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.

MCST-MVS		74.06 4	77.71 9	69.79 1	78.95 1	81.99 3	76.33 4	62.16 1	75.89 16	52.96 20	64.37 26	73.30 15	65.66 2	77.49 1	77.43 2	82.67 1	93.51 1

ESAPD		76.46 1	83.32 1	68.47 2	78.83 2	83.07 2	77.86 1	58.75 4	86.89 3	56.64 8	89.08 2	83.11 1	60.69 12	74.28 7	74.11 8	78.06 29	92.67 3

CSCG		72.98 7	76.86 11	68.46 3	78.23 3	81.74 5	77.26 3	60.00 2	75.61 19	59.06 1	62.72 28	77.42 4	56.63 36	74.24 8	77.18 3	79.56 12	89.13 14

APDe-MVS		74.59 2	80.23 3	68.01 5	76.51 4	80.20 11	77.39 2	58.18 5	85.31 4	56.84 6	84.89 3	76.08 8	60.66 13	71.85 22	71.76 17	78.47 22	91.49 6

3Dnovator	58.39 4	65.97 30	66.85 43	64.94 10	73.72 5	79.03 15	67.73 33	54.25 20	61.52 48	52.79 22	42.27 76	60.73 48	62.01 5	71.29 24	71.75 18	79.12 17	81.34 80

MAR-MVS		66.85 25	69.81 34	63.39 19	73.56 6	80.51 9	69.87 24	51.51 32	67.78 39	46.44 39	51.09 54	61.60 45	60.38 14	72.67 18	73.61 11	78.59 20	81.44 76
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
SteuartSystems-ACMMP		69.78 15	74.76 15	63.98 14	73.45 7	78.56 19	73.13 11	55.24 16	70.68 29	48.93 32	70.43 16	69.10 22	54.00 47	72.78 17	72.98 13	79.14 16	88.74 17
Skip Steuart: Steuart Systems R&D Blog.
CNVR-MVS		73.87 5	78.60 6	68.35 4	73.32 8	81.97 4	76.19 5	59.29 3	80.12 9	56.70 7	67.09 20	76.48 6	64.26 3	75.88 3	75.75 4	80.32 7	92.93 2

QAPM		65.47 33	67.82 38	62.72 22	72.56 9	81.17 8	67.43 36	55.38 15	56.07 61	43.29 54	43.60 73	65.38 30	59.10 21	72.20 19	70.76 29	78.56 21	85.59 37

CHOSEN 1792x2688		62.48 49	64.06 53	60.64 35	72.50 10	84.18 1	62.43 61	53.77 23	47.90 80	39.85 71	25.15 194	44.76 97	53.72 48	77.29 2	77.61 1	81.60 4	91.53 5

NCCC		71.36 11	75.44 13	66.60 7	72.46 11	79.18 14	74.16 7	57.83 6	76.93 14	54.19 14	63.47 27	71.08 20	61.30 9	73.56 10	73.70 10	79.69 11	90.19 8

OpenMVS	55.62 8	62.57 45	63.76 54	61.19 32	72.13 12	78.84 17	64.42 53	50.51 40	56.44 58	45.67 45	36.88 104	56.51 56	56.66 35	68.28 48	68.96 42	77.73 34	80.44 87

HSP-MVS		74.54 3	81.12 2	66.86 6	71.93 13	78.65 18	72.60 12	55.44 13	89.94 1	54.35 12	92.24 1	77.08 5	69.84 1	75.48 4	75.01 5	76.99 43	79.45 91

HPM-MVS++		72.44 8	78.73 5	65.11 9	71.88 14	77.31 26	71.98 15	55.67 11	83.11 7	53.59 16	75.90 8	78.49 3	61.00 10	73.99 9	73.31 12	76.55 46	88.97 15

SMA-MVS		73.13 6	79.49 4	65.71 8	71.08 15	80.36 10	74.71 6	56.31 7	83.60 5	53.34 18	72.81 12	80.52 2	60.83 11	74.88 6	74.53 7	77.96 31	89.72 9

MVS_111021_HR		64.66 37	67.11 42	61.80 27	71.04 16	77.91 22	62.75 60	54.78 18	51.43 69	47.54 38	53.77 47	54.85 59	56.84 31	70.59 27	71.50 20	77.86 32	89.70 10

AdaColmap		62.79 43	62.63 58	62.98 21	70.82 17	72.90 57	67.84 32	54.09 22	65.14 43	50.71 26	41.78 77	47.64 85	60.17 16	67.41 54	66.83 55	74.28 102	76.69 105

abl_6				63.79 18	70.80 18	81.22 7	65.26 51	53.25 25	77.02 13	53.02 19	65.14 25	73.74 13	60.30 15			80.13 8	90.27 7

MS-PatchMatch		61.41 55	61.88 64	60.85 33	70.57 19	75.98 33	66.29 44	46.91 76	50.56 71	48.28 36	36.30 111	51.64 65	50.95 68	72.89 14	70.65 30	82.13 3	75.17 122

APD-MVS		71.86 9	77.91 8	64.80 11	70.39 20	75.69 37	74.02 8	56.14 9	83.59 6	52.92 21	84.67 4	73.46 14	59.30 20	69.47 34	69.66 35	76.02 53	88.84 16
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
train_agg		70.74 12	76.53 12	63.98 14	70.33 21	75.16 39	72.33 14	55.78 10	75.74 17	50.41 29	80.08 7	73.15 16	57.75 28	71.96 21	70.94 27	77.25 41	88.69 18

ACMMP_Plus		71.50 10	77.27 10	64.77 12	69.64 22	79.26 12	73.53 9	54.73 19	79.32 11	54.23 13	74.81 9	74.61 12	59.40 19	73.00 11	72.17 15	77.10 42	87.72 22

TSAR-MVS + ACMM		65.95 31	72.83 18	57.93 51	69.35 23	65.85 107	73.36 10	39.84 153	76.00 15	48.69 35	82.54 6	75.03 11	49.38 87	65.33 65	63.42 104	66.94 176	81.67 73

TSAR-MVS + MP.		70.28 13	75.09 14	64.66 13	69.34 24	64.61 118	72.60 12	56.29 8	80.73 8	58.36 3	84.56 5	75.22 10	55.37 41	69.11 40	69.45 36	75.97 55	81.97 65

SD-MVS		68.30 17	72.58 19	63.31 20	69.24 25	67.85 90	70.81 21	53.65 24	79.64 10	58.52 2	74.31 10	75.37 9	53.52 53	65.63 62	63.56 102	74.13 107	81.73 72

DELS-MVS		67.36 19	70.34 33	63.89 17	69.12 26	81.55 6	70.82 20	55.02 17	53.38 65	48.83 33	56.45 40	59.35 50	60.05 18	74.93 5	74.78 6	79.51 13	91.95 4
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
CDPH-MVS		67.03 24	71.64 25	61.65 29	69.10 27	76.84 30	71.35 19	55.42 14	67.02 40	42.83 56	65.27 24	64.60 32	53.16 56	69.70 33	71.40 21	78.02 30	86.67 28

HFP-MVS		68.75 16	72.84 17	63.98 14	68.87 28	75.09 40	71.87 16	51.22 33	73.50 23	58.17 4	68.05 19	68.67 23	57.79 27	70.49 29	69.23 38	75.98 54	84.84 41

MSLP-MVS++		61.81 53	62.19 63	61.37 31	68.33 29	63.08 136	70.75 22	38.89 162	63.96 46	57.51 5	48.59 60	61.66 44	53.67 51	62.04 113	59.92 149	79.03 18	76.08 108

CLD-MVS		64.69 36	67.25 39	61.69 28	68.22 30	78.33 20	63.09 57	47.59 63	69.64 33	53.98 15	54.87 44	53.94 62	57.87 26	72.79 15	71.34 22	79.40 14	69.87 159
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
HQP-MVS		67.22 22	72.08 22	61.56 30	66.76 31	73.58 50	71.41 17	52.98 26	69.92 32	43.85 52	70.58 15	58.75 52	56.76 33	72.90 13	71.88 16	77.57 35	86.94 27

