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	courty.	delive.	electro	facade	kicker	meadow	office	pipes	playgr.	relief	relief.	terrace	terrai.

CHOSEN 1792x2688		72.55 89	71.98 99	73.22 75	86.57 47	92.41 11	75.63 90	66.77 52	62.08 100	52.32 114	30.27 224	50.74 158	66.14 106	86.22 12	85.41 8	91.90 1	96.75 13

MCST-MVS		85.75 10	86.99 14	84.31 7	94.07 3	92.80 9	88.15 10	79.10 2	85.66 23	70.72 31	76.50 35	80.45 24	82.17 5	88.35 2	87.49 3	91.63 2	97.65 4

gg-mvs-nofinetune		62.34 165	66.19 147	57.86 190	76.15 125	88.61 48	71.18 136	41.24 243	25.74 244	13.16 247	22.91 238	63.97 73	54.52 173	85.06 16	85.25 11	90.92 3	91.78 78

gm-plane-assit		54.99 210	57.99 202	51.49 218	69.27 169	54.42 246	32.32 249	42.59 236	21.18 248	13.71 245	23.61 235	43.84 175	60.21 141	87.09 5	86.55 5	90.81 4	89.28 112

MVS_Test		75.22 60	76.69 61	73.51 68	79.30 86	88.82 44	80.06 52	58.74 138	69.77 68	57.50 96	59.78 73	61.35 83	75.31 26	82.07 46	83.60 26	90.13 5	91.41 82

DPM-MVS		85.41 12	86.72 18	83.89 11	91.66 14	91.92 16	90.49 2	78.09 3	86.90 19	73.95 22	74.52 37	82.01 18	79.29 14	90.24 1	90.65 1	89.86 6	90.78 90

E2		75.18 62	75.21 70	75.15 51	79.77 77	89.10 38	78.62 58	64.19 70	65.19 86	65.90 44	58.15 75	58.36 107	72.56 47	80.74 61	81.78 44	89.84 7	93.19 50

viewcassd2359sk11		74.75 65	74.61 76	74.90 55	79.62 78	88.96 42	78.47 61	64.08 72	63.51 92	65.27 47	57.02 81	57.89 113	72.25 50	80.30 66	81.57 51	89.72 8	93.04 54

TPM-MVS					94.34 2	93.91 5	89.34 3			75.49 19	82.52 21	83.34 11	83.53 4			89.62 9	90.78 90
Ray Leroy Khuboni and Hongjun Xu: Textureless Resilient Propagation Matching in Multiple View Stereosis (TPM-MVS). SATNAC 2025
baseline1		71.47 95	72.02 98	70.82 92	80.56 74	84.51 104	76.61 86	66.93 51	56.22 135	48.66 131	55.40 91	60.43 92	62.55 126	83.35 30	80.99 64	89.60 10	83.28 169

MS-PatchMatch		70.34 104	69.00 121	71.91 87	85.20 53	85.35 97	77.84 74	61.77 112	58.01 122	55.40 103	41.26 169	58.34 108	61.69 130	81.70 52	78.29 99	89.56 11	80.02 192

E3new		74.17 70	73.83 81	74.57 59	79.40 82	88.76 45	78.30 67	63.89 78	61.21 103	64.38 53	55.65 89	57.34 117	71.87 56	79.73 74	81.28 58	89.55 12	92.86 57

E3		74.17 70	73.83 81	74.57 59	79.40 82	88.76 45	78.30 67	63.89 78	61.22 102	64.40 52	55.64 90	57.35 116	71.86 57	79.73 74	81.27 59	89.55 12	92.86 57

MGCNet		83.82 18	86.88 17	80.26 22	88.48 33	93.17 8	82.93 33	67.66 46	88.28 16	74.90 20	77.08 34	80.93 22	78.09 18	85.83 14	85.88 6	89.53 14	96.96 10

dmvs_re		67.60 124	67.21 139	68.06 116	74.07 138	79.01 154	73.31 114	68.74 40	58.27 118	42.07 164	49.72 126	43.96 174	60.66 136	76.79 113	78.04 105	89.51 15	84.69 154

CANet		80.90 29	82.93 30	78.53 31	86.83 46	92.26 13	81.19 44	66.95 50	81.60 36	69.90 34	66.93 49	74.80 33	76.79 23	84.68 19	84.77 17	89.50 16	95.50 20

viewmanbaseed2359cas		74.53 66	74.69 75	74.35 61	79.37 84	88.90 43	78.96 57	64.07 73	63.67 89	62.19 67	56.95 82	58.42 106	72.04 55	80.08 67	81.92 42	89.47 17	92.91 56

QAPM		77.50 46	77.43 54	77.59 36	91.52 15	92.00 15	81.41 41	70.63 28	66.22 77	58.05 92	54.70 93	71.79 45	74.49 34	82.46 38	82.04 38	89.46 18	92.79 61

E5new		73.48 77	72.84 90	74.23 63	79.06 89	88.52 49	78.32 64	63.99 75	58.33 116	63.34 58	54.07 102	56.89 120	71.29 65	78.99 82	80.82 71	89.35 19	92.26 68

E5		73.48 77	72.84 90	74.23 63	79.06 89	88.52 49	78.32 64	63.99 75	58.33 116	63.34 58	54.07 102	56.89 120	71.29 65	78.99 82	80.82 71	89.35 19	92.26 68

E4		73.32 80	72.68 92	74.06 66	79.06 89	88.47 52	77.98 72	63.57 85	57.73 125	63.18 60	53.48 105	56.74 123	71.26 67	78.95 84	80.84 69	89.30 21	92.55 62

E6new		72.71 87	72.05 96	73.49 69	79.01 93	88.31 58	77.06 82	62.71 102	56.63 130	62.00 69	52.31 112	55.75 133	70.93 69	78.51 92	80.72 74	89.20 22	92.14 72

E6		72.71 87	72.05 96	73.49 69	79.01 93	88.31 58	77.06 82	62.71 102	56.63 130	62.00 69	52.31 112	55.75 133	70.93 69	78.51 92	80.72 74	89.20 22	92.14 72

DELS-MVS		79.49 32	79.84 41	79.08 29	88.26 39	92.49 10	84.12 27	70.63 28	65.27 85	69.60 37	61.29 66	66.50 61	72.75 45	88.07 3	88.03 2	89.13 24	97.22 6
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
viewmacassd2359aftdt		73.00 82	72.63 93	73.44 71	78.70 98	88.45 53	78.52 59	63.49 86	57.74 124	60.15 87	52.57 111	57.01 119	70.69 73	78.85 88	81.29 57	89.10 25	92.48 64

casdiffmvs		75.20 61	75.69 68	74.63 58	79.26 88	89.07 39	78.47 61	63.59 84	67.05 74	63.79 55	55.72 88	60.32 93	73.58 37	82.16 44	81.78 44	89.08 26	93.72 45
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
MSLP-MVS++		78.57 38	77.33 55	80.02 24	88.39 36	84.79 102	84.62 24	66.17 57	75.96 54	78.40 11	61.59 64	71.47 46	73.54 39	78.43 94	78.88 93	88.97 27	90.18 101

baseline2		71.22 99	73.01 88	69.13 104	75.76 128	86.34 89	71.23 134	62.78 98	62.62 95	52.85 113	57.32 79	54.31 143	63.27 122	79.74 73	79.31 89	88.89 28	91.43 80

viewdifsd2359ckpt13		74.11 72	74.06 78	74.18 65	79.34 85	89.07 39	78.31 66	64.25 69	62.52 97	62.06 68	55.80 86	56.70 124	72.29 49	80.35 65	81.47 53	88.80 29	92.47 66

CNVR-MVS		85.96 9	87.58 12	84.06 9	92.58 5	92.40 12	87.62 12	77.77 4	88.44 15	75.93 17	79.49 27	81.97 19	81.65 6	87.04 6	86.58 4	88.79 30	97.18 7

IB-MVS	64.48 11	69.02 113	68.97 122	69.09 107	81.75 63	89.01 41	64.50 177	64.91 65	56.65 129	62.59 65	47.89 134	45.23 171	51.99 181	69.18 194	81.88 43	88.77 31	92.93 55
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
SF-MVS		87.30 7	88.71 7	85.64 3	94.57 1	94.55 4	91.01 1	79.94 1	89.15 13	79.85 8	92.37 4	83.29 12	79.75 10	83.52 27	82.72 34	88.75 32	95.37 25

SED-MVS		88.94 1	90.98 1	86.56 1	92.53 7	95.09 1	88.55 6	76.83 6	94.16 1	86.57 2	90.85 6	87.07 1	86.18 1	86.36 7	85.08 13	88.67 33	98.21 3

