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.

DVP-MVS		77.54 1	84.41 1	69.54 3	79.93 1	86.08 1	77.20 5	60.31 2	88.62 1	62.54 1	86.67 3	83.77 1	58.04 30	75.84 5	75.69 6	79.21 18	94.17 1

MCST-MVS		74.06 6	77.71 11	69.79 2	78.95 2	81.99 5	76.33 7	62.16 1	75.89 18	52.96 22	64.37 28	73.30 18	65.66 3	77.49 2	77.43 3	82.67 1	93.51 3

CSCG		72.98 9	76.86 13	68.46 5	78.23 3	81.74 7	77.26 4	60.00 3	75.61 21	59.06 3	62.72 30	77.42 5	56.63 42	74.24 9	77.18 4	79.56 13	89.13 18

DPE-MVS		75.74 3	82.82 3	67.49 8	77.07 4	82.01 4	77.05 6	57.70 8	86.55 4	55.44 12	90.50 2	82.52 2	60.33 16	72.99 13	72.98 14	77.33 44	92.19 6

APDe-MVS		74.59 5	80.23 4	68.01 7	76.51 5	80.20 12	77.39 3	58.18 6	85.31 5	56.84 9	84.89 4	76.08 10	60.66 14	71.85 24	71.76 19	78.47 27	91.49 9

DPM-MVS		74.63 4	78.53 8	70.07 1	76.10 6	82.56 3	79.30 1	59.89 4	80.49 10	57.75 7	66.98 22	76.16 9	65.95 2	79.35 1	78.47 1	81.45 5	85.71 43

3Dnovator	58.39 4	65.97 32	66.85 48	64.94 12	73.72 7	79.03 17	67.73 36	54.25 22	61.52 50	52.79 24	42.27 89	60.73 50	62.01 7	71.29 26	71.75 20	79.12 20	81.34 84

MAR-MVS		66.85 27	69.81 36	63.39 21	73.56 8	80.51 11	69.87 26	51.51 34	67.78 41	46.44 41	51.09 62	61.60 47	60.38 15	72.67 20	73.61 12	78.59 24	81.44 81
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 17	74.76 17	63.98 16	73.45 9	78.56 21	73.13 14	55.24 18	70.68 31	48.93 34	70.43 17	69.10 25	54.00 54	72.78 19	72.98 14	79.14 19	88.74 21
Skip Steuart: Steuart Systems R&D Blog.
CNVR-MVS		73.87 7	78.60 7	68.35 6	73.32 10	81.97 6	76.19 8	59.29 5	80.12 11	56.70 10	67.09 21	76.48 7	64.26 5	75.88 4	75.75 5	80.32 8	92.93 4

QAPM		65.47 35	67.82 40	62.72 24	72.56 11	81.17 10	67.43 39	55.38 17	56.07 62	43.29 58	43.60 84	65.38 33	59.10 25	72.20 21	70.76 31	78.56 25	85.59 46

CHOSEN 1792x2688		62.48 54	64.06 59	60.64 37	72.50 12	84.18 2	62.43 64	53.77 25	47.90 87	39.85 79	25.15 177	44.76 109	53.72 55	77.29 3	77.61 2	81.60 4	91.53 8

NCCC		71.36 13	75.44 15	66.60 9	72.46 13	79.18 16	74.16 10	57.83 7	76.93 16	54.19 17	63.47 29	71.08 23	61.30 12	73.56 11	73.70 11	79.69 12	90.19 11

OpenMVS	55.62 8	62.57 50	63.76 60	61.19 34	72.13 14	78.84 19	64.42 55	50.51 43	56.44 59	45.67 46	36.88 117	56.51 61	56.66 41	68.28 54	68.96 47	77.73 39	80.44 91

MSP-MVS		76.38 2	82.99 2	68.68 4	71.93 15	78.65 20	77.61 2	55.44 15	88.04 2	60.25 2	92.24 1	77.08 6	69.84 1	75.48 6	75.69 6	76.99 51	93.75 2

HPM-MVS++		72.44 10	78.73 6	65.11 11	71.88 16	77.31 29	71.98 17	55.67 13	83.11 8	53.59 19	75.90 9	78.49 4	61.00 13	73.99 10	73.31 13	76.55 54	88.97 19

SMA-MVS		73.31 8	79.53 5	66.05 10	71.25 17	80.13 13	74.99 9	56.09 11	84.14 6	54.48 15	73.74 13	80.23 3	61.43 10	74.96 7	74.09 10	78.08 34	89.42 15

MVS_111021_HR		64.66 39	67.11 46	61.80 29	71.04 18	77.91 25	62.75 63	54.78 20	51.43 75	47.54 40	53.77 53	54.85 65	56.84 37	70.59 29	71.50 22	77.86 37	89.70 13

