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 53	73.19 1	77.08 34	91.21 17	57.23 33	90.73 10	83.35 1	88.12 34	89.22 5

MVS_0304		78.45 18	78.28 19	78.98 26	80.73 107	57.91 83	84.68 35	81.64 106	68.35 2	75.77 39	90.38 29	53.98 59	90.26 13	81.30 3	87.68 42	88.77 9

CANet		76.46 40	75.93 44	78.06 39	81.29 97	57.53 88	82.35 72	83.31 79	67.78 3	70.09 116	86.34 108	54.92 50	88.90 25	72.68 58	84.55 67	87.76 36

UA-Net		73.13 74	72.93 75	73.76 119	83.58 66	51.66 190	78.75 119	77.66 191	67.75 4	72.61 93	89.42 50	49.82 114	83.29 146	53.61 207	83.14 80	86.32 84

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 57

TranMVSNet+NR-MVSNet		70.36 123	70.10 120	71.17 192	78.64 155	42.97 297	76.53 175	81.16 126	66.95 6	68.53 145	85.42 134	51.61 96	83.07 150	52.32 215	69.70 265	87.46 45

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	67.80 163	89.24 54	42.03 206	89.38 19	64.07 120	86.50 57	89.69 2

NCCC		78.58 16	78.31 18	79.39 12	87.51 12	62.61 13	85.20 30	84.42 44	66.73 8	74.67 58	89.38 52	55.30 46	89.18 21	74.19 46	87.34 44	86.38 76

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 37
Skip Steuart: Steuart Systems R&D Blog.
EPNet		73.09 75	72.16 82	75.90 69	75.95 230	56.28 107	83.05 59	72.39 263	66.53 10	65.27 210	87.00 86	50.40 110	85.47 103	62.48 137	86.32 58	85.94 95
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	71.44 181	79.20 139	44.13 283	76.02 188	82.60 93	66.48 11	68.20 149	84.60 146	56.82 36	82.82 161	54.62 197	70.43 245	87.36 52

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 25
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 64	65.37 13	78.78 22	90.64 21	58.63 25	87.24 54	79.00 12	90.37 14	85.26 130

NR-MVSNet		69.54 144	68.85 137	71.59 178	78.05 177	43.81 288	74.20 225	80.86 132	65.18 14	62.76 252	84.52 147	52.35 84	83.59 142	50.96 230	70.78 240	87.37 50

MTAPA		76.90 34	76.42 38	78.35 35	86.08 37	63.57 2	74.92 212	80.97 130	65.13 15	75.77 39	90.88 19	48.63 129	86.66 71	77.23 24	88.17 33	84.81 145

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 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 25

EI-MVSNet-Vis-set		72.42 87	71.59 87	74.91 86	78.47 159	54.02 145	77.05 163	79.33 155	65.03 18	71.68 103	79.35 256	52.75 76	84.89 116	66.46 100	74.23 191	85.83 100

casdiffmvs_mvg		76.14 45	76.30 39	75.66 75	76.46 224	51.83 189	79.67 111	85.08 33	65.02 19	75.84 38	88.58 63	59.42 22	85.08 109	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 65	79.27 137	55.24 132	79.22 116	85.00 38	64.97 21	72.65 92	79.46 252	53.65 70	87.87 44	67.45 94	82.91 86	85.89 98

WR-MVS		68.47 168	68.47 148	68.44 238	80.20 118	39.84 322	73.75 237	76.07 214	64.68 22	68.11 154	83.63 166	50.39 111	79.14 236	49.78 235	69.66 266	86.34 80

XVS		77.17 31	76.56 36	79.00 23	86.32 29	62.62 11	85.83 22	83.92 54	64.55 23	72.17 98	90.01 43	47.95 136	88.01 40	71.55 70	86.74 53	86.37 78

X-MVStestdata		70.21 126	67.28 175	79.00 23	86.32 29	62.62 11	85.83 22	83.92 54	64.55 23	72.17 98	6.49 418	47.95 136	88.01 40	71.55 70	86.74 53	86.37 78

HQP_MVS		74.31 65	73.73 68	76.06 67	81.41 94	56.31 105	84.22 43	84.01 51	64.52 25	69.27 134	86.10 115	45.26 178	87.21 57	68.16 86	80.58 110	84.65 149

plane_prior2							84.22 43		64.52 25

EI-MVSNet-UG-set		71.92 95	71.06 101	74.52 100	77.98 180	53.56 153	76.62 172	79.16 156	64.40 27	71.18 107	78.95 261	52.19 86	84.66 123	65.47 111	73.57 202	85.32 126

DU-MVS		70.01 129	69.53 126	71.44 181	78.05 177	44.13 283	75.01 208	81.51 109	64.37 28	68.20 149	84.52 147	49.12 126	82.82 161	54.62 197	70.43 245	87.37 50

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	85.45 119
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 20

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 39

LFMVS		71.78 97	71.59 87	72.32 162	83.40 70	46.38 259	79.75 109	71.08 272	64.18 32	72.80 89	88.64 62	42.58 201	83.72 138	57.41 175	84.49 70	86.86 62

IS-MVSNet		71.57 101	71.00 102	73.27 143	78.86 148	45.63 270	80.22 100	78.69 167	64.14 35	66.46 187	87.36 80	49.30 120	85.60 96	50.26 234	83.71 79	88.59 11

plane_prior3						56.09 111			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 68	63.89 37	73.60 71	90.60 22	54.85 51	86.72 69	77.20 25	88.06 36	85.74 107
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 76	77.84 184	52.25 181	75.59 195	84.17 48	63.76 38	73.15 79	82.79 178	59.58 20	86.80 67	67.24 95	86.04 59	87.89 28
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 66	80.81 106	59.01 70	82.60 69	83.64 65	63.74 39	72.52 94	87.49 77	47.18 152	85.88 91	69.47 79	80.78 106	83.66 184
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
UniMVSNet (Re)		70.63 117	70.20 116	71.89 167	78.55 156	45.29 273	75.94 189	82.92 87	63.68 40	68.16 152	83.59 167	53.89 62	83.49 144	53.97 203	71.12 238	86.89 61

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 72

EC-MVSNet		75.84 49	75.87 46	75.74 73	78.86 148	52.65 172	83.73 53	86.08 17	63.47 42	72.77 90	87.25 84	53.13 73	87.93 42	71.97 66	85.57 62	86.66 70

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 55

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 63
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 56	63.24 45	73.30 74	87.27 83	55.06 48	86.30 84	71.78 67	84.58 66	89.25 4

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 28
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 90	49.69 220	77.76 144	77.63 192	63.21 47	73.21 77	89.02 56	42.14 205	83.32 145	61.72 144	82.50 92	88.25 19

plane_prior						56.31 105	83.58 56		63.19 48						80.48 113

ACMMP		76.02 47	75.33 51	78.07 38	85.20 49	61.91 20	85.49 29	84.44 43	63.04 49	69.80 126	89.74 49	45.43 174	87.16 59	72.01 64	82.87 88	85.14 132
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		66.60 209	66.45 189	67.04 252	77.11 210	36.56 355	77.03 164	80.42 139	62.95 50	62.51 260	84.03 157	46.69 160	79.07 237	44.22 285	63.08 326	85.51 114

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 65
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 96	62.90 52	71.77 101	90.26 34	46.61 161	86.55 75	71.71 68	85.66 61	84.97 141

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 66

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 24

HFP-MVS		78.01 24	77.65 25	79.10 21	86.71 19	62.81 8	86.29 14	84.32 46	62.82 55	73.96 67	90.50 26	53.20 72	88.35 31	74.02 48	87.05 45	86.13 90

ACMMPR		77.71 25	77.23 28	79.16 17	86.75 18	62.93 7	86.29 14	84.24 47	62.82 55	73.55 72	90.56 24	49.80 115	88.24 33	74.02 48	87.03 46	86.32 84

region2R		77.67 27	77.18 29	79.15 18	86.76 17	62.95 6	86.29 14	84.16 49	62.81 57	73.30 74	90.58 23	49.90 113	88.21 34	73.78 50	87.03 46	86.29 87

casdiffmvs		74.80 56	74.89 57	74.53 99	75.59 236	50.37 207	78.17 133	85.06 35	62.80 58	74.40 61	87.86 73	57.88 27	83.61 141	69.46 80	82.79 90	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 61	74.70 58	74.34 103	75.70 232	49.99 215	77.54 149	84.63 42	62.73 59	73.98 66	87.79 76	57.67 30	83.82 137	69.49 78	82.74 91	89.20 6

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 53
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
DTE-MVSNet		65.58 221	65.34 212	66.31 263	76.06 229	34.79 368	76.43 177	79.38 154	62.55 61	61.66 270	83.83 162	45.60 168	79.15 235	41.64 314	60.88 341	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 37	89.70 17	79.85 5	91.48 1	88.19 22
Yufeng Yin; Xiaoyan Liu; Zichao Zhang: SMA-MVS: Segmentation-Guided Multi-Scale Anchor Deformation Patch Multi-View Stereo. IEEE Transactions on Circuits and Systems for Video Technology
CP-MVSNet		66.49 212	66.41 193	66.72 254	77.67 190	36.33 358	76.83 171	79.52 151	62.45 63	62.54 258	83.47 171	46.32 162	78.37 245	45.47 280	63.43 323	85.45 119

CP-MVS		77.12 32	76.68 32	78.43 33	86.05 38	63.18 5	87.55 10	83.45 71	62.44 64	72.68 91	90.50 26	48.18 134	87.34 53	73.59 52	85.71 60	84.76 148

PS-CasMVS		66.42 213	66.32 197	66.70 256	77.60 198	36.30 360	76.94 166	79.61 149	62.36 65	62.43 262	83.66 165	45.69 166	78.37 245	45.35 282	63.26 324	85.42 122

3Dnovator	64.47 5	72.49 84	71.39 93	75.79 70	77.70 188	58.99 71	80.66 96	83.15 84	62.24 66	65.46 206	86.59 99	42.38 204	85.52 99	59.59 162	84.72 65	82.85 205

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 68	80.66 4	89.64 19	87.80 34
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
HQP-NCC					80.66 108		82.31 74		62.10 68	67.85 158

ACMP_Plane					80.66 108		82.31 74		62.10 68	67.85 158

HQP-MVS		73.45 71	72.80 76	75.40 80	80.66 108	54.94 134	82.31 74	83.90 56	62.10 68	67.85 158	85.54 132	45.46 172	86.93 64	67.04 97	80.35 114	84.32 156

SPE-MVS-test		75.62 52	75.31 52	76.56 62	80.63 111	55.13 133	83.88 51	85.22 29	62.05 71	71.49 106	86.03 118	53.83 63	86.36 82	67.74 89	86.91 50	88.19 22

VPNet		67.52 188	68.11 155	65.74 276	79.18 140	36.80 353	72.17 258	72.83 260	62.04 72	67.79 164	85.83 125	48.88 128	76.60 279	51.30 226	72.97 215	83.81 174

WR-MVS_H		67.02 200	66.92 184	67.33 251	77.95 181	37.75 342	77.57 147	82.11 99	62.03 73	62.65 255	82.48 189	50.57 109	79.46 226	42.91 302	64.01 316	84.79 146

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 83	88.04 37	87.42 47
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 62	77.08 26	90.18 15	87.87 30

PGM-MVS		76.77 37	76.06 42	78.88 28	86.14 35	62.73 9	82.55 70	83.74 63	61.71 76	72.45 97	90.34 32	48.48 132	88.13 37	72.32 61	86.85 51	85.78 101

Effi-MVS+		73.31 73	72.54 79	75.62 77	77.87 182	53.64 151	79.62 113	79.61 149	61.63 77	72.02 100	82.61 183	56.44 39	85.97 89	63.99 123	79.07 134	87.25 54

MG-MVS		73.96 68	73.89 66	74.16 109	85.65 42	49.69 220	81.59 85	81.29 120	61.45 78	71.05 108	88.11 66	51.77 93	87.73 47	61.05 149	83.09 81	85.05 137

LPG-MVS_test		72.74 80	71.74 86	75.76 71	80.22 116	57.51 89	82.55 70	83.40 73	61.32 79	66.67 184	87.33 81	39.15 238	86.59 72	67.70 90	77.30 161	83.19 196