GG-mvs-BLEND		54.54 213	77.58 53	27.67 245	0.03 260	90.09 30	77.20 81	0.02 256	66.83 76	0.05 261	59.90 71	73.33 37	0.04 256	78.40 95	79.30 90	88.65 34	95.20 27

FMVSNet3		70.41 102	71.89 101	68.68 110	70.89 160	79.42 152	75.63 90	60.97 123	65.32 82	51.06 119	47.37 138	62.05 77	64.90 111	82.49 37	82.27 37	88.64 35	84.34 158

test-LLR		68.23 120	71.61 104	64.28 144	71.37 155	81.32 133	63.98 182	61.03 121	58.62 114	42.96 158	52.74 108	61.65 81	57.74 161	75.64 125	78.09 103	88.61 36	93.21 48

TESTMET0.1,1		67.38 129	71.61 104	62.45 160	66.05 190	81.32 133	63.98 182	55.36 184	58.62 114	42.96 158	52.74 108	61.65 81	57.74 161	75.64 125	78.09 103	88.61 36	93.21 48

3Dnovator	70.49 5	78.42 39	76.77 60	80.35 21	91.43 16	90.27 26	81.84 38	70.79 27	72.10 61	71.95 26	50.02 125	67.86 58	77.47 21	82.89 33	84.24 20	88.61 36	89.99 104

viewdifsd2359ckpt07		72.78 85	72.24 95	73.41 74	78.58 101	88.14 62	76.95 84	63.73 82	57.28 126	63.47 57	54.45 98	56.62 125	69.16 89	78.86 87	79.98 81	88.58 39	90.33 98

MVSTER		76.92 50	79.92 40	73.42 73	74.98 134	82.97 116	78.15 70	63.41 87	78.02 48	64.41 51	67.54 47	72.80 38	71.05 68	83.29 31	83.73 23	88.53 40	91.12 85

DVP-MVS		88.07 2	90.73 2	84.97 5	91.98 10	95.01 2	87.86 11	76.88 5	93.90 2	85.15 3	90.11 8	86.90 2	79.46 13	86.26 10	84.67 18	88.50 41	98.25 2
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
NCCC		84.16 17	85.46 23	82.64 12	92.34 8	90.57 24	86.57 15	76.51 8	86.85 20	72.91 25	77.20 33	78.69 28	79.09 16	84.64 20	84.88 16	88.44 42	95.41 23

CLD-MVS		77.36 48	77.29 56	77.45 37	82.21 60	88.11 63	81.92 37	68.96 38	77.97 49	69.62 36	62.08 62	59.44 100	73.57 38	81.75 51	81.27 59	88.41 43	90.39 97
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
DVP-MVS++		87.98 3	89.76 6	85.89 2	92.57 6	94.57 3	88.34 7	76.61 7	92.40 7	83.40 4	89.26 11	85.57 6	86.04 2	86.24 11	84.89 15	88.39 44	95.42 22

MSP-MVS		87.87 4	90.57 3	84.73 6	89.38 28	91.60 18	88.24 9	74.15 13	93.55 3	82.28 5	94.99 1	83.21 13	85.96 3	87.67 4	84.67 18	88.32 45	98.29 1
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
HyFIR lowres test		68.39 118	68.28 130	68.52 112	80.85 69	88.11 63	71.08 138	58.09 143	54.87 147	47.80 136	27.55 230	55.80 132	64.97 110	79.11 80	79.14 91	88.31 46	93.35 47

EPMVS		66.21 135	67.49 136	64.73 138	75.81 127	84.20 110	68.94 153	44.37 229	61.55 101	48.07 135	49.21 129	54.87 141	62.88 123	71.82 168	71.40 184	88.28 47	79.37 195

MVS_111021_HR		77.42 47	78.40 50	76.28 41	86.95 44	90.68 22	77.41 78	70.56 31	66.21 79	62.48 66	66.17 53	63.98 72	72.08 54	82.87 34	83.15 29	88.24 48	95.71 17

PVSNet_BlendedMVS		76.84 51	78.47 48	74.95 53	82.37 58	89.90 31	75.45 94	65.45 62	74.99 57	70.66 32	63.07 59	58.27 109	67.60 97	84.24 22	81.70 47	88.18 49	97.10 8

PVSNet_Blended		76.84 51	78.47 48	74.95 53	82.37 58	89.90 31	75.45 94	65.45 62	74.99 57	70.66 32	63.07 59	58.27 109	67.60 97	84.24 22	81.70 47	88.18 49	97.10 8

TSAR-MVS + GP.		82.27 25	85.98 21	77.94 33	80.72 72	88.25 60	81.12 45	67.71 45	87.10 18	73.31 23	85.23 16	83.68 10	76.64 24	80.43 63	81.47 53	88.15 51	95.66 18

DeepC-MVS_fast	75.41 2	81.69 26	82.10 33	81.20 18	91.04 18	87.81 68	83.42 28	74.04 14	83.77 27	71.09 29	66.88 50	72.44 39	79.48 12	85.08 15	84.97 14	88.12 52	93.78 43
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
0.4-1-1-0.2		70.06 106	70.92 110	69.06 108	67.65 179	84.98 101	74.41 110	62.76 99	63.03 94	53.95 108	51.07 120	60.32 93	67.52 102	73.73 148	74.85 138	88.04 53	88.45 124

casdiffmvs_mvg		75.57 58	76.04 65	75.02 52	80.48 75	89.31 36	80.79 49	64.04 74	66.95 75	63.87 54	57.52 78	61.33 85	72.90 43	82.01 48	81.99 41	88.03 54	93.16 52
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
test2506		69.26 107	70.79 111	67.48 122	78.64 99	86.40 87	72.22 121	62.75 100	58.05 120	45.24 143	50.76 121	54.93 140	58.05 156	79.82 71	79.70 83	87.96 55	85.90 145

ECVR-MVS		67.93 123	68.49 125	67.28 125	78.64 99	86.40 87	72.22 121	62.75 100	58.05 120	44.06 151	40.92 173	48.20 163	58.05 156	79.82 71	79.70 83	87.96 55	86.32 140

viewdifsd2359ckpt09		73.89 75	73.57 83	74.26 62	78.54 102	88.37 55	78.34 63	63.79 80	63.31 93	64.90 49	57.29 80	56.53 126	72.15 53	79.12 79	77.91 107	87.83 57	92.48 64

EPNet		79.28 37	82.25 31	75.83 44	88.31 38	90.14 28	79.43 55	68.07 43	81.76 35	61.26 78	77.26 32	70.08 51	70.06 78	82.43 40	82.00 40	87.82 58	92.09 74
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
SteuartSystems-ACMMP		82.51 23	85.35 24	79.20 27	90.25 19	89.39 35	84.79 23	70.95 26	82.86 29	68.32 39	86.44 15	77.19 29	73.07 41	83.63 26	83.64 24	87.82 58	94.34 33
Skip Steuart: Steuart Systems R&D Blog.
diffmvs		74.32 67	75.42 69	73.04 76	75.60 130	87.27 72	78.20 69	62.96 92	68.66 73	61.89 71	59.79 72	59.84 97	71.80 58	78.30 97	79.87 82	87.80 60	94.23 35
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
tpmrst		67.15 131	68.12 132	66.03 129	76.21 124	80.98 136	71.27 133	45.05 225	60.69 107	50.63 123	46.95 146	54.15 145	65.30 108	71.80 171	71.77 177	87.72 61	90.48 95

diffmvs_AUTHOR		73.73 76	74.73 73	72.56 82	75.05 133	87.15 75	77.82 75	62.29 105	66.22 77	61.10 80	57.92 76	59.72 98	71.43 62	78.25 99	79.68 85	87.71 62	94.17 37

APDe-MVS		86.37 8	88.41 9	84.00 10	91.43 16	91.83 17	88.34 7	74.67 11	91.19 8	81.76 6	91.13 5	81.94 20	80.07 9	83.38 28	82.58 36	87.69 63	96.78 11
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
ME-MVS		87.83 5	89.84 5	85.49 4	91.74 12	92.20 14	89.01 4	74.91 10	92.47 6	88.26 1	94.60 2	85.70 5	81.31 8	83.94 25	83.57 27	87.68 64	96.41 14

CostFormer		72.18 91	73.90 80	70.18 97	79.47 80	86.19 93	76.94 85	48.62 214	66.07 81	60.40 86	54.14 100	65.82 62	67.98 94	75.84 122	76.41 120	87.67 65	92.83 60

