 35	62.80 58	74.40 61	87.86 73	57.88 27	83.61 143	69.46 81	82.79 90	89.59 4
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 61	74.70 58	74.34 105	75.70 234	49.99 217	77.54 151	84.63 42	62.73 59	73.98 66	87.79 76	57.67 30	83.82 139	69.49 79	82.74 91	89.20 7

HPM-MVS		77.28 29	76.85 30	78.54 32	85.00 51	60.81 38	82.91 63	85.08 33	62.57 60	73.09 83	89.97 44	50.90 106	87.48 52	75.30 36	86.85 51	87.33 55
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
DTE-MVSNet		65.58 223	65.34 214	66.31 265	76.06 231	34.79 370	76.43 179	79.38 156	62.55 61	61.66 272	83.83 164	45.60 168	79.15 237	41.64 316	60.88 343	85.00 140

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 37	89.70 17	79.85 5	91.48 1	88.19 24
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		66.49 214	66.41 195	66.72 256	77.67 191	36.33 360	76.83 173	79.52 153	62.45 63	62.54 260	83.47 173	46.32 162	78.37 247	45.47 282	63.43 325	85.45 121

CP-MVS		77.12 32	76.68 32	78.43 33	86.05 38	63.18 5	87.55 10	83.45 72	62.44 64	72.68 91	90.50 26	48.18 134	87.34 53	73.59 52	85.71 60	84.76 150

PS-CasMVS		66.42 215	66.32 199	66.70 258	77.60 199	36.30 362	76.94 168	79.61 151	62.36 65	62.43 264	83.66 167	45.69 166	78.37 247	45.35 284	63.26 326	85.42 124

3Dnovator	64.47 5	72.49 86	71.39 94	75.79 72	77.70 189	58.99 71	80.66 96	83.15 85	62.24 66	65.46 208	86.59 101	42.38 204	85.52 101	59.59 164	84.72 65	82.85 207

MP-MVS-pluss		78.35 20	78.46 17	78.03 40	84.96 52	59.52 56	82.93 62	85.39 27	62.15 67	76.41 37	91.51 11	52.47 81	86.78 70	80.66 4	89.64 19	87.80 36
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
HQP-NCC					80.66 108		82.31 74		62.10 68	67.85 160

ACMP_Plane					80.66 108		82.31 74		62.10 68	67.85 160

HQP-MVS		73.45 71	72.80 76	75.40 82	80.66 108	54.94 134	82.31 74	83.90 57	62.10 68	67.85 160	85.54 134	45.46 172	86.93 66	67.04 98	80.35 115	84.32 158

SPE-MVS-test		75.62 52	75.31 52	76.56 64	80.63 111	55.13 133	83.88 51	85.22 29	62.05 71	71.49 107	86.03 120	53.83 63	86.36 84	67.74 90	86.91 50	88.19 24

VPNet		67.52 190	68.11 157	65.74 278	79.18 140	36.80 355	72.17 260	72.83 262	62.04 72	67.79 166	85.83 127	48.88 128	76.60 281	51.30 228	72.97 217	83.81 176

WR-MVS_H		67.02 202	66.92 186	67.33 253	77.95 181	37.75 344	77.57 149	82.11 100	62.03 73	62.65 257	82.48 191	50.57 109	79.46 228	42.91 304	64.01 318	84.79 148

DeepC-MVS_fast	68.24 3	77.25 30	76.63 33	79.12 20	86.15 34	60.86 36	84.71 34	84.85 40	61.98 74	73.06 84	88.88 58	53.72 66	89.06 23	68.27 84	88.04 37	87.42 49
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 46	82.88 77	57.83 84	84.99 31	88.13 2	61.86 75	79.16 20	90.75 20	57.96 26	87.09 63	77.08 26	90.18 15	87.87 32

PGM-MVS		76.77 37	76.06 42	78.88 28	86.14 35	62.73 9	82.55 70	83.74 64	61.71 76	72.45 97	90.34 32	48.48 132	88.13 37	72.32 61	86.85 51	85.78 103

Effi-MVS+		73.31 74	72.54 79	75.62 79	77.87 182	53.64 153	79.62 113	79.61 151	61.63 77	72.02 100	82.61 185	56.44 39	85.97 91	63.99 125	79.07 136	87.25 56

MG-MVS		73.96 68	73.89 66	74.16 111	85.65 42	49.69 222	81.59 85	81.29 121	61.45 78	71.05 110	88.11 66	51.77 93	87.73 47	61.05 151	83.09 81	85.05 139

LPG-MVS_test		72.74 81	71.74 87	75.76 73	80.22 116	57.51 89	82.55 70	83.40 74	61.32 79	66.67 186	87.33 82	39.15 240	86.59 74	67.70 91	77.30 163	83.19 198

LGP-MVS_train				75.76 73	80.22 116	57.51 89		83.40 74	61.32 79	66.67 186	87.33 82	39.15 240	86.59 74	67.70 91	77.30 163	83.19 198

CLD-MVS		73.33 73	72.68 77	75.29 86	78.82 150	53.33 161	78.23 132	84.79 41	61.30 81	70.41 115	81.04 222	52.41 82	87.12 61	64.61 121	82.49 93	85.41 125
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
RRT-MVS		71.46 106	70.70 109	73.74 124	77.76 187	49.30 228	76.60 175	80.45 140	61.25 82	68.17 153	84.78 142	44.64 183	84.90 117	64.79 117	77.88 153	87.03 59

MVS_111021_HR		74.02 67	73.46 71	75.69 76	83.01 75	60.63 40	77.29 159	78.40 183	61.18 83	70.58 113	85.97 122	54.18 58	84.00 136	67.52 94	82.98 85	82.45 214

balanced_conf03		76.58 38	76.55 37	76.68 59	81.73 88	52.90 169	80.94 91	85.70 23	61.12 84	74.90 52	87.17 86	56.46 38	88.14 36	72.87 56	88.03 38	89.00 8

FIs		70.82 116	71.43 92	68.98 233	78.33 166	38.14 340	76.96 167	83.59 68	61.02 85	67.33 173	86.73 94	55.07 47	81.64 185	54.61 201	79.22 131	87.14 58

FOURS1					86.12 36	60.82 37	88.18 1	83.61 67	60.87 86	81.50 16

FC-MVSNet-test		69.80 137	70.58 112	67.46 249	77.61 198	34.73 373	76.05 188	83.19 84	60.84 87	65.88 202	86.46 107	54.52 55	80.76 209	52.52 216	78.12 149	86.91 62

v8		70.33 126	69.28 133	73.49 137	73.15 272	50.22 211	78.62 125	80.78 135	60.79 88	66.45 190	82.11 203	49.35 119	84.98 114	63.58 131	68.71 282	85.28 130

CSCG		76.92 33	76.75 31	77.41 49	83.96 64	59.60 54	82.95 61	86.50 13	60.78 89	75.27 43	84.83 140	60.76 15	86.56 76	67.86 89	87.87 41	86.06 94

Vis-MVSNet		72.18 92	71.37 95	74.61 97	81.29 97	55.41 129	80.90 92	78.28 185	60.73 90	69.23 139	88.09 67	44.36 187	82.65 167	57.68 174	81.75 103	85.77 106
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
BP-MVS1		73.41 72	72.25 82	76.88 54	76.68 219	53.70 151	79.15 118	81.07 128	60.66 91	71.81 101	87.39 80	40.93 223	87.24 54	71.23 72	81.29 106	89.71 2

APD-MVS		78.02 23	78.04 23	77.98 41	86.44 27	60.81 38	85.52 27	84.36 46	60.61 92	79.05 21	90.30 33	55.54 45	88.32 32	73.48 53	87.03 46	84.83 146
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
ACMP	63.53 6	72.30 90	71.20 100	75.59 81	80.28 114	57.54 87	82.74 66	82.84 92	60.58 93	65.24 216	86.18 114	39.25 238	86.03 89	66.95 101	76.79 170	83.22 196
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
testdata1							72.65 250		60.50 94

UGNet		68.81 160	67.39 172	73.06 148	78.33 166	54.47 140	79.77 108	75.40 227	60.45 95	63.22 244	84.40 152	32.71 313	80.91 205	51.71 226	80.56 113	83.81 176
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 82	71.49 91	76.40 65	81.99 85	59.58 55	76.92 169	76.74 209	60.40 96	74.81 54	85.95 123	45.54 170	85.76 96	70.41 76	70.61 245	83.86 175

hse-mvs2		71.04 110	69.86 123	74.60 98	79.58 130	57.12 99	73.96 231	75.25 230	60.40 96	74.81 54	81.95 205	45.54 170	82.90 156	70.41 76	66.83 297	83.77 180

EPP-MVSNet		72.16 95	71.31 97	74.71 91	78.68 154	49.70 220	82.10 78	81.65 106	60.40 96	65.94 198	85.84 126	51.74 94	86.37 83	55.93 185	79.55 126	88.07 29

UniMVSNet_ETH3D		67.60 189	67.07 185	69.18 232	77.39 204	42.29 303	74.18 228	75.59 222	60.37 99	66.77 183	86.06 119	37.64 255	78.93 245	52.16 219	73.49 206	86.32 86

test_prior2							81.75 81		60.37 99	75.01 47	89.06 55	56.22 41		72.19 62	88.96 24

SD-MVS		77.70 26	77.62 26	77.93 42	84.47 59	61.88 21	84.55 37	83.87 60	60.37 99	79.89 18	89.38 52	54.97 49	85.58 100	76.12 31	84.94 64	86.33 84
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		69.68 141	70.19 119	68.16 243	79.73 127	41.63 312	70.53 283	77.38 199	60.37 99	70.69 112	86.63 99	51.08 102	77.09 269	53.61 209	81.69 105	85.75 108

sasdasda		74.67 59	74.98 55	73.71 126	78.94 146	50.56 206	80.23 98	83.87 60	60.30 103	77.15 32	86.56 103	59.65 17	82.00 179	66.01 107	82.12 94	88.58 14

canonicalmvs		74.67 59	74.98 55	73.71 126	78.94 146	50.56 206	80.23 98	83.87 60	60.30 103	77.15 32	86.56 103	59.65 17	82.00 179	66.01 107	82.12 94	88.58 14

v7n		69.01 158	67.36 174	73.98 114	72.51 286	52.65 174	78.54 129	81.30 120	60.26 105	62.67 256	81.62 211	43.61 192	84.49 126	57.01 178	68.70 283	84.79 148

reproduce-ours		76.90 34	76.58 34	77.87 43	83.99 62	60.46 43	84.75 32	83.34 77	60.22 106	77.85 27	91.42 13	50.67 107	87.69 48	72.46 59	84.53 68	85.46 119

our_new_method		76.90 34	76.58 34	77.87 43	83.99 62	60.46 43	84.75 32	83.34 77	60.22 106	77.85 27	91.42 13	50.67 107	87.69 48	72.46 59	84.53 68	85.46 119

HPM-MVS_fast		74.30 66	73.46 71	76.80 56	84.45 60	59.04 69	83.65 55	81.05 129	60.15 108	70.43 114	89.84 46	41.09 222	85.59 99	67.61 93	82.90 87	85.77 106

VPA-MVSNet		69.02 157	69.47 130	67.69 247	77.42 203	41.00 317	74.04 229	79.68 149	60.06 109	69.26 138	84.81 141	51.06 103	77.58 260	54.44 202	74.43 191	84.48 155

v10		70.21 128	69.02 137	73.81 118	73.51 269	50.92 198	78.74 122	81.39 113	60.05 110	66.39 191	81.83 208	47.58 143	85.41 108	62.80 136	68.86 281	85.09 138