LGP-MVS_train				75.76 71	80.22 116	57.51 89		83.40 73	61.32 79	66.67 184	87.33 81	39.15 238	86.59 72	67.70 90	77.30 161	83.19 196

CLD-MVS		73.33 72	72.68 77	75.29 84	78.82 150	53.33 159	78.23 130	84.79 41	61.30 81	70.41 113	81.04 220	52.41 82	87.12 60	64.61 119	82.49 93	85.41 123
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
RRT-MVS		71.46 104	70.70 107	73.74 122	77.76 187	49.30 226	76.60 173	80.45 138	61.25 82	68.17 151	84.78 140	44.64 183	84.90 115	64.79 115	77.88 151	87.03 57

MVS_111021_HR		74.02 67	73.46 71	75.69 74	83.01 75	60.63 40	77.29 157	78.40 181	61.18 83	70.58 111	85.97 120	54.18 58	84.00 134	67.52 93	82.98 85	82.45 212

balanced_conf03		76.58 38	76.55 37	76.68 57	81.73 88	52.90 167	80.94 91	85.70 23	61.12 84	74.90 52	87.17 85	56.46 38	88.14 36	72.87 56	88.03 38	89.00 7

FIs		70.82 114	71.43 91	68.98 231	78.33 166	38.14 338	76.96 165	83.59 67	61.02 85	67.33 171	86.73 92	55.07 47	81.64 183	54.61 199	79.22 130	87.14 56

FOURS1					86.12 36	60.82 37	88.18 1	83.61 66	60.87 86	81.50 16

FC-MVSNet-test		69.80 135	70.58 110	67.46 247	77.61 197	34.73 371	76.05 186	83.19 83	60.84 87	65.88 200	86.46 105	54.52 55	80.76 207	52.52 214	78.12 147	86.91 60

v8		70.33 124	69.28 131	73.49 135	73.15 270	50.22 209	78.62 123	80.78 133	60.79 88	66.45 188	82.11 201	49.35 119	84.98 112	63.58 129	68.71 280	85.28 128

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	84.83 138	60.76 15	86.56 74	67.86 88	87.87 41	86.06 92

Vis-MVSNet		72.18 90	71.37 94	74.61 95	81.29 97	55.41 129	80.90 92	78.28 183	60.73 90	69.23 137	88.09 67	44.36 187	82.65 165	57.68 172	81.75 103	85.77 104
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 45	60.61 91	79.05 21	90.30 33	55.54 45	88.32 32	73.48 53	87.03 46	84.83 144
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 79	80.28 114	57.54 87	82.74 66	82.84 91	60.58 92	65.24 214	86.18 112	39.25 236	86.03 87	66.95 99	76.79 168	83.22 194
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
testdata1							72.65 248		60.50 93

UGNet		68.81 158	67.39 170	73.06 146	78.33 166	54.47 140	79.77 108	75.40 225	60.45 94	63.22 242	84.40 150	32.71 311	80.91 203	51.71 224	80.56 112	83.81 174
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 63	81.99 85	59.58 55	76.92 167	76.74 207	60.40 95	74.81 54	85.95 121	45.54 170	85.76 94	70.41 75	70.61 243	83.86 173

hse-mvs2		71.04 108	69.86 121	74.60 96	79.58 130	57.12 99	73.96 229	75.25 228	60.40 95	74.81 54	81.95 203	45.54 170	82.90 154	70.41 75	66.83 295	83.77 178

EPP-MVSNet		72.16 93	71.31 96	74.71 89	78.68 154	49.70 218	82.10 78	81.65 105	60.40 95	65.94 196	85.84 124	51.74 94	86.37 81	55.93 183	79.55 125	88.07 27

UniMVSNet_ETH3D		67.60 187	67.07 183	69.18 230	77.39 203	42.29 301	74.18 226	75.59 220	60.37 98	66.77 181	86.06 117	37.64 253	78.93 243	52.16 217	73.49 204	86.32 84

test_prior2							81.75 81		60.37 98	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 59	60.37 98	79.89 18	89.38 52	54.97 49	85.58 98	76.12 31	84.94 64	86.33 82
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	70.19 117	68.16 241	79.73 127	41.63 310	70.53 281	77.38 197	60.37 98	70.69 110	86.63 97	51.08 102	77.09 267	53.61 207	81.69 105	85.75 106

sasdasda		74.67 59	74.98 55	73.71 124	78.94 146	50.56 204	80.23 98	83.87 59	60.30 102	77.15 32	86.56 101	59.65 17	82.00 177	66.01 105	82.12 94	88.58 12

canonicalmvs		74.67 59	74.98 55	73.71 124	78.94 146	50.56 204	80.23 98	83.87 59	60.30 102	77.15 32	86.56 101	59.65 17	82.00 177	66.01 105	82.12 94	88.58 12

v7n		69.01 156	67.36 172	73.98 112	72.51 284	52.65 172	78.54 127	81.30 119	60.26 104	62.67 254	81.62 209	43.61 192	84.49 124	57.01 176	68.70 281	84.79 146

reproduce-ours		76.90 34	76.58 34	77.87 43	83.99 62	60.46 43	84.75 32	83.34 76	60.22 105	77.85 27	91.42 13	50.67 107	87.69 48	72.46 59	84.53 68	85.46 117

our_new_method		76.90 34	76.58 34	77.87 43	83.99 62	60.46 43	84.75 32	83.34 76	60.22 105	77.85 27	91.42 13	50.67 107	87.69 48	72.46 59	84.53 68	85.46 117

HPM-MVS_fast		74.30 66	73.46 71	76.80 55	84.45 60	59.04 69	83.65 55	81.05 127	60.15 107	70.43 112	89.84 46	41.09 222	85.59 97	67.61 92	82.90 87	85.77 104

VPA-MVSNet		69.02 155	69.47 128	67.69 245	77.42 202	41.00 315	74.04 227	79.68 147	60.06 108	69.26 136	84.81 139	51.06 103	77.58 258	54.44 200	74.43 189	84.48 153

v10		70.21 126	69.02 135	73.81 116	73.51 267	50.92 196	78.74 120	81.39 112	60.05 109	66.39 189	81.83 206	47.58 143	85.41 106	62.80 134	68.86 279	85.09 136

SR-MVS		76.13 46	75.70 47	77.40 51	85.87 40	61.20 29	85.52 27	82.19 97	59.99 110	75.10 45	90.35 31	47.66 141	86.52 76	71.64 69	82.99 83	84.47 154

9.14			78.75 15		83.10 72		84.15 46	88.26 1	59.90 111	78.57 23	90.36 30	57.51 32	86.86 66	77.39 23	89.52 21

v2v482		70.50 120	69.45 129	73.66 127	72.62 280	50.03 214	77.58 146	80.51 137	59.90 111	69.52 128	82.14 199	47.53 145	84.88 118	65.07 114	70.17 253	86.09 91

Baseline_NR-MVSNet		67.05 199	67.56 162	65.50 279	75.65 233	37.70 344	75.42 198	74.65 240	59.90 111	68.14 153	83.15 176	49.12 126	77.20 265	52.23 216	69.78 262	81.60 225

API-MVS		72.17 91	71.41 92	74.45 101	81.95 86	57.22 92	84.03 48	80.38 140	59.89 114	68.40 146	82.33 192	49.64 116	87.83 46	51.87 221	84.16 75	78.30 277

Effi-MVS+-dtu		69.64 141	67.53 165	75.95 68	76.10 228	62.29 15	80.20 101	76.06 215	59.83 115	65.26 213	77.09 291	41.56 214	84.02 133	60.60 153	71.09 239	81.53 226

reproduce_model		76.43 41	76.08 41	77.49 48	83.47 69	60.09 47	84.60 36	82.90 88	59.65 116	77.31 30	91.43 12	49.62 117	87.24 54	71.99 65	83.75 78	85.14 132

MVSMamba_PlusPlus		75.75 51	75.44 49	76.67 58	80.84 105	53.06 164	78.62 123	85.13 32	59.65 116	71.53 105	87.47 78	56.92 34	88.17 35	72.18 63	86.63 56	88.80 8

CANet_DTU		68.18 175	67.71 161	69.59 221	74.83 247	46.24 261	78.66 122	76.85 204	59.60 118	63.45 240	82.09 202	35.25 277	77.41 261	59.88 159	78.76 139	85.14 132

EI-MVSNet		69.27 152	68.44 150	71.73 173	74.47 256	49.39 225	75.20 203	78.45 177	59.60 118	69.16 138	76.51 303	51.29 98	82.50 169	59.86 161	71.45 235	83.30 191

IterMVS-LS		69.22 154	68.48 146	71.43 183	74.44 258	49.40 224	76.23 181	77.55 193	59.60 118	65.85 201	81.59 212	51.28 99	81.58 186	59.87 160	69.90 260	83.30 191
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
MGCFI-Net		72.45 85	73.34 73	69.81 218	77.77 186	43.21 294	75.84 192	81.18 124	59.59 121	75.45 42	86.64 95	57.74 28	77.94 251	63.92 124	81.90 99	88.30 17

VDDNet		71.81 96	71.33 95	73.26 144	82.80 78	47.60 250	78.74 120	75.27 227	59.59 121	72.94 86	89.40 51	41.51 216	83.91 135	58.75 167	82.99 83	88.26 18

alignmvs		73.86 69	73.99 64	73.45 137	78.20 169	50.50 206	78.57 125	82.43 94	59.40 123	76.57 35	86.71 94	56.42 40	81.23 194	65.84 108	81.79 100	88.62 10

MVS_Test		72.45 85	72.46 80	72.42 161	74.88 245	48.50 238	76.28 180	83.14 85	59.40 123	72.46 95	84.68 141	55.66 44	81.12 195	65.98 107	79.66 122	87.63 40

TSAR-MVS + MP.		78.44 19	78.28 19	78.90 27	84.96 52	61.41 26	84.03 48	83.82 62	59.34 125	79.37 19	89.76 48	59.84 16	87.62 51	76.69 27	86.74 53	87.68 38
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 92	83.02 74	59.29 61	82.30 77	81.88 101	59.34 125	71.59 104	86.83 88	45.94 165	83.65 140	65.09 113	85.22 63	81.06 240

PAPM_NR		72.63 82	71.80 85	75.13 85	81.72 89	53.42 157	79.91 106	83.28 81	59.14 127	66.31 191	85.90 122	51.86 91	86.06 85	57.45 174	80.62 108	85.91 97

testing91		64.46 236	63.80 227	66.47 260	78.43 161	40.06 320	67.63 305	69.59 286	59.06 128	63.18 244	78.05 272	34.05 289	76.99 269	48.30 251	75.87 177	82.37 214

save fliter					86.17 33	61.30 28	83.98 50	79.66 148	59.00 129

v148		68.24 174	67.19 181	71.40 184	70.43 319	47.77 247	75.76 193	77.03 202	58.91 130	67.36 170	80.10 239	48.60 131	81.89 179	60.01 157	66.52 298	84.53 151

TransMVSNet (Re)		64.72 231	64.33 221	65.87 275	75.22 241	38.56 334	74.66 218	75.08 236	58.90 131	61.79 268	82.63 182	51.18 100	78.07 250	43.63 295	55.87 364	80.99 242

Anonymous202405211		66.84 204	65.99 203	69.40 225	80.19 119	42.21 303	71.11 274	71.31 271	58.80 132	67.90 156	86.39 107	29.83 333	79.65 223	49.60 241	78.78 138	86.33 82

test2506		65.33 226	64.61 219	67.50 246	79.46 133	34.19 376	74.43 223	51.92 382	58.72 133	66.75 182	88.05 69	25.99 363	80.92 202	51.94 220	84.25 72	87.39 48

ECVR-MVS		67.72 185	67.51 166	68.35 239	79.46 133	36.29 361	74.79 215	66.93 307	58.72 133	67.19 173	88.05 69	36.10 270	81.38 189	52.07 218	84.25 72	87.39 48

test1111		67.21 192	67.14 182	67.42 248	79.24 138	34.76 370	73.89 234	65.65 316	58.71 135	66.96 178	87.95 72	36.09 271	80.53 209	52.03 219	83.79 77	86.97 59