AdaColmap		62.79 48	62.63 64	62.98 23	70.82 19	72.90 64	67.84 35	54.09 24	65.14 45	50.71 28	41.78 91	47.64 96	60.17 19	67.41 60	66.83 64	74.28 97	76.69 107

abl_6				63.79 20	70.80 20	81.22 9	65.26 54	53.25 27	77.02 15	53.02 21	65.14 27	73.74 16	60.30 17			80.13 9	90.27 10

MS-PatchMatch		61.41 61	61.88 72	60.85 35	70.57 21	75.98 36	66.29 48	46.91 78	50.56 77	48.28 38	36.30 120	51.64 72	50.95 77	72.89 16	70.65 32	82.13 3	75.17 116

APD-MVS		71.86 11	77.91 10	64.80 13	70.39 22	75.69 40	74.02 11	56.14 10	83.59 7	52.92 23	84.67 5	73.46 17	59.30 24	69.47 38	69.66 39	76.02 60	88.84 20
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
train_agg		70.74 14	76.53 14	63.98 16	70.33 23	75.16 44	72.33 16	55.78 12	75.74 19	50.41 31	80.08 8	73.15 19	57.75 34	71.96 23	70.94 29	77.25 48	88.69 22

ACMMP_NAP		71.50 12	77.27 12	64.77 14	69.64 24	79.26 14	73.53 12	54.73 21	79.32 13	54.23 16	74.81 10	74.61 14	59.40 23	73.00 12	72.17 17	77.10 50	87.72 28

TSAR-MVS + ACMM		65.95 33	72.83 20	57.93 53	69.35 25	65.85 114	73.36 13	39.84 140	76.00 17	48.69 37	82.54 7	75.03 13	49.38 90	65.33 73	63.42 101	66.94 160	81.67 78

TSAR-MVS + MP.		70.28 15	75.09 16	64.66 15	69.34 26	64.61 122	72.60 15	56.29 9	80.73 9	58.36 5	84.56 6	75.22 12	55.37 49	69.11 46	69.45 41	75.97 62	81.97 73
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
SD-MVS		68.30 19	72.58 21	63.31 22	69.24 27	67.85 95	70.81 23	53.65 26	79.64 12	58.52 4	74.31 11	75.37 11	53.52 60	65.63 70	63.56 99	74.13 102	81.73 77
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
DELS-MVS		67.36 21	70.34 35	63.89 19	69.12 28	81.55 8	70.82 22	55.02 19	53.38 70	48.83 35	56.45 44	59.35 52	60.05 21	74.93 8	74.78 8	79.51 14	91.95 7
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 26	71.64 27	61.65 31	69.10 29	76.84 33	71.35 21	55.42 16	67.02 42	42.83 60	65.27 26	64.60 35	53.16 63	69.70 37	71.40 23	78.02 36	86.67 35

HFP-MVS		68.75 18	72.84 19	63.98 16	68.87 30	75.09 45	71.87 18	51.22 35	73.50 25	58.17 6	68.05 20	68.67 26	57.79 33	70.49 31	69.23 43	75.98 61	84.84 50

MSLP-MVS++		61.81 59	62.19 69	61.37 33	68.33 31	63.08 136	70.75 24	38.89 146	63.96 48	57.51 8	48.59 70	61.66 46	53.67 58	62.04 109	59.92 144	79.03 21	76.08 110

CLD-MVS		64.69 38	67.25 43	61.69 30	68.22 32	78.33 22	63.09 60	47.59 69	69.64 35	53.98 18	54.87 50	53.94 68	57.87 31	72.79 17	71.34 24	79.40 16	69.87 150
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 24	72.08 24	61.56 32	66.76 33	73.58 57	71.41 19	52.98 28	69.92 34	43.85 54	70.58 16	58.75 54	56.76 39	72.90 15	71.88 18	77.57 40	86.94 34

OPM-MVS		61.59 60	62.30 68	60.76 36	66.53 34	73.35 59	71.41 19	54.18 23	40.82 115	41.57 72	45.70 79	54.84 66	54.43 53	69.92 35	69.19 44	76.45 55	82.25 67

MP-MVS		67.34 22	73.08 18	60.64 37	66.20 35	76.62 34	69.22 29	50.92 37	70.07 32	48.81 36	69.66 18	70.12 24	53.68 57	68.41 51	69.13 45	74.98 81	87.53 30
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
zzz-MVS		67.78 20	72.46 22	62.33 27	66.09 36	74.21 50	70.05 25	51.54 33	77.27 14	54.61 14	60.30 37	71.51 22	56.73 40	69.19 44	68.63 51	74.96 82	86.11 40

3Dnovator+	55.76 7	62.70 49	65.10 55	59.90 44	65.89 37	72.15 69	62.94 62	49.82 46	62.77 49	49.06 33	43.62 83	61.47 49	58.60 28	68.51 50	66.75 65	73.08 123	80.40 92

PGM-MVS		65.35 36	70.43 34	59.43 47	65.78 38	73.75 54	69.41 27	48.18 62	68.80 38	45.37 47	65.88 25	64.04 37	52.68 69	68.94 47	68.68 50	75.18 76	82.93 64