SR-MVS		76.13 46	75.70 47	77.40 51	85.87 40	61.20 29	85.52 27	82.19 98	59.99 111	75.10 45	90.35 31	47.66 141	86.52 78	71.64 69	82.99 83	84.47 156

9.14			78.75 15		83.10 72		84.15 46	88.26 1	59.90 112	78.57 23	90.36 30	57.51 32	86.86 68	77.39 23	89.52 21

v2v482		70.50 122	69.45 131	73.66 129	72.62 282	50.03 216	77.58 148	80.51 139	59.90 112	69.52 130	82.14 201	47.53 145	84.88 120	65.07 116	70.17 255	86.09 93

Baseline_NR-MVSNet		67.05 201	67.56 164	65.50 281	75.65 235	37.70 346	75.42 200	74.65 242	59.90 112	68.14 155	83.15 178	49.12 126	77.20 267	52.23 218	69.78 264	81.60 227

API-MVS		72.17 93	71.41 93	74.45 103	81.95 86	57.22 92	84.03 48	80.38 142	59.89 115	68.40 148	82.33 194	49.64 116	87.83 46	51.87 223	84.16 75	78.30 279

Effi-MVS+-dtu		69.64 143	67.53 167	75.95 70	76.10 230	62.29 15	80.20 101	76.06 217	59.83 116	65.26 215	77.09 293	41.56 214	84.02 135	60.60 155	71.09 241	81.53 228

reproduce_model		76.43 41	76.08 41	77.49 48	83.47 69	60.09 47	84.60 36	82.90 89	59.65 117	77.31 30	91.43 12	49.62 117	87.24 54	71.99 65	83.75 78	85.14 134

MVSMamba_PlusPlus		75.75 51	75.44 49	76.67 60	80.84 105	53.06 166	78.62 125	85.13 32	59.65 117	71.53 106	87.47 78	56.92 34	88.17 35	72.18 63	86.63 56	88.80 10

CANet_DTU		68.18 177	67.71 163	69.59 223	74.83 249	46.24 263	78.66 124	76.85 206	59.60 119	63.45 242	82.09 204	35.25 279	77.41 263	59.88 161	78.76 141	85.14 134

EI-MVSNet		69.27 154	68.44 152	71.73 175	74.47 258	49.39 227	75.20 205	78.45 179	59.60 119	69.16 140	76.51 305	51.29 98	82.50 171	59.86 163	71.45 237	83.30 193

IterMVS-LS		69.22 156	68.48 148	71.43 185	74.44 260	49.40 226	76.23 183	77.55 195	59.60 119	65.85 203	81.59 214	51.28 99	81.58 188	59.87 162	69.90 262	83.30 193
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
MGCFI-Net		72.45 87	73.34 73	69.81 220	77.77 186	43.21 296	75.84 194	81.18 125	59.59 122	75.45 42	86.64 97	57.74 28	77.94 253	63.92 126	81.90 99	88.30 19

VDDNet		71.81 98	71.33 96	73.26 146	82.80 78	47.60 252	78.74 122	75.27 229	59.59 122	72.94 86	89.40 51	41.51 216	83.91 137	58.75 169	82.99 83	88.26 20

alignmvs		73.86 69	73.99 64	73.45 139	78.20 169	50.50 208	78.57 127	82.43 95	59.40 124	76.57 35	86.71 96	56.42 40	81.23 196	65.84 110	81.79 100	88.62 12

MVS_Test		72.45 87	72.46 80	72.42 163	74.88 247	48.50 240	76.28 182	83.14 86	59.40 124	72.46 95	84.68 143	55.66 44	81.12 197	65.98 109	79.66 123	87.63 42

TSAR-MVS + MP.		78.44 19	78.28 19	78.90 27	84.96 52	61.41 26	84.03 48	83.82 63	59.34 126	79.37 19	89.76 48	59.84 16	87.62 51	76.69 27	86.74 53	87.68 40
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 70	73.47 70	74.66 94	83.02 74	59.29 61	82.30 77	81.88 102	59.34 126	71.59 105	86.83 90	45.94 165	83.65 142	65.09 115	85.22 63	81.06 242

PAPM_NR		72.63 84	71.80 86	75.13 87	81.72 89	53.42 159	79.91 106	83.28 82	59.14 128	66.31 193	85.90 124	51.86 91	86.06 87	57.45 176	80.62 109	85.91 99

testing91		64.46 238	63.80 229	66.47 262	78.43 161	40.06 322	67.63 307	69.59 288	59.06 129	63.18 246	78.05 274	34.05 291	76.99 271	48.30 253	75.87 179	82.37 216

save fliter					86.17 33	61.30 28	83.98 50	79.66 150	59.00 130

v148		68.24 176	67.19 183	71.40 186	70.43 321	47.77 249	75.76 195	77.03 204	58.91 131	67.36 172	80.10 241	48.60 131	81.89 181	60.01 159	66.52 300	84.53 153

TransMVSNet (Re)		64.72 233	64.33 223	65.87 277	75.22 243	38.56 336	74.66 220	75.08 238	58.90 132	61.79 270	82.63 184	51.18 100	78.07 252	43.63 297	55.87 366	80.99 244

Anonymous202405211		66.84 206	65.99 205	69.40 227	80.19 119	42.21 305	71.11 276	71.31 273	58.80 133	67.90 158	86.39 109	29.83 335	79.65 225	49.60 243	78.78 140	86.33 84

test2506		65.33 228	64.61 221	67.50 248	79.46 133	34.19 378	74.43 225	51.92 384	58.72 134	66.75 184	88.05 69	25.99 365	80.92 204	51.94 222	84.25 72	87.39 50

ECVR-MVS		67.72 187	67.51 168	68.35 241	79.46 133	36.29 363	74.79 217	66.93 309	58.72 134	67.19 175	88.05 69	36.10 272	81.38 191	52.07 220	84.25 72	87.39 50

test1111		67.21 194	67.14 184	67.42 250	79.24 138	34.76 372	73.89 236	65.65 318	58.71 136	66.96 180	87.95 72	36.09 273	80.53 211	52.03 221	83.79 77	86.97 61

LCM-MVSNet-Re		61.88 269	61.35 261	63.46 297	74.58 256	31.48 391	61.42 351	58.14 362	58.71 136	53.02 358	79.55 252	43.07 196	76.80 275	45.69 275	77.96 151	82.11 222

testing99		64.05 242	63.29 239	66.34 264	78.17 173	39.76 326	67.33 312	68.00 302	58.60 138	63.03 249	78.10 273	32.57 318	76.94 273	48.22 254	75.58 183	82.34 217

v1144		70.42 124	69.31 132	73.76 121	73.22 270	50.64 203	77.83 144	81.43 112	58.58 139	69.40 134	81.16 219	47.53 145	85.29 110	64.01 124	70.64 243	85.34 127

TSAR-MVS + GP.		74.90 55	74.15 63	77.17 52	82.00 84	58.77 75	81.80 80	78.57 172	58.58 139	74.32 63	84.51 151	55.94 43	87.22 57	67.11 97	84.48 71	85.52 115

BH-RMVSNet		68.81 160	67.42 171	72.97 149	80.11 122	52.53 178	74.26 226	76.29 212	58.48 141	68.38 149	84.20 154	42.59 200	83.83 138	46.53 267	75.91 178	82.56 209

APD-MVS_3200maxsize		74.96 54	74.39 61	76.67 60	82.20 81	58.24 80	83.67 54	83.29 81	58.41 142	73.71 70	90.14 36	45.62 167	85.99 90	69.64 78	82.85 89	85.78 103

OMC-MVS		71.40 108	70.60 110	73.78 119	76.60 222	53.15 163	79.74 110	79.78 147	58.37 143	68.75 143	86.45 108	45.43 174	80.60 210	62.58 137	77.73 154	87.58 45

nrg030		72.96 78	73.01 74	72.84 152	75.41 241	50.24 210	80.02 102	82.89 91	58.36 144	74.44 60	86.73 94	58.90 24	80.83 206	65.84 110	74.46 189	87.44 48

K. test v3		60.47 280	57.11 298	70.56 205	73.74 268	48.22 243	75.10 209	62.55 341	58.27 145	53.62 354	76.31 309	27.81 350	81.59 187	47.42 258	39.18 399	81.88 225

FA-MVS(test-final)		69.82 136	68.48 148	73.84 117	78.44 160	50.04 215	75.58 199	78.99 162	58.16 146	67.59 169	82.14 201	42.66 199	85.63 97	56.60 180	76.19 176	85.84 101

MVS_111021_LR		69.50 148	68.78 142	71.65 178	78.38 162	59.33 59	74.82 216	70.11 282	58.08 147	67.83 164	84.68 143	41.96 207	76.34 286	65.62 112	77.54 156	79.30 271

SR-MVS-dyc-post		74.57 62	73.90 65	76.58 63	83.49 67	59.87 52	84.29 40	81.36 115	58.07 148	73.14 80	90.07 37	44.74 181	85.84 94	68.20 85	81.76 101	84.03 166

RE-MVS-def			73.71 69		83.49 67	59.87 52	84.29 40	81.36 115	58.07 148	73.14 80	90.07 37	43.06 197		68.20 85	81.76 101	84.03 166

SDMVSNet		68.03 179	68.10 158	67.84 245	77.13 209	48.72 238	65.32 328	79.10 159	58.02 150	65.08 219	82.55 187	47.83 138	73.40 299	63.92 126	73.92 197	81.41 230

sd_testset		64.46 238	64.45 222	64.51 291	77.13 209	42.25 304	62.67 344	72.11 268	58.02 150	65.08 219	82.55 187	41.22 221	69.88 320	47.32 260	73.92 197	81.41 230

GeoE		71.01 111	70.15 120	73.60 134	79.57 131	52.17 184	78.93 120	78.12 186	58.02 150	67.76 168	83.87 163	52.36 83	82.72 165	56.90 179	75.79 180	85.92 98

ZD-MVS					86.64 21	60.38 45		82.70 93	57.95 153	78.10 24	90.06 39	56.12 42	88.84 26	74.05 47	87.00 49

EIA-MVS		71.78 99	70.60 110	75.30 85	79.85 125	53.54 156	77.27 160	83.26 83	57.92 154	66.49 188	79.39 256	52.07 88	86.69 72	60.05 158	79.14 135	85.66 111

test_yl		69.69 139	69.13 134	71.36 187	78.37 164	45.74 268	74.71 218	80.20 144	57.91 155	70.01 123	83.83 164	42.44 202	82.87 159	54.97 195	79.72 121	85.48 117

DCV-MVSNet		69.69 139	69.13 134	71.36 187	78.37 164	45.74 268	74.71 218	80.20 144	57.91 155	70.01 123	83.83 164	42.44 202	82.87 159	54.97 195	79.72 121	85.48 117

MonoMVSNet		64.15 241	63.31 238	66.69 259	70.51 319	44.12 287	74.47 223	74.21 249	57.81 157	63.03 249	76.62 301	38.33 248	77.31 265	54.22 203	60.59 348	78.64 277

dcpmvs_2		74.55 63	75.23 53	72.48 159	82.34 80	53.34 160	77.87 141	81.46 111	57.80 158	75.49 41	86.81 91	62.22 13	77.75 258	71.09 73	82.02 97	86.34 82

Fast-Effi-MVS+-dtu		67.37 192	65.33 215	73.48 138	72.94 277	57.78 86	77.47 153	76.88 205	57.60 159	61.97 267	76.85 297	39.31 236	80.49 214	54.72 198	70.28 253	82.17 221

v1192		69.97 133	68.68 144	73.85 116	73.19 271	50.94 196	77.68 147	81.36 115	57.51 160	68.95 142	80.85 229	45.28 177	85.33 109	62.97 135	70.37 249	85.27 131