LCM-MVSNet-Re		61.88 267	61.35 259	63.46 295	74.58 254	31.48 389	61.42 349	58.14 360	58.71 135	53.02 356	79.55 250	43.07 196	76.80 273	45.69 273	77.96 149	82.11 220

testing99		64.05 240	63.29 237	66.34 262	78.17 173	39.76 324	67.33 310	68.00 300	58.60 137	63.03 247	78.10 271	32.57 316	76.94 271	48.22 252	75.58 181	82.34 215

v1144		70.42 122	69.31 130	73.76 119	73.22 268	50.64 201	77.83 142	81.43 111	58.58 138	69.40 132	81.16 217	47.53 145	85.29 108	64.01 122	70.64 241	85.34 125

TSAR-MVS + GP.		74.90 55	74.15 63	77.17 52	82.00 84	58.77 75	81.80 80	78.57 170	58.58 138	74.32 63	84.51 149	55.94 43	87.22 56	67.11 96	84.48 71	85.52 113

BH-RMVSNet		68.81 158	67.42 169	72.97 147	80.11 122	52.53 176	74.26 224	76.29 210	58.48 140	68.38 147	84.20 152	42.59 200	83.83 136	46.53 265	75.91 176	82.56 207

APD-MVS_3200maxsize		74.96 54	74.39 61	76.67 58	82.20 81	58.24 80	83.67 54	83.29 80	58.41 141	73.71 70	90.14 36	45.62 167	85.99 88	69.64 77	82.85 89	85.78 101

OMC-MVS		71.40 106	70.60 108	73.78 117	76.60 220	53.15 161	79.74 110	79.78 145	58.37 142	68.75 141	86.45 106	45.43 174	80.60 208	62.58 135	77.73 152	87.58 43

nrg030		72.96 77	73.01 74	72.84 150	75.41 239	50.24 208	80.02 102	82.89 90	58.36 143	74.44 60	86.73 92	58.90 24	80.83 204	65.84 108	74.46 187	87.44 46

K. test v3		60.47 278	57.11 296	70.56 203	73.74 266	48.22 241	75.10 207	62.55 339	58.27 144	53.62 352	76.31 307	27.81 348	81.59 185	47.42 256	39.18 397	81.88 223

FA-MVS(test-final)		69.82 134	68.48 146	73.84 115	78.44 160	50.04 213	75.58 197	78.99 160	58.16 145	67.59 167	82.14 199	42.66 199	85.63 95	56.60 178	76.19 174	85.84 99

MVS_111021_LR		69.50 146	68.78 140	71.65 176	78.38 162	59.33 59	74.82 214	70.11 280	58.08 146	67.83 162	84.68 141	41.96 207	76.34 284	65.62 110	77.54 154	79.30 269

SR-MVS-dyc-post		74.57 62	73.90 65	76.58 61	83.49 67	59.87 52	84.29 40	81.36 114	58.07 147	73.14 80	90.07 37	44.74 181	85.84 92	68.20 84	81.76 101	84.03 164

RE-MVS-def			73.71 69		83.49 67	59.87 52	84.29 40	81.36 114	58.07 147	73.14 80	90.07 37	43.06 197		68.20 84	81.76 101	84.03 164

SDMVSNet		68.03 177	68.10 156	67.84 243	77.13 208	48.72 236	65.32 326	79.10 157	58.02 149	65.08 217	82.55 185	47.83 138	73.40 297	63.92 124	73.92 195	81.41 228

sd_testset		64.46 236	64.45 220	64.51 289	77.13 208	42.25 302	62.67 342	72.11 266	58.02 149	65.08 217	82.55 185	41.22 221	69.88 318	47.32 258	73.92 195	81.41 228

GeoE		71.01 109	70.15 118	73.60 132	79.57 131	52.17 182	78.93 118	78.12 184	58.02 149	67.76 166	83.87 161	52.36 83	82.72 163	56.90 177	75.79 178	85.92 96

ZD-MVS					86.64 21	60.38 45		82.70 92	57.95 152	78.10 24	90.06 39	56.12 42	88.84 26	74.05 47	87.00 49

EIA-MVS		71.78 97	70.60 108	75.30 83	79.85 125	53.54 154	77.27 158	83.26 82	57.92 153	66.49 186	79.39 254	52.07 88	86.69 70	60.05 156	79.14 133	85.66 109

test_yl		69.69 137	69.13 132	71.36 185	78.37 164	45.74 266	74.71 216	80.20 142	57.91 154	70.01 121	83.83 162	42.44 202	82.87 157	54.97 193	79.72 120	85.48 115

DCV-MVSNet		69.69 137	69.13 132	71.36 185	78.37 164	45.74 266	74.71 216	80.20 142	57.91 154	70.01 121	83.83 162	42.44 202	82.87 157	54.97 193	79.72 120	85.48 115

MonoMVSNet		64.15 239	63.31 236	66.69 257	70.51 317	44.12 285	74.47 221	74.21 247	57.81 156	63.03 247	76.62 299	38.33 246	77.31 263	54.22 201	60.59 346	78.64 275

dcpmvs_2		74.55 63	75.23 53	72.48 157	82.34 80	53.34 158	77.87 139	81.46 110	57.80 157	75.49 41	86.81 89	62.22 13	77.75 256	71.09 72	82.02 97	86.34 80

Fast-Effi-MVS+-dtu		67.37 190	65.33 213	73.48 136	72.94 275	57.78 86	77.47 151	76.88 203	57.60 158	61.97 265	76.85 295	39.31 234	80.49 212	54.72 196	70.28 251	82.17 219

v1192		69.97 131	68.68 142	73.85 114	73.19 269	50.94 194	77.68 145	81.36 114	57.51 159	68.95 140	80.85 227	45.28 177	85.33 107	62.97 133	70.37 247	85.27 129

ACMH+	57.40 11	66.12 215	64.06 222	72.30 163	77.79 185	52.83 170	80.39 97	78.03 185	57.30 160	57.47 314	82.55 185	27.68 349	84.17 128	45.54 276	69.78 262	79.90 259

diffmvs		70.69 116	70.43 111	71.46 180	69.45 335	48.95 232	72.93 245	78.46 176	57.27 161	71.69 102	83.97 160	51.48 97	77.92 253	70.70 74	77.95 150	87.53 44
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		68.27 172	67.29 174	71.21 189	79.74 126	53.22 160	76.06 185	77.46 196	57.19 162	66.10 193	81.61 210	45.37 176	83.50 143	45.42 281	76.68 170	76.91 301

thres100view900		63.28 249	62.41 247	65.89 274	77.31 205	38.66 333	72.65 248	69.11 293	57.07 163	62.45 261	81.03 221	37.01 265	79.17 232	31.84 367	73.25 210	79.83 261

DP-MVS Recon		72.15 94	70.73 106	76.40 63	86.57 24	57.99 82	81.15 90	82.96 86	57.03 164	66.78 180	85.56 129	44.50 185	88.11 38	51.77 223	80.23 117	83.10 200

thres600view7		63.30 248	62.27 248	66.41 261	77.18 207	38.87 331	72.35 255	69.11 293	56.98 165	62.37 263	80.96 223	37.01 265	79.00 241	31.43 374	73.05 214	81.36 231

V42		68.65 162	67.35 173	72.56 155	68.93 341	50.18 210	72.90 246	79.47 152	56.92 166	69.45 131	80.26 236	46.29 163	82.99 151	64.07 120	67.82 287	84.53 151

MCST-MVS		77.48 28	77.45 27	77.54 47	86.67 20	58.36 79	83.22 58	86.93 5	56.91 167	74.91 51	88.19 65	59.15 23	87.68 50	73.67 51	87.45 43	86.57 73

GA-MVS		65.53 222	63.70 229	71.02 196	70.87 312	48.10 242	70.48 282	74.40 242	56.69 168	64.70 225	76.77 296	33.66 297	81.10 196	55.42 192	70.32 250	83.87 172

v144192		69.71 136	68.51 145	73.33 142	73.10 271	50.13 211	77.54 149	80.64 134	56.65 169	68.57 144	80.55 230	46.87 159	84.96 114	62.98 132	69.66 266	84.89 143

tfpn200view9		63.18 251	62.18 250	66.21 266	76.85 215	39.62 325	71.96 262	69.44 289	56.63 170	62.61 256	79.83 242	37.18 259	79.17 232	31.84 367	73.25 210	79.83 261

thres400		63.31 247	62.18 250	66.72 254	76.85 215	39.62 325	71.96 262	69.44 289	56.63 170	62.61 256	79.83 242	37.18 259	79.17 232	31.84 367	73.25 210	81.36 231

GBi-Net		67.21 192	66.55 187	69.19 227	77.63 192	43.33 291	77.31 154	77.83 188	56.62 172	65.04 219	82.70 179	41.85 209	80.33 214	47.18 260	72.76 217	83.92 169

test1		67.21 192	66.55 187	69.19 227	77.63 192	43.33 291	77.31 154	77.83 188	56.62 172	65.04 219	82.70 179	41.85 209	80.33 214	47.18 260	72.76 217	83.92 169

FMVSNet2		66.93 202	66.31 198	68.79 234	77.63 192	42.98 296	76.11 183	77.47 194	56.62 172	65.22 216	82.17 197	41.85 209	80.18 220	47.05 263	72.72 220	83.20 195

DPM-MVS		75.47 53	75.00 54	76.88 54	81.38 96	59.16 62	79.94 104	85.71 22	56.59 175	72.46 95	86.76 90	56.89 35	87.86 45	66.36 101	88.91 25	83.64 186

v1921920		69.47 147	68.17 154	73.36 141	73.06 272	50.10 212	77.39 152	80.56 135	56.58 176	68.59 142	80.37 232	44.72 182	84.98 112	62.47 138	69.82 261	85.00 138

FMVSNet1		66.70 207	65.87 204	69.19 227	77.49 200	43.33 291	77.31 154	77.83 188	56.45 177	64.60 227	82.70 179	38.08 251	80.33 214	46.08 269	72.31 225	83.92 169

v1240		69.24 153	67.91 157	73.25 145	73.02 274	49.82 216	77.21 159	80.54 136	56.43 178	68.34 148	80.51 231	43.33 195	84.99 110	62.03 142	69.77 264	84.95 142

testing222		62.29 262	61.31 260	65.25 284	77.87 182	38.53 335	68.34 300	66.31 313	56.37 179	63.15 246	77.58 286	28.47 343	76.18 287	37.04 336	76.65 171	81.05 241

CDPH-MVS		76.31 42	75.67 48	78.22 37	85.35 48	59.14 65	81.31 88	84.02 50	56.32 180	74.05 65	88.98 57	53.34 71	87.92 43	69.23 81	88.42 28	87.59 42

Vis-MVSNet (Re-imp)		63.69 244	63.88 225	63.14 299	74.75 249	31.04 390	71.16 272	63.64 332	56.32 180	59.80 290	84.99 136	44.51 184	75.46 289	39.12 324	80.62 108	82.92 202

AdaColmap		69.99 130	68.66 143	73.97 113	84.94 54	57.83 84	82.63 68	78.71 166	56.28 182	64.34 228	84.14 154	41.57 213	87.06 63	46.45 266	78.88 135	77.02 297

PS-MVSNAJss		72.24 89	71.21 97	75.31 82	78.50 157	55.93 115	81.63 82	82.12 98	56.24 183	70.02 120	85.68 128	47.05 154	84.34 127	65.27 112	74.41 190	85.67 108

c3_l		68.33 171	67.56 162	70.62 202	70.87 312	46.21 262	74.47 221	78.80 164	56.22 184	66.19 192	78.53 269	51.88 90	81.40 188	62.08 139	69.04 275	84.25 158

Fast-Effi-MVS+		70.28 125	69.12 134	73.73 123	78.50 157	51.50 191	75.01 208	79.46 153	56.16 185	68.59 142	79.55 250	53.97 60	84.05 130	53.34 209	77.53 155	85.65 110

PHI-MVS		75.87 48	75.36 50	77.41 49	80.62 112	55.91 116	84.28 42	85.78 20	56.08 186	73.41 73	86.58 100	50.94 105	88.54 28	70.79 73	89.71 17	87.79 35

baseline1		63.81 243	63.87 226	63.62 294	76.29 225	36.36 356	71.78 264	67.29 304	56.05 187	64.23 233	82.95 177	47.11 153	74.41 294	47.30 259	61.85 335	80.10 256

train_agg		76.27 43	76.15 40	76.64 60	85.58 43	61.59 24	81.62 83	81.26 121	55.86 188	74.93 49	88.81 59	53.70 67	84.68 121	75.24 38	88.33 30	83.65 185

test_8					85.40 46	60.96 34	81.54 86	81.18 124	55.86 188	74.81 54	88.80 61	53.70 67	84.45 125