MSDG		52.58 111	51.40 142	53.95 79	65.48 39	64.31 130	61.44 69	44.02 105	44.17 96	32.92 108	30.40 155	31.81 162	46.35 108	62.13 107	62.55 111	73.49 113	64.41 164

ACMMPR		66.20 31	71.51 30	60.00 43	65.34 40	74.04 52	69.39 28	50.92 37	71.97 29	46.04 43	66.79 23	65.68 30	53.07 64	68.93 48	69.12 46	75.21 75	84.05 57

DWT-MVSNet_training		61.22 62	63.52 62	58.53 49	65.00 41	76.55 35	59.50 82	48.22 61	51.79 73	42.14 67	47.85 73	50.21 80	55.46 48	66.16 67	67.92 57	80.85 6	84.14 56

X-MVS		63.53 44	68.62 38	57.60 57	64.77 42	73.06 61	65.82 50	50.53 42	65.77 44	42.02 68	58.20 40	63.42 40	47.83 101	68.25 55	68.50 52	74.61 92	83.16 63

CANet		67.21 25	71.83 26	61.83 28	64.51 43	79.25 15	66.72 45	48.73 53	68.49 39	50.63 30	61.40 33	66.47 29	61.44 9	69.31 43	69.90 35	78.94 22	88.00 25

SR-MVS					63.74 44			48.51 58				73.80 15

FC-MVSNet-train		55.68 84	57.00 100	54.13 78	63.37 45	66.16 110	46.77 152	52.14 31	42.36 106	37.67 85	48.50 71	41.42 125	51.28 73	61.58 114	63.22 103	73.56 111	75.76 113

ACMH	47.82 13	50.10 131	49.60 151	50.69 99	63.36 46	66.99 103	56.83 98	52.13 32	31.06 165	17.74 173	28.22 167	26.24 186	45.17 116	60.88 123	63.80 97	68.91 149	70.00 149
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
CostFormer		62.45 55	65.68 53	58.67 48	63.29 47	77.65 26	67.62 37	38.42 149	54.04 67	46.00 44	48.27 72	57.89 57	56.97 36	67.03 63	67.79 59	79.74 10	87.09 33

ACMM	53.73 9	57.91 71	58.27 90	57.49 58	63.10 48	66.45 108	65.65 51	49.02 50	53.69 68	42.67 64	36.41 119	46.07 105	50.38 80	64.74 79	64.63 88	74.14 101	75.91 111
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
mPP-MVS					63.08 49							62.34 43

PHI-MVS		65.17 37	72.07 25	57.11 64	63.02 50	77.35 28	67.04 42	48.14 64	68.03 40	37.56 86	66.00 24	65.39 32	53.19 62	70.68 28	70.57 33	73.72 109	86.46 39

DeepC-MVS_fast	60.18 3	66.84 28	70.69 33	62.36 26	62.76 51	73.21 60	67.96 33	52.31 29	72.26 28	51.03 25	56.50 43	64.26 36	63.37 6	71.64 25	70.85 30	76.70 53	86.10 41
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 52	73.06 61	61.80 66			42.02 68		63.42 40				74.68 90

X-MVStestdata					62.70 52	73.06 61	61.80 66			42.02 68		63.42 40				74.68 90

ACMMP		63.27 45	67.85 39	57.93 53	62.64 54	72.30 68	68.23 31	48.77 52	66.50 43	43.05 59	62.07 31	57.84 58	49.98 82	66.58 65	66.46 71	74.93 83	83.17 61
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 30	71.61 28	60.14 41	62.59 55	78.98 18	67.13 41	45.75 90	64.35 47	45.23 48	60.69 35	67.67 28	61.73 8	71.09 27	71.03 27	78.41 30	87.44 31

baseline1		57.21 77	60.53 78	53.33 81	62.50 56	69.86 81	57.33 94	50.59 40	43.39 98	30.00 123	48.60 69	51.09 76	42.36 133	69.38 41	68.03 54	77.20 49	73.39 123

DeepPCF-MVS	62.48 1	70.07 16	78.36 9	60.39 40	62.38 57	76.96 32	65.54 52	52.23 30	87.46 3	49.07 32	74.05 12	76.19 8	59.01 26	72.79 17	71.61 21	74.13 102	89.49 14

CP-MVS		64.37 41	69.48 37	58.39 50	62.21 58	71.81 71	67.27 40	49.51 47	69.40 37	45.76 45	60.41 36	64.96 34	51.84 71	67.33 61	67.57 60	73.78 108	84.89 49

canonicalmvs		65.55 34	70.75 32	59.49 46	62.11 59	78.26 24	66.52 46	43.82 109	71.54 30	47.84 39	61.30 34	61.68 45	58.48 29	67.56 57	69.67 38	78.16 33	85.25 48