ACMH+	57.40 11	66.12 217	64.06 224	72.30 165	77.79 185	52.83 172	80.39 97	78.03 187	57.30 161	57.47 316	82.55 187	27.68 351	84.17 130	45.54 278	69.78 264	79.90 261

diffmvs		70.69 118	70.43 113	71.46 182	69.45 337	48.95 234	72.93 247	78.46 178	57.27 162	71.69 103	83.97 162	51.48 97	77.92 255	70.70 75	77.95 152	87.53 46
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		68.27 174	67.29 176	71.21 191	79.74 126	53.22 162	76.06 187	77.46 198	57.19 163	66.10 195	81.61 212	45.37 176	83.50 145	45.42 283	76.68 172	76.91 303

thres100view900		63.28 251	62.41 249	65.89 276	77.31 206	38.66 335	72.65 250	69.11 295	57.07 164	62.45 263	81.03 223	37.01 267	79.17 234	31.84 369	73.25 212	79.83 263

DP-MVS Recon		72.15 96	70.73 108	76.40 65	86.57 24	57.99 82	81.15 90	82.96 87	57.03 165	66.78 182	85.56 131	44.50 185	88.11 38	51.77 225	80.23 118	83.10 202

thres600view7		63.30 250	62.27 250	66.41 263	77.18 208	38.87 333	72.35 257	69.11 295	56.98 166	62.37 265	80.96 225	37.01 267	79.00 243	31.43 376	73.05 216	81.36 233

V42		68.65 164	67.35 175	72.56 157	68.93 343	50.18 212	72.90 248	79.47 154	56.92 167	69.45 133	80.26 238	46.29 163	82.99 153	64.07 122	67.82 289	84.53 153

MCST-MVS		77.48 28	77.45 27	77.54 47	86.67 20	58.36 79	83.22 58	86.93 5	56.91 168	74.91 51	88.19 65	59.15 23	87.68 50	73.67 51	87.45 43	86.57 75

GA-MVS		65.53 224	63.70 231	71.02 198	70.87 314	48.10 244	70.48 284	74.40 244	56.69 169	64.70 227	76.77 298	33.66 299	81.10 198	55.42 194	70.32 252	83.87 174

v144192		69.71 138	68.51 147	73.33 144	73.10 273	50.13 213	77.54 151	80.64 136	56.65 170	68.57 146	80.55 232	46.87 159	84.96 116	62.98 134	69.66 268	84.89 145

tfpn200view9		63.18 253	62.18 252	66.21 268	76.85 216	39.62 327	71.96 264	69.44 291	56.63 171	62.61 258	79.83 244	37.18 261	79.17 234	31.84 369	73.25 212	79.83 263

thres400		63.31 249	62.18 252	66.72 256	76.85 216	39.62 327	71.96 264	69.44 291	56.63 171	62.61 258	79.83 244	37.18 261	79.17 234	31.84 369	73.25 212	81.36 233

GBi-Net		67.21 194	66.55 189	69.19 229	77.63 193	43.33 293	77.31 156	77.83 190	56.62 173	65.04 221	82.70 181	41.85 209	80.33 216	47.18 262	72.76 219	83.92 171

test1		67.21 194	66.55 189	69.19 229	77.63 193	43.33 293	77.31 156	77.83 190	56.62 173	65.04 221	82.70 181	41.85 209	80.33 216	47.18 262	72.76 219	83.92 171

FMVSNet2		66.93 204	66.31 200	68.79 236	77.63 193	42.98 298	76.11 185	77.47 196	56.62 173	65.22 218	82.17 199	41.85 209	80.18 222	47.05 265	72.72 222	83.20 197

DPM-MVS		75.47 53	75.00 54	76.88 54	81.38 96	59.16 62	79.94 104	85.71 22	56.59 176	72.46 95	86.76 92	56.89 35	87.86 45	66.36 103	88.91 25	83.64 188

v1921920		69.47 149	68.17 156	73.36 143	73.06 274	50.10 214	77.39 154	80.56 137	56.58 177	68.59 144	80.37 234	44.72 182	84.98 114	62.47 140	69.82 263	85.00 140

FMVSNet1		66.70 209	65.87 206	69.19 229	77.49 201	43.33 293	77.31 156	77.83 190	56.45 178	64.60 229	82.70 181	38.08 253	80.33 216	46.08 271	72.31 227	83.92 171

v1240		69.24 155	67.91 159	73.25 147	73.02 276	49.82 218	77.21 161	80.54 138	56.43 179	68.34 150	80.51 233	43.33 195	84.99 112	62.03 144	69.77 266	84.95 144

testing222		62.29 264	61.31 262	65.25 286	77.87 182	38.53 337	68.34 302	66.31 315	56.37 180	63.15 248	77.58 288	28.47 345	76.18 289	37.04 338	76.65 173	81.05 243

CDPH-MVS		76.31 42	75.67 48	78.22 37	85.35 48	59.14 65	81.31 88	84.02 51	56.32 181	74.05 65	88.98 57	53.34 71	87.92 43	69.23 82	88.42 28	87.59 44

Vis-MVSNet (Re-imp)		63.69 246	63.88 227	63.14 301	74.75 251	31.04 392	71.16 274	63.64 334	56.32 181	59.80 292	84.99 138	44.51 184	75.46 291	39.12 326	80.62 109	82.92 204

AdaColmap		69.99 132	68.66 145	73.97 115	84.94 54	57.83 84	82.63 68	78.71 168	56.28 183	64.34 230	84.14 156	41.57 213	87.06 64	46.45 268	78.88 137	77.02 299

PS-MVSNAJss		72.24 91	71.21 99	75.31 84	78.50 157	55.93 115	81.63 82	82.12 99	56.24 184	70.02 122	85.68 130	47.05 154	84.34 129	65.27 114	74.41 192	85.67 110

c3_l		68.33 173	67.56 164	70.62 204	70.87 314	46.21 264	74.47 223	78.80 166	56.22 185	66.19 194	78.53 271	51.88 90	81.40 190	62.08 141	69.04 277	84.25 160

Fast-Effi-MVS+		70.28 127	69.12 136	73.73 125	78.50 157	51.50 193	75.01 210	79.46 155	56.16 186	68.59 144	79.55 252	53.97 60	84.05 132	53.34 211	77.53 157	85.65 112

PHI-MVS		75.87 48	75.36 50	77.41 49	80.62 112	55.91 116	84.28 42	85.78 20	56.08 187	73.41 73	86.58 102	50.94 105	88.54 28	70.79 74	89.71 17	87.79 37

baseline1		63.81 245	63.87 228	63.62 296	76.29 227	36.36 358	71.78 266	67.29 306	56.05 188	64.23 235	82.95 179	47.11 153	74.41 296	47.30 261	61.85 337	80.10 258

train_agg		76.27 43	76.15 40	76.64 62	85.58 43	61.59 24	81.62 83	81.26 122	55.86 189	74.93 49	88.81 59	53.70 67	84.68 123	75.24 38	88.33 30	83.65 187

test_8					85.40 46	60.96 34	81.54 86	81.18 125	55.86 189	74.81 54	88.80 61	53.70 67	84.45 127

FMVSNet3		66.32 216	65.61 211	68.46 239	76.48 225	42.34 302	74.98 212	77.15 203	55.83 191	65.04 221	81.16 219	39.91 229	80.14 223	47.18 262	72.76 219	82.90 206

PAPR		71.72 102	70.82 106	74.41 104	81.20 101	51.17 194	79.55 115	83.33 79	55.81 192	66.93 181	84.61 147	50.95 104	86.06 87	55.79 188	79.20 132	86.00 95

eth_miper_zixun_eth		67.63 188	66.28 201	71.67 177	71.60 300	48.33 242	73.68 240	77.88 188	55.80 193	65.91 199	78.62 269	47.35 151	82.88 158	59.45 165	66.25 301	83.81 176

ACMH	55.70 15	65.20 230	63.57 233	70.07 213	78.07 176	52.01 189	79.48 116	79.69 148	55.75 194	56.59 323	80.98 224	27.12 356	80.94 202	42.90 305	71.58 235	77.25 297
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
IB-MVS	56.42 12	65.40 227	62.73 246	73.40 142	74.89 246	52.78 173	73.09 246	75.13 234	55.69 195	58.48 309	73.73 335	32.86 308	86.32 85	50.63 233	70.11 256	81.10 241
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		61.53 272	60.94 269	63.30 299	68.95 342	36.93 354	67.60 308	72.80 263	55.67 196	59.95 289	76.63 300	45.01 180	72.22 306	39.74 324	62.09 336	80.74 248

TEST9					85.58 43	61.59 24	81.62 83	81.26 122	55.65 197	74.93 49	88.81 59	53.70 67	84.68 123

thres200		62.20 265	61.16 267	65.34 284	75.38 242	39.99 323	69.60 294	69.29 293	55.64 198	61.87 269	76.99 294	37.07 266	78.96 244	31.28 377	73.28 211	77.06 298

pm-mvs1		65.24 229	64.97 219	66.04 273	72.38 289	39.40 330	72.62 252	75.63 221	55.53 199	62.35 266	83.18 177	47.45 147	76.47 284	49.06 247	66.54 299	82.24 218

testing11		62.81 256	61.90 255	65.54 280	78.38 162	40.76 319	67.59 309	66.78 311	55.48 200	60.13 284	77.11 292	31.67 324	76.79 276	45.53 279	74.45 190	79.06 272

ACMM	61.98 7	70.80 117	69.73 125	74.02 113	80.59 113	58.59 77	82.68 67	82.02 101	55.46 201	67.18 176	84.39 153	38.51 245	83.17 151	60.65 154	76.10 177	80.30 254
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
Anonymous20240529		69.91 134	69.02 137	72.56 157	80.19 119	47.65 250	77.56 150	80.99 131	55.45 202	69.88 126	86.76 92	39.24 239	82.18 177	54.04 204	77.10 167	87.85 33

tt0805		67.77 186	67.24 181	69.34 228	74.87 248	40.08 321	77.36 155	81.37 114	55.31 203	66.33 192	84.65 145	37.35 259	82.55 170	55.65 191	72.28 228	85.39 126

GDP-MVS		72.64 83	71.28 98	76.70 57	77.72 188	54.22 144	79.57 114	84.45 43	55.30 204	71.38 108	86.97 88	39.94 228	87.00 65	67.02 100	79.20 132	88.89 9

CPTT-MVS		72.78 80	72.08 85	74.87 90	84.88 57	61.41 26	84.15 46	77.86 189	55.27 205	67.51 171	88.08 68	41.93 208	81.85 182	69.04 83	80.01 119	81.35 235

XVG-OURS		68.76 163	67.37 173	72.90 151	74.32 263	57.22 92	70.09 290	78.81 165	55.24 206	67.79 166	85.81 129	36.54 270	78.28 249	62.04 143	75.74 181	83.19 198

tfpnnormal		62.47 260	61.63 258	64.99 288	74.81 250	39.01 332	71.22 272	73.72 254	55.22 207	60.21 283	80.09 242	41.26 220	76.98 272	30.02 382	68.09 287	78.97 275

cl____		67.18 197	66.26 202	69.94 215	70.20 324	45.74 268	73.30 242	76.83 207	55.10 208	65.27 212	79.57 251	47.39 149	80.53 211	59.41 167	69.22 275	83.53 190