FMVSNet3		66.32 214	65.61 209	68.46 237	76.48 223	42.34 300	74.98 210	77.15 201	55.83 190	65.04 219	81.16 217	39.91 227	80.14 221	47.18 260	72.76 217	82.90 204

PAPR		71.72 100	70.82 104	74.41 102	81.20 101	51.17 192	79.55 114	83.33 78	55.81 191	66.93 179	84.61 145	50.95 104	86.06 85	55.79 186	79.20 131	86.00 93

eth_miper_zixun_eth		67.63 186	66.28 199	71.67 175	71.60 298	48.33 240	73.68 238	77.88 186	55.80 192	65.91 197	78.62 267	47.35 151	82.88 156	59.45 163	66.25 299	83.81 174

ACMH	55.70 15	65.20 228	63.57 231	70.07 211	78.07 176	52.01 187	79.48 115	79.69 146	55.75 193	56.59 321	80.98 222	27.12 354	80.94 200	42.90 303	71.58 233	77.25 295
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
IB-MVS	56.42 12	65.40 225	62.73 244	73.40 140	74.89 244	52.78 171	73.09 244	75.13 232	55.69 194	58.48 307	73.73 333	32.86 306	86.32 83	50.63 231	70.11 254	81.10 239
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		61.53 270	60.94 267	63.30 297	68.95 340	36.93 352	67.60 306	72.80 261	55.67 195	59.95 287	76.63 298	45.01 180	72.22 304	39.74 322	62.09 334	80.74 246

TEST9					85.58 43	61.59 24	81.62 83	81.26 121	55.65 196	74.93 49	88.81 59	53.70 67	84.68 121

thres200		62.20 263	61.16 265	65.34 282	75.38 240	39.99 321	69.60 292	69.29 291	55.64 197	61.87 267	76.99 292	37.07 264	78.96 242	31.28 375	73.28 209	77.06 296

pm-mvs1		65.24 227	64.97 217	66.04 271	72.38 287	39.40 328	72.62 250	75.63 219	55.53 198	62.35 264	83.18 175	47.45 147	76.47 282	49.06 245	66.54 297	82.24 216

testing11		62.81 254	61.90 253	65.54 278	78.38 162	40.76 317	67.59 307	66.78 309	55.48 199	60.13 282	77.11 290	31.67 322	76.79 274	45.53 277	74.45 188	79.06 270

ACMM	61.98 7	70.80 115	69.73 123	74.02 111	80.59 113	58.59 77	82.68 67	82.02 100	55.46 200	67.18 174	84.39 151	38.51 243	83.17 149	60.65 152	76.10 175	80.30 252
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
Anonymous20240529		69.91 132	69.02 135	72.56 155	80.19 119	47.65 248	77.56 148	80.99 129	55.45 201	69.88 124	86.76 90	39.24 237	82.18 175	54.04 202	77.10 165	87.85 31

tt0805		67.77 184	67.24 179	69.34 226	74.87 246	40.08 319	77.36 153	81.37 113	55.31 202	66.33 190	84.65 143	37.35 257	82.55 168	55.65 189	72.28 226	85.39 124

CPTT-MVS		72.78 79	72.08 84	74.87 88	84.88 57	61.41 26	84.15 46	77.86 187	55.27 203	67.51 169	88.08 68	41.93 208	81.85 180	69.04 82	80.01 118	81.35 233

XVG-OURS		68.76 161	67.37 171	72.90 149	74.32 261	57.22 92	70.09 288	78.81 163	55.24 204	67.79 164	85.81 127	36.54 268	78.28 247	62.04 141	75.74 179	83.19 196

tfpnnormal		62.47 258	61.63 256	64.99 286	74.81 248	39.01 330	71.22 270	73.72 252	55.22 205	60.21 281	80.09 240	41.26 220	76.98 270	30.02 380	68.09 285	78.97 273

cl____		67.18 195	66.26 200	69.94 213	70.20 322	45.74 266	73.30 240	76.83 205	55.10 206	65.27 210	79.57 249	47.39 149	80.53 209	59.41 165	69.22 273	83.53 188

DIV-MVS_self_test		67.18 195	66.26 200	69.94 213	70.20 322	45.74 266	73.29 241	76.83 205	55.10 206	65.27 210	79.58 248	47.38 150	80.53 209	59.43 164	69.22 273	83.54 187

PC_three_1452									55.09 208	84.46 4	89.84 46	66.68 5	89.41 18	74.24 44	91.38 2	88.42 14

EPNet_dtu		61.90 266	61.97 252	61.68 307	72.89 276	39.78 323	75.85 191	65.62 317	55.09 208	54.56 342	79.36 255	37.59 254	67.02 336	39.80 321	76.95 166	78.25 278
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
PVSNet_Blended_VisFu		71.45 105	70.39 112	74.65 93	82.01 83	58.82 74	79.93 105	80.35 141	55.09 208	65.82 202	82.16 198	49.17 123	82.64 166	60.34 154	78.62 142	82.50 211

cl22		67.47 189	66.45 189	70.54 204	69.85 330	46.49 258	73.85 235	77.35 198	55.07 211	65.51 205	77.92 276	47.64 142	81.10 196	61.58 147	69.32 269	84.01 166

miper_ehance_all_eth		68.03 177	67.24 179	70.40 206	70.54 316	46.21 262	73.98 228	78.68 168	55.07 211	66.05 194	77.80 280	52.16 87	81.31 191	61.53 148	69.32 269	83.67 182

PS-MVSNAJ		70.51 119	69.70 124	72.93 148	81.52 91	55.79 119	74.92 212	79.00 159	55.04 213	69.88 124	78.66 264	47.05 154	82.19 174	61.61 145	79.58 123	80.83 244

mmtdpeth		60.40 279	59.12 280	64.27 292	69.59 332	48.99 230	70.67 279	70.06 281	54.96 214	62.78 250	73.26 337	27.00 356	67.66 329	58.44 170	45.29 389	76.16 306

xiu_mvs_v2_base		70.52 118	69.75 122	72.84 150	81.21 100	55.63 123	75.11 205	78.92 161	54.92 215	69.96 123	79.68 247	47.00 158	82.09 176	61.60 146	79.37 126	80.81 245

MAR-MVS		71.51 102	70.15 118	75.60 78	81.84 87	59.39 58	81.38 87	82.90 88	54.90 216	68.08 155	78.70 262	47.73 139	85.51 100	51.68 225	84.17 74	81.88 223
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		62.56 256	61.20 264	66.62 258	70.62 315	44.30 282	70.13 287	73.13 258	54.78 217	61.13 276	76.37 306	25.63 366	75.63 288	58.75 167	60.29 347	79.93 258

XVG-OURS-SEG-HR		68.81 158	67.47 168	72.82 152	74.40 259	56.87 102	70.59 280	79.04 158	54.77 218	66.99 177	86.01 119	39.57 232	78.21 248	62.54 136	73.33 208	83.37 190

testing3		56.54 307	55.92 309	58.41 329	77.52 199	27.93 399	69.72 291	56.36 369	54.75 219	58.63 305	77.80 280	20.88 382	71.75 307	25.31 396	62.25 332	75.53 313

Anonymous20231211		69.28 151	68.47 148	71.73 173	80.28 114	47.18 254	79.98 103	82.37 95	54.61 220	67.24 172	84.01 158	39.43 233	82.41 172	55.45 191	72.83 216	85.62 111

SixPastTwentyTwo		61.65 269	58.80 284	70.20 209	75.80 231	47.22 253	75.59 195	69.68 284	54.61 220	54.11 346	79.26 257	27.07 355	82.96 152	43.27 297	49.79 382	80.41 250

test_0402		63.25 250	61.01 266	69.96 212	80.00 123	54.37 143	76.86 170	72.02 267	54.58 222	58.71 302	80.79 229	35.00 280	84.36 126	26.41 394	64.71 310	71.15 363

tttt0517		67.83 183	65.66 208	74.33 104	76.69 217	50.82 198	77.86 140	73.99 250	54.54 223	64.64 226	82.53 188	35.06 279	85.50 101	55.71 187	69.91 259	86.67 69

BH-w/o		66.85 203	65.83 205	69.90 216	79.29 135	52.46 178	74.66 218	76.65 208	54.51 224	64.85 223	78.12 270	45.59 169	82.95 153	43.26 298	75.54 182	74.27 330

AUN-MVS		68.45 170	66.41 193	74.57 98	79.53 132	57.08 100	73.93 232	75.23 229	54.44 225	66.69 183	81.85 205	37.10 263	82.89 155	62.07 140	66.84 294	83.75 179

LTVRE_ROB	55.42 16	63.15 252	61.23 263	68.92 232	76.57 221	47.80 245	59.92 358	76.39 209	54.35 226	58.67 303	82.46 190	29.44 337	81.49 187	42.12 307	71.14 237	77.46 289
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 78	74.27 106	71.28 307	55.88 117	78.21 132	75.56 221	54.31 227	74.86 53	87.80 75	54.72 52	80.23 218	78.07 21	78.48 143	86.70 67

test_fmvsmconf0.01_n		72.17 91	71.50 89	74.16 109	67.96 347	55.58 126	78.06 136	74.67 239	54.19 228	74.54 59	88.23 64	50.35 112	80.24 217	78.07 21	77.46 157	86.65 71

test_fmvsmconf0.1_n		72.81 78	72.33 81	74.24 107	69.89 329	55.81 118	78.22 131	75.40 225	54.17 229	75.00 48	88.03 71	53.82 64	80.23 218	78.08 20	78.34 146	86.69 68

ETVMVS		59.51 288	58.81 282	61.58 309	77.46 201	34.87 367	64.94 331	59.35 355	54.06 230	61.08 277	76.67 297	29.54 334	71.87 306	32.16 363	74.07 193	78.01 285

ab-mvs		66.65 208	66.42 192	67.37 249	76.17 227	41.73 307	70.41 284	76.14 213	53.99 231	65.98 195	83.51 169	49.48 118	76.24 285	48.60 248	73.46 206	84.14 162

IU-MVS					87.77 4	59.15 63		85.53 26	53.93 232	84.64 3				79.07 11	90.87 5	88.37 16

XVG-ACMP-BASELINE		64.36 238	62.23 249	70.74 200	72.35 288	52.45 179	70.80 278	78.45 177	53.84 233	59.87 288	81.10 219	16.24 390	79.32 229	55.64 190	71.76 230	80.47 248

FE-MVS		65.91 217	63.33 235	73.63 130	77.36 204	51.95 188	72.62 250	75.81 216	53.70 234	65.31 208	78.96 260	28.81 342	86.39 80	43.93 290	73.48 205	82.55 208

thisisatest0530		67.92 181	65.78 206	74.33 104	76.29 225	51.03 193	76.89 168	74.25 246	53.67 235	65.59 204	81.76 207	35.15 278	85.50 101	55.94 182	72.47 221	86.47 75

PVSNet_BlendedMVS		68.56 167	67.72 159	71.07 195	77.03 212	50.57 202	74.50 220	81.52 107	53.66 236	64.22 234	79.72 246	49.13 124	82.87 157	55.82 184	73.92 195	79.77 264

patch_mono-2		69.85 133	71.09 100	66.16 267	79.11 143	54.80 138	71.97 261	74.31 244	53.50 237	70.90 109	84.17 153	57.63 31	63.31 350	66.17 102	82.02 97	80.38 251

EG-PatchMatch MVS		64.71 232	62.87 241	70.22 207	77.68 189	53.48 155	77.99 137	78.82 162	53.37 238	56.03 326	77.41 288	24.75 371	84.04 131	46.37 267	73.42 207	73.14 336

DP-MVS		65.68 219	63.66 230	71.75 172	84.93 55	56.87 102	80.74 95	73.16 257	53.06 239	59.09 299	82.35 191	36.79 267	85.94 90	32.82 361	69.96 258	72.45 344

TR-MVS		66.59 211	65.07 216	71.17 192	79.18 140	49.63 222	73.48 239	75.20 231	52.95 240	67.90 156	80.33 235	39.81 230	83.68 139	43.20 299	73.56 203	80.20 253