DPE-MVS		87.60 6	90.44 4	84.29 8	92.09 9	93.44 6	88.69 5	75.11 9	93.06 5	80.80 7	94.23 3	86.70 3	81.44 7	84.84 18	83.52 28	87.64 66	97.28 5
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
ETV-MVS		76.25 53	80.22 39	71.63 89	78.23 104	87.95 67	72.75 116	60.27 133	77.50 52	57.73 93	71.53 38	66.60 60	73.16 40	80.99 58	81.23 61	87.63 67	95.73 16

CANet_DTU		72.84 84	76.63 62	68.43 114	76.81 119	86.62 83	75.54 93	54.71 193	72.06 62	43.54 153	67.11 48	58.46 104	72.40 48	81.13 57	80.82 71	87.57 68	90.21 100

EC-MVSNet		76.05 55	78.87 45	72.77 78	78.87 97	86.63 81	77.50 77	57.04 166	75.34 55	61.68 75	64.20 56	69.56 53	73.96 35	82.12 45	80.65 76	87.57 68	93.57 46

OpenMVS	67.62 8	74.92 64	73.91 79	76.09 43	90.10 22	90.38 25	78.01 71	66.35 55	66.09 80	62.80 62	46.33 150	64.55 70	71.77 59	79.92 70	80.88 68	87.52 70	89.20 113

usedtu_dtu_shiyan1		62.43 164	64.08 157	60.50 172	59.68 218	80.58 141	66.18 174	61.75 114	53.08 154	36.05 199	36.33 200	41.74 179	51.86 182	77.70 101	77.95 106	87.47 71	81.17 188

test1111		66.72 133	67.80 133	65.45 132	77.42 115	86.63 81	69.69 148	62.98 91	55.29 141	39.47 174	40.12 178	47.11 166	55.70 168	79.96 69	80.00 80	87.47 71	85.49 150

GBi-Net		69.21 108	70.40 113	67.81 118	69.49 165	78.65 158	74.54 101	60.97 123	65.32 82	51.06 119	47.37 138	62.05 77	63.43 119	77.49 104	78.22 100	87.37 73	83.73 161

test1		69.21 108	70.40 113	67.81 118	69.49 165	78.65 158	74.54 101	60.97 123	65.32 82	51.06 119	47.37 138	62.05 77	63.43 119	77.49 104	78.22 100	87.37 73	83.73 161

FMVSNet2		68.06 121	68.57 124	67.45 123	69.49 165	78.65 158	74.54 101	60.23 135	56.29 134	49.64 129	42.13 165	57.08 118	63.43 119	81.15 56	80.99 64	87.37 73	83.73 161

sasdasda		77.65 43	79.59 42	75.39 46	81.52 64	89.83 33	81.32 42	60.74 127	80.05 41	66.72 41	68.43 43	65.09 64	74.72 32	78.87 85	82.73 32	87.32 76	92.16 70

canonicalmvs		77.65 43	79.59 42	75.39 46	81.52 64	89.83 33	81.32 42	60.74 127	80.05 41	66.72 41	68.43 43	65.09 64	74.72 32	78.87 85	82.73 32	87.32 76	92.16 70

HPM-MVS++		85.64 11	88.43 8	82.39 13	92.65 4	90.24 27	85.83 18	74.21 12	90.68 10	75.63 18	86.77 14	84.15 9	78.68 17	86.33 8	85.26 10	87.32 76	95.60 19

ET-MVSNet_ETH3D		71.38 97	74.70 74	67.51 121	51.61 233	88.06 65	77.29 79	60.95 126	63.61 90	48.36 133	66.60 51	60.67 88	79.55 11	73.56 149	80.58 77	87.30 79	89.80 106

CSCG		82.90 22	84.52 25	81.02 19	91.85 11	93.43 7	87.14 13	74.01 15	81.96 33	76.14 15	70.84 39	82.49 15	69.71 80	82.32 42	85.18 12	87.26 80	95.40 24

SMA-MVS		85.24 13	88.27 10	81.72 16	91.74 12	90.71 21	86.71 14	73.16 20	90.56 11	74.33 21	83.07 19	85.88 4	77.16 22	86.28 9	85.58 7	87.23 81	95.77 15
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
CDPH-MVS		79.39 36	82.13 32	76.19 42	89.22 31	88.34 56	84.20 26	71.00 25	79.67 45	56.97 97	77.77 30	72.24 43	68.50 93	81.33 53	82.74 31	87.23 81	92.84 59

EIA-MVS		73.48 77	76.05 64	70.47 95	78.12 105	87.21 73	71.78 126	60.63 129	69.66 69	55.56 102	64.86 55	60.69 87	69.53 83	77.35 108	78.59 94	87.22 83	94.01 40

test-mter		64.06 152	69.24 119	58.01 188	59.07 220	77.40 171	59.13 209	48.11 217	55.64 140	39.18 178	51.56 119	58.54 102	55.38 170	73.52 150	76.00 125	87.22 83	92.05 76

train_agg		83.35 20	86.93 16	79.17 28	89.70 25	88.41 54	85.60 21	72.89 22	86.31 21	66.58 43	90.48 7	82.24 17	73.06 42	83.10 32	82.64 35	87.21 85	95.30 26

FA-MVS(training)		70.24 105	71.77 102	68.45 113	77.52 113	86.03 94	73.33 113	49.12 213	63.55 91	55.77 99	48.91 130	56.26 128	67.78 96	77.60 103	79.62 86	87.19 86	90.40 96

DI_MVS_pp		73.94 74	74.85 72	72.88 77	76.57 122	86.80 78	80.41 50	61.47 116	62.35 99	59.44 89	47.91 133	68.12 55	72.24 51	82.84 35	81.50 52	87.15 87	94.42 32

MAR-MVS		77.19 49	78.37 51	75.81 45	89.87 23	90.58 23	79.33 56	65.56 61	77.62 51	58.33 91	59.24 74	67.98 56	74.83 29	82.37 41	83.12 30	86.95 88	87.67 130
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
baseline		72.89 83	74.46 77	71.07 90	75.99 126	87.50 70	74.57 100	60.49 130	70.72 65	57.60 94	60.63 69	60.97 86	70.79 72	75.27 128	76.33 121	86.94 89	89.79 107

APD-MVS		84.83 14	87.00 13	82.30 14	89.61 26	89.21 37	86.51 16	73.64 17	90.98 9	77.99 13	89.89 9	80.04 26	79.18 15	82.00 49	81.37 55	86.88 90	95.49 21
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
MIMVSNet		57.78 199	59.71 194	55.53 206	54.79 228	77.10 174	63.89 184	45.02 226	46.59 178	36.79 194	28.36 228	40.77 187	45.84 208	74.97 130	76.58 117	86.87 91	73.60 212

GeoE		68.96 114	69.32 118	68.54 111	76.61 121	83.12 115	71.78 126	56.87 168	60.21 109	54.86 106	45.95 151	54.79 142	64.27 115	74.59 134	75.54 132	86.84 92	91.01 87

DeepC-MVS	74.46 3	80.30 31	81.05 36	79.42 25	87.42 42	88.50 51	83.23 29	73.27 19	82.78 30	71.01 30	62.86 61	69.93 52	74.80 30	84.30 21	84.20 21	86.79 93	94.77 28
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
MGCFI-Net		74.26 68	78.69 46	69.10 105	80.64 73	87.32 71	73.21 115	59.20 136	79.76 44	50.18 127	68.10 45	64.86 69	64.65 114	78.28 98	80.83 70	86.69 94	91.69 79

TSAR-MVS + MP.		84.39 15	86.58 19	81.83 15	88.09 40	86.47 85	85.63 20	73.62 18	90.13 12	79.24 10	89.67 10	82.99 14	77.72 20	81.22 54	80.92 67	86.68 95	94.66 30
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
viewmambaseed2359dif		72.54 90	72.88 89	72.13 84	74.78 136	86.45 86	77.24 80	61.65 115	62.61 96	61.83 72	55.85 84	57.51 115	70.64 75	75.71 123	77.90 108	86.65 96	94.16 38

ACMMP_NAP		83.54 19	86.37 20	80.25 23	89.57 27	90.10 29	85.27 22	71.66 24	87.38 17	73.08 24	84.23 18	80.16 25	75.31 26	84.85 17	83.64 24	86.57 97	94.21 36

tpm		64.85 145	66.02 149	63.48 150	74.52 137	78.38 161	70.98 140	44.99 227	51.61 158	43.28 157	47.66 136	53.18 149	60.57 137	70.58 182	71.30 187	86.54 98	89.45 111