OPM-MVS		61.59 54	62.30 62	60.76 34	66.53 32	73.35 51	71.41 17	54.18 21	40.82 102	41.57 69	45.70 68	54.84 60	54.43 46	69.92 32	69.19 39	76.45 47	82.25 57

MP-MVS		67.34 20	73.08 16	60.64 35	66.20 33	76.62 31	69.22 27	50.92 35	70.07 30	48.81 34	69.66 17	70.12 21	53.68 50	68.41 45	69.13 40	74.98 72	87.53 23

zzz-MVS		67.78 18	72.46 20	62.33 25	66.09 34	74.21 43	70.05 23	51.54 31	77.27 12	54.61 11	60.30 35	71.51 19	56.73 34	69.19 38	68.63 46	74.96 73	86.11 32

3Dnovator+	55.76 7	62.70 44	65.10 50	59.90 41	65.89 35	72.15 60	62.94 59	49.82 43	62.77 47	49.06 31	43.62 72	61.47 47	58.60 24	68.51 44	66.75 56	73.08 127	80.40 88

PGM-MVS		65.35 34	70.43 32	59.43 44	65.78 36	73.75 47	69.41 25	48.18 56	68.80 36	45.37 46	65.88 23	64.04 34	52.68 62	68.94 41	68.68 45	75.18 67	82.93 54

MSDG		52.58 109	51.40 146	53.95 70	65.48 37	64.31 128	61.44 64	44.02 115	44.17 87	32.92 111	30.40 168	31.81 171	46.35 113	62.13 111	62.55 115	73.49 117	64.41 173

ACMMPR		66.20 29	71.51 28	60.00 40	65.34 38	74.04 45	69.39 26	50.92 35	71.97 27	46.04 42	66.79 21	65.68 27	53.07 57	68.93 42	69.12 41	75.21 66	84.05 48

DWT-MVSNet_training		61.22 56	63.52 56	58.53 46	65.00 39	76.55 32	59.50 87	48.22 55	51.79 68	42.14 64	47.85 63	50.21 71	55.46 40	66.16 59	67.92 50	80.85 5	84.14 47

X-MVS		63.53 41	68.62 36	57.60 54	64.77 40	73.06 54	65.82 46	50.53 39	65.77 42	42.02 65	58.20 37	63.42 37	47.83 106	68.25 49	68.50 47	74.61 89	83.16 53

CANet		67.21 23	71.83 24	61.83 26	64.51 41	79.25 13	66.72 41	48.73 49	68.49 37	50.63 28	61.40 31	66.47 26	61.44 7	69.31 37	69.90 32	78.94 19	88.00 20

tpmp4_e23		59.70 59	61.03 68	58.14 48	63.70 42	73.33 52	65.69 47	39.53 155	52.56 66	46.23 41	41.59 78	47.46 86	57.38 29	65.01 67	65.89 63	76.31 49	81.36 79

FC-MVSNet-train		55.68 73	57.00 89	54.13 69	63.37 43	66.16 103	46.77 161	52.14 29	42.36 95	37.67 77	48.50 61	41.42 109	51.28 66	61.58 118	63.22 106	73.56 115	75.76 114

ACMH	47.82 13	50.10 137	49.60 158	50.69 104	63.36 44	66.99 97	56.83 102	52.13 30	31.06 172	17.74 185	28.22 181	26.24 200	45.17 121	60.88 129	63.80 100	68.91 161	70.00 157
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
CostFormer		62.45 50	65.68 47	58.67 45	63.29 45	77.65 23	67.62 34	38.42 165	54.04 63	46.00 43	48.27 62	57.89 54	56.97 30	67.03 57	67.79 51	79.74 9	87.09 26

ACMM	53.73 9	57.91 64	58.27 80	57.49 55	63.10 46	66.45 101	65.65 48	49.02 46	53.69 64	42.67 61	36.41 108	46.07 93	50.38 70	64.74 70	64.63 82	74.14 106	75.91 112
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
mPP-MVS					63.08 47							62.34 40

PHI-MVS		65.17 35	72.07 23	57.11 59	63.02 48	77.35 25	67.04 39	48.14 58	68.03 38	37.56 78	66.00 22	65.39 29	53.19 55	70.68 26	70.57 31	73.72 113	86.46 31

DeepC-MVS_fast	60.18 3	66.84 26	70.69 31	62.36 24	62.76 49	73.21 53	67.96 31	52.31 27	72.26 26	51.03 23	56.50 39	64.26 33	63.37 4	71.64 23	70.85 28	76.70 45	86.10 33
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
XVS					62.70 50	73.06 54	61.80 62			42.02 65		63.42 37				74.68 87

X-MVStestdata					62.70 50	73.06 54	61.80 62			42.02 65		63.42 37				74.68 87

ACMMP		63.27 42	67.85 37	57.93 51	62.64 52	72.30 59	68.23 29	48.77 48	66.50 41	43.05 55	62.07 29	57.84 55	49.98 73	66.58 58	66.46 61	74.93 77	83.17 52
Qingshan Xu, Weihang Kong, Wenbing Tao, Marc Pollefeys: Multi-Scale Geometric Consistency Guided and Planar Prior Assisted Multi-View Stereo. IEEE Transactions on Pattern Analysis and Machine Intelligence
MVS_0304		66.31 28	71.61 26	60.14 39	62.59 53	78.98 16	67.13 38	45.75 87	64.35 45	45.23 47	60.69 33	67.67 25	61.73 6	71.09 25	71.03 25	78.41 25	87.44 24

DeepPCF-MVS	62.48 1	70.07 14	78.36 7	60.39 38	62.38 54	76.96 29	65.54 49	52.23 28	87.46 2	49.07 30	74.05 11	76.19 7	59.01 22	72.79 15	71.61 19	74.13 107	89.49 11

CP-MVS		64.37 39	69.48 35	58.39 47	62.21 55	71.81 61	67.27 37	49.51 44	69.40 35	45.76 44	60.41 34	64.96 31	51.84 64	67.33 55	67.57 52	73.78 112	84.89 40

canonicalmvs		65.55 32	70.75 30	59.49 43	62.11 56	78.26 21	66.52 42	43.82 118	71.54 28	47.84 37	61.30 32	61.68 43	58.48 25	67.56 51	69.67 34	78.16 28	85.25 39

LGP-MVS_train		59.69 60	62.59 59	56.31 63	61.94 57	68.15 89	66.90 40	48.15 57	59.75 51	38.47 74	50.38 56	48.34 83	46.87 111	65.39 64	64.93 70	75.51 64	81.21 82

Effi-MVS+		59.63 61	61.78 67	57.12 58	61.56 58	71.63 62	63.61 56	47.59 63	47.18 81	37.79 75	45.29 69	49.93 73	56.27 37	67.45 52	67.06 54	75.91 56	83.93 49

HyFIR lowres test		57.12 69	59.11 71	54.80 67	61.55 59	77.55 24	59.02 90	45.00 94	41.84 100	33.93 99	22.44 201	49.16 78	51.02 67	68.39 46	68.71 44	78.26 27	85.70 35

TSAR-MVS + GP.		66.77 27	72.21 21	60.44 37	61.23 60	70.00 69	64.26 55	47.79 59	72.98 24	56.32 9	71.35 14	72.33 17	55.68 39	65.49 63	66.66 57	77.35 37	86.62 29