ET-MVSNet_ETH3D		67.96 180	65.72 207	74.68 91	76.67 218	55.62 125	75.11 205	74.74 237	52.91 241	60.03 285	80.12 238	33.68 296	82.64 166	61.86 143	76.34 172	85.78 101

QAPM		70.05 128	68.81 139	73.78 117	76.54 222	53.43 156	83.23 57	83.48 69	52.89 242	65.90 198	86.29 109	41.55 215	86.49 78	51.01 228	78.40 145	81.42 227

OpenMVS	61.03 9	68.85 157	67.56 162	72.70 154	74.26 262	53.99 146	81.21 89	81.34 118	52.70 243	62.75 253	85.55 131	38.86 241	84.14 129	48.41 250	83.01 82	79.97 257

pmmvs6		63.69 244	62.82 243	66.27 265	70.63 314	39.27 329	73.13 243	75.47 224	52.69 244	59.75 292	82.30 193	39.71 231	77.03 268	47.40 257	64.35 315	82.53 209

IterMVS		62.79 255	61.27 261	67.35 250	69.37 336	52.04 186	71.17 271	68.24 299	52.63 245	59.82 289	76.91 294	37.32 258	72.36 301	52.80 213	63.19 325	77.66 287
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
mvs_tets		68.18 175	66.36 195	73.63 130	75.61 235	55.35 131	80.77 94	78.56 171	52.48 246	64.27 231	84.10 156	27.45 351	81.84 181	63.45 131	70.56 244	83.69 181

jajsoiax		68.25 173	66.45 189	73.66 127	75.62 234	55.49 128	80.82 93	78.51 173	52.33 247	64.33 229	84.11 155	28.28 345	81.81 182	63.48 130	70.62 242	83.67 182

TAMVS		66.78 206	65.27 214	71.33 188	79.16 142	53.67 150	73.84 236	69.59 286	52.32 248	65.28 209	81.72 208	44.49 186	77.40 262	42.32 306	78.66 141	82.92 202

CDS-MVSNet		66.80 205	65.37 211	71.10 194	78.98 145	53.13 163	73.27 242	71.07 273	52.15 249	64.72 224	80.23 237	43.56 193	77.10 266	45.48 279	78.88 135	83.05 201
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
mvsmamba		68.47 168	66.56 186	74.21 108	79.60 129	52.95 165	74.94 211	75.48 223	52.09 250	60.10 283	83.27 172	36.54 268	84.70 120	59.32 166	77.69 153	84.99 140

PVSNet_Blended		68.59 163	67.72 159	71.19 190	77.03 212	50.57 202	72.51 253	81.52 107	51.91 251	64.22 234	77.77 283	49.13 124	82.87 157	55.82 184	79.58 123	80.14 255

mvs_anonymous		68.03 177	67.51 166	69.59 221	72.08 292	44.57 280	71.99 260	75.23 229	51.67 252	67.06 176	82.57 184	54.68 53	77.94 251	56.56 179	75.71 180	86.26 88

xiu_mvs_v1_base_debu		68.58 164	67.28 175	72.48 157	78.19 170	57.19 94	75.28 200	75.09 233	51.61 253	70.04 117	81.41 214	32.79 307	79.02 238	63.81 126	77.31 158	81.22 235

xiu_mvs_v1_base		68.58 164	67.28 175	72.48 157	78.19 170	57.19 94	75.28 200	75.09 233	51.61 253	70.04 117	81.41 214	32.79 307	79.02 238	63.81 126	77.31 158	81.22 235

xiu_mvs_v1_base_debi		68.58 164	67.28 175	72.48 157	78.19 170	57.19 94	75.28 200	75.09 233	51.61 253	70.04 117	81.41 214	32.79 307	79.02 238	63.81 126	77.31 158	81.22 235

MVSTER		67.16 197	65.58 210	71.88 168	70.37 321	49.70 218	70.25 286	78.45 177	51.52 256	69.16 138	80.37 232	38.45 244	82.50 169	60.19 155	71.46 234	83.44 189

CNLPA		65.43 223	64.02 223	69.68 219	78.73 153	58.07 81	77.82 143	70.71 276	51.49 257	61.57 272	83.58 168	38.23 249	70.82 310	43.90 291	70.10 255	80.16 254

原ACMM1				74.69 90	85.39 47	59.40 57		83.42 72	51.47 258	70.27 115	86.61 98	48.61 130	86.51 77	53.85 205	87.96 39	78.16 279

miper_enhance_ethall		67.11 198	66.09 202	70.17 210	69.21 338	45.98 264	72.85 247	78.41 180	51.38 259	65.65 203	75.98 312	51.17 101	81.25 192	60.82 151	69.32 269	83.29 193

MSDG		61.81 268	59.23 278	69.55 224	72.64 279	52.63 174	70.45 283	75.81 216	51.38 259	53.70 349	76.11 308	29.52 335	81.08 198	37.70 331	65.79 303	74.93 321

test20.03		53.87 328	54.02 326	53.41 360	61.47 381	28.11 398	61.30 350	59.21 356	51.34 261	52.09 358	77.43 287	33.29 301	58.55 371	29.76 381	60.27 348	73.58 335

MVSFormer		71.50 103	70.38 113	74.88 87	78.76 151	57.15 97	82.79 64	78.48 174	51.26 262	69.49 129	83.22 173	43.99 190	83.24 147	66.06 103	79.37 126	84.23 159

test_djsdf		69.45 148	67.74 158	74.58 97	74.57 255	54.92 136	82.79 64	78.48 174	51.26 262	65.41 207	83.49 170	38.37 245	83.24 147	66.06 103	69.25 272	85.56 112

dmvs_testset		50.16 345	51.90 335	44.94 380	66.49 357	11.78 420	61.01 355	51.50 383	51.17 264	50.30 370	67.44 374	39.28 235	60.29 361	22.38 400	57.49 357	62.76 385

PAPM		67.92 181	66.69 185	71.63 177	78.09 175	49.02 229	77.09 162	81.24 123	51.04 265	60.91 278	83.98 159	47.71 140	84.99 110	40.81 315	79.32 129	80.90 243

Syy-MVS		56.00 314	56.23 307	55.32 346	74.69 251	26.44 405	65.52 321	57.49 364	50.97 266	56.52 322	72.18 341	39.89 228	68.09 325	24.20 397	64.59 313	71.44 359

myMVS_eth3d		54.86 324	54.61 318	55.61 345	74.69 251	27.31 402	65.52 321	57.49 364	50.97 266	56.52 322	72.18 341	21.87 380	68.09 325	27.70 388	64.59 313	71.44 359

miper_lstm_enhance		62.03 265	60.88 268	65.49 280	66.71 355	46.25 260	56.29 376	75.70 218	50.68 268	61.27 274	75.48 319	40.21 226	68.03 327	56.31 181	65.25 306	82.18 217

gg-mvs-nofinetune		57.86 298	56.43 305	62.18 305	72.62 280	35.35 366	66.57 311	56.33 370	50.65 269	57.64 313	57.10 396	30.65 325	76.36 283	37.38 333	78.88 135	74.82 323

TAPA-MVS	59.36 10	66.60 209	65.20 215	70.81 198	76.63 219	48.75 234	76.52 176	80.04 144	50.64 270	65.24 214	84.93 137	39.15 238	78.54 244	36.77 338	76.88 167	85.14 132
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
dmvs_re		56.77 306	56.83 301	56.61 340	69.23 337	41.02 312	58.37 363	64.18 328	50.59 271	57.45 315	71.42 349	35.54 275	58.94 369	37.23 334	67.45 290	69.87 372

MVP-Stereo		65.41 224	63.80 227	70.22 207	77.62 196	55.53 127	76.30 179	78.53 172	50.59 271	56.47 324	78.65 265	39.84 229	82.68 164	44.10 289	72.12 228	72.44 345
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 81	77.63 192	55.71 120	76.04 187	81.81 103	50.30 273	69.66 127	85.40 135	52.51 79	84.89 116	51.82 222	80.24 116	85.45 119
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
mvs5depth		55.64 317	53.81 328	61.11 314	59.39 391	40.98 316	65.89 316	68.28 298	50.21 274	58.11 310	75.42 320	17.03 386	67.63 331	43.79 293	46.21 386	74.73 325

baseline2		63.42 246	61.26 262	69.89 217	72.55 282	47.62 249	71.54 265	68.38 297	50.11 275	54.82 338	75.55 317	43.06 197	80.96 199	48.13 253	67.16 293	81.11 238

test-LLR		58.15 296	58.13 292	58.22 331	68.57 342	44.80 276	65.46 323	57.92 361	50.08 276	55.44 330	69.82 362	32.62 313	57.44 375	49.66 239	73.62 200	72.41 346

test0.0.03 1		53.32 333	53.59 330	52.50 366	62.81 376	29.45 393	59.51 359	54.11 378	50.08 276	54.40 344	74.31 329	32.62 313	55.92 384	30.50 378	63.95 318	72.15 351

fmvsm_s_conf0.5_n		69.58 142	68.84 138	71.79 171	72.31 290	52.90 167	77.90 138	62.43 342	49.97 278	72.85 88	85.90 122	52.21 85	76.49 280	75.75 33	70.26 252	85.97 94

COLMAP_ROB	52.97 17	61.27 274	58.81 282	68.64 235	74.63 253	52.51 177	78.42 128	73.30 255	49.92 279	50.96 362	81.51 213	23.06 374	79.40 227	31.63 371	65.85 301	74.01 333
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	71.93 166	72.47 285	53.82 148	78.25 129	62.26 344	49.78 280	73.12 82	86.21 111	52.66 77	76.79 274	75.02 39	68.88 277	85.18 131

WBMVS		60.54 276	60.61 270	60.34 317	78.00 179	35.95 363	64.55 333	64.89 321	49.63 281	63.39 241	78.70 262	33.85 294	67.65 330	42.10 308	70.35 249	77.43 290

tpmvs		58.47 292	56.95 299	63.03 301	70.20 322	41.21 311	67.90 304	67.23 305	49.62 282	54.73 340	70.84 353	34.14 288	76.24 285	36.64 342	61.29 339	71.64 355

fmvsm_s_conf0.1_n		69.41 149	68.60 144	71.83 169	71.07 309	52.88 169	77.85 141	62.44 341	49.58 283	72.97 85	86.22 110	51.68 95	76.48 281	75.53 34	70.10 255	86.14 89

UBG		59.62 287	59.53 276	59.89 318	78.12 174	35.92 364	64.11 337	60.81 352	49.45 284	61.34 273	75.55 317	33.05 302	67.39 334	38.68 326	74.62 186	76.35 305

thisisatest0515		65.83 218	63.50 232	72.82 152	73.75 265	49.50 223	71.32 268	73.12 259	49.39 285	63.82 236	76.50 305	34.95 281	84.84 119	53.20 211	75.49 183	84.13 163

fmvsm_s_conf0.1_n_a		69.32 150	68.44 150	71.96 165	70.91 311	53.78 149	78.12 134	62.30 343	49.35 286	73.20 78	86.55 103	51.99 89	76.79 274	74.83 41	68.68 282	85.32 126

HY-MVS	56.14 13	64.55 235	63.89 224	66.55 259	74.73 250	41.02 312	69.96 289	74.43 241	49.29 287	61.66 270	80.92 224	47.43 148	76.68 278	44.91 284	71.69 231	81.94 221

MIMVSNet1		55.17 322	54.31 323	57.77 336	70.03 326	32.01 387	65.68 319	64.81 322	49.19 288	46.75 380	76.00 309	25.53 367	64.04 348	28.65 385	62.13 333	77.26 294

SCA		60.49 277	58.38 288	66.80 253	74.14 264	48.06 243	63.35 339	63.23 335	49.13 289	59.33 298	72.10 343	37.45 255	74.27 295	44.17 286	62.57 329	78.05 281

test_fmvsmvis_n_1920		70.84 112	70.38 113	72.22 164	71.16 308	55.39 130	75.86 190	72.21 265	49.03 290	73.28 76	86.17 113	51.83 92	77.29 264	75.80 32	78.05 148	83.98 167

testgi		51.90 337	52.37 334	50.51 372	60.39 389	23.55 412	58.42 362	58.15 359	49.03 290	51.83 359	79.21 258	22.39 375	55.59 385	29.24 384	62.64 328	72.40 348