DIV-MVS_self_test		67.18 197	66.26 202	69.94 215	70.20 324	45.74 268	73.29 243	76.83 207	55.10 208	65.27 212	79.58 250	47.38 150	80.53 211	59.43 166	69.22 275	83.54 189

PC_three_1452									55.09 210	84.46 4	89.84 46	66.68 5	89.41 18	74.24 44	91.38 2	88.42 16

EPNet_dtu		61.90 268	61.97 254	61.68 309	72.89 278	39.78 325	75.85 193	65.62 319	55.09 210	54.56 344	79.36 257	37.59 256	67.02 338	39.80 323	76.95 168	78.25 280
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
PVSNet_Blended_VisFu		71.45 107	70.39 114	74.65 95	82.01 83	58.82 74	79.93 105	80.35 143	55.09 210	65.82 204	82.16 200	49.17 123	82.64 168	60.34 156	78.62 144	82.50 213

cl22		67.47 191	66.45 191	70.54 206	69.85 332	46.49 260	73.85 237	77.35 200	55.07 213	65.51 207	77.92 278	47.64 142	81.10 198	61.58 149	69.32 271	84.01 168

miper_ehance_all_eth		68.03 179	67.24 181	70.40 208	70.54 318	46.21 264	73.98 230	78.68 170	55.07 213	66.05 196	77.80 282	52.16 87	81.31 193	61.53 150	69.32 271	83.67 184

PS-MVSNAJ		70.51 121	69.70 126	72.93 150	81.52 91	55.79 119	74.92 214	79.00 161	55.04 215	69.88 126	78.66 266	47.05 154	82.19 176	61.61 147	79.58 124	80.83 246

mmtdpeth		60.40 281	59.12 282	64.27 294	69.59 334	48.99 232	70.67 281	70.06 283	54.96 216	62.78 252	73.26 339	27.00 358	67.66 331	58.44 172	45.29 391	76.16 308

xiu_mvs_v2_base		70.52 120	69.75 124	72.84 152	81.21 100	55.63 123	75.11 207	78.92 163	54.92 217	69.96 125	79.68 249	47.00 158	82.09 178	61.60 148	79.37 127	80.81 247

MAR-MVS		71.51 104	70.15 120	75.60 80	81.84 87	59.39 58	81.38 87	82.90 89	54.90 218	68.08 157	78.70 264	47.73 139	85.51 102	51.68 227	84.17 74	81.88 225
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
reproduce_monomvs		62.56 258	61.20 266	66.62 260	70.62 317	44.30 284	70.13 289	73.13 260	54.78 219	61.13 278	76.37 308	25.63 368	75.63 290	58.75 169	60.29 349	79.93 260

XVG-OURS-SEG-HR		68.81 160	67.47 170	72.82 154	74.40 261	56.87 102	70.59 282	79.04 160	54.77 220	66.99 179	86.01 121	39.57 234	78.21 250	62.54 138	73.33 210	83.37 192

testing3		56.54 309	55.92 311	58.41 331	77.52 200	27.93 401	69.72 293	56.36 371	54.75 221	58.63 307	77.80 282	20.88 384	71.75 309	25.31 398	62.25 334	75.53 315

Anonymous20231211		69.28 153	68.47 150	71.73 175	80.28 114	47.18 256	79.98 103	82.37 96	54.61 222	67.24 174	84.01 160	39.43 235	82.41 174	55.45 193	72.83 218	85.62 113

SixPastTwentyTwo		61.65 271	58.80 286	70.20 211	75.80 233	47.22 255	75.59 197	69.68 286	54.61 222	54.11 348	79.26 259	27.07 357	82.96 154	43.27 299	49.79 384	80.41 252

test_0402		63.25 252	61.01 268	69.96 214	80.00 123	54.37 143	76.86 172	72.02 269	54.58 224	58.71 304	80.79 231	35.00 282	84.36 128	26.41 396	64.71 312	71.15 365

tttt0517		67.83 185	65.66 210	74.33 106	76.69 218	50.82 200	77.86 142	73.99 252	54.54 225	64.64 228	82.53 190	35.06 281	85.50 103	55.71 189	69.91 261	86.67 71

BH-w/o		66.85 205	65.83 207	69.90 218	79.29 135	52.46 180	74.66 220	76.65 210	54.51 226	64.85 225	78.12 272	45.59 169	82.95 155	43.26 300	75.54 184	74.27 332

AUN-MVS		68.45 172	66.41 195	74.57 100	79.53 132	57.08 100	73.93 234	75.23 231	54.44 227	66.69 185	81.85 207	37.10 265	82.89 157	62.07 142	66.84 296	83.75 181

LTVRE_ROB	55.42 16	63.15 254	61.23 265	68.92 234	76.57 223	47.80 247	59.92 360	76.39 211	54.35 228	58.67 305	82.46 192	29.44 339	81.49 189	42.12 309	71.14 239	77.46 291
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 77	72.59 78	74.27 108	71.28 309	55.88 117	78.21 134	75.56 223	54.31 229	74.86 53	87.80 75	54.72 52	80.23 220	78.07 21	78.48 145	86.70 69

test_fmvsmconf0.01_n		72.17 93	71.50 90	74.16 111	67.96 349	55.58 126	78.06 138	74.67 241	54.19 230	74.54 59	88.23 64	50.35 112	80.24 219	78.07 21	77.46 159	86.65 73

test_fmvsmconf0.1_n		72.81 79	72.33 81	74.24 109	69.89 331	55.81 118	78.22 133	75.40 227	54.17 231	75.00 48	88.03 71	53.82 64	80.23 220	78.08 20	78.34 148	86.69 70

ETVMVS		59.51 290	58.81 284	61.58 311	77.46 202	34.87 369	64.94 333	59.35 357	54.06 232	61.08 279	76.67 299	29.54 336	71.87 308	32.16 365	74.07 195	78.01 287

ab-mvs		66.65 210	66.42 194	67.37 251	76.17 229	41.73 309	70.41 286	76.14 215	53.99 233	65.98 197	83.51 171	49.48 118	76.24 287	48.60 250	73.46 208	84.14 164

IU-MVS					87.77 4	59.15 63		85.53 26	53.93 234	84.64 3				79.07 11	90.87 5	88.37 18

XVG-ACMP-BASELINE		64.36 240	62.23 251	70.74 202	72.35 290	52.45 181	70.80 280	78.45 179	53.84 235	59.87 290	81.10 221	16.24 392	79.32 231	55.64 192	71.76 232	80.47 250

FE-MVS		65.91 219	63.33 237	73.63 132	77.36 205	51.95 190	72.62 252	75.81 218	53.70 236	65.31 210	78.96 262	28.81 344	86.39 82	43.93 292	73.48 207	82.55 210

thisisatest0530		67.92 183	65.78 208	74.33 106	76.29 227	51.03 195	76.89 170	74.25 248	53.67 237	65.59 206	81.76 209	35.15 280	85.50 103	55.94 184	72.47 223	86.47 77

PVSNet_BlendedMVS		68.56 169	67.72 161	71.07 197	77.03 213	50.57 204	74.50 222	81.52 108	53.66 238	64.22 236	79.72 248	49.13 124	82.87 159	55.82 186	73.92 197	79.77 266

patch_mono-2		69.85 135	71.09 102	66.16 269	79.11 143	54.80 138	71.97 263	74.31 246	53.50 239	70.90 111	84.17 155	57.63 31	63.31 352	66.17 104	82.02 97	80.38 253

EG-PatchMatch MVS		64.71 234	62.87 243	70.22 209	77.68 190	53.48 157	77.99 139	78.82 164	53.37 240	56.03 328	77.41 290	24.75 373	84.04 133	46.37 269	73.42 209	73.14 338

DP-MVS		65.68 221	63.66 232	71.75 174	84.93 55	56.87 102	80.74 95	73.16 259	53.06 241	59.09 301	82.35 193	36.79 269	85.94 92	32.82 363	69.96 260	72.45 346

TR-MVS		66.59 213	65.07 218	71.17 194	79.18 140	49.63 224	73.48 241	75.20 233	52.95 242	67.90 158	80.33 237	39.81 232	83.68 141	43.20 301	73.56 205	80.20 255

ET-MVSNet_ETH3D		67.96 182	65.72 209	74.68 93	76.67 220	55.62 125	75.11 207	74.74 239	52.91 243	60.03 287	80.12 240	33.68 298	82.64 168	61.86 145	76.34 174	85.78 103

QAPM		70.05 130	68.81 141	73.78 119	76.54 224	53.43 158	83.23 57	83.48 70	52.89 244	65.90 200	86.29 111	41.55 215	86.49 80	51.01 230	78.40 147	81.42 229

OpenMVS	61.03 9	68.85 159	67.56 164	72.70 156	74.26 264	53.99 147	81.21 89	81.34 119	52.70 245	62.75 255	85.55 133	38.86 243	84.14 131	48.41 252	83.01 82	79.97 259

pmmvs6		63.69 246	62.82 245	66.27 267	70.63 316	39.27 331	73.13 245	75.47 226	52.69 246	59.75 294	82.30 195	39.71 233	77.03 270	47.40 259	64.35 317	82.53 211

IterMVS		62.79 257	61.27 263	67.35 252	69.37 338	52.04 188	71.17 273	68.24 301	52.63 247	59.82 291	76.91 296	37.32 260	72.36 303	52.80 215	63.19 327	77.66 289
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
mvs_tets		68.18 177	66.36 197	73.63 132	75.61 237	55.35 131	80.77 94	78.56 173	52.48 248	64.27 233	84.10 158	27.45 353	81.84 183	63.45 133	70.56 246	83.69 183

jajsoiax		68.25 175	66.45 191	73.66 129	75.62 236	55.49 128	80.82 93	78.51 175	52.33 249	64.33 231	84.11 157	28.28 347	81.81 184	63.48 132	70.62 244	83.67 184

TAMVS		66.78 208	65.27 216	71.33 190	79.16 142	53.67 152	73.84 238	69.59 288	52.32 250	65.28 211	81.72 210	44.49 186	77.40 264	42.32 308	78.66 143	82.92 204

CDS-MVSNet		66.80 207	65.37 213	71.10 196	78.98 145	53.13 165	73.27 244	71.07 275	52.15 251	64.72 226	80.23 239	43.56 193	77.10 268	45.48 281	78.88 137	83.05 203
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
mvsmamba		68.47 170	66.56 188	74.21 110	79.60 129	52.95 167	74.94 213	75.48 225	52.09 252	60.10 285	83.27 174	36.54 270	84.70 122	59.32 168	77.69 155	84.99 142

PVSNet_Blended		68.59 165	67.72 161	71.19 192	77.03 213	50.57 204	72.51 255	81.52 108	51.91 253	64.22 236	77.77 285	49.13 124	82.87 159	55.82 186	79.58 124	80.14 257

mvs_anonymous		68.03 179	67.51 168	69.59 223	72.08 294	44.57 282	71.99 262	75.23 231	51.67 254	67.06 178	82.57 186	54.68 53	77.94 253	56.56 181	75.71 182	86.26 90

xiu_mvs_v1_base_debu		68.58 166	67.28 177	72.48 159	78.19 170	57.19 94	75.28 202	75.09 235	51.61 255	70.04 119	81.41 216	32.79 309	79.02 240	63.81 128	77.31 160	81.22 237

xiu_mvs_v1_base		68.58 166	67.28 177	72.48 159	78.19 170	57.19 94	75.28 202	75.09 235	51.61 255	70.04 119	81.41 216	32.79 309	79.02 240	63.81 128	77.31 160	81.22 237

xiu_mvs_v1_base_debi		68.58 166	67.28 177	72.48 159	78.19 170	57.19 94	75.28 202	75.09 235	51.61 255	70.04 119	81.41 216	32.79 309	79.02 240	63.81 128	77.31 160	81.22 237