ACMP	56.21 5	59.78 58	61.81 66	57.41 56	61.15 61	68.88 85	65.98 45	48.85 47	58.56 54	44.19 50	48.89 59	46.31 91	48.56 98	63.61 97	64.49 93	75.75 59	81.91 66
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
IB-MVS	53.15 10	57.33 67	59.02 73	55.37 65	60.83 62	77.11 27	54.51 118	50.10 42	43.22 89	42.82 58	40.50 83	37.61 118	44.67 126	59.27 149	69.81 33	79.29 15	85.59 37
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
tpm cat1		57.41 66	58.26 81	56.42 62	60.80 63	72.56 58	64.35 54	38.43 164	49.18 77	46.36 40	36.69 106	43.50 99	54.47 43	61.39 121	62.64 113	74.11 109	81.81 70

gg-mvs-nofinetune		50.82 131	55.83 94	44.97 146	60.63 64	75.69 37	53.40 125	34.48 192	20.05 217	6.93 214	18.27 210	52.70 63	33.57 159	70.50 28	72.93 14	80.84 6	80.68 86

EPNet		64.39 38	70.93 29	56.77 61	60.58 65	75.77 34	59.28 89	50.58 38	69.93 31	40.73 70	68.59 18	61.60 45	53.72 48	68.65 43	68.07 48	75.75 59	83.87 50
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
MVS_Test		63.75 40	67.24 40	59.68 42	60.01 66	76.99 28	68.13 30	45.17 92	57.45 55	43.74 53	53.07 48	56.16 58	61.33 8	70.27 30	71.11 24	79.72 10	85.63 36

tpmrst		57.23 68	59.08 72	55.06 66	59.91 67	70.65 66	60.71 68	35.38 186	47.91 79	42.58 62	39.78 87	45.45 95	54.44 45	62.19 110	62.82 109	77.37 36	84.73 42

dps		52.84 105	52.92 129	52.74 78	59.89 68	69.49 77	54.47 119	37.38 170	42.49 94	39.53 72	35.33 113	32.71 161	51.83 65	60.45 135	61.12 135	73.33 121	68.86 163

DeepC-MVS	60.65 2	67.33 21	71.52 27	62.44 23	59.79 69	74.84 41	68.89 28	55.56 12	73.91 22	53.50 17	55.00 43	65.63 28	60.08 17	71.99 20	71.33 23	76.85 44	87.94 21
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
EG-PatchMatch MVS		50.23 134	50.89 149	49.47 118	59.54 70	70.88 63	52.46 135	44.01 116	26.22 198	31.91 115	24.97 195	31.45 174	33.48 161	64.79 69	66.51 60	75.40 65	71.39 144

tpm		54.94 76	57.86 86	51.54 96	59.48 71	67.04 96	58.34 93	34.60 190	41.93 99	34.41 92	42.40 75	47.14 88	49.07 90	61.46 119	61.67 127	73.31 122	83.39 51

Effi-MVS+-dtu		53.63 94	54.85 108	52.20 88	59.32 72	61.33 157	56.42 109	40.24 151	43.84 88	34.22 95	39.49 92	46.18 92	53.00 60	58.72 154	57.49 162	69.99 155	76.91 102

PCF-MVS	55.99 6	62.31 51	66.60 44	57.32 57	59.12 73	73.68 49	67.53 35	48.71 50	61.35 49	42.83 56	51.33 53	63.48 36	53.48 54	65.64 61	64.87 71	72.22 134	85.83 34
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
PVSNet_BlendedMVS		62.53 46	66.37 45	58.05 49	58.17 74	75.70 35	61.30 65	48.67 51	58.67 52	50.93 24	55.43 41	49.39 75	53.01 58	69.46 35	66.55 58	76.24 51	89.39 12

PVSNet_Blended		62.53 46	66.37 45	58.05 49	58.17 74	75.70 35	61.30 65	48.67 51	58.67 52	50.93 24	55.43 41	49.39 75	53.01 58	69.46 35	66.55 58	76.24 51	89.39 12

TransMVSNet (Re)		47.46 153	48.94 164	45.74 140	57.96 76	64.29 129	48.26 149	48.47 53	26.33 197	19.33 174	29.45 178	31.28 179	25.31 191	63.05 103	62.70 110	75.10 70	65.47 170

DI_MVS_plusplus_trai		61.86 52	65.26 48	57.90 53	57.93 77	74.51 42	66.30 43	46.49 82	49.96 73	41.62 68	42.69 74	61.77 42	58.74 23	70.25 31	69.32 37	76.31 49	88.30 19

NR-MVSNet		48.84 145	51.76 142	45.44 142	57.66 78	60.64 160	47.39 155	47.63 61	37.26 120	13.31 194	37.31 101	29.64 189	33.53 160	63.52 99	62.09 122	73.10 126	71.89 140

PVSNet_Blended_VisFu		58.56 63	62.33 61	54.16 68	56.90 79	73.92 46	57.72 95	46.16 85	44.23 86	42.73 59	46.26 65	51.06 69	46.28 114	67.99 50	65.38 67	75.18 67	87.44 24

ACMH+	47.85 12	49.13 143	48.86 165	49.44 119	56.75 80	62.01 152	56.62 107	47.55 65	37.49 119	23.98 154	26.68 185	29.46 190	43.12 130	57.45 162	58.85 155	68.62 163	70.05 156

EPMVS		54.07 84	56.06 92	51.75 93	56.74 81	70.80 64	55.32 114	34.20 196	46.46 83	36.59 82	40.38 85	42.55 101	49.77 78	61.25 124	60.90 138	77.86 32	70.08 155

gm-plane-assit		45.41 165	48.03 168	42.34 166	56.49 82	40.48 216	24.54 221	34.15 199	14.44 226	6.59 215	17.82 211	35.32 144	49.82 76	72.93 12	74.11 8	82.47 2	81.12 83

conf0.002		51.63 121	53.79 118	49.12 121	56.33 83	64.84 116	53.05 129	47.38 67	35.86 135	24.83 145	37.86 99	38.15 115	41.08 136	61.04 127	62.70 110	72.05 135	76.06 109

conf0.01		51.32 124	53.22 121	49.11 122	56.29 84	64.78 117	53.05 129	47.37 68	35.86 135	24.83 145	36.85 105	36.64 129	41.08 136	61.01 128	61.37 129	72.03 136	76.01 110

Fast-Effi-MVS+-dtu		52.47 111	55.89 93	48.48 127	56.25 85	65.07 114	58.75 92	23.79 225	41.27 101	27.07 137	37.95 98	41.34 110	50.85 69	62.90 107	62.34 119	74.17 105	80.37 89

MVS_111021_LR		57.06 70	60.60 69	52.93 72	56.25 85	65.14 113	55.16 116	41.21 146	52.32 67	44.89 48	53.92 46	49.27 77	52.16 63	61.46 119	60.54 143	67.92 165	81.53 75

tfpn111		51.00 128	52.68 134	49.04 124	56.10 87	64.52 123	53.05 129	47.31 71	35.86 135	24.79 148	36.35 109	34.10 154	41.08 136	60.84 130	61.37 129	71.90 139	75.70 116

conf200view11		50.87 130	52.45 138	49.04 124	56.10 87	64.52 123	53.05 129	47.31 71	35.86 135	24.79 148	34.74 124	34.10 154	41.08 136	60.84 130	61.37 129	71.90 139	75.70 116

thres100view900		52.33 114	53.91 116	50.48 107	56.10 87	67.79 91	56.18 111	49.18 45	35.86 135	25.22 143	34.74 124	34.10 154	42.41 134	64.45 74	62.62 114	73.81 111	77.85 97

tfpn200view9		50.91 129	52.45 138	49.11 122	56.10 87	64.53 121	53.06 128	47.31 71	35.86 135	25.22 143	34.74 124	34.10 154	41.08 136	60.84 130	61.37 129	71.90 139	75.70 116

thres200		50.76 132	52.52 136	48.70 126	55.98 91	64.60 119	55.29 115	47.34 69	33.91 153	24.36 152	34.33 133	33.90 158	37.27 146	60.84 130	62.41 118	71.99 137	77.63 98