MIMVSNet		57.35 300	57.07 297	58.22 331	74.21 263	37.18 347	62.46 343	60.88 351	48.88 292	55.29 333	75.99 311	31.68 321	62.04 355	31.87 366	72.35 223	75.43 315

gm-plane-assit					71.40 304	41.72 309			48.85 293		73.31 335		82.48 171	48.90 246

fmvsm_l_conf0.5_n		70.99 110	70.82 104	71.48 179	71.45 300	54.40 142	77.18 160	70.46 278	48.67 294	75.17 44	86.86 87	53.77 65	76.86 272	76.33 30	77.51 156	83.17 199

UWE-MVS		60.18 280	59.78 274	61.39 312	77.67 190	33.92 379	69.04 298	63.82 330	48.56 295	64.27 231	77.64 285	27.20 353	70.40 315	33.56 358	76.24 173	79.83 261

cascas		65.98 216	63.42 233	73.64 129	77.26 206	52.58 175	72.26 257	77.21 200	48.56 295	61.21 275	74.60 327	32.57 316	85.82 93	50.38 233	76.75 169	82.52 210

PLC	56.13 14	65.09 229	63.21 238	70.72 201	81.04 103	54.87 137	78.57 125	77.47 194	48.51 297	55.71 327	81.89 204	33.71 295	79.71 222	41.66 312	70.37 247	77.58 288
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
LS3D		64.71 232	62.50 246	71.34 187	79.72 128	55.71 120	79.82 107	74.72 238	48.50 298	56.62 320	84.62 144	33.59 298	82.34 173	29.65 382	75.23 184	75.97 307

anonymousdsp		67.00 201	64.82 218	73.57 133	70.09 325	56.13 110	76.35 178	77.35 198	48.43 299	64.99 222	80.84 228	33.01 304	80.34 213	64.66 117	67.64 289	84.23 159

无先验							79.66 112	74.30 245	48.40 300				80.78 206	53.62 206		79.03 272

114514_t		70.83 113	69.56 125	74.64 94	86.21 31	54.63 139	82.34 73	81.81 103	48.22 301	63.01 249	85.83 125	40.92 223	87.10 61	57.91 171	79.79 119	82.18 217

tpm		57.34 301	58.16 290	54.86 349	71.80 297	34.77 369	67.47 309	56.04 373	48.20 302	60.10 283	76.92 293	37.17 261	53.41 392	40.76 316	65.01 307	76.40 304

test_fmvsm_n_1920		71.73 99	71.14 99	73.50 134	72.52 283	56.53 104	75.60 194	76.16 211	48.11 303	77.22 31	85.56 129	53.10 74	77.43 260	74.86 40	77.14 163	86.55 74

MDA-MVSNet-bldmvs		53.87 328	50.81 340	63.05 300	66.25 359	48.58 237	56.93 374	63.82 330	48.09 304	41.22 392	70.48 358	30.34 328	68.00 328	34.24 353	45.92 388	72.57 342

XXY-MVS		60.68 275	61.67 255	57.70 337	70.43 319	38.45 336	64.19 335	66.47 310	48.05 305	63.22 242	80.86 226	49.28 121	60.47 359	45.25 283	67.28 292	74.19 331

F-COLMAP		63.05 253	60.87 269	69.58 223	76.99 214	53.63 152	78.12 134	76.16 211	47.97 306	52.41 357	81.61 210	27.87 347	78.11 249	40.07 318	66.66 296	77.00 298

fmvsm_l_conf0.5_n_a		70.50 120	70.27 115	71.18 191	71.30 306	54.09 144	76.89 168	69.87 282	47.90 307	74.37 62	86.49 104	53.07 75	76.69 277	75.41 35	77.11 164	82.76 206

Patchmatch-RL test		58.16 295	55.49 312	66.15 268	67.92 348	48.89 233	60.66 356	51.07 386	47.86 308	59.36 295	62.71 390	34.02 291	72.27 303	56.41 180	59.40 350	77.30 292

D2MVS		62.30 261	60.29 272	68.34 240	66.46 358	48.42 239	65.70 318	73.42 254	47.71 309	58.16 309	75.02 323	30.51 326	77.71 257	53.96 204	71.68 232	78.90 274

ANet_high		41.38 364	37.47 371	53.11 362	39.73 417	24.45 410	56.94 373	69.69 283	47.65 310	26.04 409	52.32 399	12.44 398	62.38 354	21.80 401	10.61 418	72.49 343

CostFormer		64.04 241	62.51 245	68.61 236	71.88 295	45.77 265	71.30 269	70.60 277	47.55 311	64.31 230	76.61 301	41.63 212	79.62 225	49.74 237	69.00 276	80.42 249

PatchmatchNet		59.84 283	58.24 289	64.65 288	73.05 273	46.70 257	69.42 294	62.18 345	47.55 311	58.88 301	71.96 345	34.49 285	69.16 320	42.99 301	63.60 320	78.07 280
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
KD-MVS_self_test		55.22 321	53.89 327	59.21 323	57.80 395	27.47 401	57.75 369	74.32 243	47.38 313	50.90 363	70.00 361	28.45 344	70.30 316	40.44 317	57.92 355	79.87 260

ITE_SJBPF				62.09 306	66.16 360	44.55 281		64.32 326	47.36 314	55.31 332	80.34 234	19.27 383	62.68 353	36.29 346	62.39 331	79.04 271

KD-MVS_2432*1600		53.45 330	51.50 338	59.30 320	62.82 374	37.14 348	55.33 377	71.79 269	47.34 315	55.09 335	70.52 356	21.91 378	70.45 313	35.72 348	42.97 392	70.31 368

miper_refine_blended		53.45 330	51.50 338	59.30 320	62.82 374	37.14 348	55.33 377	71.79 269	47.34 315	55.09 335	70.52 356	21.91 378	70.45 313	35.72 348	42.97 392	70.31 368

OurMVSNet-221017-0		61.37 273	58.63 286	69.61 220	72.05 293	48.06 243	73.93 232	72.51 262	47.23 317	54.74 339	80.92 224	21.49 381	81.24 193	48.57 249	56.22 363	79.53 266

tpmrst		58.24 294	58.70 285	56.84 339	66.97 352	34.32 374	69.57 293	61.14 350	47.17 318	58.58 306	71.60 348	41.28 219	60.41 360	49.20 243	62.84 327	75.78 310

PVSNet	50.76 19	58.40 293	57.39 295	61.42 310	75.53 237	44.04 286	61.43 348	63.45 333	47.04 319	56.91 318	73.61 334	27.00 356	64.76 346	39.12 324	72.40 222	75.47 314

WB-MVSnew		59.66 285	59.69 275	59.56 319	75.19 243	35.78 365	69.34 295	64.28 327	46.88 320	61.76 269	75.79 313	40.61 224	65.20 345	32.16 363	71.21 236	77.70 286

FMVSNet5		55.86 315	54.93 315	58.66 328	71.05 310	36.35 357	64.18 336	62.48 340	46.76 321	50.66 367	74.73 326	25.80 364	64.04 348	33.11 359	65.57 304	75.59 312

jason		69.65 140	68.39 152	73.43 139	78.27 168	56.88 101	77.12 161	73.71 253	46.53 322	69.34 133	83.22 173	43.37 194	79.18 231	64.77 116	79.20 131	84.23 159
jason: jason.
MS-PatchMatch		62.42 259	61.46 258	65.31 283	75.21 242	52.10 183	72.05 259	74.05 249	46.41 323	57.42 316	74.36 328	34.35 287	77.57 259	45.62 275	73.67 199	66.26 382

1112_ss		64.00 242	63.36 234	65.93 273	79.28 136	42.58 299	71.35 267	72.36 264	46.41 323	60.55 280	77.89 278	46.27 164	73.28 298	46.18 268	69.97 257	81.92 222

lupinMVS		69.57 143	68.28 153	73.44 138	78.76 151	57.15 97	76.57 174	73.29 256	46.19 325	69.49 129	82.18 195	43.99 190	79.23 230	64.66 117	79.37 126	83.93 168

testdata				64.66 287	81.52 91	52.93 166		65.29 319	46.09 326	73.88 68	87.46 79	38.08 251	66.26 341	53.31 210	78.48 143	74.78 324

UnsupCasMVSNet_eth		53.16 335	52.47 333	55.23 347	59.45 390	33.39 382	59.43 360	69.13 292	45.98 327	50.35 369	72.32 340	29.30 338	58.26 373	42.02 310	44.30 390	74.05 332

AllTest		57.08 303	54.65 317	64.39 290	71.44 301	49.03 227	69.92 290	67.30 302	45.97 328	47.16 377	79.77 244	17.47 384	67.56 332	33.65 355	59.16 351	76.57 302

TestCases				64.39 290	71.44 301	49.03 227		67.30 302	45.97 328	47.16 377	79.77 244	17.47 384	67.56 332	33.65 355	59.16 351	76.57 302

WTY-MVS		59.75 284	60.39 271	57.85 335	72.32 289	37.83 341	61.05 354	64.18 328	45.95 330	61.91 266	79.11 259	47.01 157	60.88 358	42.50 305	69.49 268	74.83 322

IterMVS-SCA-FT		62.49 257	61.52 257	65.40 281	71.99 294	50.80 199	71.15 273	69.63 285	45.71 331	60.61 279	77.93 275	37.45 255	65.99 342	55.67 188	63.50 322	79.42 267

WB-MVS		43.26 358	43.41 358	42.83 384	63.32 373	10.32 422	58.17 365	45.20 400	45.42 332	40.44 395	67.26 377	34.01 292	58.98 368	11.96 413	24.88 407	59.20 388

旧先验2							76.08 184		45.32 333	76.55 36			65.56 344	58.75 167

OpenMVS_ROB	52.78 18	60.03 281	58.14 291	65.69 277	70.47 318	44.82 275	75.33 199	70.86 275	45.04 334	56.06 325	76.00 309	26.89 358	79.65 223	35.36 350	67.29 291	72.60 341

TinyColmap		54.14 325	51.72 336	61.40 311	66.84 354	41.97 304	66.52 312	68.51 296	44.81 335	42.69 391	75.77 314	11.66 400	72.94 299	31.96 365	56.77 361	69.27 376

MDTV_nov1_ep13			57.00 298		72.73 278	38.26 337	65.02 330	64.73 324	44.74 336	55.46 329	72.48 339	32.61 315	70.47 312	37.47 332	67.75 288

新几何1				70.76 199	85.66 41	61.13 30		66.43 311	44.68 337	70.29 114	86.64 95	41.29 218	75.23 290	49.72 238	81.75 103	75.93 308

Patchmtry		57.16 302	56.47 304	59.23 322	69.17 339	34.58 372	62.98 340	63.15 336	44.53 338	56.83 319	74.84 324	35.83 273	68.71 322	40.03 319	60.91 340	74.39 329

ppachtmachnet_test		58.06 297	55.38 313	66.10 270	69.51 333	48.99 230	68.01 303	66.13 314	44.50 339	54.05 347	70.74 354	32.09 320	72.34 302	36.68 341	56.71 362	76.99 300

PatchT		53.17 334	53.44 331	52.33 367	68.29 346	25.34 409	58.21 364	54.41 377	44.46 340	54.56 342	69.05 368	33.32 300	60.94 357	36.93 337	61.76 337	70.73 366

EPMVS		53.96 326	53.69 329	54.79 350	66.12 361	31.96 388	62.34 345	49.05 390	44.42 341	55.54 328	71.33 351	30.22 329	56.70 378	41.65 313	62.54 330	75.71 311

pmmvs4		61.48 272	59.39 277	67.76 244	71.57 299	53.86 147	71.42 266	65.34 318	44.20 342	59.46 294	77.92 276	35.90 272	74.71 292	43.87 292	64.87 309	74.71 326

dp		51.89 338	51.60 337	52.77 364	68.44 345	32.45 386	62.36 344	54.57 376	44.16 343	49.31 372	67.91 370	28.87 341	56.61 380	33.89 354	54.89 366	69.24 377

PatchMatch-RL		56.25 312	54.55 319	61.32 313	77.06 211	56.07 112	65.57 320	54.10 379	44.13 344	53.49 355	71.27 352	25.20 368	66.78 337	36.52 344	63.66 319	61.12 386

our_test_3		56.49 308	54.42 320	62.68 303	69.51 333	45.48 271	66.08 315	61.49 348	44.11 345	50.73 366	69.60 365	33.05 302	68.15 324	38.38 328	56.86 359	74.40 328