MVSTER		67.16 199	65.58 212	71.88 170	70.37 323	49.70 220	70.25 288	78.45 179	51.52 258	69.16 140	80.37 234	38.45 246	82.50 171	60.19 157	71.46 236	83.44 191

CNLPA		65.43 225	64.02 225	69.68 221	78.73 153	58.07 81	77.82 145	70.71 278	51.49 259	61.57 274	83.58 170	38.23 251	70.82 312	43.90 293	70.10 257	80.16 256

原ACMM1				74.69 92	85.39 47	59.40 57		83.42 73	51.47 260	70.27 117	86.61 100	48.61 130	86.51 79	53.85 207	87.96 39	78.16 281

miper_enhance_ethall		67.11 200	66.09 204	70.17 212	69.21 340	45.98 266	72.85 249	78.41 182	51.38 261	65.65 205	75.98 314	51.17 101	81.25 194	60.82 153	69.32 271	83.29 195

MSDG		61.81 270	59.23 280	69.55 226	72.64 281	52.63 176	70.45 285	75.81 218	51.38 261	53.70 351	76.11 310	29.52 337	81.08 200	37.70 333	65.79 305	74.93 323

test20.03		53.87 330	54.02 328	53.41 362	61.47 383	28.11 400	61.30 352	59.21 358	51.34 263	52.09 360	77.43 289	33.29 303	58.55 373	29.76 383	60.27 350	73.58 337

MVSFormer		71.50 105	70.38 115	74.88 89	78.76 151	57.15 97	82.79 64	78.48 176	51.26 264	69.49 131	83.22 175	43.99 190	83.24 149	66.06 105	79.37 127	84.23 161

test_djsdf		69.45 150	67.74 160	74.58 99	74.57 257	54.92 136	82.79 64	78.48 176	51.26 264	65.41 209	83.49 172	38.37 247	83.24 149	66.06 105	69.25 274	85.56 114

dmvs_testset		50.16 347	51.90 337	44.94 382	66.49 359	11.78 422	61.01 357	51.50 385	51.17 266	50.30 372	67.44 376	39.28 237	60.29 363	22.38 402	57.49 359	62.76 387

PAPM		67.92 183	66.69 187	71.63 179	78.09 175	49.02 231	77.09 164	81.24 124	51.04 267	60.91 280	83.98 161	47.71 140	84.99 112	40.81 317	79.32 130	80.90 245

Syy-MVS		56.00 316	56.23 309	55.32 348	74.69 253	26.44 407	65.52 323	57.49 366	50.97 268	56.52 324	72.18 343	39.89 230	68.09 327	24.20 399	64.59 315	71.44 361

myMVS_eth3d		54.86 326	54.61 320	55.61 347	74.69 253	27.31 404	65.52 323	57.49 366	50.97 268	56.52 324	72.18 343	21.87 382	68.09 327	27.70 390	64.59 315	71.44 361

miper_lstm_enhance		62.03 267	60.88 270	65.49 282	66.71 357	46.25 262	56.29 378	75.70 220	50.68 270	61.27 276	75.48 321	40.21 227	68.03 329	56.31 183	65.25 308	82.18 219

gg-mvs-nofinetune		57.86 300	56.43 307	62.18 307	72.62 282	35.35 368	66.57 313	56.33 372	50.65 271	57.64 315	57.10 398	30.65 327	76.36 285	37.38 335	78.88 137	74.82 325

TAPA-MVS	59.36 10	66.60 211	65.20 217	70.81 200	76.63 221	48.75 236	76.52 178	80.04 146	50.64 272	65.24 216	84.93 139	39.15 240	78.54 246	36.77 340	76.88 169	85.14 134
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
dmvs_re		56.77 308	56.83 303	56.61 342	69.23 339	41.02 314	58.37 365	64.18 330	50.59 273	57.45 317	71.42 351	35.54 277	58.94 371	37.23 336	67.45 292	69.87 374

MVP-Stereo		65.41 226	63.80 229	70.22 209	77.62 197	55.53 127	76.30 181	78.53 174	50.59 273	56.47 326	78.65 267	39.84 231	82.68 166	44.10 291	72.12 230	72.44 347
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
PCF-MVS	61.88 8	70.95 113	69.49 129	75.35 83	77.63 193	55.71 120	76.04 189	81.81 104	50.30 275	69.66 129	85.40 137	52.51 79	84.89 118	51.82 224	80.24 117	85.45 121
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
mvs5depth		55.64 319	53.81 330	61.11 316	59.39 393	40.98 318	65.89 318	68.28 300	50.21 276	58.11 312	75.42 322	17.03 388	67.63 333	43.79 295	46.21 388	74.73 327

baseline2		63.42 248	61.26 264	69.89 219	72.55 284	47.62 251	71.54 267	68.38 299	50.11 277	54.82 340	75.55 319	43.06 197	80.96 201	48.13 255	67.16 295	81.11 240

test-LLR		58.15 298	58.13 294	58.22 333	68.57 344	44.80 278	65.46 325	57.92 363	50.08 278	55.44 332	69.82 364	32.62 315	57.44 377	49.66 241	73.62 202	72.41 348

test0.0.03 1		53.32 335	53.59 332	52.50 368	62.81 378	29.45 395	59.51 361	54.11 380	50.08 278	54.40 346	74.31 331	32.62 315	55.92 386	30.50 380	63.95 320	72.15 353

fmvsm_s_conf0.5_n		69.58 144	68.84 140	71.79 173	72.31 292	52.90 169	77.90 140	62.43 344	49.97 280	72.85 88	85.90 124	52.21 85	76.49 282	75.75 33	70.26 254	85.97 96

COLMAP_ROB	52.97 17	61.27 276	58.81 284	68.64 237	74.63 255	52.51 179	78.42 130	73.30 257	49.92 281	50.96 364	81.51 215	23.06 376	79.40 229	31.63 373	65.85 303	74.01 335
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		69.54 146	68.74 143	71.93 168	72.47 287	53.82 149	78.25 131	62.26 346	49.78 282	73.12 82	86.21 113	52.66 77	76.79 276	75.02 39	68.88 279	85.18 133

WBMVS		60.54 278	60.61 272	60.34 319	78.00 179	35.95 365	64.55 335	64.89 323	49.63 283	63.39 243	78.70 264	33.85 296	67.65 332	42.10 310	70.35 251	77.43 292

tpmvs		58.47 294	56.95 301	63.03 303	70.20 324	41.21 313	67.90 306	67.23 307	49.62 284	54.73 342	70.84 355	34.14 290	76.24 287	36.64 344	61.29 341	71.64 357

fmvsm_s_conf0.1_n		69.41 151	68.60 146	71.83 171	71.07 311	52.88 171	77.85 143	62.44 343	49.58 285	72.97 85	86.22 112	51.68 95	76.48 283	75.53 34	70.10 257	86.14 91

UBG		59.62 289	59.53 278	59.89 320	78.12 174	35.92 366	64.11 339	60.81 354	49.45 286	61.34 275	75.55 319	33.05 304	67.39 336	38.68 328	74.62 188	76.35 307

thisisatest0515		65.83 220	63.50 234	72.82 154	73.75 267	49.50 225	71.32 270	73.12 261	49.39 287	63.82 238	76.50 307	34.95 283	84.84 121	53.20 213	75.49 185	84.13 165

fmvsm_s_conf0.1_n_a		69.32 152	68.44 152	71.96 167	70.91 313	53.78 150	78.12 136	62.30 345	49.35 288	73.20 78	86.55 105	51.99 89	76.79 276	74.83 41	68.68 284	85.32 128

HY-MVS	56.14 13	64.55 237	63.89 226	66.55 261	74.73 252	41.02 314	69.96 291	74.43 243	49.29 289	61.66 272	80.92 226	47.43 148	76.68 280	44.91 286	71.69 233	81.94 223

MIMVSNet1		55.17 324	54.31 325	57.77 338	70.03 328	32.01 389	65.68 321	64.81 324	49.19 290	46.75 382	76.00 311	25.53 369	64.04 350	28.65 387	62.13 335	77.26 296

SCA		60.49 279	58.38 290	66.80 255	74.14 266	48.06 245	63.35 341	63.23 337	49.13 291	59.33 300	72.10 345	37.45 257	74.27 297	44.17 288	62.57 331	78.05 283

test_fmvsmvis_n_1920		70.84 114	70.38 115	72.22 166	71.16 310	55.39 130	75.86 192	72.21 267	49.03 292	73.28 76	86.17 115	51.83 92	77.29 266	75.80 32	78.05 150	83.98 169

testgi		51.90 339	52.37 336	50.51 374	60.39 391	23.55 414	58.42 364	58.15 361	49.03 292	51.83 361	79.21 260	22.39 377	55.59 387	29.24 386	62.64 330	72.40 350

MIMVSNet		57.35 302	57.07 299	58.22 333	74.21 265	37.18 349	62.46 345	60.88 353	48.88 294	55.29 335	75.99 313	31.68 323	62.04 357	31.87 368	72.35 225	75.43 317

gm-plane-assit					71.40 306	41.72 311			48.85 295		73.31 337		82.48 173	48.90 248

fmvsm_l_conf0.5_n		70.99 112	70.82 106	71.48 181	71.45 302	54.40 142	77.18 162	70.46 280	48.67 296	75.17 44	86.86 89	53.77 65	76.86 274	76.33 30	77.51 158	83.17 201

UWE-MVS		60.18 282	59.78 276	61.39 314	77.67 191	33.92 381	69.04 300	63.82 332	48.56 297	64.27 233	77.64 287	27.20 355	70.40 317	33.56 360	76.24 175	79.83 263

cascas		65.98 218	63.42 235	73.64 131	77.26 207	52.58 177	72.26 259	77.21 202	48.56 297	61.21 277	74.60 329	32.57 318	85.82 95	50.38 235	76.75 171	82.52 212

PLC	56.13 14	65.09 231	63.21 240	70.72 203	81.04 103	54.87 137	78.57 127	77.47 196	48.51 299	55.71 329	81.89 206	33.71 297	79.71 224	41.66 314	70.37 249	77.58 290
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
LS3D		64.71 234	62.50 248	71.34 189	79.72 128	55.71 120	79.82 107	74.72 240	48.50 300	56.62 322	84.62 146	33.59 300	82.34 175	29.65 384	75.23 186	75.97 309

anonymousdsp		67.00 203	64.82 220	73.57 135	70.09 327	56.13 110	76.35 180	77.35 200	48.43 301	64.99 224	80.84 230	33.01 306	80.34 215	64.66 119	67.64 291	84.23 161

无先验							79.66 112	74.30 247	48.40 302				80.78 208	53.62 208		79.03 274

114514_t		70.83 115	69.56 127	74.64 96	86.21 31	54.63 139	82.34 73	81.81 104	48.22 303	63.01 251	85.83 127	40.92 224	87.10 62	57.91 173	79.79 120	82.18 219

tpm		57.34 303	58.16 292	54.86 351	71.80 299	34.77 371	67.47 311	56.04 375	48.20 304	60.10 285	76.92 295	37.17 263	53.41 394	40.76 318	65.01 309	76.40 306

test_fmvsm_n_1920		71.73 101	71.14 101	73.50 136	72.52 285	56.53 104	75.60 196	76.16 213	48.11 305	77.22 31	85.56 131	53.10 74	77.43 262	74.86 40	77.14 165	86.55 76