IS_MVSNet		51.53 122	57.98 84	44.01 153	55.96 92	66.16 103	47.65 154	42.84 131	39.82 105	19.09 177	44.97 70	50.28 70	27.20 187	63.43 101	63.84 99	71.33 144	77.33 99

PatchmatchNet		53.37 100	55.62 96	50.75 102	55.93 93	70.54 67	51.39 138	36.41 175	44.85 84	37.26 79	39.40 94	42.54 102	47.83 106	60.29 137	60.88 140	75.69 62	70.87 149
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
LS3D		49.59 139	49.75 157	49.40 120	55.88 94	59.86 168	56.31 110	45.33 90	48.57 78	28.32 132	31.54 155	36.81 128	46.27 115	57.17 163	55.88 175	64.29 185	58.42 192

diffmvs		61.00 57	65.21 49	56.08 64	55.72 95	74.18 44	64.62 52	43.25 124	56.71 56	42.71 60	50.01 57	62.20 41	54.45 44	64.56 72	64.30 96	75.75 59	84.53 45

IterMVS-LS		53.36 101	55.65 95	50.68 105	55.34 96	59.04 170	55.00 117	39.98 152	38.72 110	33.22 110	44.52 71	47.05 89	49.63 81	61.82 116	61.77 124	70.92 147	76.61 107
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
UA-Net		47.19 156	53.02 127	40.38 176	55.31 97	60.02 167	38.41 187	38.68 163	36.42 129	22.47 162	51.95 50	58.72 53	25.62 190	54.11 179	53.40 188	61.79 198	56.51 196

MVSTER		62.51 48	67.22 41	57.02 60	55.05 98	69.23 83	63.02 58	46.88 77	61.11 50	43.95 51	59.20 36	58.86 51	56.80 32	69.13 39	70.98 26	76.41 48	82.04 59

thres400		50.39 133	52.22 140	48.26 128	55.02 99	66.32 102	52.97 133	48.33 54	32.68 161	22.94 158	33.21 146	33.38 160	37.27 146	62.74 108	61.38 128	73.04 128	75.81 113

CPTT-MVS		59.54 62	64.47 52	53.79 71	54.99 100	67.63 93	65.48 50	44.59 108	64.81 44	37.74 76	51.55 51	59.90 49	49.77 78	61.83 115	61.26 134	70.18 153	84.31 46

EPP-MVSNet		52.91 104	58.91 74	45.91 138	54.99 100	68.84 86	49.27 144	42.71 133	37.53 118	20.20 170	46.09 66	56.19 57	36.90 148	61.37 122	60.90 138	71.41 143	81.41 77

tfpn_ndepth		46.53 162	49.41 160	43.18 161	54.66 102	61.56 155	42.25 177	45.66 89	35.68 141	18.31 183	36.55 107	34.84 149	28.88 183	55.45 174	57.01 168	69.32 159	64.78 172

Fast-Effi-MVS+		55.73 72	58.26 81	52.76 77	54.33 103	68.19 88	57.05 99	34.66 188	46.92 82	38.96 73	40.53 82	41.55 107	55.69 38	65.31 66	65.99 62	75.90 57	79.34 92

view600		48.85 144	50.58 153	46.82 133	54.19 104	64.94 115	50.81 139	47.53 66	31.78 167	21.59 164	32.31 151	32.63 163	34.28 156	61.06 125	57.41 163	72.54 131	73.96 125

MDTV_nov1_ep13		52.99 103	55.59 100	49.95 114	54.08 105	70.69 65	56.47 108	38.42 165	42.78 91	30.19 125	39.56 91	43.31 100	45.78 116	60.07 142	62.11 121	74.74 82	70.62 150

thres600view7		48.44 147	50.23 154	46.35 136	54.05 106	64.60 119	50.18 142	47.34 69	31.73 168	20.74 167	32.28 152	32.62 164	33.79 158	60.84 130	56.11 173	71.99 137	73.40 129

thresconf0.02		47.89 151	50.76 152	44.54 147	53.86 107	63.96 130	46.23 165	47.72 60	33.00 160	17.08 186	36.35 109	37.80 116	29.86 177	60.01 144	60.57 142	72.49 132	63.62 178

view800		47.68 152	49.78 156	45.24 144	53.39 108	63.19 135	48.13 151	46.57 81	30.98 173	20.25 169	31.52 156	31.90 170	31.52 169	59.37 147	59.61 152	71.56 142	71.89 140

EPNet_dtu		49.85 138	56.99 90	41.52 172	52.79 109	57.06 181	41.44 180	43.13 126	56.13 60	19.24 176	52.11 49	48.38 82	22.14 197	58.19 156	58.38 157	70.35 151	68.71 164
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
tfpnnormal		46.61 161	46.82 174	46.37 135	52.70 110	62.31 149	50.39 141	47.17 74	25.74 201	21.80 163	23.13 199	24.15 209	33.45 162	60.28 138	60.77 141	72.70 130	71.39 144

tfpn		46.62 160	49.07 163	43.75 155	52.70 110	61.49 156	45.65 167	45.68 88	30.25 178	18.84 180	30.87 163	33.67 159	29.22 182	57.80 158	59.49 153	70.44 150	69.95 158

v18		53.63 94	54.35 112	52.80 76	52.25 112	62.94 138	60.80 67	42.78 132	39.23 107	36.81 80	35.07 117	37.78 117	49.82 76	63.69 90	64.65 81	74.32 98	77.07 101

v16		53.50 96	54.17 113	52.73 79	52.24 113	62.90 139	60.67 69	42.67 135	38.72 110	36.70 81	34.84 123	37.59 120	49.69 80	63.72 87	64.68 77	74.39 96	76.72 103

v17		53.40 99	54.09 114	52.60 81	52.22 114	62.90 139	60.64 71	42.66 136	38.24 113	36.04 83	34.85 122	37.59 120	49.63 81	63.70 89	64.68 77	74.39 96	76.70 104

CANet_DTU		57.87 65	63.63 55	51.15 99	52.18 115	70.20 68	58.14 94	37.32 171	56.49 57	31.06 120	57.38 38	50.05 72	53.67 51	64.98 68	65.04 69	74.57 90	81.29 81

v8		53.77 92	54.82 109	52.54 83	52.12 116	66.95 99	60.56 75	43.23 125	37.17 124	35.35 86	34.96 118	37.50 122	49.51 86	63.67 95	64.59 83	74.48 92	78.91 95

v1neww		54.32 81	55.60 98	52.81 74	52.11 117	69.43 80	60.57 72	44.86 97	37.13 126	35.34 87	34.95 120	37.46 124	49.53 83	63.69 90	64.59 83	74.47 93	81.99 61

v7new		54.32 81	55.60 98	52.81 74	52.11 117	69.43 80	60.57 72	44.86 97	37.13 126	35.34 87	34.95 120	37.46 124	49.53 83	63.69 90	64.59 83	74.47 93	81.99 61

v6		54.32 81	55.61 97	52.82 73	52.11 117	69.44 79	60.57 72	44.86 97	37.15 125	35.40 85	34.96 118	37.47 123	49.52 85	63.68 93	64.59 83	74.47 93	81.99 61

v7		53.99 87	55.20 101	52.57 82	52.08 120	69.46 78	59.68 83	44.92 96	35.90 132	34.33 93	33.99 137	35.55 141	50.08 72	64.38 76	64.67 79	74.32 98	82.47 55

v10		53.44 98	54.40 111	52.31 87	52.08 120	66.99 97	59.68 83	43.41 121	35.90 132	34.30 94	33.98 138	35.56 140	50.10 71	64.39 75	64.67 79	74.32 98	79.30 93

v1144		53.47 97	54.65 110	52.10 89	51.93 122	69.81 71	59.32 88	44.77 105	33.21 159	32.52 112	33.55 144	34.34 153	49.29 88	64.58 71	64.81 74	74.74 82	82.27 56

v15		52.60 108	53.17 123	51.94 90	51.92 123	62.76 141	60.04 80	42.19 138	34.35 144	33.96 98	34.37 132	36.40 130	48.73 96	63.75 86	64.59 83	74.79 78	75.97 111