LGP-MVS_train		59.69 65	62.59 65	56.31 68	61.94 60	68.15 94	66.90 43	48.15 63	59.75 53	38.47 82	50.38 65	48.34 93	46.87 106	65.39 72	64.93 82	75.51 71	81.21 86

Effi-MVS+		59.63 66	61.78 75	57.12 63	61.56 61	71.63 72	63.61 58	47.59 69	47.18 88	37.79 83	45.29 80	49.93 82	56.27 43	67.45 58	67.06 62	75.91 63	83.93 58

HyFIR lowres test		57.12 78	59.11 80	54.80 74	61.55 62	77.55 27	59.02 85	45.00 94	41.84 112	33.93 103	22.44 184	49.16 88	51.02 76	68.39 52	68.71 49	78.26 32	85.70 44

TSAR-MVS + GP.		66.77 29	72.21 23	60.44 39	61.23 63	70.00 79	64.26 57	47.79 66	72.98 26	56.32 11	71.35 15	72.33 20	55.68 47	65.49 71	66.66 66	77.35 43	86.62 36

ACMP	56.21 5	59.78 64	61.81 74	57.41 59	61.15 64	68.88 89	65.98 49	48.85 51	58.56 56	44.19 52	48.89 68	46.31 102	48.56 95	63.61 92	64.49 91	75.75 67	81.91 74
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
Anonymous202405211			56.81 103		60.91 65	73.48 58	59.82 79	48.68 55	39.26 121		24.00 180	46.77 100	50.73 79	65.28 75	65.72 73	75.37 74	83.17 61

casdiffmvs		63.87 42	67.08 47	60.12 42	60.90 66	78.29 23	67.91 34	48.01 65	55.89 64	44.97 49	50.45 64	56.94 60	59.54 22	70.17 34	69.81 36	79.41 15	87.99 26

IB-MVS	53.15 10	57.33 75	59.02 82	55.37 72	60.83 67	77.11 30	54.51 114	50.10 45	43.22 99	42.82 62	40.50 96	37.61 132	44.67 121	59.27 141	69.81 36	79.29 17	85.59 46
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 74	58.26 91	56.42 67	60.80 68	72.56 66	64.35 56	38.43 148	49.18 83	46.36 42	36.69 118	43.50 114	54.47 51	61.39 117	62.64 109	74.11 104	81.81 75

gg-mvs-nofinetune		50.82 125	55.83 108	44.97 138	60.63 69	75.69 40	53.40 121	34.48 173	20.05 199	6.93 193	18.27 192	52.70 69	33.57 152	70.50 30	72.93 16	80.84 7	80.68 90

EPNet		64.39 40	70.93 31	56.77 66	60.58 70	75.77 37	59.28 84	50.58 41	69.93 33	40.73 75	68.59 19	61.60 47	53.72 55	68.65 49	68.07 53	75.75 67	83.87 59
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
CS-MVS		62.84 46	67.51 41	57.38 60	60.49 71	75.48 43	62.36 65	43.72 111	53.40 69	41.28 73	57.32 42	58.61 56	57.80 32	69.85 36	69.49 40	78.64 23	88.45 23

MVS_Test		63.75 43	67.24 44	59.68 45	60.01 72	76.99 31	68.13 32	45.17 92	57.45 57	43.74 55	53.07 56	56.16 63	61.33 11	70.27 32	71.11 26	79.72 11	85.63 45

DCV-MVSNet		56.80 80	58.96 83	54.28 76	59.96 73	66.74 106	60.37 76	44.87 96	41.01 114	36.81 89	47.57 74	47.87 95	48.23 98	64.41 82	65.17 79	75.45 72	79.95 94

tpmrst		57.23 76	59.08 81	55.06 73	59.91 74	70.65 76	60.71 73	35.38 167	47.91 86	42.58 65	39.78 100	45.45 107	54.44 52	62.19 106	62.82 106	77.37 42	84.73 51

dps		52.84 108	52.92 129	52.74 85	59.89 75	69.49 85	54.47 115	37.38 155	42.49 105	39.53 80	35.33 122	32.71 155	51.83 72	60.45 128	61.12 130	73.33 117	68.86 156

DeepC-MVS	60.65 2	67.33 23	71.52 29	62.44 25	59.79 76	74.84 46	68.89 30	55.56 14	73.91 24	53.50 20	55.00 49	65.63 31	60.08 20	71.99 22	71.33 25	76.85 52	87.94 27
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
Anonymous20231211		56.40 81	57.00 100	55.70 71	59.78 77	72.49 67	61.29 72	46.83 80	40.50 116	40.46 76	22.12 186	49.73 83	51.07 75	64.39 83	65.30 78	74.74 86	84.44 54

baseline2		59.20 68	61.72 76	56.27 69	59.61 78	74.12 51	58.65 87	49.42 48	48.10 85	40.12 78	49.10 67	44.15 111	51.24 74	66.65 64	67.88 58	78.56 25	82.06 69