MDA-MVSNet-bldmvs		53.87 330	50.81 342	63.05 302	66.25 361	48.58 239	56.93 376	63.82 332	48.09 306	41.22 394	70.48 360	30.34 330	68.00 330	34.24 355	45.92 390	72.57 344

XXY-MVS		60.68 277	61.67 257	57.70 339	70.43 321	38.45 338	64.19 337	66.47 312	48.05 307	63.22 244	80.86 228	49.28 121	60.47 361	45.25 285	67.28 294	74.19 333

F-COLMAP		63.05 255	60.87 271	69.58 225	76.99 215	53.63 154	78.12 136	76.16 213	47.97 308	52.41 359	81.61 212	27.87 349	78.11 251	40.07 320	66.66 298	77.00 300

fmvsm_l_conf0.5_n_a		70.50 122	70.27 117	71.18 193	71.30 308	54.09 145	76.89 170	69.87 284	47.90 309	74.37 62	86.49 106	53.07 75	76.69 279	75.41 35	77.11 166	82.76 208

Patchmatch-RL test		58.16 297	55.49 314	66.15 270	67.92 350	48.89 235	60.66 358	51.07 388	47.86 310	59.36 297	62.71 392	34.02 293	72.27 305	56.41 182	59.40 352	77.30 294

D2MVS		62.30 263	60.29 274	68.34 242	66.46 360	48.42 241	65.70 320	73.42 256	47.71 311	58.16 311	75.02 325	30.51 328	77.71 259	53.96 206	71.68 234	78.90 276

ANet_high		41.38 366	37.47 373	53.11 364	39.73 419	24.45 412	56.94 375	69.69 285	47.65 312	26.04 411	52.32 401	12.44 400	62.38 356	21.80 403	10.61 420	72.49 345

CostFormer		64.04 243	62.51 247	68.61 238	71.88 297	45.77 267	71.30 271	70.60 279	47.55 313	64.31 232	76.61 303	41.63 212	79.62 227	49.74 239	69.00 278	80.42 251

PatchmatchNet		59.84 285	58.24 291	64.65 290	73.05 275	46.70 259	69.42 296	62.18 347	47.55 313	58.88 303	71.96 347	34.49 287	69.16 322	42.99 303	63.60 322	78.07 282
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
KD-MVS_self_test		55.22 323	53.89 329	59.21 325	57.80 397	27.47 403	57.75 371	74.32 245	47.38 315	50.90 365	70.00 363	28.45 346	70.30 318	40.44 319	57.92 357	79.87 262

ITE_SJBPF				62.09 308	66.16 362	44.55 283		64.32 328	47.36 316	55.31 334	80.34 236	19.27 385	62.68 355	36.29 348	62.39 333	79.04 273

KD-MVS_2432*1600		53.45 332	51.50 340	59.30 322	62.82 376	37.14 350	55.33 379	71.79 271	47.34 317	55.09 337	70.52 358	21.91 380	70.45 315	35.72 350	42.97 394	70.31 370

miper_refine_blended		53.45 332	51.50 340	59.30 322	62.82 376	37.14 350	55.33 379	71.79 271	47.34 317	55.09 337	70.52 358	21.91 380	70.45 315	35.72 350	42.97 394	70.31 370

OurMVSNet-221017-0		61.37 275	58.63 288	69.61 222	72.05 295	48.06 245	73.93 234	72.51 264	47.23 319	54.74 341	80.92 226	21.49 383	81.24 195	48.57 251	56.22 365	79.53 268

tpmrst		58.24 296	58.70 287	56.84 341	66.97 354	34.32 376	69.57 295	61.14 352	47.17 320	58.58 308	71.60 350	41.28 219	60.41 362	49.20 245	62.84 329	75.78 312

PVSNet	50.76 19	58.40 295	57.39 297	61.42 312	75.53 239	44.04 288	61.43 350	63.45 335	47.04 321	56.91 320	73.61 336	27.00 358	64.76 348	39.12 326	72.40 224	75.47 316

WB-MVSnew		59.66 287	59.69 277	59.56 321	75.19 245	35.78 367	69.34 297	64.28 329	46.88 322	61.76 271	75.79 315	40.61 225	65.20 347	32.16 365	71.21 238	77.70 288

FMVSNet5		55.86 317	54.93 317	58.66 330	71.05 312	36.35 359	64.18 338	62.48 342	46.76 323	50.66 369	74.73 328	25.80 366	64.04 350	33.11 361	65.57 306	75.59 314

jason		69.65 142	68.39 154	73.43 141	78.27 168	56.88 101	77.12 163	73.71 255	46.53 324	69.34 135	83.22 175	43.37 194	79.18 233	64.77 118	79.20 132	84.23 161
jason: jason.
MS-PatchMatch		62.42 261	61.46 260	65.31 285	75.21 244	52.10 185	72.05 261	74.05 251	46.41 325	57.42 318	74.36 330	34.35 289	77.57 261	45.62 277	73.67 201	66.26 384

1112_ss		64.00 244	63.36 236	65.93 275	79.28 136	42.58 301	71.35 269	72.36 266	46.41 325	60.55 282	77.89 280	46.27 164	73.28 300	46.18 270	69.97 259	81.92 224

lupinMVS		69.57 145	68.28 155	73.44 140	78.76 151	57.15 97	76.57 176	73.29 258	46.19 327	69.49 131	82.18 197	43.99 190	79.23 232	64.66 119	79.37 127	83.93 170

testdata				64.66 289	81.52 91	52.93 168		65.29 321	46.09 328	73.88 68	87.46 79	38.08 253	66.26 343	53.31 212	78.48 145	74.78 326

UnsupCasMVSNet_eth		53.16 337	52.47 335	55.23 349	59.45 392	33.39 384	59.43 362	69.13 294	45.98 329	50.35 371	72.32 342	29.30 340	58.26 375	42.02 312	44.30 392	74.05 334

AllTest		57.08 305	54.65 319	64.39 292	71.44 303	49.03 229	69.92 292	67.30 304	45.97 330	47.16 379	79.77 246	17.47 386	67.56 334	33.65 357	59.16 353	76.57 304

TestCases				64.39 292	71.44 303	49.03 229		67.30 304	45.97 330	47.16 379	79.77 246	17.47 386	67.56 334	33.65 357	59.16 353	76.57 304

WTY-MVS		59.75 286	60.39 273	57.85 337	72.32 291	37.83 343	61.05 356	64.18 330	45.95 332	61.91 268	79.11 261	47.01 157	60.88 360	42.50 307	69.49 270	74.83 324

IterMVS-SCA-FT		62.49 259	61.52 259	65.40 283	71.99 296	50.80 201	71.15 275	69.63 287	45.71 333	60.61 281	77.93 277	37.45 257	65.99 344	55.67 190	63.50 324	79.42 269

WB-MVS		43.26 360	43.41 360	42.83 386	63.32 375	10.32 424	58.17 367	45.20 402	45.42 334	40.44 397	67.26 379	34.01 294	58.98 370	11.96 415	24.88 409	59.20 390

旧先验2							76.08 186		45.32 335	76.55 36			65.56 346	58.75 169

OpenMVS_ROB	52.78 18	60.03 283	58.14 293	65.69 279	70.47 320	44.82 277	75.33 201	70.86 277	45.04 336	56.06 327	76.00 311	26.89 360	79.65 225	35.36 352	67.29 293	72.60 343

TinyColmap		54.14 327	51.72 338	61.40 313	66.84 356	41.97 306	66.52 314	68.51 298	44.81 337	42.69 393	75.77 316	11.66 402	72.94 301	31.96 367	56.77 363	69.27 378

MDTV_nov1_ep13			57.00 300		72.73 280	38.26 339	65.02 332	64.73 326	44.74 338	55.46 331	72.48 341	32.61 317	70.47 314	37.47 334	67.75 290

新几何1				70.76 201	85.66 41	61.13 30		66.43 313	44.68 339	70.29 116	86.64 97	41.29 218	75.23 292	49.72 240	81.75 103	75.93 310

Patchmtry		57.16 304	56.47 306	59.23 324	69.17 341	34.58 374	62.98 342	63.15 338	44.53 340	56.83 321	74.84 326	35.83 275	68.71 324	40.03 321	60.91 342	74.39 331

ppachtmachnet_test		58.06 299	55.38 315	66.10 272	69.51 335	48.99 232	68.01 305	66.13 316	44.50 341	54.05 349	70.74 356	32.09 322	72.34 304	36.68 343	56.71 364	76.99 302

PatchT		53.17 336	53.44 333	52.33 369	68.29 348	25.34 411	58.21 366	54.41 379	44.46 342	54.56 344	69.05 370	33.32 302	60.94 359	36.93 339	61.76 339	70.73 368

EPMVS		53.96 328	53.69 331	54.79 352	66.12 363	31.96 390	62.34 347	49.05 392	44.42 343	55.54 330	71.33 353	30.22 331	56.70 380	41.65 315	62.54 332	75.71 313

pmmvs4		61.48 274	59.39 279	67.76 246	71.57 301	53.86 148	71.42 268	65.34 320	44.20 344	59.46 296	77.92 278	35.90 274	74.71 294	43.87 294	64.87 311	74.71 328

dp		51.89 340	51.60 339	52.77 366	68.44 347	32.45 388	62.36 346	54.57 378	44.16 345	49.31 374	67.91 372	28.87 343	56.61 382	33.89 356	54.89 368	69.24 379

PatchMatch-RL		56.25 314	54.55 321	61.32 315	77.06 212	56.07 112	65.57 322	54.10 381	44.13 346	53.49 357	71.27 354	25.20 370	66.78 339	36.52 346	63.66 321	61.12 388

our_test_3		56.49 310	54.42 322	62.68 305	69.51 335	45.48 273	66.08 317	61.49 350	44.11 347	50.73 368	69.60 367	33.05 304	68.15 326	38.38 330	56.86 361	74.40 330

USDC		56.35 313	54.24 326	62.69 304	64.74 368	40.31 320	65.05 331	73.83 253	43.93 348	47.58 377	77.71 286	15.36 395	75.05 293	38.19 332	61.81 338	72.70 342

PM-MVS		52.33 338	50.19 346	58.75 329	62.10 381	45.14 276	65.75 319	40.38 409	43.60 349	53.52 355	72.65 340	9.16 410	65.87 345	50.41 234	54.18 371	65.24 386

pmmvs-eth3d		58.81 293	56.31 308	66.30 266	67.61 351	52.42 182	72.30 258	64.76 325	43.55 350	54.94 339	74.19 332	28.95 341	72.60 302	43.31 298	57.21 360	73.88 336

SSC-MVS		41.96 365	41.99 364	41.90 387	62.46 380	9.28 426	57.41 374	44.32 405	43.38 351	38.30 403	66.45 382	32.67 314	58.42 374	10.98 416	21.91 412	57.99 394

new-patchmatchnet		47.56 354	47.73 354	47.06 377	58.81 395	9.37 425	48.78 396	59.21 358	43.28 352	44.22 389	68.66 371	25.67 367	57.20 379	31.57 375	49.35 385	74.62 329

Test_1112_low_res		62.32 262	61.77 256	64.00 295	79.08 144	39.53 329	68.17 303	70.17 281	43.25 353	59.03 302	79.90 243	44.08 188	71.24 311	43.79 295	68.42 285	81.25 236

RPMNet		61.53 272	58.42 289	70.86 199	69.96 329	52.07 186	65.31 329	81.36 115	43.20 354	59.36 297	70.15 362	35.37 278	85.47 105	36.42 347	64.65 313	75.06 319

tpm2		62.07 266	60.10 275	67.99 244	72.79 279	43.86 289	71.05 278	66.85 310	43.14 355	62.77 253	75.39 323	38.32 249	80.80 207	41.69 313	68.88 279	79.32 270