USDC		56.35 311	54.24 324	62.69 302	64.74 366	40.31 318	65.05 329	73.83 251	43.93 346	47.58 375	77.71 284	15.36 393	75.05 291	38.19 330	61.81 336	72.70 340

PM-MVS		52.33 336	50.19 344	58.75 327	62.10 379	45.14 274	65.75 317	40.38 407	43.60 347	53.52 353	72.65 338	9.16 408	65.87 343	50.41 232	54.18 369	65.24 384

pmmvs-eth3d		58.81 291	56.31 306	66.30 264	67.61 349	52.42 180	72.30 256	64.76 323	43.55 348	54.94 337	74.19 330	28.95 339	72.60 300	43.31 296	57.21 358	73.88 334

SSC-MVS		41.96 363	41.99 362	41.90 385	62.46 378	9.28 424	57.41 372	44.32 403	43.38 349	38.30 401	66.45 380	32.67 312	58.42 372	10.98 414	21.91 410	57.99 392

new-patchmatchnet		47.56 352	47.73 352	47.06 375	58.81 393	9.37 423	48.78 394	59.21 356	43.28 350	44.22 387	68.66 369	25.67 365	57.20 377	31.57 373	49.35 383	74.62 327

Test_1112_low_res		62.32 260	61.77 254	64.00 293	79.08 144	39.53 327	68.17 301	70.17 279	43.25 351	59.03 300	79.90 241	44.08 188	71.24 309	43.79 293	68.42 283	81.25 234

RPMNet		61.53 270	58.42 287	70.86 197	69.96 327	52.07 184	65.31 327	81.36 114	43.20 352	59.36 295	70.15 360	35.37 276	85.47 103	36.42 345	64.65 311	75.06 317

tpm2		62.07 264	60.10 273	67.99 242	72.79 277	43.86 287	71.05 276	66.85 308	43.14 353	62.77 251	75.39 321	38.32 247	80.80 205	41.69 311	68.88 277	79.32 268

JIA-IIPM		51.56 339	47.68 353	63.21 298	64.61 367	50.73 200	47.71 396	58.77 358	42.90 354	48.46 374	51.72 400	24.97 369	70.24 317	36.06 347	53.89 370	68.64 378

1314		64.61 234	63.21 238	68.80 233	71.87 296	47.46 251	73.95 230	78.39 182	42.88 355	59.97 286	76.60 302	38.11 250	79.39 228	54.84 195	72.32 224	79.55 265

HyFIR lowres test		65.67 220	63.01 240	73.67 126	79.97 124	55.65 122	69.07 297	75.52 222	42.68 356	63.53 239	77.95 274	40.43 225	81.64 183	46.01 270	71.91 229	83.73 180

CR-MVSNet		59.91 282	57.90 294	65.96 272	69.96 327	52.07 184	65.31 327	63.15 336	42.48 357	59.36 295	74.84 324	35.83 273	70.75 311	45.50 278	64.65 311	75.06 317

test222					83.14 71	58.68 76	72.57 252	63.45 333	41.78 358	67.56 168	86.12 114	37.13 262			78.73 140	74.98 320

TDRefinement		53.44 332	50.72 341	61.60 308	64.31 369	46.96 255	70.89 277	65.27 320	41.78 358	44.61 386	77.98 273	11.52 402	66.36 340	28.57 386	51.59 376	71.49 358

sss		56.17 313	56.57 303	54.96 348	66.93 353	36.32 359	57.94 366	61.69 347	41.67 360	58.64 304	75.32 322	38.72 242	56.25 382	42.04 309	66.19 300	72.31 349

PVSNet_0	43.31 20	47.46 353	45.64 356	52.92 363	67.60 350	44.65 278	54.06 382	54.64 375	41.59 361	46.15 382	58.75 393	30.99 324	58.66 370	32.18 362	24.81 408	55.46 396

MVS		67.37 190	66.33 196	70.51 205	75.46 238	50.94 194	73.95 230	81.85 102	41.57 362	62.54 258	78.57 268	47.98 135	85.47 103	52.97 212	82.05 96	75.14 316

Anonymous20240521		55.30 319	54.41 321	57.96 334	60.92 388	41.73 307	71.09 275	71.06 274	41.18 363	48.65 373	73.31 335	16.93 387	59.25 366	42.54 304	64.01 316	72.90 338

Anonymous20231206		55.10 323	55.30 314	54.48 351	69.81 331	33.94 378	62.91 341	62.13 346	41.08 364	55.18 334	75.65 315	32.75 310	56.59 381	30.32 379	67.86 286	72.91 337

MDA-MVSNet_test_wron		50.71 344	48.95 346	56.00 344	61.17 383	41.84 305	51.90 388	56.45 367	40.96 365	44.79 385	67.84 371	30.04 331	55.07 389	36.71 340	50.69 379	71.11 364

YYNet1		50.73 343	48.96 345	56.03 343	61.10 384	41.78 306	51.94 387	56.44 368	40.94 366	44.84 384	67.80 372	30.08 330	55.08 388	36.77 338	50.71 378	71.22 361

dongtai		34.52 373	34.94 373	33.26 394	61.06 385	16.00 419	52.79 386	23.78 420	40.71 367	39.33 399	48.65 408	16.91 388	48.34 400	12.18 412	19.05 412	35.44 411

CHOSEN 1792x2688		65.08 230	62.84 242	71.82 170	81.49 93	56.26 108	66.32 314	74.20 248	40.53 368	63.16 245	78.65 265	41.30 217	77.80 255	45.80 272	74.09 192	81.40 230

pmmvs5		56.47 309	55.68 311	58.86 326	61.41 382	36.71 354	66.37 313	62.75 338	40.38 369	53.70 349	76.62 299	34.56 283	67.05 335	40.02 320	65.27 305	72.83 339

test_vis1_n_1920		58.86 290	59.06 281	58.25 330	63.76 370	43.14 295	67.49 308	66.36 312	40.22 370	65.89 199	71.95 346	31.04 323	59.75 364	59.94 158	64.90 308	71.85 353

MDTV_nov1_ep13_2view						25.89 407	61.22 351		40.10 371	51.10 361		32.97 305		38.49 327		78.61 276

tpm cat1		59.25 289	56.95 299	66.15 268	72.19 291	46.96 255	68.09 302	65.76 315	40.03 372	57.81 312	70.56 355	38.32 247	74.51 293	38.26 329	61.50 338	77.00 298

test-mter		56.42 310	55.82 310	58.22 331	68.57 342	44.80 276	65.46 323	57.92 361	39.94 373	55.44 330	69.82 362	21.92 377	57.44 375	49.66 239	73.62 200	72.41 346

UnsupCasMVSNet_bld		50.07 346	48.87 347	53.66 356	60.97 387	33.67 380	57.62 370	64.56 325	39.47 374	47.38 376	64.02 388	27.47 350	59.32 365	34.69 352	43.68 391	67.98 380

TESTMET0.1,1		55.28 320	54.90 316	56.42 341	66.56 356	43.67 289	65.46 323	56.27 371	39.18 375	53.83 348	67.44 374	24.21 372	55.46 386	48.04 254	73.11 213	70.13 370

mamv4		56.85 305	58.00 293	53.43 359	72.46 286	54.47 140	57.56 371	54.74 374	38.81 376	57.42 316	79.45 253	47.57 144	38.70 411	60.88 150	53.07 372	67.11 381

ADS-MVSNet2		51.33 341	48.76 348	59.07 325	66.02 362	44.60 279	50.90 390	59.76 354	36.90 377	50.74 364	66.18 382	26.38 359	63.11 351	27.17 390	54.76 367	69.50 374

ADS-MVSNet		48.48 350	47.77 351	50.63 371	66.02 362	29.92 392	50.90 390	50.87 388	36.90 377	50.74 364	66.18 382	26.38 359	52.47 394	27.17 390	54.76 367	69.50 374

RPSCF		55.80 316	54.22 325	60.53 316	65.13 365	42.91 298	64.30 334	57.62 363	36.84 379	58.05 311	82.28 194	28.01 346	56.24 383	37.14 335	58.61 353	82.44 213

test_cas_vis1_n_1920		56.91 304	56.71 302	57.51 338	59.13 392	45.40 272	63.58 338	61.29 349	36.24 380	67.14 175	71.85 347	29.89 332	56.69 379	57.65 173	63.58 321	70.46 367

Patchmatch-test		49.08 348	48.28 350	51.50 370	64.40 368	30.85 391	45.68 400	48.46 393	35.60 381	46.10 383	72.10 343	34.47 286	46.37 403	27.08 392	60.65 344	77.27 293

CHOSEN 280x420		47.83 351	46.36 355	52.24 369	67.37 351	49.78 217	38.91 408	43.11 405	35.00 382	43.27 390	63.30 389	28.95 339	49.19 399	36.53 343	60.80 342	57.76 393

N_pmnet		39.35 368	40.28 365	36.54 391	63.76 370	1.62 428	49.37 393	0.76 427	34.62 383	43.61 389	66.38 381	26.25 361	42.57 407	26.02 395	51.77 375	65.44 383

kuosan		29.62 380	30.82 379	26.02 399	52.99 398	16.22 418	51.09 389	22.71 421	33.91 384	33.99 403	40.85 409	15.89 391	33.11 416	7.59 420	18.37 413	28.72 413

PMMVS		53.96 326	53.26 332	56.04 342	62.60 377	50.92 196	61.17 352	56.09 372	32.81 385	53.51 354	66.84 379	34.04 290	59.93 363	44.14 288	68.18 284	57.27 394

CMPMVS	42.80 21	57.81 299	55.97 308	63.32 296	60.98 386	47.38 252	64.66 332	69.50 288	32.06 386	46.83 379	77.80 280	29.50 336	71.36 308	48.68 247	73.75 198	71.21 362
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
ttmdpeth		45.56 354	42.95 359	53.39 361	52.33 402	29.15 394	57.77 367	48.20 394	31.81 387	49.86 371	77.21 289	8.69 409	59.16 367	27.31 389	33.40 404	71.84 354

CVMVSNet		59.63 286	59.14 279	61.08 315	74.47 256	38.84 332	75.20 203	68.74 295	31.15 388	58.24 308	76.51 303	32.39 318	68.58 323	49.77 236	65.84 302	75.81 309

FPMVS		42.18 362	41.11 364	45.39 377	58.03 394	41.01 314	49.50 392	53.81 380	30.07 389	33.71 404	64.03 386	11.69 399	52.08 397	14.01 408	55.11 365	43.09 405

EU-MVSNet		55.61 318	54.41 321	59.19 324	65.41 364	33.42 381	72.44 254	71.91 268	28.81 390	51.27 360	73.87 332	24.76 370	69.08 321	43.04 300	58.20 354	75.06 317

test_vis1_n		49.89 347	48.69 349	53.50 358	53.97 396	37.38 346	61.53 347	47.33 397	28.54 391	59.62 293	67.10 378	13.52 395	52.27 395	49.07 244	57.52 356	70.84 365

test_fmvs1_n		51.37 340	50.35 343	54.42 353	52.85 399	37.71 343	61.16 353	51.93 381	28.15 392	63.81 237	69.73 364	13.72 394	53.95 390	51.16 227	60.65 344	71.59 356

LF4IMVS		42.95 359	42.26 361	45.04 378	48.30 407	32.50 385	54.80 379	48.49 392	28.03 393	40.51 394	70.16 359	9.24 407	43.89 406	31.63 371	49.18 384	58.72 390

test_fmvs1		51.32 342	50.48 342	53.81 355	53.57 397	37.51 345	60.63 357	51.16 384	28.02 394	63.62 238	69.23 367	16.41 389	53.93 391	51.01 228	60.70 343	69.99 371

MVS-HIRNet		45.52 355	44.48 357	48.65 374	68.49 344	34.05 377	59.41 361	44.50 402	27.03 395	37.96 402	50.47 404	26.16 362	64.10 347	26.74 393	59.52 349	47.82 403