SPE-MVS-test		75.09 63	77.84 52	71.87 88	79.27 87	86.92 77	70.53 144	60.36 131	75.13 56	63.13 61	67.92 46	65.08 66	71.43 62	78.15 100	78.51 97	86.53 99	93.16 52

PVSNet_Blended_VisFu		71.76 94	73.54 85	69.69 100	79.01 93	87.16 74	72.05 123	61.80 111	56.46 133	59.66 88	53.88 104	62.48 75	59.08 150	81.17 55	78.90 92	86.53 99	94.74 29

Fast-Effi-MVS+		67.59 125	67.56 135	67.62 120	73.67 141	81.14 135	71.12 137	54.79 192	58.88 113	50.61 124	46.70 148	47.05 167	69.12 90	76.06 120	76.44 119	86.43 101	86.65 135

CS-MVS		75.84 56	78.61 47	72.61 81	79.03 92	86.74 79	74.43 108	60.27 133	74.15 60	62.78 63	66.26 52	64.25 71	72.81 44	83.36 29	81.69 49	86.32 102	93.85 42

GA-MVS		64.55 148	65.76 151	63.12 152	69.68 164	81.56 129	69.59 149	58.16 142	45.23 184	35.58 202	47.01 145	41.82 178	59.41 146	79.62 76	78.54 95	86.32 102	86.56 136

HFP-MVS		82.48 24	84.12 26	80.56 20	90.15 20	87.55 69	84.28 25	69.67 33	85.22 24	77.95 14	84.69 17	75.94 32	75.04 28	81.85 50	81.17 62	86.30 104	92.40 67

HQP-MVS		78.26 40	80.91 37	75.17 50	85.67 51	84.33 108	83.01 31	69.38 34	79.88 43	55.83 98	79.85 26	64.90 68	70.81 71	82.46 38	81.78 44	86.30 104	93.18 51

Effi-MVS+		70.42 100	71.23 106	69.47 101	78.04 106	85.24 98	75.57 92	58.88 137	59.56 111	48.47 132	52.73 110	54.94 139	69.69 81	78.34 96	77.06 113	86.18 106	90.73 94

PGM-MVS		79.42 35	81.84 34	76.60 40	88.38 37	86.69 80	82.97 32	65.75 59	80.39 40	64.94 48	81.95 24	72.11 44	71.41 64	80.45 62	80.55 78	86.18 106	90.76 93

PHI-MVS		79.43 34	84.06 27	74.04 67	86.15 49	91.57 19	80.85 48	68.90 39	82.22 32	51.81 117	78.10 29	74.28 34	70.39 77	84.01 24	84.00 22	86.14 108	94.24 34

ACMMPR		80.62 30	82.98 29	77.87 34	88.41 35	87.05 76	83.02 30	69.18 36	83.91 26	68.35 38	82.89 20	73.64 36	72.16 52	80.78 60	81.13 63	86.10 109	91.43 80

PatchmatchNet		65.43 142	67.71 134	62.78 156	73.49 143	82.83 117	66.42 172	45.40 224	60.40 108	45.27 142	49.22 128	57.60 114	60.01 142	70.61 180	71.38 185	86.08 110	81.91 185
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
v2v482		63.68 155	62.85 170	64.65 139	68.01 175	80.46 143	71.90 124	57.60 152	44.26 186	42.82 160	39.80 180	38.62 200	61.56 131	73.06 154	74.86 137	86.03 111	88.90 118

FC-MVSNet-train		68.83 115	68.29 128	69.47 101	78.35 103	79.94 146	64.72 176	66.38 54	54.96 144	54.51 107	56.75 83	47.91 165	66.91 104	75.57 127	75.75 127	85.92 112	87.12 132

v8		63.44 157	62.58 172	64.43 141	68.28 173	78.07 163	71.82 125	54.85 190	46.70 177	45.20 144	39.40 181	40.91 185	60.54 138	72.85 158	74.39 146	85.92 112	85.76 147

3Dnovator+	70.16 6	77.87 42	77.29 56	78.55 30	89.25 30	88.32 57	80.09 51	67.95 44	74.89 59	71.83 27	52.05 117	70.68 49	76.27 25	82.27 43	82.04 38	85.92 112	90.77 92

MP-MVS		80.94 28	83.49 28	77.96 32	88.48 33	88.16 61	82.82 34	69.34 35	80.79 39	69.67 35	82.35 22	77.13 30	71.60 61	80.97 59	80.96 66	85.87 115	94.06 39
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
blend_shiyan4		66.60 134	67.24 138	65.85 130	68.02 174	76.25 180	75.94 87	58.03 144	64.52 88	53.78 110	52.14 114	60.47 89	53.51 176	67.10 201	66.76 208	85.79 116	83.46 165

v10		63.00 160	62.22 175	63.90 148	67.88 177	77.78 167	71.59 130	54.34 194	45.37 183	42.76 161	38.53 183	38.93 198	61.05 135	74.39 138	74.52 144	85.75 117	86.04 142

ACMMP		77.61 45	79.59 42	75.30 49	85.87 50	85.58 96	81.42 40	67.38 49	79.38 46	62.61 64	78.53 28	65.79 63	68.80 92	78.56 91	78.50 98	85.75 117	90.80 89
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
OPM-MVS		72.74 86	70.93 109	74.85 56	85.30 52	84.34 107	82.82 34	69.79 32	49.96 163	55.39 104	54.09 101	60.14 96	70.04 79	80.38 64	79.43 88	85.74 119	88.20 126
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
thres100view900		67.14 132	66.09 148	68.38 115	77.70 108	83.84 112	74.52 104	66.33 56	49.16 167	43.40 155	43.24 154	41.34 180	62.59 125	79.31 78	75.92 126	85.73 120	89.81 105

CP-MVS		79.44 33	81.51 35	77.02 38	86.95 44	85.96 95	82.00 36	68.44 42	81.82 34	67.39 40	77.43 31	73.68 35	71.62 60	79.56 77	79.58 87	85.73 120	92.51 63

pmmvs5		59.72 186	60.24 190	59.11 184	62.77 207	77.33 173	63.17 190	54.00 197	40.21 203	37.23 191	40.41 175	35.99 213	51.75 183	72.55 163	72.74 169	85.72 122	82.45 181

EPNet_dtu		66.17 136	70.13 116	61.54 167	81.04 67	77.39 172	68.87 154	62.50 104	69.78 67	33.51 210	63.77 58	56.22 129	37.65 223	72.20 164	72.18 176	85.69 123	79.38 194
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
XVS					82.43 56	86.27 90	75.70 88			61.07 81		72.27 40				85.67 124

X-MVStestdata					82.43 56	86.27 90	75.70 88			61.07 81		72.27 40				85.67 124

PatchT		60.46 183	63.85 159	56.51 203	65.95 192	75.68 186	47.34 230	41.39 240	53.89 153	41.40 165	37.84 189	50.30 159	57.29 164	72.76 159	73.27 161	85.67 124	83.23 170

X-MVS		78.16 41	80.55 38	75.38 48	87.99 41	86.27 90	81.05 46	68.98 37	78.33 47	61.07 81	75.25 36	72.27 40	67.52 102	80.03 68	80.52 79	85.66 127	91.20 84

v1144		63.00 160	62.39 174	63.70 149	67.72 178	80.27 144	71.23 134	56.40 169	42.51 191	40.81 170	38.12 188	37.73 201	60.42 140	74.46 136	74.55 143	85.64 128	89.12 114

v144192		62.05 172	61.46 181	62.73 159	66.59 188	79.87 147	69.30 151	55.88 174	41.50 198	39.41 176	37.23 191	36.45 209	59.62 144	72.69 161	73.51 154	85.61 129	88.93 116

SD-MVS		84.31 16	86.96 15	81.22 17	88.98 32	88.68 47	85.65 19	73.85 16	89.09 14	79.63 9	87.34 13	84.84 7	73.71 36	82.66 36	81.60 50	85.48 130	94.51 31
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
wanda-best-256-512		57.69 200	57.90 203	57.46 195	48.58 238	75.44 189	63.15 191	57.47 155	39.27 208	38.64 181	34.66 210	40.34 191	51.44 185	66.38 203	66.54 210	85.46 131	82.64 174

FE-blended-shiyan7		57.69 200	57.90 203	57.46 195	48.58 238	75.44 189	63.15 191	57.47 155	39.27 208	38.64 181	34.66 210	40.34 191	51.44 185	66.38 203	66.54 210	85.46 131	82.64 174

usedtu_blend_shiyan5		62.84 163	63.39 162	62.21 163	48.58 238	75.44 189	74.43 108	57.47 155	39.26 211	53.78 110	52.14 114	60.47 89	53.51 176	66.38 203	66.54 210	85.46 131	83.46 165