EG-PatchMatch MVS		50.23 128	50.89 145	49.47 113	59.54 79	70.88 73	52.46 129	44.01 106	26.22 186	31.91 112	24.97 178	31.45 166	33.48 154	64.79 78	66.51 70	75.40 73	71.39 139

tpm		54.94 87	57.86 96	51.54 92	59.48 80	67.04 102	58.34 88	34.60 171	41.93 111	34.41 98	42.40 88	47.14 98	49.07 93	61.46 115	61.67 125	73.31 118	83.39 60

Effi-MVS+-dtu		53.63 98	54.85 115	52.20 89	59.32 81	61.33 147	56.42 105	40.24 138	43.84 97	34.22 100	39.49 105	46.18 104	53.00 67	58.72 147	57.49 153	69.99 145	76.91 106

EIA-MVS		60.56 63	64.29 58	56.20 70	59.14 82	72.68 65	59.55 81	43.56 113	51.78 74	41.01 74	55.47 46	51.93 71	55.87 44	65.01 76	66.57 67	78.06 35	86.60 38

PCF-MVS	55.99 6	62.31 56	66.60 49	57.32 62	59.12 83	73.68 56	67.53 38	48.71 54	61.35 51	42.83 60	51.33 61	63.48 39	53.48 61	65.64 69	64.87 83	72.22 128	85.83 42
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
PVSNet_BlendedMVS		62.53 51	66.37 50	58.05 51	58.17 84	75.70 38	61.30 70	48.67 56	58.67 54	50.93 26	55.43 47	49.39 85	53.01 65	69.46 39	66.55 68	76.24 58	89.39 16

PVSNet_Blended		62.53 51	66.37 50	58.05 51	58.17 84	75.70 38	61.30 70	48.67 56	58.67 54	50.93 26	55.43 47	49.39 85	53.01 65	69.46 39	66.55 68	76.24 58	89.39 16

TransMVSNet (Re)		47.46 144	48.94 156	45.74 133	57.96 86	64.29 131	48.26 142	48.47 59	26.33 185	19.33 165	29.45 164	31.28 169	25.31 179	63.05 97	62.70 107	75.10 79	65.47 162

DI_MVS_plusplus_trai		61.86 58	65.26 54	57.90 56	57.93 87	74.51 48	66.30 47	46.49 85	49.96 79	41.62 71	42.69 87	61.77 44	58.74 27	70.25 33	69.32 42	76.31 57	88.30 24

ETV-MVS		62.81 47	67.50 42	57.34 61	57.83 88	74.47 49	61.55 68	43.46 114	53.12 71	43.49 56	58.46 39	57.16 59	60.22 18	69.37 42	69.98 34	77.47 41	89.91 12

NR-MVSNet		48.84 138	51.76 137	45.44 135	57.66 89	60.64 149	47.39 146	47.63 67	37.26 132	13.31 178	37.31 114	29.64 176	33.53 153	63.52 93	62.09 118	73.10 122	71.89 135

diffmvs		62.30 57	66.05 52	57.92 55	57.08 90	75.60 42	66.90 43	47.06 77	55.45 66	43.37 57	53.45 55	55.60 64	57.21 35	66.57 66	68.00 55	75.89 65	87.70 29

PVSNet_Blended_VisFu		58.56 70	62.33 67	54.16 77	56.90 91	73.92 53	57.72 90	46.16 88	44.23 95	42.73 63	46.26 76	51.06 77	46.28 109	67.99 56	65.38 77	75.18 76	87.44 31

ACMH+	47.85 12	49.13 137	48.86 157	49.44 114	56.75 92	62.01 143	56.62 103	47.55 71	37.49 131	23.98 146	26.68 172	29.46 177	43.12 128	57.45 154	58.85 148	68.62 151	70.05 148

EPMVS		54.07 92	56.06 106	51.75 91	56.74 93	70.80 74	55.32 110	34.20 177	46.46 91	36.59 90	40.38 98	42.55 117	49.77 86	61.25 121	60.90 133	77.86 37	70.08 147

gm-plane-assit		45.41 156	48.03 160	42.34 154	56.49 94	40.48 199	24.54 203	34.15 180	14.44 205	6.59 194	17.82 193	35.32 143	49.82 85	72.93 14	74.11 9	82.47 2	81.12 87

Fast-Effi-MVS+-dtu		52.47 112	55.89 107	48.48 120	56.25 95	65.07 121	58.75 86	23.79 200	41.27 113	27.07 136	37.95 112	41.34 126	50.85 78	62.90 102	62.34 115	74.17 100	80.37 93