JIA-IIPM		51.56 341	47.68 355	63.21 300	64.61 369	50.73 202	47.71 398	58.77 360	42.90 356	48.46 376	51.72 402	24.97 371	70.24 319	36.06 349	53.89 372	68.64 380

1314		64.61 236	63.21 240	68.80 235	71.87 298	47.46 253	73.95 232	78.39 184	42.88 357	59.97 288	76.60 304	38.11 252	79.39 230	54.84 197	72.32 226	79.55 267

HyFIR lowres test		65.67 222	63.01 242	73.67 128	79.97 124	55.65 122	69.07 299	75.52 224	42.68 358	63.53 241	77.95 276	40.43 226	81.64 185	46.01 272	71.91 231	83.73 182

CR-MVSNet		59.91 284	57.90 296	65.96 274	69.96 329	52.07 186	65.31 329	63.15 338	42.48 359	59.36 297	74.84 326	35.83 275	70.75 313	45.50 280	64.65 313	75.06 319

test222					83.14 71	58.68 76	72.57 254	63.45 335	41.78 360	67.56 170	86.12 116	37.13 264			78.73 142	74.98 322

TDRefinement		53.44 334	50.72 343	61.60 310	64.31 371	46.96 257	70.89 279	65.27 322	41.78 360	44.61 388	77.98 275	11.52 404	66.36 342	28.57 388	51.59 378	71.49 360

sss		56.17 315	56.57 305	54.96 350	66.93 355	36.32 361	57.94 368	61.69 349	41.67 362	58.64 306	75.32 324	38.72 244	56.25 384	42.04 311	66.19 302	72.31 351

PVSNet_0	43.31 20	47.46 355	45.64 358	52.92 365	67.60 352	44.65 280	54.06 384	54.64 377	41.59 363	46.15 384	58.75 395	30.99 326	58.66 372	32.18 364	24.81 410	55.46 398

MVS		67.37 192	66.33 198	70.51 207	75.46 240	50.94 196	73.95 232	81.85 103	41.57 364	62.54 260	78.57 270	47.98 135	85.47 105	52.97 214	82.05 96	75.14 318

Anonymous20240521		55.30 321	54.41 323	57.96 336	60.92 390	41.73 309	71.09 277	71.06 276	41.18 365	48.65 375	73.31 337	16.93 389	59.25 368	42.54 306	64.01 318	72.90 340

Anonymous20231206		55.10 325	55.30 316	54.48 353	69.81 333	33.94 380	62.91 343	62.13 348	41.08 366	55.18 336	75.65 317	32.75 312	56.59 383	30.32 381	67.86 288	72.91 339

MDA-MVSNet_test_wron		50.71 346	48.95 348	56.00 346	61.17 385	41.84 307	51.90 390	56.45 369	40.96 367	44.79 387	67.84 373	30.04 333	55.07 391	36.71 342	50.69 381	71.11 366

YYNet1		50.73 345	48.96 347	56.03 345	61.10 386	41.78 308	51.94 389	56.44 370	40.94 368	44.84 386	67.80 374	30.08 332	55.08 390	36.77 340	50.71 380	71.22 363

dongtai		34.52 375	34.94 375	33.26 396	61.06 387	16.00 421	52.79 388	23.78 422	40.71 369	39.33 401	48.65 410	16.91 390	48.34 402	12.18 414	19.05 414	35.44 413

CHOSEN 1792x2688		65.08 232	62.84 244	71.82 172	81.49 93	56.26 108	66.32 316	74.20 250	40.53 370	63.16 247	78.65 267	41.30 217	77.80 257	45.80 274	74.09 194	81.40 232

pmmvs5		56.47 311	55.68 313	58.86 328	61.41 384	36.71 356	66.37 315	62.75 340	40.38 371	53.70 351	76.62 301	34.56 285	67.05 337	40.02 322	65.27 307	72.83 341

test_vis1_n_1920		58.86 292	59.06 283	58.25 332	63.76 372	43.14 297	67.49 310	66.36 314	40.22 372	65.89 201	71.95 348	31.04 325	59.75 366	59.94 160	64.90 310	71.85 355

MDTV_nov1_ep13_2view						25.89 409	61.22 353		40.10 373	51.10 363		32.97 307		38.49 329		78.61 278

tpm cat1		59.25 291	56.95 301	66.15 270	72.19 293	46.96 257	68.09 304	65.76 317	40.03 374	57.81 314	70.56 357	38.32 249	74.51 295	38.26 331	61.50 340	77.00 300

test-mter		56.42 312	55.82 312	58.22 333	68.57 344	44.80 278	65.46 325	57.92 363	39.94 375	55.44 332	69.82 364	21.92 379	57.44 377	49.66 241	73.62 202	72.41 348

UnsupCasMVSNet_bld		50.07 348	48.87 349	53.66 358	60.97 389	33.67 382	57.62 372	64.56 327	39.47 376	47.38 378	64.02 390	27.47 352	59.32 367	34.69 354	43.68 393	67.98 382

TESTMET0.1,1		55.28 322	54.90 318	56.42 343	66.56 358	43.67 291	65.46 325	56.27 373	39.18 377	53.83 350	67.44 376	24.21 374	55.46 388	48.04 256	73.11 215	70.13 372

mamv4		56.85 307	58.00 295	53.43 361	72.46 288	54.47 140	57.56 373	54.74 376	38.81 378	57.42 318	79.45 255	47.57 144	38.70 413	60.88 152	53.07 374	67.11 383

ADS-MVSNet2		51.33 343	48.76 350	59.07 327	66.02 364	44.60 281	50.90 392	59.76 356	36.90 379	50.74 366	66.18 384	26.38 361	63.11 353	27.17 392	54.76 369	69.50 376

ADS-MVSNet		48.48 352	47.77 353	50.63 373	66.02 364	29.92 394	50.90 392	50.87 390	36.90 379	50.74 366	66.18 384	26.38 361	52.47 396	27.17 392	54.76 369	69.50 376

RPSCF		55.80 318	54.22 327	60.53 318	65.13 367	42.91 300	64.30 336	57.62 365	36.84 381	58.05 313	82.28 196	28.01 348	56.24 385	37.14 337	58.61 355	82.44 215

test_cas_vis1_n_1920		56.91 306	56.71 304	57.51 340	59.13 394	45.40 274	63.58 340	61.29 351	36.24 382	67.14 177	71.85 349	29.89 334	56.69 381	57.65 175	63.58 323	70.46 369

Patchmatch-test		49.08 350	48.28 352	51.50 372	64.40 370	30.85 393	45.68 402	48.46 395	35.60 383	46.10 385	72.10 345	34.47 288	46.37 405	27.08 394	60.65 346	77.27 295

CHOSEN 280x420		47.83 353	46.36 357	52.24 371	67.37 353	49.78 219	38.91 410	43.11 407	35.00 384	43.27 392	63.30 391	28.95 341	49.19 401	36.53 345	60.80 344	57.76 395

N_pmnet		39.35 370	40.28 367	36.54 393	63.76 372	1.62 430	49.37 395	0.76 429	34.62 385	43.61 391	66.38 383	26.25 363	42.57 409	26.02 397	51.77 377	65.44 385

kuosan		29.62 382	30.82 381	26.02 401	52.99 400	16.22 420	51.09 391	22.71 423	33.91 386	33.99 405	40.85 411	15.89 393	33.11 418	7.59 422	18.37 415	28.72 415

PMMVS		53.96 328	53.26 334	56.04 344	62.60 379	50.92 198	61.17 354	56.09 374	32.81 387	53.51 356	66.84 381	34.04 292	59.93 365	44.14 290	68.18 286	57.27 396

CMPMVS	42.80 21	57.81 301	55.97 310	63.32 298	60.98 388	47.38 254	64.66 334	69.50 290	32.06 388	46.83 381	77.80 282	29.50 338	71.36 310	48.68 249	73.75 200	71.21 364
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
ttmdpeth		45.56 356	42.95 361	53.39 363	52.33 404	29.15 396	57.77 369	48.20 396	31.81 389	49.86 373	77.21 291	8.69 411	59.16 369	27.31 391	33.40 406	71.84 356

CVMVSNet		59.63 288	59.14 281	61.08 317	74.47 258	38.84 334	75.20 205	68.74 297	31.15 390	58.24 310	76.51 305	32.39 320	68.58 325	49.77 238	65.84 304	75.81 311

FPMVS		42.18 364	41.11 366	45.39 379	58.03 396	41.01 316	49.50 394	53.81 382	30.07 391	33.71 406	64.03 388	11.69 401	52.08 399	14.01 410	55.11 367	43.09 407

EU-MVSNet		55.61 320	54.41 323	59.19 326	65.41 366	33.42 383	72.44 256	71.91 270	28.81 392	51.27 362	73.87 334	24.76 372	69.08 323	43.04 302	58.20 356	75.06 319

test_vis1_n		49.89 349	48.69 351	53.50 360	53.97 398	37.38 348	61.53 349	47.33 399	28.54 393	59.62 295	67.10 380	13.52 397	52.27 397	49.07 246	57.52 358	70.84 367

test_fmvs1_n		51.37 342	50.35 345	54.42 355	52.85 401	37.71 345	61.16 355	51.93 383	28.15 394	63.81 239	69.73 366	13.72 396	53.95 392	51.16 229	60.65 346	71.59 358

LF4IMVS		42.95 361	42.26 363	45.04 380	48.30 409	32.50 387	54.80 381	48.49 394	28.03 395	40.51 396	70.16 361	9.24 409	43.89 408	31.63 373	49.18 386	58.72 392

test_fmvs1		51.32 344	50.48 344	53.81 357	53.57 399	37.51 347	60.63 359	51.16 386	28.02 396	63.62 240	69.23 369	16.41 391	53.93 393	51.01 230	60.70 345	69.99 373

MVS-HIRNet		45.52 357	44.48 359	48.65 376	68.49 346	34.05 379	59.41 363	44.50 404	27.03 397	37.96 404	50.47 406	26.16 364	64.10 349	26.74 395	59.52 351	47.82 405

PMVS	28.69 22	36.22 373	33.29 378	45.02 381	36.82 421	35.98 364	54.68 382	48.74 393	26.31 398	21.02 414	51.61 403	2.88 423	60.10 364	9.99 419	47.58 387	38.99 412
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
pmmvs3		44.92 358	41.95 365	53.86 356	52.58 403	43.55 292	62.11 348	46.90 401	26.05 399	40.63 395	60.19 394	11.08 407	57.91 376	31.83 372	46.15 389	60.11 389

test_fmvs2		48.69 351	47.49 356	52.29 370	48.63 408	33.06 386	57.76 370	48.05 397	25.71 400	59.76 293	69.60 367	11.57 403	52.23 398	49.45 244	56.86 361	71.58 359

PMMVS2		27.40 383	25.91 386	31.87 398	39.46 420	6.57 427	31.17 413	28.52 418	23.96 401	20.45 415	48.94 409	4.20 419	37.94 414	16.51 407	19.97 413	51.09 400

MVStest1		42.65 362	39.29 369	52.71 367	47.26 411	34.58 374	54.41 383	50.84 391	23.35 402	39.31 402	74.08 333	12.57 399	55.09 389	23.32 400	28.47 408	68.47 381