FE-MVSNET3		61.91 174	63.26 163	60.33 174	48.58 238	75.44 189	63.15 191	57.47 155	39.27 208	53.78 110	52.14 114	60.47 89	53.51 176	66.38 203	66.54 210	85.46 131	82.59 176

blended_shiyan8		57.49 204	57.71 206	57.24 198	48.52 242	75.34 193	62.85 195	57.32 162	38.77 213	38.43 184	34.41 213	40.31 193	50.92 190	66.25 208	66.37 214	85.37 135	82.55 178

blended_shiyan6		57.50 203	57.73 205	57.23 199	48.51 243	75.34 193	62.85 195	57.33 160	38.78 212	38.38 185	34.46 212	40.29 194	50.91 191	66.27 207	66.37 214	85.37 135	82.59 176

v1921920		61.66 176	61.10 184	62.31 161	66.32 189	79.57 150	68.41 156	55.49 182	41.03 199	38.69 180	36.64 199	35.27 217	59.60 145	73.23 152	73.41 156	85.37 135	88.51 123

UniMVSNet_NR-MVSNet		62.30 167	63.51 161	60.89 169	69.48 168	77.83 166	64.07 180	63.94 77	50.03 162	31.17 215	44.82 152	41.12 183	51.37 187	71.02 176	74.81 139	85.30 138	84.95 152

thres400		65.18 144	64.44 156	66.04 128	76.40 123	82.63 120	71.52 131	64.27 68	44.93 185	40.69 171	41.86 166	40.79 186	58.12 154	77.67 102	74.64 140	85.26 139	88.56 121

v1192		62.25 168	61.64 179	62.96 153	66.88 184	79.72 148	69.96 146	55.77 176	41.58 196	39.42 175	37.05 193	35.96 214	60.50 139	74.30 141	74.09 148	85.24 140	88.76 119

NR-MVSNet		61.08 180	62.09 177	59.90 176	71.96 152	75.87 182	63.60 186	61.96 107	49.31 165	27.95 220	42.76 156	33.85 224	48.82 196	74.35 139	74.05 150	85.13 141	84.45 156

v1240		61.09 179	60.55 188	61.72 166	65.92 193	79.28 153	67.16 166	54.91 189	39.79 205	38.10 187	36.08 202	34.64 219	59.15 149	72.86 157	73.36 158	85.10 142	87.84 128

test0.0.03 1		57.35 205	59.89 193	54.38 212	71.37 155	73.45 204	52.71 221	61.03 121	46.11 180	26.33 224	41.73 167	44.08 173	29.72 228	71.43 175	70.90 188	85.10 142	71.56 221

V42		62.86 162	62.97 167	62.74 158	60.84 213	78.99 156	71.46 132	57.13 165	46.85 175	44.28 150	38.87 182	40.73 188	57.63 163	72.60 162	74.14 147	85.09 144	88.63 120

v148		62.00 173	61.19 183	62.96 153	67.46 182	79.49 151	67.87 158	57.66 151	42.30 192	45.02 146	38.20 187	38.89 199	54.77 172	69.83 190	72.60 172	84.96 145	87.01 133

Baseline_NR-MVSNet		59.47 188	60.28 189	58.54 187	66.69 185	73.90 202	61.63 201	62.90 96	49.15 169	26.87 222	35.18 207	37.62 202	48.20 197	69.67 191	73.61 153	84.92 146	82.82 173

FMVSNet5		58.86 192	60.24 190	57.25 197	52.66 232	66.25 227	63.77 185	52.86 205	57.85 123	37.92 189	36.12 201	52.22 154	51.37 187	70.88 178	71.43 183	84.92 146	66.91 232

TranMVSNet+NR-MVSNet		60.38 184	61.30 182	59.30 182	68.34 172	75.57 188	63.38 189	63.78 81	46.74 176	27.73 221	42.56 160	36.84 207	47.66 199	70.36 185	74.59 142	84.91 148	82.46 180

thres600view7		63.77 154	63.14 165	64.51 140	75.49 131	81.61 126	69.59 149	62.95 93	43.96 188	38.90 179	41.09 170	40.24 195	55.25 171	76.24 117	71.54 179	84.89 149	87.30 131

thres200		65.58 139	64.74 154	66.56 127	77.52 113	81.61 126	73.44 112	62.95 93	46.23 179	42.45 162	42.76 156	41.18 182	58.12 154	76.24 117	75.59 130	84.89 149	89.58 108

tfpn200view9		65.90 138	64.96 152	67.00 126	77.70 108	81.58 128	71.71 129	62.94 95	49.16 167	43.40 155	43.24 154	41.34 180	61.42 132	76.24 117	74.63 141	84.84 151	88.52 122

Fast-Effi-MVS+-dtu		63.05 159	64.72 155	61.11 168	71.21 158	76.81 176	70.72 142	43.13 235	52.51 157	35.34 203	46.55 149	46.36 168	61.40 133	71.57 174	71.44 182	84.84 151	87.79 129

EG-PatchMatch MVS		58.73 194	58.03 201	59.55 179	72.32 149	80.49 142	63.44 188	55.55 180	32.49 232	38.31 186	28.87 227	37.22 205	42.84 215	74.30 141	75.70 128	84.84 151	77.14 201

IterMVS-LS		66.08 137	66.56 144	65.51 131	73.67 141	74.88 196	70.89 141	53.55 200	50.42 161	48.32 134	50.59 123	55.66 135	61.83 129	73.93 143	74.42 145	84.82 154	86.01 143
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
LGP-MVS_train		72.02 93	73.18 87	70.67 94	82.13 61	80.26 145	79.58 54	63.04 90	70.09 66	51.98 115	65.06 54	55.62 136	62.49 127	75.97 121	76.32 122	84.80 155	88.93 116

PCF-MVS	70.85 4	75.73 57	76.55 63	74.78 57	83.67 54	88.04 66	81.47 39	70.62 30	69.24 72	57.52 95	60.59 70	69.18 54	70.65 74	77.11 109	77.65 109	84.75 156	94.01 40
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
IS_MVSNet		67.29 130	71.98 99	61.82 165	76.92 118	84.32 109	65.90 175	58.22 141	55.75 139	39.22 177	54.51 96	62.47 76	45.99 207	78.83 89	78.52 96	84.70 157	89.47 110

AdaColmap		76.23 54	73.55 84	79.35 26	89.38 28	85.00 100	79.99 53	73.04 21	76.60 53	71.17 28	55.18 92	57.99 111	77.87 19	76.82 112	76.82 115	84.67 158	86.45 137

viewdifsd2359ckpt11		69.15 110	68.30 127	70.14 98	73.44 145	82.79 118	72.24 119	61.20 119	54.59 150	61.70 74	53.16 106	52.89 152	67.57 100	71.81 170	72.73 170	84.66 159	90.10 102

viewmsd2359difaftdt		69.14 111	68.29 128	70.13 99	73.44 145	82.79 118	72.24 119	61.20 119	54.60 149	61.68 75	53.16 106	52.87 153	67.58 99	71.82 168	72.73 170	84.66 159	90.10 102

thisisatest0530		68.38 119	70.98 108	65.35 133	72.61 148	84.42 105	68.21 157	57.98 145	59.77 110	50.80 122	54.63 94	58.48 103	57.92 158	76.99 111	77.47 110	84.60 161	85.07 151

FMVSNet1		63.48 156	63.07 166	63.97 146	65.31 195	76.37 179	71.77 128	57.90 148	43.32 190	45.66 140	35.06 208	49.43 160	58.57 152	77.49 104	78.22 100	84.59 162	81.60 187

tfpnnormal		58.97 191	56.48 210	61.89 164	71.27 157	76.21 181	66.65 170	61.76 113	32.90 230	36.41 196	27.83 229	29.14 237	50.64 193	73.06 154	73.05 165	84.58 163	83.15 172

Vis-MVSNet		65.53 141	69.83 117	60.52 171	70.80 161	84.59 103	66.37 173	55.47 183	48.40 170	40.62 172	57.67 77	58.43 105	45.37 210	77.49 104	76.24 123	84.47 164	85.99 144
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
ACMP	68.86 7	72.15 92	72.25 94	72.03 85	80.96 68	80.87 138	77.93 73	64.13 71	69.29 70	60.79 84	64.04 57	53.54 148	63.91 117	73.74 147	75.27 134	84.45 165	88.98 115
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
TransMVSNet (Re)		57.83 197	56.90 208	58.91 185	72.26 150	74.69 199	63.57 187	61.42 117	32.30 233	32.65 211	33.97 214	35.96 214	39.17 221	73.84 146	72.84 168	84.37 166	74.69 207