V14		52.51 110	53.06 125	51.87 91	51.91 124	62.70 143	59.93 81	42.13 139	34.16 147	33.88 100	34.22 134	36.35 133	48.62 97	63.72 87	64.59 83	74.77 79	75.69 119

v1141		53.78 89	55.02 105	52.33 85	51.89 125	69.75 73	60.24 77	44.81 102	34.04 151	33.34 107	34.57 127	36.17 138	48.76 93	63.90 82	64.81 74	74.94 74	81.87 69

divwei89l23v2f112		53.78 89	55.02 105	52.33 85	51.89 125	69.74 75	60.25 76	44.82 101	34.06 149	33.33 108	34.56 130	36.18 136	48.75 94	63.90 82	64.82 72	74.94 74	81.88 67

v1		53.78 89	55.02 105	52.34 84	51.89 125	69.75 73	60.24 77	44.81 102	34.05 150	33.39 106	34.57 127	36.18 136	48.75 94	63.90 82	64.82 72	74.94 74	81.88 67

V9		52.42 113	52.94 128	51.81 92	51.89 125	62.64 145	59.81 82	42.08 141	33.97 152	33.85 101	34.05 136	36.28 134	48.49 99	63.68 93	64.59 83	74.76 80	75.41 120

conf0.05thres1000		45.26 167	46.99 172	43.24 159	51.87 129	60.52 163	45.17 169	45.24 91	27.06 193	18.60 181	26.24 187	31.23 180	28.82 184	56.88 166	58.52 156	69.71 157	68.50 165

v12		52.31 115	52.81 131	51.72 94	51.87 129	62.56 146	59.66 85	42.02 142	33.77 154	33.70 104	33.88 139	36.20 135	48.36 100	63.64 96	64.56 90	74.73 85	75.08 123

v13		52.22 117	52.69 133	51.67 95	51.85 131	62.48 148	59.57 86	41.97 143	33.61 156	33.69 105	33.71 142	36.11 139	48.23 103	63.57 98	64.55 91	74.72 86	74.77 124

Vis-MVSNet (Re-imp)		44.31 175	51.67 144	35.72 193	51.82 132	55.24 189	34.57 197	41.63 145	39.10 108	8.84 209	45.93 67	46.63 90	14.45 212	54.09 180	57.03 167	63.00 193	63.65 177

v11		52.23 116	52.83 130	51.53 97	51.73 133	62.49 147	58.82 91	41.81 144	33.53 157	33.23 109	33.73 141	35.10 146	49.07 90	64.49 73	64.71 76	74.49 91	75.75 115

v2v482		54.00 85	55.12 102	52.69 80	51.73 133	69.42 82	60.65 70	45.09 93	34.56 143	33.73 103	35.29 114	35.36 143	49.92 74	64.05 81	65.16 68	75.00 71	81.98 64

test-LLR		54.62 79	58.66 76	49.89 115	51.68 135	65.89 105	47.88 152	46.35 83	42.51 92	29.84 126	41.41 79	48.87 79	45.20 119	62.91 105	64.43 94	78.43 23	84.62 43

test0.0.03 1		43.07 181	46.95 173	38.54 184	51.68 135	58.77 173	35.28 192	46.35 83	32.05 165	12.44 196	28.53 180	35.52 142	14.40 213	57.12 165	56.93 169	71.11 145	59.69 185

GA-MVS		53.77 92	56.41 91	50.70 103	51.63 137	69.96 70	57.55 97	44.39 109	34.31 145	27.15 135	40.99 81	36.40 130	47.65 108	67.45 52	67.16 53	75.83 58	78.60 96

UniMVSNet_NR-MVSNet		49.56 140	53.04 126	45.49 141	51.59 138	64.42 127	46.97 159	51.01 34	37.87 114	16.42 187	39.87 86	34.91 148	33.43 163	59.59 146	62.70 110	73.52 116	71.94 137

v1192		52.69 106	53.86 117	51.31 98	51.22 139	69.76 72	57.37 98	44.39 109	32.21 163	31.39 119	32.41 150	32.44 165	49.19 89	64.25 77	64.17 97	74.31 101	81.81 70

tfpnview11		42.71 184	45.29 182	39.71 177	51.06 140	58.61 177	38.47 185	44.80 104	30.44 177	13.60 190	31.25 159	30.97 182	22.40 194	54.20 178	55.04 181	67.90 166	56.51 196

v144192		52.43 112	53.63 119	51.03 100	51.06 140	69.60 76	56.94 101	44.84 100	32.15 164	30.88 121	32.45 149	32.71 161	48.36 100	62.98 104	63.52 103	74.10 110	82.02 60

tfpn_n400		42.55 185	45.11 184	39.55 179	50.95 142	58.68 175	38.40 188	44.75 106	29.29 182	13.60 190	31.25 159	30.97 182	22.38 195	53.96 182	55.66 177	67.20 173	56.00 199

tfpnconf		42.55 185	45.11 184	39.55 179	50.95 142	58.68 175	38.40 188	44.75 106	29.29 182	13.60 190	31.25 159	30.97 182	22.38 195	53.96 182	55.66 177	67.20 173	56.00 199

tfpn1000		41.76 189	45.01 186	37.96 188	50.95 142	58.44 178	34.94 194	44.09 114	30.68 175	12.08 197	30.14 169	31.96 169	18.67 201	51.96 190	53.45 187	67.05 175	58.40 193

v1921920		51.95 118	53.19 122	50.51 106	50.82 145	69.14 84	55.45 113	44.34 113	31.53 169	30.53 123	31.96 153	31.67 172	48.31 102	63.12 102	63.28 105	73.59 114	81.60 74

FMVSNet3		55.66 74	59.68 70	50.96 101	50.59 146	66.49 100	57.57 96	46.61 78	49.30 74	28.77 129	39.61 88	51.42 66	43.85 128	68.29 47	68.80 43	78.35 26	73.86 126

TranMVSNet+NR-MVSNet		48.06 150	51.36 147	44.21 151	50.38 147	62.09 151	47.28 156	50.88 37	36.11 130	13.25 195	37.51 100	31.60 173	30.70 173	59.34 148	62.53 116	72.81 129	70.31 152

v1240		51.42 123	52.66 135	49.97 113	50.31 148	68.70 87	54.05 122	43.85 117	30.78 174	30.22 124	31.43 157	31.03 181	47.98 104	62.62 109	63.16 107	73.40 119	80.93 84

v148		51.72 119	53.15 124	50.05 111	50.15 149	67.51 94	56.98 100	42.85 130	32.60 162	32.41 114	33.88 139	34.71 150	44.45 127	61.06 125	63.00 108	73.45 118	79.24 94

PatchT		48.11 149	51.27 148	44.43 148	50.13 150	61.58 154	33.59 198	32.92 205	40.38 103	31.74 116	30.60 167	36.93 127	45.00 123	58.80 152	61.11 136	73.19 124	69.47 160

CNLPA		54.00 85	57.08 88	50.40 108	49.83 151	61.75 153	53.47 124	37.27 172	74.55 20	44.85 49	33.58 143	45.42 96	52.94 61	58.89 151	53.66 186	64.06 186	71.68 143

pmmvs4		51.28 125	52.50 137	49.85 116	49.54 152	63.02 137	52.83 134	43.41 121	44.65 85	35.71 84	34.38 131	32.25 166	45.14 122	60.21 141	60.03 147	72.44 133	72.98 135