PMVS	28.69 22	36.22 371	33.29 376	45.02 379	36.82 419	35.98 362	54.68 380	48.74 391	26.31 396	21.02 412	51.61 401	2.88 421	60.10 362	9.99 417	47.58 385	38.99 410
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
pmmvs3		44.92 356	41.95 363	53.86 354	52.58 401	43.55 290	62.11 346	46.90 399	26.05 397	40.63 393	60.19 392	11.08 405	57.91 374	31.83 370	46.15 387	60.11 387

test_fmvs2		48.69 349	47.49 354	52.29 368	48.63 406	33.06 384	57.76 368	48.05 395	25.71 398	59.76 291	69.60 365	11.57 401	52.23 396	49.45 242	56.86 359	71.58 357

PMMVS2		27.40 381	25.91 384	31.87 396	39.46 418	6.57 425	31.17 411	28.52 416	23.96 399	20.45 413	48.94 407	4.20 417	37.94 412	16.51 405	19.97 411	51.09 398

MVStest1		42.65 360	39.29 367	52.71 365	47.26 409	34.58 372	54.41 381	50.84 389	23.35 400	39.31 400	74.08 331	12.57 397	55.09 387	23.32 398	28.47 406	68.47 379

Gipuma		34.77 372	31.91 377	43.33 382	62.05 380	37.87 339	20.39 413	67.03 306	23.23 401	18.41 414	25.84 414	4.24 415	62.73 352	14.71 407	51.32 377	29.38 412
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
test_vis1_rt		41.35 365	39.45 366	47.03 376	46.65 410	37.86 340	47.76 395	38.65 408	23.10 402	44.21 388	51.22 402	11.20 404	44.08 405	39.27 323	53.02 373	59.14 389

new_pmnet		34.13 374	34.29 375	33.64 393	52.63 400	18.23 417	44.43 403	33.90 413	22.81 403	30.89 406	53.18 398	10.48 406	35.72 415	20.77 402	39.51 396	46.98 404

mvsany_test1		39.38 367	38.16 370	43.02 383	49.05 404	34.28 375	44.16 404	25.94 418	22.74 404	46.57 381	62.21 391	23.85 373	41.16 410	33.01 360	35.91 400	53.63 397

LCM-MVSNet		40.30 366	35.88 372	53.57 357	42.24 412	29.15 394	45.21 402	60.53 353	22.23 405	28.02 407	50.98 403	3.72 418	61.78 356	31.22 376	38.76 398	69.78 373

test_fmvs3		44.30 357	42.55 360	49.55 373	42.83 411	27.15 404	53.03 384	44.93 401	22.03 406	53.69 351	64.94 385	4.21 416	49.63 398	47.47 255	49.82 381	71.88 352

APD_test1		37.39 370	34.94 373	44.72 381	48.88 405	33.19 383	52.95 385	44.00 404	19.49 407	27.28 408	58.59 394	3.18 420	52.84 393	18.92 403	41.17 395	48.14 402

mvsany_test3		32.62 375	30.57 380	38.77 389	36.16 420	24.20 411	38.10 409	20.63 422	19.14 408	40.36 396	57.43 395	5.06 413	36.63 414	29.59 383	28.66 405	55.49 395

E-PMN		23.77 382	22.73 386	26.90 397	42.02 413	20.67 414	42.66 405	35.70 411	17.43 409	10.28 419	25.05 415	6.42 411	42.39 408	10.28 416	14.71 415	17.63 414

EMVS		22.97 383	21.84 387	26.36 398	40.20 416	19.53 416	41.95 406	34.64 412	17.09 410	9.73 420	22.83 416	7.29 410	42.22 409	9.18 418	13.66 416	17.32 415

test_vis3_rt		32.09 376	30.20 381	37.76 390	35.36 421	27.48 400	40.60 407	28.29 417	16.69 411	32.52 405	40.53 410	1.96 422	37.40 413	33.64 357	42.21 394	48.39 400

test_f		31.86 377	31.05 378	34.28 392	32.33 423	21.86 413	32.34 410	30.46 415	16.02 412	39.78 398	55.45 397	4.80 414	32.36 417	30.61 377	37.66 399	48.64 399

DSMNet-mixed		39.30 369	38.72 368	41.03 386	51.22 403	19.66 415	45.53 401	31.35 414	15.83 413	39.80 397	67.42 376	22.19 376	45.13 404	22.43 399	52.69 374	58.31 391

testf1		31.46 378	28.89 382	39.16 387	41.99 414	28.78 396	46.45 398	37.56 409	14.28 414	21.10 410	48.96 405	1.48 424	47.11 401	13.63 409	34.56 401	41.60 406

APD_test2		31.46 378	28.89 382	39.16 387	41.99 414	28.78 396	46.45 398	37.56 409	14.28 414	21.10 410	48.96 405	1.48 424	47.11 401	13.63 409	34.56 401	41.60 406

MVE	17.77 23	21.41 384	17.77 389	32.34 395	34.34 422	25.44 408	16.11 414	24.11 419	11.19 416	13.22 416	31.92 412	1.58 423	30.95 418	10.47 415	17.03 414	40.62 409
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
DeepMVS_CX				12.03 402	17.97 424	10.91 421		10.60 425	7.46 417	11.07 418	28.36 413	3.28 419	11.29 421	8.01 419	9.74 420	13.89 416

wuyk23d		13.32 387	12.52 390	15.71 401	47.54 408	26.27 406	31.06 412	1.98 426	4.93 418	5.18 421	1.94 421	0.45 426	18.54 420	6.81 421	12.83 417	2.33 418

test_method		19.68 385	18.10 388	24.41 400	13.68 425	3.11 427	12.06 416	42.37 406	2.00 419	11.97 417	36.38 411	5.77 412	29.35 419	15.06 406	23.65 409	40.76 408

tmp_tt		9.43 388	11.14 391	4.30 403	2.38 426	4.40 426	13.62 415	16.08 424	0.39 420	15.89 415	13.06 417	15.80 392	5.54 422	12.63 411	10.46 419	2.95 417

EGC-MVSNET		42.47 361	38.48 369	54.46 352	74.33 260	48.73 235	70.33 285	51.10 385	0.03 421	0.18 422	67.78 373	13.28 396	66.49 339	18.91 404	50.36 380	48.15 401

testmvs		4.52 391	6.03 394	0.01 405	0.01 427	0.00 430	53.86 383	0.00 428	0.01 422	0.04 423	0.27 422	0.00 428	0.00 423	0.04 422	0.00 421	0.03 420

test123		4.73 390	6.30 393	0.02 404	0.01 427	0.01 429	56.36 375	0.00 428	0.01 422	0.04 423	0.21 423	0.01 427	0.00 423	0.03 423	0.00 421	0.04 419

mmdepth		0.00 393	0.00 396	0.00 406	0.00 429	0.00 430	0.00 417	0.00 428	0.00 424	0.00 425	0.00 424	0.00 428	0.00 423	0.00 424	0.00 421	0.00 421

monomultidepth		0.00 393	0.00 396	0.00 406	0.00 429	0.00 430	0.00 417	0.00 428	0.00 424	0.00 425	0.00 424	0.00 428	0.00 423	0.00 424	0.00 421	0.00 421

test_blank		0.00 393	0.00 396	0.00 406	0.00 429	0.00 430	0.00 417	0.00 428	0.00 424	0.00 425	0.00 424	0.00 428	0.00 423	0.00 424	0.00 421	0.00 421

uanet_test		0.00 393	0.00 396	0.00 406	0.00 429	0.00 430	0.00 417	0.00 428	0.00 424	0.00 425	0.00 424	0.00 428	0.00 423	0.00 424	0.00 421	0.00 421

DCPMVS		0.00 393	0.00 396	0.00 406	0.00 429	0.00 430	0.00 417	0.00 428	0.00 424	0.00 425	0.00 424	0.00 428	0.00 423	0.00 424	0.00 421	0.00 421

cdsmvs_eth3d_5k		17.50 386	23.34 385	0.00 406	0.00 429	0.00 430	0.00 417	78.63 169	0.00 424	0.00 425	82.18 195	49.25 122	0.00 423	0.00 424	0.00 421	0.00 421

pcd_1.5k_mvsjas		3.92 392	5.23 395	0.00 406	0.00 429	0.00 430	0.00 417	0.00 428	0.00 424	0.00 425	0.00 424	47.05 154	0.00 423	0.00 424	0.00 421	0.00 421

sosnet-low-res		0.00 393	0.00 396	0.00 406	0.00 429	0.00 430	0.00 417	0.00 428	0.00 424	0.00 425	0.00 424	0.00 428	0.00 423	0.00 424	0.00 421	0.00 421

sosnet		0.00 393	0.00 396	0.00 406	0.00 429	0.00 430	0.00 417	0.00 428	0.00 424	0.00 425	0.00 424	0.00 428	0.00 423	0.00 424	0.00 421	0.00 421

uncertanet		0.00 393	0.00 396	0.00 406	0.00 429	0.00 430	0.00 417	0.00 428	0.00 424	0.00 425	0.00 424	0.00 428	0.00 423	0.00 424	0.00 421	0.00 421

Regformer		0.00 393	0.00 396	0.00 406	0.00 429	0.00 430	0.00 417	0.00 428	0.00 424	0.00 425	0.00 424	0.00 428	0.00 423	0.00 424	0.00 421	0.00 421

ab-mvs-re		6.49 389	8.65 392	0.00 406	0.00 429	0.00 430	0.00 417	0.00 428	0.00 424	0.00 425	77.89 278	0.00 428	0.00 423	0.00 424	0.00 421	0.00 421

uanet		0.00 393	0.00 396	0.00 406	0.00 429	0.00 430	0.00 417	0.00 428	0.00 424	0.00 425	0.00 424	0.00 428	0.00 423	0.00 424	0.00 421	0.00 421

WAC-MVS						27.31 402								27.77 387

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 31

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 31

eth-test2					0.00 429

eth-test					0.00 429

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 20

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 41

GSMVS																78.05 281

test_part2					87.58 9	60.47 42				83.42 12

sam_mvs1												34.74 282				78.05 281

sam_mvs												33.43 299

ambc				65.13 285	63.72 372	37.07 350	47.66 397	78.78 165		54.37 345	71.42 349	11.24 403	80.94 200	45.64 274	53.85 371	77.38 291

MTGPA								80.97 130

test_post1							68.67 299				3.64 419	32.39 318	69.49 319	44.17 286

test_post											3.55 420	33.90 293	66.52 338

patchmatchnet-post											64.03 386	34.50 284	74.27 295

GG-mvs-BLEND				62.34 304	71.36 305	37.04 351	69.20 296	57.33 366		54.73 340	65.48 384	30.37 327	77.82 254	34.82 351	74.93 185	72.17 350

MTMP							86.03 19	17.08 423

test9_res														75.28 37	88.31 32	83.81 174

agg_prior2														73.09 55	87.93 40	84.33 155

agg_prior					85.04 50	59.96 50		81.04 128		74.68 57			84.04 131

test_prior4						62.51 14	82.08 79

test_prior				76.69 56	84.20 61	57.27 91		84.88 39					86.43 79			86.38 76

新几何2							76.12 182

旧先验1					83.04 73	53.15 161		67.52 301			87.85 74	44.08 188			80.76 107	78.03 284

原ACMM2							79.02 117

testdata2													72.18 305	46.95 264

segment_acmp												54.23 57

test12				77.76 45	84.52 58	58.41 78		83.36 75		72.93 87		54.61 54	88.05 39		88.12 34	86.81 64

plane_prior7					81.41 94	55.96 114

plane_prior6					81.20 101	56.24 109						45.26 178

plane_prior5								84.01 51					87.21 57	68.16 86	80.58 110	84.65 149

plane_prior4											86.10 115

plane_prior1					81.27 99

n2								0.00 428

nn								0.00 428

door-mid								47.19 398

lessismore_v0				69.91 215	71.42 303	47.80 245		50.90 387		50.39 368	75.56 316	27.43 352	81.33 190	45.91 271	34.10 403	80.59 247

test11								83.47 70

door								47.60 396

HQP5-MVS						54.94 134

BP-MVS														67.04 97

HQP4-MVS										67.85 158			86.93 64			84.32 156

HQP3-MVS								83.90 56							80.35 114

HQP2-MVS												45.46 172

NP-MVS					80.98 104	56.05 113					85.54 132

ACMMP++_ref															74.07 193

ACMMP++															72.16 227

Test By Simon												48.33 133

High-resolution multi-view benchmark