MVS_111021_LR		57.06 79	60.60 77	52.93 83	56.25 95	65.14 120	55.16 112	41.21 132	52.32 72	44.89 50	53.92 52	49.27 87	52.16 70	61.46 115	60.54 137	67.92 153	81.53 80

thres100view900		52.33 114	53.91 120	50.48 102	56.10 97	67.79 96	56.18 107	49.18 49	35.86 144	25.22 142	34.74 127	34.10 151	42.41 132	64.45 81	62.62 110	73.81 107	77.85 102

tfpn200view9		50.91 123	52.45 134	49.11 117	56.10 97	64.53 125	53.06 124	47.31 74	35.86 144	25.22 142	34.74 127	34.10 151	41.08 135	60.84 124	61.37 127	71.90 131	75.70 114

SCA		50.88 124	53.70 122	47.59 124	55.99 99	55.81 171	43.14 166	33.45 183	45.16 92	37.14 88	41.83 90	43.82 113	44.43 123	60.37 129	60.02 142	71.38 133	68.90 155

thres200		50.76 126	52.52 132	48.70 119	55.98 100	64.60 123	55.29 111	47.34 72	33.91 151	24.36 145	34.33 131	33.90 153	37.27 142	60.84 124	62.41 114	71.99 129	77.63 103

IS_MVSNet		51.53 118	57.98 94	44.01 144	55.96 101	66.16 110	47.65 145	42.84 126	39.82 119	19.09 168	44.97 81	50.28 79	27.20 175	63.43 95	63.84 96	71.33 134	77.33 104

PatchmatchNet		53.37 102	55.62 110	50.75 97	55.93 102	70.54 77	51.39 133	36.41 160	44.85 93	37.26 87	39.40 107	42.54 118	47.83 101	60.29 131	60.88 135	75.69 69	70.87 141
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
LS3D		49.59 133	49.75 150	49.40 115	55.88 103	59.86 155	56.31 106	45.33 91	48.57 84	28.32 131	31.54 147	36.81 137	46.27 110	57.17 155	55.88 164	64.29 168	58.42 181

IterMVS-LS		53.36 103	55.65 109	50.68 100	55.34 104	59.04 158	55.00 113	39.98 139	38.72 124	33.22 107	44.52 82	47.05 99	49.63 88	61.82 112	61.77 120	70.92 137	76.61 109
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
UA-Net		47.19 147	53.02 128	40.38 163	55.31 105	60.02 154	38.41 176	38.68 147	36.42 138	22.47 154	51.95 58	58.72 55	25.62 178	54.11 168	53.40 173	61.79 181	56.51 184

MVSTER		62.51 53	67.22 45	57.02 65	55.05 106	69.23 87	63.02 61	46.88 79	61.11 52	43.95 53	59.20 38	58.86 53	56.80 38	69.13 45	70.98 28	76.41 56	82.04 70

thres400		50.39 127	52.22 135	48.26 121	55.02 107	66.32 109	52.97 125	48.33 60	32.68 155	22.94 150	33.21 138	33.38 154	37.27 142	62.74 103	61.38 126	73.04 124	75.81 112

CPTT-MVS		59.54 67	64.47 57	53.79 80	54.99 108	67.63 98	65.48 53	44.59 99	64.81 46	37.74 84	51.55 59	59.90 51	49.77 86	61.83 111	61.26 129	70.18 142	84.31 55

EPP-MVSNet		52.91 107	58.91 84	45.91 131	54.99 108	68.84 90	49.27 139	42.71 127	37.53 130	20.20 160	46.09 77	56.19 62	36.90 144	61.37 118	60.90 133	71.41 132	81.41 82

baseline		58.65 69	61.99 70	54.75 75	54.70 110	71.85 70	60.20 77	43.91 107	55.99 63	40.13 77	53.50 54	50.91 78	55.76 45	61.29 119	61.73 121	73.83 106	78.68 100

Fast-Effi-MVS+		55.73 83	58.26 91	52.76 84	54.33 111	68.19 93	57.05 95	34.66 169	46.92 89	38.96 81	40.53 95	41.55 123	55.69 46	65.31 74	65.99 72	75.90 64	79.34 96

MDTV_nov1_ep13		52.99 106	55.59 111	49.95 109	54.08 112	70.69 75	56.47 104	38.42 149	42.78 101	30.19 122	39.56 104	43.31 116	45.78 111	60.07 136	62.11 117	74.74 86	70.62 142

thres600view7		48.44 140	50.23 148	46.35 129	54.05 113	64.60 123	50.18 136	47.34 72	31.73 161	20.74 158	32.28 144	32.62 157	33.79 151	60.84 124	56.11 162	71.99 129	73.40 122

EPNet_dtu		49.85 132	56.99 102	41.52 159	52.79 114	57.06 165	41.44 170	43.13 121	56.13 61	19.24 167	52.11 57	48.38 92	22.14 182	58.19 149	58.38 149	70.35 140	68.71 157
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
tfpnnormal		46.61 152	46.82 165	46.37 128	52.70 115	62.31 140	50.39 135	47.17 75	25.74 188	21.80 155	23.13 182	24.15 194	33.45 155	60.28 132	60.77 136	72.70 126	71.39 139