GBi-Net		54.66 77	58.42 78	50.26 109	49.36 153	65.81 108	56.80 103	46.61 78	49.30 74	28.77 129	39.61 88	51.42 66	42.71 131	64.25 77	65.54 64	77.32 38	73.03 132

test1		54.66 77	58.42 78	50.26 109	49.36 153	65.81 108	56.80 103	46.61 78	49.30 74	28.77 129	39.61 88	51.42 66	42.71 131	64.25 77	65.54 64	77.32 38	73.03 132

FMVSNet2		53.94 88	57.29 87	50.03 112	49.36 153	65.81 108	56.80 103	45.95 86	43.13 90	28.04 133	35.68 112	48.18 84	42.71 131	67.23 56	67.95 49	77.32 38	73.03 132

pm-mvs1		46.14 163	49.34 162	42.41 165	48.93 156	62.22 150	44.98 170	42.68 134	27.66 189	20.76 166	29.88 174	34.96 147	26.41 189	60.03 143	60.42 144	70.70 149	70.20 153

testpf		31.84 213	34.86 213	28.32 213	48.89 157	32.91 226	26.53 217	25.77 224	21.99 208	10.05 206	23.39 197	25.55 204	14.07 214	39.23 222	42.32 218	44.58 224	58.65 189

Anonymous20231206		40.63 190	43.29 191	37.53 189	48.88 158	55.81 186	34.99 193	44.98 95	28.16 186	10.16 205	17.26 215	27.50 196	18.28 202	54.00 181	55.07 180	67.85 167	65.23 171

ADS-MVSNet		45.39 166	46.42 177	44.19 152	48.74 159	57.52 180	43.91 174	31.93 209	35.89 134	27.11 136	30.12 170	32.06 168	45.30 117	53.13 188	55.19 179	68.15 164	61.07 184

v7n		47.22 155	48.38 166	45.87 139	48.20 160	63.58 131	50.69 140	40.93 149	26.60 196	26.44 139	26.52 186	29.65 188	38.19 144	58.22 155	60.23 146	70.79 148	73.83 127

Vis-MVSNet		51.13 126	58.04 83	43.06 162	47.68 161	67.71 92	49.10 147	39.09 161	37.75 116	22.57 160	51.03 55	48.78 81	32.42 167	62.12 112	61.80 123	67.49 170	77.12 100
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
MVS-HIRNet		43.98 177	43.63 190	44.39 150	47.66 162	59.31 169	32.66 204	33.88 201	30.15 179	33.75 102	16.82 217	28.39 194	45.25 118	53.92 185	55.00 182	73.16 125	61.80 181

IterMVS		50.23 134	53.27 120	46.68 134	47.59 163	60.58 162	53.10 127	36.62 174	36.07 131	25.89 140	39.42 93	40.05 113	43.65 129	60.22 140	61.35 133	73.23 123	75.23 121
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
CDS-MVSNet		49.25 141	53.97 115	43.75 155	47.53 164	64.53 121	48.59 148	42.27 137	33.77 154	26.64 138	40.46 84	42.26 104	30.01 175	61.77 117	61.71 125	67.48 171	73.28 131
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
testgi		34.51 206	37.42 206	31.12 209	47.37 165	50.34 196	24.38 222	41.21 146	20.32 215	5.64 220	20.56 203	26.55 199	8.06 228	49.28 195	52.65 189	60.05 201	42.23 222

CR-MVSNet		48.82 146	51.85 141	45.29 143	46.74 166	55.95 184	52.06 136	34.21 194	42.17 96	31.74 116	32.92 148	42.53 103	45.00 123	58.80 152	61.11 136	61.99 197	69.47 160

MDTV_nov1_ep13_2view		44.44 171	45.75 180	42.91 163	46.13 167	63.43 133	46.53 164	34.20 196	29.08 185	19.95 173	26.23 188	27.89 195	35.88 152	53.36 187	56.43 172	74.74 82	63.86 176

test20.03		36.00 202	38.92 200	32.60 201	45.92 168	50.99 194	28.05 215	43.69 120	21.62 211	6.03 216	17.61 213	25.91 202	8.34 227	51.26 191	52.60 191	63.58 188	52.46 207

UniMVSNet (Re)		46.89 159	51.65 145	41.34 173	45.60 169	62.71 142	44.05 173	47.10 75	37.24 122	13.55 193	36.90 103	34.54 152	26.76 188	57.56 159	59.90 150	70.98 146	72.69 136

FMVSNet1		50.14 136	52.78 132	47.06 131	45.56 170	63.56 132	54.22 120	43.74 119	34.10 148	25.37 142	29.79 175	42.06 105	38.70 142	64.25 77	65.54 64	74.75 81	70.18 154

RPMNet		43.70 178	48.17 167	38.48 185	45.52 171	55.95 184	37.66 190	26.63 221	42.17 96	25.47 141	29.59 177	37.61 118	33.87 157	50.85 193	52.02 193	61.75 199	69.00 162

v748		44.90 168	46.14 179	43.46 158	45.37 172	60.89 159	48.15 150	39.42 156	25.81 200	24.36 152	25.90 190	28.48 193	34.44 154	53.39 186	57.35 164	69.00 160	71.14 148

TESTMET0.1,1		53.30 102	58.66 76	47.04 132	44.94 173	65.89 105	47.88 152	35.95 180	42.51 92	29.84 126	41.41 79	48.87 79	45.20 119	62.91 105	64.43 94	78.43 23	84.62 43

V42		52.63 107	55.08 103	49.76 117	44.93 174	67.49 95	60.19 79	42.13 139	37.21 123	34.08 97	34.57 127	37.30 126	47.29 109	63.48 100	64.15 98	69.96 156	81.38 78

TAMVS		44.27 176	49.35 161	38.35 186	44.74 175	61.04 158	39.07 184	31.82 210	29.95 180	18.34 182	33.55 144	39.94 114	30.01 175	56.85 167	57.58 161	66.13 178	66.54 167

pmmvs6		41.90 188	44.01 189	39.43 181	44.45 176	58.77 173	41.92 178	39.22 160	21.74 209	19.08 178	17.40 214	31.33 177	24.28 193	55.94 170	56.67 170	67.60 169	66.24 168

DU-MVS		47.33 154	50.86 150	43.20 160	44.43 177	60.64 160	46.97 159	47.63 61	37.26 120	16.42 187	37.31 101	31.39 175	33.43 163	57.53 160	59.98 148	70.35 151	71.94 137

Baseline_NR-MVSNet		47.14 157	50.83 151	42.84 164	44.43 177	63.31 134	44.50 172	50.36 41	37.71 117	11.25 201	30.84 164	32.09 167	30.96 171	57.53 160	63.73 101	75.53 63	70.60 151

PMMVS		55.74 71	62.68 57	47.64 130	44.34 179	65.58 111	47.22 158	37.96 167	56.43 59	34.11 96	61.51 30	47.41 87	54.55 42	65.88 60	62.49 117	67.67 168	79.48 90

Anonymous20231211		32.12 212	32.10 219	32.15 206	44.26 180	46.14 207	29.39 210	39.72 154	14.08 229	3.70 228	7.94 230	13.30 227	16.12 206	43.07 213	47.88 207	59.72 202	52.28 209

CMPMVS	33.64 16	44.39 174	46.41 178	42.03 167	44.21 181	56.50 183	46.73 162	26.48 222	34.20 146	35.14 89	24.22 196	34.64 151	40.52 141	56.50 169	56.07 174	59.12 204	62.74 180
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
LP		38.21 194	37.72 204	38.79 183	44.07 182	51.16 192	35.54 191	31.37 212	25.38 204	23.73 155	18.64 208	18.03 219	29.31 181	47.85 198	52.63 190	68.71 162	50.34 214