IterMVS		61.87 175	63.55 160	59.90 176	67.29 183	72.20 208	67.34 165	48.56 215	47.48 173	37.86 190	47.07 143	48.27 161	54.08 174	72.12 165	73.71 152	84.30 167	83.99 160
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
tttt0517		67.99 122	70.61 112	64.94 136	71.94 153	83.96 111	67.62 161	57.98 145	59.30 112	49.90 128	54.50 97	57.98 112	57.92 158	76.48 115	77.47 110	84.24 168	84.58 155

UGNet		67.57 127	71.69 103	62.76 157	69.88 163	82.58 121	66.43 171	58.64 139	54.71 148	51.87 116	61.74 63	62.01 80	45.46 209	74.78 133	74.99 135	84.24 168	91.02 86
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
MDTV_nov1_ep13_2view		54.47 214	54.61 213	54.30 213	60.50 214	73.82 203	57.92 212	43.38 232	39.43 207	32.51 212	33.23 215	34.05 222	47.26 201	62.36 222	66.21 218	84.24 168	73.19 215

MDTV_nov1_ep13		65.21 143	67.28 137	62.79 155	70.91 159	81.72 125	69.28 152	49.50 212	58.08 119	43.94 152	50.50 124	56.02 130	58.86 151	70.72 179	73.37 157	84.24 168	80.52 191

ACMM	66.70 10	70.42 100	68.49 125	72.67 79	82.85 55	77.76 168	77.70 76	64.76 66	64.61 87	60.74 85	49.29 127	53.97 146	65.86 107	74.97 130	75.57 131	84.13 172	83.29 168
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
TSAR-MVS + ACMM		81.59 27	85.84 22	76.63 39	89.82 24	86.53 84	86.32 17	66.72 53	85.96 22	65.43 46	88.98 12	82.29 16	67.57 100	82.06 47	81.33 56	83.93 173	93.75 44

UniMVSNet (Re)		60.62 182	62.93 169	57.92 189	67.64 180	77.90 165	61.75 200	61.24 118	49.83 164	29.80 219	42.57 159	40.62 189	43.36 213	70.49 184	73.27 161	83.76 174	85.81 146

DeepPCF-MVS	76.94 1	83.08 21	87.77 11	77.60 35	90.11 21	90.96 20	78.48 60	72.63 23	93.10 4	65.84 45	80.67 25	81.55 21	74.80 30	85.94 13	85.39 9	83.75 175	96.77 12

SCA		63.90 153	66.67 141	60.66 170	73.75 139	71.78 211	59.87 207	43.66 231	61.13 105	45.03 145	51.64 118	59.45 99	57.92 158	70.96 177	70.80 189	83.71 176	80.92 190

FE-MVSNET2		50.42 224	51.98 226	48.61 224	44.79 246	68.96 220	52.01 222	55.50 181	32.55 231	19.88 235	21.60 242	28.20 239	35.80 224	68.31 196	71.76 178	83.69 177	72.45 218

pmmvs4		63.14 158	62.46 173	63.94 147	66.03 191	76.40 178	66.82 168	57.60 152	56.74 128	50.26 126	40.81 174	37.51 203	59.26 148	71.75 172	71.48 181	83.68 178	82.53 179

MSDG		65.57 140	61.57 180	70.24 96	82.02 62	76.47 177	74.46 107	68.73 41	56.52 132	50.33 125	38.47 184	41.10 184	62.42 128	72.12 165	72.94 166	83.47 179	73.37 214

DCV-MVSNet		69.13 112	69.07 120	69.21 103	77.65 110	77.52 170	74.68 99	57.85 149	54.92 145	55.34 105	55.74 87	55.56 137	66.35 105	75.05 129	76.56 118	83.35 180	88.13 127

EPP-MVSNet		67.58 126	71.10 107	63.48 150	75.71 129	83.35 114	66.85 167	57.83 150	53.02 155	41.15 168	55.82 85	67.89 57	56.01 167	74.40 137	72.92 167	83.33 181	90.30 99

DU-MVS		60.87 181	61.82 178	59.76 178	66.69 185	75.87 182	64.07 180	61.96 107	49.31 165	31.17 215	42.76 156	36.95 206	51.37 187	69.67 191	73.20 164	83.30 182	84.95 152

tpm cat1		67.47 128	67.05 140	67.98 117	76.63 120	81.51 130	74.49 106	47.65 219	61.18 104	61.12 79	42.51 161	53.02 151	64.74 113	70.11 188	71.50 180	83.22 183	89.49 109

MVS_111021_LR		74.26 68	75.95 66	72.27 83	79.43 81	85.04 99	72.71 117	65.27 64	70.92 64	63.58 56	69.32 41	60.31 95	69.43 85	77.01 110	77.15 112	83.22 183	91.93 77

Anonymous202405211			66.35 146		78.00 107	84.41 106	74.85 98	63.18 89	51.00 159		31.37 221	53.73 147	69.67 82	76.28 116	76.84 114	83.21 185	90.85 88

CPTT-MVS		75.43 59	77.13 58	73.44 71	81.43 66	82.55 122	80.96 47	64.35 67	77.95 50	61.39 77	69.20 42	70.94 48	69.38 87	73.89 144	73.32 159	83.14 186	92.06 75

pm-mvs1		59.21 190	59.58 195	58.77 186	67.97 176	77.07 175	64.12 178	57.20 163	34.73 227	36.86 192	35.34 205	40.54 190	43.34 214	74.32 140	73.30 160	83.13 187	81.77 186

MVS-HIRNet		53.86 217	53.02 219	54.85 208	60.30 215	72.36 207	44.63 239	42.20 238	39.45 206	43.47 154	21.66 241	34.00 223	55.47 169	65.42 212	67.16 205	83.02 188	71.08 224

Anonymous20231211		68.44 117	66.37 145	70.86 91	77.58 111	83.49 113	75.15 97	61.89 109	52.54 156	58.50 90	28.89 226	56.78 122	69.29 88	74.96 132	76.61 116	82.73 189	91.36 83

CDS-MVSNet		64.22 150	65.89 150	62.28 162	70.05 162	80.59 140	69.91 147	57.98 145	43.53 189	46.58 138	48.22 132	50.76 157	46.45 204	75.68 124	76.08 124	82.70 190	86.34 139
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
TSAR-MVS + COLMAP		73.09 81	76.86 59	68.71 109	74.97 135	82.49 123	74.51 105	61.83 110	83.16 28	49.31 130	82.22 23	51.62 155	68.94 91	78.76 90	75.52 133	82.67 191	84.23 159

v7n		57.04 206	56.64 209	57.52 193	62.85 206	74.75 198	61.76 199	51.80 208	35.58 226	36.02 200	32.33 218	33.61 225	50.16 194	67.73 199	70.34 194	82.51 192	82.12 183

Vis-MVSNet (Re-imp)		62.25 168	68.74 123	54.68 209	73.70 140	78.74 157	56.51 215	57.49 154	55.22 142	26.86 223	54.56 95	61.35 83	31.06 226	73.10 153	74.90 136	82.49 193	83.31 167

Effi-MVS+-dtu		64.58 147	64.08 157	65.16 134	73.04 147	75.17 195	70.68 143	56.23 172	54.12 152	44.71 148	47.42 137	51.10 156	63.82 118	68.08 198	66.32 217	82.47 194	86.38 138

TAPA-MVS	67.10 9	71.45 96	73.47 86	69.10 105	77.04 117	80.78 139	73.81 111	62.10 106	80.80 38	51.28 118	60.91 67	63.80 74	67.98 94	74.59 134	72.42 173	82.37 195	80.97 189
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
OMC-MVS		74.03 73	75.82 67	71.95 86	79.56 79	80.98 136	75.35 96	63.21 88	84.48 25	61.83 72	61.54 65	66.89 59	69.41 86	76.60 114	74.07 149	82.34 196	86.15 141

dps		64.08 151	63.22 164	65.08 135	75.27 132	79.65 149	66.68 169	46.63 223	56.94 127	55.67 101	43.96 153	43.63 176	64.00 116	69.50 193	69.82 195	82.25 197	79.02 196

pmnet_mix02		53.92 216	53.30 218	54.65 211	61.89 210	71.33 213	54.54 219	54.17 196	40.38 201	34.65 205	34.76 209	30.68 235	40.44 219	60.97 224	63.71 225	82.19 198	71.24 223