CANet_DTU		57.87 72	63.63 61	51.15 94	52.18 116	70.20 78	58.14 89	37.32 156	56.49 58	31.06 117	57.38 41	50.05 81	53.67 58	64.98 77	65.04 81	74.57 93	81.29 85

v8		53.77 96	54.82 116	52.54 87	52.12 117	66.95 105	60.56 75	43.23 120	37.17 136	35.35 93	34.96 126	37.50 134	49.51 89	63.67 91	64.59 89	74.48 94	78.91 99

v10		53.44 101	54.40 118	52.31 88	52.08 118	66.99 103	59.68 80	43.41 115	35.90 142	34.30 99	33.98 133	35.56 140	50.10 81	64.39 83	64.67 87	74.32 95	79.30 97

v1144		53.47 100	54.65 117	52.10 90	51.93 119	69.81 82	59.32 83	44.77 98	33.21 154	32.52 109	33.55 136	34.34 150	49.29 91	64.58 80	64.81 86	74.74 86	82.27 66

Vis-MVSNet (Re-imp)		44.31 162	51.67 139	35.72 176	51.82 120	55.24 175	34.57 182	41.63 131	39.10 122	8.84 191	45.93 78	46.63 101	14.45 192	54.09 169	57.03 156	63.00 176	63.65 168

v2v482		54.00 93	55.12 112	52.69 86	51.73 121	69.42 86	60.65 74	45.09 93	34.56 147	33.73 106	35.29 123	35.36 142	49.92 83	64.05 89	65.16 80	75.00 80	81.98 72

test-LLR		54.62 90	58.66 86	49.89 110	51.68 122	65.89 112	47.88 143	46.35 86	42.51 103	29.84 124	41.41 92	48.87 89	45.20 114	62.91 100	64.43 92	78.43 28	84.62 52

test0.0.03 1		43.07 169	46.95 164	38.54 168	51.68 122	58.77 161	35.28 178	46.35 86	32.05 159	12.44 180	28.53 166	35.52 141	14.40 193	57.12 157	56.93 157	71.11 135	59.69 175

GA-MVS		53.77 96	56.41 105	50.70 98	51.63 124	69.96 80	57.55 92	44.39 100	34.31 148	27.15 134	40.99 94	36.40 138	47.65 103	67.45 58	67.16 61	75.83 66	78.60 101

UniMVSNet_NR-MVSNet		49.56 134	53.04 127	45.49 134	51.59 125	64.42 129	46.97 150	51.01 36	37.87 126	16.42 174	39.87 99	34.91 146	33.43 156	59.59 139	62.70 107	73.52 112	71.94 132

thisisatest0530		53.61 99	57.22 98	49.40 115	51.30 126	68.22 92	52.72 128	43.34 118	42.72 102	35.31 94	43.57 85	44.14 112	44.37 124	63.00 98	64.86 84	69.34 148	74.00 117

v1192		52.69 109	53.86 121	51.31 93	51.22 127	69.76 83	57.37 93	44.39 100	32.21 157	31.39 116	32.41 143	32.44 158	49.19 92	64.25 85	64.17 94	74.31 96	81.81 75

v144192		52.43 113	53.63 123	51.03 95	51.06 128	69.60 84	56.94 97	44.84 97	32.15 158	30.88 118	32.45 142	32.71 155	48.36 96	62.98 99	63.52 100	74.10 105	82.02 71

v1921920		51.95 115	53.19 125	50.51 101	50.82 129	69.14 88	55.45 109	44.34 104	31.53 162	30.53 120	31.96 145	31.67 163	48.31 97	63.12 96	63.28 102	73.59 110	81.60 79

FMVSNet3		55.66 85	59.68 79	50.96 96	50.59 130	66.49 107	57.57 91	46.61 82	49.30 80	28.77 128	39.61 101	51.42 73	43.85 126	68.29 53	68.80 48	78.35 31	73.86 118

TranMVSNet+NR-MVSNet		48.06 143	51.36 143	44.21 142	50.38 131	62.09 142	47.28 147	50.88 39	36.11 139	13.25 179	37.51 113	31.60 165	30.70 166	59.34 140	62.53 112	72.81 125	70.31 144

tttt0517		53.05 105	56.73 104	48.76 118	50.35 132	67.51 99	51.96 132	43.34 118	42.00 110	33.88 104	43.19 86	43.49 115	44.37 124	62.58 105	64.86 84	68.67 150	73.46 120

v1240		51.42 119	52.66 131	49.97 108	50.31 133	68.70 91	54.05 118	43.85 108	30.78 166	30.22 121	31.43 148	31.03 170	47.98 99	62.62 104	63.16 104	73.40 115	80.93 88

v148		51.72 116	53.15 126	50.05 106	50.15 134	67.51 99	56.98 96	42.85 125	32.60 156	32.41 111	33.88 134	34.71 147	44.45 122	61.06 122	63.00 105	73.45 114	79.24 98