WR-MVS		37.61 195	42.15 192	32.31 204	43.64 183	51.85 190	29.39 210	43.35 123	27.65 190	4.40 223	29.90 173	29.80 187	10.46 220	46.73 201	51.98 194	62.60 195	57.16 194

pmmvs5		47.02 158	50.02 155	43.51 157	43.48 184	62.65 144	47.24 157	37.78 169	30.59 176	24.80 147	35.26 115	30.43 185	34.36 155	59.05 150	60.28 145	73.40 119	71.92 139

LTVRE_ROB	32.83 17	35.10 204	37.46 205	32.35 203	43.12 185	49.99 198	28.52 213	33.23 204	12.73 230	8.18 210	27.71 183	21.34 212	32.64 166	46.92 200	48.11 204	48.41 220	55.45 202
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
PLC	44.22 14	49.14 142	51.75 143	46.10 137	42.78 186	55.60 188	53.11 126	34.46 193	55.69 62	32.47 113	34.16 135	41.45 108	48.91 92	57.13 164	54.09 184	64.84 183	64.10 174
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
pmmvs-eth3d		44.67 170	45.27 183	43.98 154	42.56 187	55.72 187	44.97 171	40.81 150	31.96 166	29.13 128	26.09 189	25.27 206	36.69 149	55.13 176	56.62 171	69.68 158	66.12 169

OMC-MVS		55.48 75	61.85 65	48.04 129	41.55 188	60.32 164	56.80 103	31.78 211	75.67 18	42.30 63	51.52 52	54.15 61	49.91 75	60.28 138	57.59 160	65.91 179	73.42 128

DTE-MVSNet		36.91 198	40.44 196	32.79 200	40.74 189	47.55 204	30.71 208	44.39 109	27.03 194	4.32 224	30.88 162	25.99 201	12.73 215	45.58 203	50.80 197	63.86 187	55.23 203

UGNet		51.04 127	58.79 75	42.00 168	40.59 190	65.32 112	46.65 163	39.26 159	39.90 104	27.30 134	54.12 45	52.03 64	30.93 172	59.85 145	59.62 151	67.23 172	80.70 85
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
PEN-MVS		38.23 193	41.72 193	34.15 195	40.56 191	50.07 197	33.17 201	44.35 112	27.64 191	5.54 221	30.84 164	26.67 198	14.99 210	45.64 202	52.38 192	66.29 177	58.83 188

1111		29.41 219	30.75 220	27.85 214	39.46 192	37.63 221	22.26 223	32.15 207	17.93 222	7.92 211	13.48 221	20.98 213	17.30 204	44.76 206	46.51 213	47.99 221	33.96 226

.test1245		19.53 226	19.26 228	19.85 226	39.46 192	37.63 221	22.26 223	32.15 207	17.93 222	7.92 211	13.48 221	20.98 213	17.30 204	44.76 206	0.01 234	0.00 238	0.03 235

v52		44.41 172	46.76 175	41.67 169	38.93 194	60.06 165	49.26 145	36.02 177	25.57 202	24.73 151	25.66 191	31.34 176	35.93 150	55.52 172	57.99 158	65.14 181	71.21 146

V4		44.41 172	46.76 175	41.67 169	38.93 194	60.05 166	49.26 145	36.02 177	25.55 203	24.75 150	25.66 191	31.33 177	35.93 150	55.52 172	57.99 158	65.14 181	71.21 146

ambc			35.52 212		38.36 196	40.40 217	28.38 214		25.20 205	14.87 189	13.22 223	7.54 234	19.34 200	55.63 171	47.79 208	47.91 222	58.89 187

MIMVSNet		45.62 164	49.56 159	41.02 174	38.17 197	64.43 126	49.48 143	35.43 185	36.53 128	20.06 172	22.58 200	35.16 145	28.75 185	61.97 114	62.20 120	74.20 103	64.07 175

PatchMatch-RL		43.37 179	44.93 187	41.56 171	37.94 198	51.70 191	40.02 182	35.75 181	39.04 109	30.71 122	35.14 116	27.43 197	46.58 112	51.99 189	50.55 198	58.38 206	58.64 190

WR-MVS_H		36.29 200	40.35 198	31.55 207	37.80 199	49.94 199	30.57 209	41.11 148	26.90 195	4.14 225	30.72 166	28.85 191	10.45 221	42.47 215	47.99 206	65.24 180	55.54 201

CP-MVSNet		37.09 197	40.62 195	32.99 197	37.56 200	48.25 202	32.75 202	43.05 127	27.88 188	5.93 217	31.27 158	25.82 203	15.09 208	43.37 211	48.82 200	63.54 190	58.90 186

PS-CasMVS		36.84 199	40.23 199	32.89 198	37.44 201	48.09 203	32.68 203	42.97 129	27.36 192	5.89 218	30.08 172	25.48 205	14.96 211	43.28 212	48.71 201	63.39 191	58.63 191

FC-MVSNet-test		30.97 215	37.38 207	23.49 222	37.42 202	33.68 225	19.43 228	39.27 158	31.37 171	1.67 236	38.56 97	28.85 191	6.06 232	41.40 218	43.80 217	37.10 227	44.03 221

N_pmnet		34.09 208	35.74 211	32.17 205	37.25 203	43.17 213	32.26 206	35.57 183	26.22 198	10.60 204	20.44 204	19.38 217	20.20 199	44.59 208	47.00 211	57.13 209	49.35 216

SixPastTwentyTwo		36.11 201	37.80 203	34.13 196	37.13 204	46.72 206	34.58 196	34.96 187	21.20 213	11.66 198	29.15 179	19.88 216	29.77 178	44.93 204	48.34 203	56.67 210	54.41 205

testus		29.45 218	32.20 218	26.23 216	37.01 205	37.90 220	17.56 229	35.70 182	18.23 220	3.39 229	17.04 216	14.78 223	11.78 217	42.48 214	49.38 199	51.92 219	45.62 219

new-patchmatchnet		30.47 216	32.80 217	27.75 215	36.81 206	43.98 210	24.85 220	39.29 157	20.52 214	4.06 226	15.94 218	16.05 222	9.57 222	41.32 219	42.05 220	51.94 218	49.74 215

TAPA-MVS	47.92 11	51.66 120	57.88 85	44.40 149	36.46 207	58.42 179	53.82 123	30.83 213	69.51 34	34.97 90	46.90 64	49.67 74	46.99 110	58.00 157	54.64 183	63.33 192	68.00 166
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
COLMAP_ROB	34.79 15	38.65 192	40.72 194	36.23 192	36.41 208	49.22 201	45.51 168	27.60 219	37.81 115	20.54 168	23.37 198	24.25 208	28.11 186	51.02 192	48.55 202	59.22 203	50.82 212
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
test2356		34.09 208	36.84 209	30.87 210	36.25 209	43.59 212	27.92 216	35.44 184	21.73 210	6.94 213	19.31 207	18.23 218	17.77 203	49.28 195	51.58 195	60.94 200	54.17 206

anonymousdsp		43.03 182	47.19 170	38.18 187	36.00 210	56.92 182	38.44 186	34.56 191	24.22 206	22.53 161	29.69 176	29.92 186	35.21 153	53.96 182	58.98 154	62.32 196	76.66 106

CVMVSNet		38.91 191	44.49 188	32.40 202	34.57 211	47.20 205	34.81 195	34.20 196	31.45 170	8.95 208	38.86 96	36.38 132	24.30 192	47.77 199	46.94 212	57.59 208	62.85 179

USDC		42.80 183	45.57 181	39.58 178	34.55 212	51.13 193	42.61 176	36.21 176	39.59 106	23.65 156	33.13 147	20.87 215	37.86 145	55.35 175	57.16 166	62.61 194	61.75 182

TSAR-MVS + COLMAP		54.37 80	62.43 60	44.98 145	34.33 213	58.94 172	54.11 121	34.15 199	74.06 21	34.57 91	71.63 13	42.03 106	47.88 105	61.26 123	57.33 165	64.83 184	71.74 142

test-mter		48.31 148	55.04 104	40.45 175	34.12 214	59.02 171	41.77 179	28.05 217	38.43 112	22.67 159	39.35 95	44.40 98	41.88 135	60.30 136	61.68 126	74.20 103	82.12 58