Anonymous20231206		52.23 220	52.80 222	51.56 217	64.70 198	69.41 218	51.01 224	58.60 140	36.63 219	22.44 230	21.80 240	31.42 231	30.52 227	66.79 202	67.83 201	82.10 199	75.73 203

PMMVS		70.37 103	75.06 71	64.90 137	71.46 154	81.88 124	64.10 179	55.64 178	71.31 63	46.69 137	70.69 40	58.56 101	69.53 83	79.03 81	75.63 129	81.96 200	88.32 125

TAMVS		58.86 192	60.91 185	56.47 204	62.38 209	77.57 169	58.97 210	52.98 203	38.76 214	36.17 197	42.26 164	47.94 164	46.45 204	70.23 187	70.79 190	81.86 201	78.82 197

UniMVSNet_ETH3D		57.83 197	56.46 211	59.43 181	63.24 204	73.22 205	67.70 159	55.58 179	36.17 222	36.84 193	32.64 216	35.14 218	51.50 184	65.81 210	69.81 196	81.73 202	82.44 182

PLC	64.00 12	68.54 116	66.66 142	70.74 93	80.28 76	74.88 196	72.64 118	63.70 83	69.26 71	55.71 100	47.24 141	55.31 138	70.42 76	72.05 167	70.67 191	81.66 203	77.19 200
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
ADS-MVSNet		58.40 196	59.16 197	57.52 193	65.80 194	74.57 200	60.26 204	40.17 244	50.51 160	38.01 188	40.11 179	44.72 172	59.36 147	64.91 214	66.55 209	81.53 204	72.72 217

PEN-MVS		51.04 221	52.94 220	48.82 222	61.45 212	66.00 228	48.68 227	57.20 163	36.87 217	15.36 241	36.98 194	32.72 226	28.77 232	57.63 231	66.37 214	81.44 205	74.00 210

pmmvs-eth3d		55.20 207	53.95 216	56.65 202	57.34 226	67.77 223	57.54 213	53.74 199	40.93 200	41.09 169	31.19 222	29.10 238	49.07 195	65.54 211	67.28 203	81.14 206	75.81 202

WR-MVS_H		49.62 228	52.63 223	46.11 232	58.80 221	67.58 224	46.14 236	54.94 187	36.51 220	13.63 246	36.75 197	35.67 216	22.10 241	56.43 235	62.76 229	81.06 207	72.73 216

thisisatest0515		59.37 189	60.68 187	57.84 191	64.39 199	75.65 187	58.56 211	53.86 198	41.55 197	42.12 163	40.40 176	39.59 196	47.09 202	71.69 173	73.79 151	81.02 208	82.08 184

CNLPA		71.37 98	70.27 115	72.66 80	80.79 71	81.33 132	71.07 139	65.75 59	82.36 31	64.80 50	42.46 162	56.49 127	72.70 46	73.00 156	70.52 193	80.84 209	85.76 147

UA-Net		64.62 146	68.23 131	60.42 173	77.53 112	81.38 131	60.08 206	57.47 155	47.01 174	44.75 147	60.68 68	71.32 47	41.84 217	73.27 151	72.25 175	80.83 210	71.68 220

DTE-MVSNet		49.82 227	51.92 227	47.37 228	61.75 211	64.38 233	45.89 237	57.33 160	36.11 223	12.79 248	36.87 195	31.93 229	25.73 237	58.01 229	65.22 221	80.75 211	70.93 225

CP-MVSNet		50.57 223	52.60 224	48.21 226	58.77 222	65.82 229	48.17 228	56.29 171	37.41 216	16.59 238	37.14 192	31.95 228	29.21 229	56.60 234	63.71 225	80.22 212	75.56 204

PS-CasMVS		50.17 225	52.02 225	48.02 227	58.60 223	65.54 230	48.04 229	56.19 173	36.42 221	16.42 240	35.68 204	31.33 232	28.85 231	56.42 236	63.54 227	80.01 213	75.18 205

USDC		59.69 187	60.03 192	59.28 183	64.04 200	71.84 209	63.15 191	55.36 184	54.90 146	35.02 204	48.34 131	29.79 236	58.16 153	70.60 181	71.33 186	79.99 214	73.42 213

WR-MVS		51.02 222	54.56 214	46.90 229	63.84 201	69.23 219	44.78 238	56.38 170	38.19 215	14.19 243	37.38 190	36.82 208	22.39 240	60.14 226	66.20 219	79.81 215	73.95 211

ACMH	59.42 14	61.59 177	59.22 196	64.36 143	78.92 96	78.26 162	67.65 160	67.48 48	39.81 204	30.98 217	38.25 186	34.59 220	61.37 134	70.55 183	73.47 155	79.74 216	79.59 193
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
ACMH+	60.36 13	61.16 178	58.38 198	64.42 142	77.37 116	74.35 201	68.45 155	62.81 97	45.86 181	38.48 183	35.71 203	37.35 204	59.81 143	67.24 200	69.80 197	79.58 217	78.32 198

anonymousdsp		54.99 210	57.24 207	52.36 215	53.82 230	71.75 212	51.49 223	48.14 216	33.74 228	33.66 209	38.34 185	36.13 212	47.54 200	64.53 218	70.60 192	79.53 218	85.59 149

pmmvs6		54.20 215	53.54 217	54.97 207	63.22 205	72.98 206	60.17 205	52.32 207	26.77 243	34.30 207	23.29 237	36.23 211	40.33 220	68.77 195	68.76 199	79.47 219	78.00 199

test20.03		47.23 234	48.69 234	45.53 233	63.28 203	64.39 232	41.01 243	56.93 167	29.16 237	15.21 242	23.90 234	30.76 234	17.51 247	64.63 217	65.26 220	79.21 220	62.71 241

CR-MVSNet		62.31 166	64.75 153	59.47 180	68.63 171	71.29 214	67.53 162	43.18 233	55.83 137	41.40 165	41.04 171	55.85 131	57.29 164	72.76 159	73.27 161	78.77 221	83.23 170

testgi		48.51 231	50.53 229	46.16 231	64.78 196	67.15 226	41.54 242	54.81 191	29.12 238	17.03 237	32.07 219	31.98 227	20.15 244	65.26 213	67.00 206	78.67 222	61.10 244

RPMNet		58.63 195	62.80 171	53.76 214	67.59 181	71.29 214	54.60 218	38.13 245	55.83 137	35.70 201	41.58 168	53.04 150	47.89 198	66.10 209	67.38 202	78.65 223	84.40 157

LS3D		64.54 149	62.14 176	67.34 124	80.85 69	75.79 184	69.99 145	65.87 58	60.77 106	44.35 149	42.43 163	45.95 170	65.01 109	69.88 189	68.69 200	77.97 224	71.43 222

CHOSEN 280x420		62.23 170	66.57 143	57.17 200	59.88 216	68.92 221	61.20 203	42.28 237	54.17 151	39.57 173	47.78 135	64.97 67	62.68 124	73.85 145	69.52 198	77.43 225	86.75 134

FE-MVSNET		44.36 236	46.68 237	41.65 235	37.55 249	61.05 239	42.06 241	54.34 194	27.09 241	9.86 253	20.55 243	25.56 246	28.72 233	60.12 227	66.83 207	77.36 226	65.56 235

PatchMatch-RL		62.22 171	60.69 186	64.01 145	68.74 170	75.75 185	59.27 208	60.35 132	56.09 136	53.80 109	47.06 144	36.45 209	64.80 112	68.22 197	67.22 204	77.10 227	74.02 209

CVMVSNet		54.92 212	58.16 199	51.13 219	62.61 208	68.44 222	55.45 217	52.38 206	42.28 193	21.45 231	47.10 142	46.10 169	37.96 222	64.42 219	63.81 224	76.92 228	75.01 206

N_pmnet		47.67 232	47.00 236	48.45 225	54.72 229	62.78 236	46.95 232	51.25 209	36.01 224	26.09 225	26.59 232	25.93 245	35.50 225	55.67 238	59.01 234	76.22 229	63.04 239

usedtu_dtu_shiyan2		40.99 240	42.22 243	39.56 239	22.63 255	59.44 241	46.80 233	43.69 230	19.05 252	21.04 232	16.27 250	23.77 247	27.46 235	53.16 241	55.09 242	75.73 230	68.78 226

COLMAP_ROB	51.17 15	55.13 208	52.90 221	57.73 192	73.47 144	67.21 225	62.13 198	55.82 175	47.83 171	34.39 206	31.60 220	34.24 221	44.90 211	63.88 221	62.52 230	75.67 231	63.02 240
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
MIMVSNet1		40.84 241	43.46 238	37.79 241	32.14 250	58.92 243	39.24 245	50.83 210	27.00 242	11.29 250	16.76 249	26.53 243	17.75 246	57.14 233	61.12 233	75.46 232	56.78 245