Gipuma		34.77 374	31.91 379	43.33 384	62.05 382	37.87 341	20.39 415	67.03 308	23.23 403	18.41 416	25.84 416	4.24 417	62.73 354	14.71 409	51.32 379	29.38 414
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
test_vis1_rt		41.35 367	39.45 368	47.03 378	46.65 412	37.86 342	47.76 397	38.65 410	23.10 404	44.21 390	51.22 404	11.20 406	44.08 407	39.27 325	53.02 375	59.14 391

new_pmnet		34.13 376	34.29 377	33.64 395	52.63 402	18.23 419	44.43 405	33.90 415	22.81 405	30.89 408	53.18 400	10.48 408	35.72 417	20.77 404	39.51 398	46.98 406

mvsany_test1		39.38 369	38.16 372	43.02 385	49.05 406	34.28 377	44.16 406	25.94 420	22.74 406	46.57 383	62.21 393	23.85 375	41.16 412	33.01 362	35.91 402	53.63 399

LCM-MVSNet		40.30 368	35.88 374	53.57 359	42.24 414	29.15 396	45.21 404	60.53 355	22.23 407	28.02 409	50.98 405	3.72 420	61.78 358	31.22 378	38.76 400	69.78 375

test_fmvs3		44.30 359	42.55 362	49.55 375	42.83 413	27.15 406	53.03 386	44.93 403	22.03 408	53.69 353	64.94 387	4.21 418	49.63 400	47.47 257	49.82 383	71.88 354

APD_test1		37.39 372	34.94 375	44.72 383	48.88 407	33.19 385	52.95 387	44.00 406	19.49 409	27.28 410	58.59 396	3.18 422	52.84 395	18.92 405	41.17 397	48.14 404

mvsany_test3		32.62 377	30.57 382	38.77 391	36.16 422	24.20 413	38.10 411	20.63 424	19.14 410	40.36 398	57.43 397	5.06 415	36.63 416	29.59 385	28.66 407	55.49 397

E-PMN		23.77 384	22.73 388	26.90 399	42.02 415	20.67 416	42.66 407	35.70 413	17.43 411	10.28 421	25.05 417	6.42 413	42.39 410	10.28 418	14.71 417	17.63 416

EMVS		22.97 385	21.84 389	26.36 400	40.20 418	19.53 418	41.95 408	34.64 414	17.09 412	9.73 422	22.83 418	7.29 412	42.22 411	9.18 420	13.66 418	17.32 417

test_vis3_rt		32.09 378	30.20 383	37.76 392	35.36 423	27.48 402	40.60 409	28.29 419	16.69 413	32.52 407	40.53 412	1.96 424	37.40 415	33.64 359	42.21 396	48.39 402

test_f		31.86 379	31.05 380	34.28 394	32.33 425	21.86 415	32.34 412	30.46 417	16.02 414	39.78 400	55.45 399	4.80 416	32.36 419	30.61 379	37.66 401	48.64 401

DSMNet-mixed		39.30 371	38.72 370	41.03 388	51.22 405	19.66 417	45.53 403	31.35 416	15.83 415	39.80 399	67.42 378	22.19 378	45.13 406	22.43 401	52.69 376	58.31 393

testf1		31.46 380	28.89 384	39.16 389	41.99 416	28.78 398	46.45 400	37.56 411	14.28 416	21.10 412	48.96 407	1.48 426	47.11 403	13.63 411	34.56 403	41.60 408

APD_test2		31.46 380	28.89 384	39.16 389	41.99 416	28.78 398	46.45 400	37.56 411	14.28 416	21.10 412	48.96 407	1.48 426	47.11 403	13.63 411	34.56 403	41.60 408

MVE	17.77 23	21.41 386	17.77 391	32.34 397	34.34 424	25.44 410	16.11 416	24.11 421	11.19 418	13.22 418	31.92 414	1.58 425	30.95 420	10.47 417	17.03 416	40.62 411
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
DeepMVS_CX				12.03 404	17.97 426	10.91 423		10.60 427	7.46 419	11.07 420	28.36 415	3.28 421	11.29 423	8.01 421	9.74 422	13.89 418

wuyk23d		13.32 389	12.52 392	15.71 403	47.54 410	26.27 408	31.06 414	1.98 428	4.93 420	5.18 423	1.94 423	0.45 428	18.54 422	6.81 423	12.83 419	2.33 420

test_method		19.68 387	18.10 390	24.41 402	13.68 427	3.11 429	12.06 418	42.37 408	2.00 421	11.97 419	36.38 413	5.77 414	29.35 421	15.06 408	23.65 411	40.76 410

tmp_tt		9.43 390	11.14 393	4.30 405	2.38 428	4.40 428	13.62 417	16.08 426	0.39 422	15.89 417	13.06 419	15.80 394	5.54 424	12.63 413	10.46 421	2.95 419

EGC-MVSNET		42.47 363	38.48 371	54.46 354	74.33 262	48.73 237	70.33 287	51.10 387	0.03 423	0.18 424	67.78 375	13.28 398	66.49 341	18.91 406	50.36 382	48.15 403

testmvs		4.52 393	6.03 396	0.01 407	0.01 429	0.00 432	53.86 385	0.00 430	0.01 424	0.04 425	0.27 424	0.00 430	0.00 425	0.04 424	0.00 423	0.03 422

test123		4.73 392	6.30 395	0.02 406	0.01 429	0.01 431	56.36 377	0.00 430	0.01 424	0.04 425	0.21 425	0.01 429	0.00 425	0.03 425	0.00 423	0.04 421

mmdepth		0.00 395	0.00 398	0.00 408	0.00 431	0.00 432	0.00 419	0.00 430	0.00 426	0.00 427	0.00 426	0.00 430	0.00 425	0.00 426	0.00 423	0.00 423

monomultidepth		0.00 395	0.00 398	0.00 408	0.00 431	0.00 432	0.00 419	0.00 430	0.00 426	0.00 427	0.00 426	0.00 430	0.00 425	0.00 426	0.00 423	0.00 423

test_blank		0.00 395	0.00 398	0.00 408	0.00 431	0.00 432	0.00 419	0.00 430	0.00 426	0.00 427	0.00 426	0.00 430	0.00 425	0.00 426	0.00 423	0.00 423

uanet_test		0.00 395	0.00 398	0.00 408	0.00 431	0.00 432	0.00 419	0.00 430	0.00 426	0.00 427	0.00 426	0.00 430	0.00 425	0.00 426	0.00 423	0.00 423

DCPMVS		0.00 395	0.00 398	0.00 408	0.00 431	0.00 432	0.00 419	0.00 430	0.00 426	0.00 427	0.00 426	0.00 430	0.00 425	0.00 426	0.00 423	0.00 423

cdsmvs_eth3d_5k		17.50 388	23.34 387	0.00 408	0.00 431	0.00 432	0.00 419	78.63 171	0.00 426	0.00 427	82.18 197	49.25 122	0.00 425	0.00 426	0.00 423	0.00 423

pcd_1.5k_mvsjas		3.92 394	5.23 397	0.00 408	0.00 431	0.00 432	0.00 419	0.00 430	0.00 426	0.00 427	0.00 426	47.05 154	0.00 425	0.00 426	0.00 423	0.00 423

sosnet-low-res		0.00 395	0.00 398	0.00 408	0.00 431	0.00 432	0.00 419	0.00 430	0.00 426	0.00 427	0.00 426	0.00 430	0.00 425	0.00 426	0.00 423	0.00 423

sosnet		0.00 395	0.00 398	0.00 408	0.00 431	0.00 432	0.00 419	0.00 430	0.00 426	0.00 427	0.00 426	0.00 430	0.00 425	0.00 426	0.00 423	0.00 423

uncertanet		0.00 395	0.00 398	0.00 408	0.00 431	0.00 432	0.00 419	0.00 430	0.00 426	0.00 427	0.00 426	0.00 430	0.00 425	0.00 426	0.00 423	0.00 423

Regformer		0.00 395	0.00 398	0.00 408	0.00 431	0.00 432	0.00 419	0.00 430	0.00 426	0.00 427	0.00 426	0.00 430	0.00 425	0.00 426	0.00 423	0.00 423

ab-mvs-re		6.49 391	8.65 394	0.00 408	0.00 431	0.00 432	0.00 419	0.00 430	0.00 426	0.00 427	77.89 280	0.00 430	0.00 425	0.00 426	0.00 423	0.00 423

uanet		0.00 395	0.00 398	0.00 408	0.00 431	0.00 432	0.00 419	0.00 430	0.00 426	0.00 427	0.00 426	0.00 430	0.00 425	0.00 426	0.00 423	0.00 423

WAC-MVS						27.31 404								27.77 389

MSC_two_6792asdad				79.95 4	87.24 14	61.04 31		85.62 24					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 24					90.96 1	79.31 9	90.65 8	87.85 33

eth-test2					0.00 431

eth-test					0.00 431

OPU-MVS				79.83 7	87.54 11	60.93 35	87.82 7				89.89 45	67.01 1	90.33 12	73.16 54	91.15 4	88.23 22

test_0728_SECOND				79.19 16	87.82 3	59.11 66	87.85 5	87.15 3					90.84 3	78.66 15	90.61 11	87.62 43

GSMVS																78.05 283

test_part2					87.58 9	60.47 42				83.42 12

sam_mvs1												34.74 284				78.05 283

sam_mvs												33.43 301

ambc				65.13 287	63.72 374	37.07 352	47.66 399	78.78 167		54.37 347	71.42 351	11.24 405	80.94 202	45.64 276	53.85 373	77.38 293

MTGPA								80.97 132

test_post1							68.67 301				3.64 421	32.39 320	69.49 321	44.17 288

test_post											3.55 422	33.90 295	66.52 340

patchmatchnet-post											64.03 388	34.50 286	74.27 297

GG-mvs-BLEND				62.34 306	71.36 307	37.04 353	69.20 298	57.33 368		54.73 342	65.48 386	30.37 329	77.82 256	34.82 353	74.93 187	72.17 352

MTMP							86.03 19	17.08 425

test9_res														75.28 37	88.31 32	83.81 176

agg_prior2														73.09 55	87.93 40	84.33 157

agg_prior					85.04 50	59.96 50		81.04 130		74.68 57			84.04 133

test_prior4						62.51 14	82.08 79

test_prior				76.69 58	84.20 61	57.27 91		84.88 39					86.43 81			86.38 78

新几何2							76.12 184

旧先验1					83.04 73	53.15 163		67.52 303			87.85 74	44.08 188			80.76 108	78.03 286

原ACMM2							79.02 119

testdata2													72.18 307	46.95 266

segment_acmp												54.23 57

test12				77.76 45	84.52 58	58.41 78		83.36 76		72.93 87		54.61 54	88.05 39		88.12 34	86.81 66

plane_prior7					81.41 94	55.96 114

plane_prior6					81.20 101	56.24 109						45.26 178

plane_prior5								84.01 52					87.21 58	68.16 87	80.58 111	84.65 151

plane_prior4											86.10 117

plane_prior1					81.27 99

n2								0.00 430

nn								0.00 430

door-mid								47.19 400

lessismore_v0				69.91 217	71.42 305	47.80 247		50.90 389		50.39 370	75.56 318	27.43 354	81.33 192	45.91 273	34.10 405	80.59 249

test11								83.47 71

door								47.60 398

HQP5-MVS						54.94 134

BP-MVS														67.04 98

HQP4-MVS										67.85 160			86.93 66			84.32 158

HQP3-MVS								83.90 57							80.35 115

HQP2-MVS												45.46 172

NP-MVS					80.98 104	56.05 113					85.54 134

ACMMP++_ref															74.07 195

ACMMP++															72.16 229

Test By Simon												48.33 133

High-resolution multi-view benchmark