CHOSEN 280x420		42.39 187	47.40 169	36.54 191	33.56 215	39.66 219	40.67 181	26.88 220	34.66 142	18.03 184	30.09 171	45.59 94	44.82 125	54.46 177	54.00 185	55.28 213	73.32 130

EU-MVSNet		33.00 211	36.49 210	28.92 211	33.10 216	42.86 214	29.32 212	35.99 179	22.94 207	5.83 219	25.29 193	24.43 207	15.21 207	41.22 220	41.65 221	54.08 214	57.01 195

testmv		27.97 220	29.98 221	25.62 218	32.54 217	36.86 223	20.53 225	33.33 202	14.11 227	2.64 231	12.76 225	11.77 229	11.07 218	42.34 216	45.44 215	53.60 216	46.60 217

test1235678		27.96 221	29.97 222	25.62 218	32.54 217	36.83 224	20.53 225	33.33 202	14.10 228	2.64 231	12.75 226	11.76 230	11.07 218	42.34 216	45.43 216	53.60 216	46.59 218

TinyColmap		37.18 196	37.37 208	36.95 190	31.17 219	45.21 209	39.71 183	34.65 189	29.83 181	20.20 170	18.54 209	13.72 226	38.27 143	50.33 194	51.57 196	57.71 207	52.42 208

FMVSNet5		43.29 180	47.07 171	38.87 182	30.46 220	50.99 194	45.87 166	37.19 173	42.17 96	19.32 175	26.77 184	40.51 111	30.26 174	56.82 168	55.81 176	70.10 154	56.46 198

FPMVS		26.87 222	28.19 223	25.32 220	27.09 221	29.49 229	32.28 205	17.79 230	28.09 187	11.33 199	19.38 206	14.69 224	20.88 198	35.11 224	32.82 226	42.56 225	37.75 224

no-one		21.91 224	22.52 227	21.20 224	25.97 222	30.78 228	13.29 232	32.75 206	9.08 233	1.84 233	6.18 232	7.00 235	8.03 229	25.56 229	40.16 222	45.29 223	38.83 223

MDA-MVSNet-bldmvs		34.31 207	34.11 214	34.54 194	24.73 223	49.66 200	33.42 200	43.03 128	21.59 212	11.10 202	19.81 205	12.68 228	31.41 170	35.59 223	48.05 205	63.56 189	51.39 211

pmmvs3		31.22 214	33.62 215	28.43 212	22.82 224	40.26 218	26.40 218	22.05 228	16.89 224	10.99 203	14.72 219	16.26 221	29.70 179	44.82 205	47.39 209	58.61 205	54.98 204

PM-MVS		34.96 205	38.17 202	31.22 208	22.78 225	40.82 215	33.56 199	23.61 226	29.16 184	21.43 165	28.00 182	21.43 211	31.90 168	44.33 209	42.12 219	54.07 215	61.34 183

test12356		20.09 225	22.80 225	16.93 227	22.59 226	24.43 230	13.32 231	25.93 223	12.67 231	1.58 238	11.53 228	9.25 232	2.29 233	33.15 227	37.05 223	35.85 229	31.54 227

PMVS	18.18 18	21.95 223	22.85 224	20.90 225	21.92 227	14.78 232	19.95 227	17.31 231	15.69 225	11.32 200	13.70 220	13.91 225	15.02 209	34.92 225	31.72 227	39.85 226	35.20 225
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
E-PMN		10.66 230	8.30 232	13.42 230	19.91 228	7.87 236	4.30 237	29.47 215	8.37 236	1.70 235	3.67 233	1.29 241	9.12 224	8.98 234	13.59 231	16.03 233	14.30 233

MIMVSNet1		29.60 217	33.37 216	25.20 221	19.52 229	43.94 211	26.29 219	37.92 168	19.95 218	3.79 227	12.64 227	21.99 210	7.70 230	43.83 210	46.32 214	55.97 212	44.92 220

EMVS		10.15 231	7.67 233	13.05 231	19.22 230	7.77 237	4.48 235	29.34 216	8.65 235	1.67 236	3.55 234	1.36 240	9.15 223	8.15 235	11.79 233	14.44 234	12.43 234

TDRefinement		35.76 203	38.23 201	32.88 199	19.09 231	46.04 208	43.29 175	29.49 214	33.49 158	19.04 179	22.29 202	17.82 220	29.69 180	48.60 197	47.24 210	56.65 211	52.12 210

Gipuma		17.16 228	17.83 229	16.36 228	18.76 232	12.15 235	11.97 233	27.78 218	17.94 221	4.86 222	2.53 236	2.73 238	8.90 225	34.32 226	36.09 225	25.92 231	19.06 230
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
RPSCF		33.61 210	40.43 197	25.65 217	16.00 233	32.41 227	31.73 207	13.33 233	50.13 72	23.12 157	31.56 154	40.09 112	32.73 165	41.14 221	37.05 223	36.99 228	50.63 213

PMMVS2		12.25 229	14.17 230	10.00 232	11.39 234	14.35 233	8.21 234	19.29 229	9.31 232	0.19 240	7.38 231	6.19 236	1.10 235	19.26 230	21.13 230	19.85 232	21.56 229

new_pmnet		19.10 227	22.71 226	14.89 229	10.93 235	24.08 231	14.22 230	13.94 232	18.68 219	2.93 230	12.84 224	11.27 231	11.94 216	30.57 228	30.58 228	35.38 230	30.93 228

MVE	10.35 19	9.76 232	11.08 231	8.22 233	4.43 236	13.04 234	3.36 238	23.57 227	5.74 237	1.76 234	3.09 235	1.75 239	6.78 231	12.78 232	23.04 229	9.44 235	18.09 231
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
tmp_tt				4.41 234	2.56 237	1.81 239	2.61 239	0.27 235	20.12 216	9.81 207	17.69 212	9.04 233	1.96 234	12.88 231	12.11 232	9.23 236

GG-mvs-BLEND		44.87 169	64.59 51	21.86 223	0.01 238	73.70 48	55.99 112	0.01 236	50.70 70	0.01 241	49.18 58	63.61 35	0.01 236	63.83 85	64.50 92	75.13 69	86.62 29

sosnet-low-res		0.00 235	0.00 236	0.00 235	0.00 239	0.00 240	0.00 241	0.00 237	0.00 240	0.00 242	0.00 239	0.00 242	0.00 238	0.00 237	0.00 237	0.00 238	0.00 238

sosnet		0.00 235	0.00 236	0.00 235	0.00 239	0.00 240	0.00 241	0.00 237	0.00 240	0.00 242	0.00 239	0.00 242	0.00 238	0.00 237	0.00 237	0.00 238	0.00 238

testmvs		0.01 233	0.01 234	0.00 235	0.00 239	0.00 240	0.00 241	0.00 237	0.01 238	0.00 242	0.02 237	0.00 242	0.00 238	0.01 236	0.01 234	0.00 238	0.03 235

test123		0.01 233	0.01 234	0.00 235	0.00 239	0.00 240	0.00 241	0.00 237	0.01 238	0.00 242	0.02 237	0.00 242	0.01 236	0.00 237	0.01 234	0.00 238	0.03 235

MTAPA										54.82 10		71.98 18

MTMP										50.64 27		68.31 24

Patchmatch-RL test							0.69 240

NP-MVS									72.62 25

Patchmtry						64.49 125	52.06 136	34.21 194		31.74 116

DeepMVS_CX						5.87 238	4.32 236	1.74 234	9.04 234	1.30 239	7.97 229	3.16 237	8.56 226	9.74 233		6.30 237	14.51 232

High-resolution multi-view benchmark