CMPMVS	43.63 17	57.67 202	55.43 212	60.28 175	72.01 151	79.00 155	62.77 197	53.23 202	41.77 195	45.42 141	30.74 223	39.03 197	53.01 179	64.81 216	64.65 223	75.26 233	68.03 230
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
TinyColmap		52.66 219	50.09 231	55.65 205	59.72 217	64.02 235	57.15 214	52.96 204	40.28 202	32.51 212	32.42 217	20.97 250	56.65 166	63.95 220	65.15 222	74.91 234	63.87 238

MDA-MVSNet-bldmvs		44.15 237	42.27 242	46.34 230	38.34 248	62.31 237	46.28 234	55.74 177	29.83 236	20.98 233	27.11 231	16.45 256	41.98 216	41.11 248	57.47 237	74.72 235	61.65 243

new-patchmatchnet		42.21 238	42.97 239	41.33 237	53.05 231	59.89 240	39.38 244	49.61 211	28.26 240	12.10 249	22.17 239	21.54 249	19.22 245	50.96 242	56.04 239	74.61 236	61.92 242

TDRefinement		52.70 218	51.02 228	54.66 210	57.41 225	65.06 231	61.47 202	54.94 187	44.03 187	33.93 208	30.13 225	27.57 240	46.17 206	61.86 223	62.48 231	74.01 237	66.06 233

PM-MVS		50.11 226	50.38 230	49.80 220	47.23 245	62.08 238	50.91 225	44.84 228	41.90 194	36.10 198	35.22 206	26.05 244	46.83 203	57.64 230	55.42 241	72.90 238	74.32 208

pmmvs3		41.86 239	42.29 241	41.36 236	39.80 247	52.66 247	38.93 246	35.85 249	23.40 247	20.22 234	19.30 244	20.84 251	40.56 218	55.98 237	58.79 235	72.80 239	65.03 236

SixPastTwentyTwo		49.11 230	49.22 233	48.99 221	58.54 224	64.14 234	47.18 231	47.75 218	31.15 235	24.42 226	41.01 172	26.55 242	44.04 212	54.76 239	58.70 236	71.99 240	68.21 228

IterMVS-SCA-FT		60.21 185	62.97 167	57.00 201	66.64 187	71.84 209	67.53 162	46.93 222	47.56 172	36.77 195	46.85 147	48.21 162	52.51 180	70.36 185	72.40 174	71.63 241	83.53 164

EU-MVSNet		44.84 235	47.85 235	41.32 238	49.26 236	56.59 245	43.07 240	47.64 220	33.03 229	13.82 244	36.78 196	30.99 233	24.37 238	53.80 240	55.57 240	69.78 242	68.21 228

RPSCF		55.07 209	58.06 200	51.57 216	48.87 237	58.95 242	53.68 220	41.26 242	62.42 98	45.88 139	54.38 99	54.26 144	53.75 175	57.15 232	53.53 243	66.01 243	65.75 234

LTVRE_ROB	47.26 16	49.41 229	49.91 232	48.82 222	64.76 197	69.79 217	49.05 226	47.12 221	20.36 250	16.52 239	36.65 198	26.96 241	50.76 192	60.47 225	63.16 228	64.73 244	72.00 219
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
FC-MVSNet-test		47.24 233	54.37 215	38.93 240	59.49 219	58.25 244	34.48 248	53.36 201	45.66 182	6.66 254	50.62 122	42.02 177	16.62 248	58.39 228	61.21 232	62.99 245	64.40 237

ambc			42.30 240		50.36 235	49.51 248	35.47 247		32.04 234	23.53 227	17.36 246	8.95 258	29.06 230	64.88 215	56.26 238	61.29 246	67.12 231

FPMVS		39.11 242	36.39 244	42.28 234	55.97 227	45.94 249	46.23 235	41.57 239	35.73 225	22.61 228	23.46 236	19.82 252	28.32 234	43.57 245	40.67 247	58.96 247	45.54 247

new_pmnet		33.19 243	35.52 245	30.47 243	27.55 254	45.31 250	29.29 250	30.92 250	29.00 239	9.88 252	18.77 245	17.64 254	26.77 236	44.07 244	45.98 245	58.41 248	47.87 246

PMVS	27.44 18	32.08 244	29.07 248	35.60 242	48.33 244	24.79 253	26.97 251	41.34 241	20.45 249	22.50 229	17.11 248	18.64 253	20.44 243	41.99 247	38.06 248	54.02 249	42.44 248
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
PMMVS2		20.45 248	22.31 250	18.27 250	20.52 256	26.73 252	14.85 256	28.43 252	13.69 253	0.79 260	10.35 252	9.10 257	3.83 255	27.64 251	32.87 249	41.17 250	35.81 249

Gipuma		24.91 247	24.61 249	25.26 246	31.47 251	21.59 254	18.06 253	37.53 246	25.43 245	10.03 251	4.18 256	4.25 260	14.85 249	43.20 246	47.03 244	39.62 251	26.55 253
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
test_method		28.15 246	34.48 246	20.76 247	6.76 259	21.18 255	21.03 252	18.41 253	36.77 218	17.52 236	15.67 251	31.63 230	24.05 239	41.03 249	26.69 251	36.82 252	68.38 227

WB-MVS		30.42 245	32.63 247	27.84 244	51.51 234	41.64 251	17.75 254	55.06 186	20.11 251	2.46 259	26.13 233	16.63 255	3.90 254	44.91 243	44.54 246	36.34 253	34.48 250

tmp_tt				16.09 251	13.07 257	8.12 260	13.61 257	2.08 255	55.09 143	30.10 218	40.26 177	22.83 248	5.35 253	29.91 250	25.25 252	32.33 254

E-PMN		15.08 249	11.65 252	19.08 248	28.73 252	12.31 258	6.95 259	36.87 248	10.71 255	3.63 257	5.13 253	2.22 263	13.81 251	11.34 254	18.50 253	24.49 255	21.32 254

EMVS		14.40 250	10.71 253	18.70 249	28.15 253	12.09 259	7.06 258	36.89 247	11.00 254	3.56 258	4.95 254	2.27 262	13.91 250	10.13 255	16.06 254	22.63 256	18.51 255

DeepMVS_CX						19.81 257	17.01 255	10.02 254	23.61 246	5.85 255	17.21 247	8.03 259	21.13 242	22.60 252		21.42 257	30.01 251

MVE	15.98 19	14.37 251	16.36 251	12.04 252	7.72 258	20.24 256	5.90 260	29.05 251	8.28 256	3.92 256	4.72 255	2.42 261	9.57 252	18.89 253	31.46 250	16.07 258	28.53 252
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
testmvs		0.05 252	0.08 254	0.01 253	0.00 261	0.01 261	0.03 262	0.01 257	0.05 257	0.00 262	0.14 258	0.01 264	0.03 258	0.05 256	0.05 255	0.01 259	0.24 257

uanet_test		0.00 254	0.00 256	0.00 255	0.00 261	0.00 263	0.00 264	0.00 258	0.00 259	0.00 262	0.00 259	0.00 265	0.00 259	0.00 258	0.00 257	0.00 260	0.00 258

sosnet-low-res		0.00 254	0.00 256	0.00 255	0.00 261	0.00 263	0.00 264	0.00 258	0.00 259	0.00 262	0.00 259	0.00 265	0.00 259	0.00 258	0.00 257	0.00 260	0.00 258

sosnet		0.00 254	0.00 256	0.00 255	0.00 261	0.00 263	0.00 264	0.00 258	0.00 259	0.00 262	0.00 259	0.00 265	0.00 259	0.00 258	0.00 257	0.00 260	0.00 258

test123		0.05 252	0.08 254	0.01 253	0.00 261	0.01 261	0.01 263	0.00 258	0.05 257	0.00 262	0.16 257	0.00 265	0.04 256	0.02 257	0.05 255	0.00 260	0.26 256

RE-MVS-def										31.47 214

9.14												84.47 8

SR-MVS					86.33 48			67.54 47				80.78 23

our_test_3					63.32 202	71.07 216	55.90 216

MTAPA										78.32 12		79.42 27

MTMP										76.04 16		76.65 31

Patchmatch-RL test							2.17 261

mPP-MVS					86.96 43							70.61 50

NP-MVS									81.60 36

Patchmtry						78.06 164	67.53 162	43.18 233		41.40 165

High-resolution multi-view benchmark