PatchT		48.11 142	51.27 144	44.43 139	50.13 135	61.58 145	33.59 183	32.92 185	40.38 117	31.74 113	30.60 154	36.93 136	45.00 118	58.80 144	61.11 131	73.19 120	69.47 151

CNLPA		54.00 93	57.08 99	50.40 103	49.83 136	61.75 144	53.47 120	37.27 157	74.55 22	44.85 51	33.58 135	45.42 108	52.94 68	58.89 143	53.66 172	64.06 169	71.68 137

our_test_3					49.68 137	61.50 146	45.84 158

pmmvs4		51.28 120	52.50 133	49.85 111	49.54 138	63.02 137	52.83 127	43.41 115	44.65 94	35.71 92	34.38 130	32.25 159	45.14 117	60.21 135	60.03 141	72.44 127	72.98 129

GBi-Net		54.66 88	58.42 88	50.26 104	49.36 139	65.81 115	56.80 99	46.61 82	49.30 80	28.77 128	39.61 101	51.42 73	42.71 129	64.25 85	65.54 74	77.32 45	73.03 126

test1		54.66 88	58.42 88	50.26 104	49.36 139	65.81 115	56.80 99	46.61 82	49.30 80	28.77 128	39.61 101	51.42 73	42.71 129	64.25 85	65.54 74	77.32 45	73.03 126

FMVSNet2		53.94 95	57.29 97	50.03 107	49.36 139	65.81 115	56.80 99	45.95 89	43.13 100	28.04 132	35.68 121	48.18 94	42.71 129	67.23 62	67.95 56	77.32 45	73.03 126

pm-mvs1		46.14 153	49.34 155	42.41 153	48.93 142	62.22 141	44.98 160	42.68 128	27.66 178	20.76 157	29.88 160	34.96 145	26.41 177	60.03 137	60.42 138	70.70 139	70.20 145

Anonymous20231206		40.63 174	43.29 176	37.53 172	48.88 143	55.81 171	34.99 179	44.98 95	28.16 175	10.16 188	17.26 197	27.50 182	18.28 186	54.00 170	55.07 167	67.85 154	65.23 163

ADS-MVSNet		45.39 157	46.42 166	44.19 143	48.74 144	57.52 164	43.91 164	31.93 186	35.89 143	27.11 135	30.12 156	32.06 161	45.30 112	53.13 174	55.19 166	68.15 152	61.07 174

v7n		47.22 146	48.38 158	45.87 132	48.20 145	63.58 132	50.69 134	40.93 136	26.60 184	26.44 138	26.52 173	29.65 175	38.19 140	58.22 148	60.23 140	70.79 138	73.83 119

Vis-MVSNet		51.13 121	58.04 93	43.06 150	47.68 146	67.71 97	49.10 140	39.09 145	37.75 128	22.57 152	51.03 63	48.78 91	32.42 161	62.12 108	61.80 119	67.49 157	77.12 105
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
MVS-HIRNet		43.98 164	43.63 175	44.39 141	47.66 147	59.31 157	32.66 189	33.88 182	30.15 169	33.75 105	16.82 198	28.39 180	45.25 113	53.92 172	55.00 168	73.16 121	61.80 171

IterMVS		50.23 128	53.27 124	46.68 127	47.59 148	60.58 151	53.10 123	36.62 159	36.07 140	25.89 139	39.42 106	40.05 129	43.65 127	60.22 134	61.35 128	73.23 119	75.23 115
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
CDS-MVSNet		49.25 135	53.97 119	43.75 146	47.53 149	64.53 125	48.59 141	42.27 129	33.77 152	26.64 137	40.46 97	42.26 120	30.01 168	61.77 113	61.71 122	67.48 158	73.28 125
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
testgi		34.51 189	37.42 190	31.12 191	47.37 150	50.34 181	24.38 204	41.21 132	20.32 197	5.64 199	20.56 187	26.55 185	8.06 204	49.28 180	52.65 174	60.05 183	42.23 201

CR-MVSNet		48.82 139	51.85 136	45.29 136	46.74 151	55.95 169	52.06 130	34.21 175	42.17 107	31.74 113	32.92 140	42.53 119	45.00 118	58.80 144	61.11 131	61.99 180	69.47 151

IterMVS-SCA-FT		45.87 154	51.55 141	39.24 166	46.22 152	59.43 156	52.89 126	31.93 186	36.01 141	23.68 147	38.86 109	39.88 131	39.05 137	56.25 161	58.17 150	41.70 201	72.25 131

MDTV_nov1_ep13_2view		44.44 160	45.75 169	42.91 151	46.13 153	63.43 134	46.53 155	34.20 177	29.08 173	19.95 163	26.23 174	27.89 181	35.88 146	53.36 173	56.43 160	74.74 86	63.86 167

test20.03		36.00 185	38.92 185	32.60 184	45.92 154	50.99 179	28.05 199	43.69 112	21.62 193	6.03 195	17.61 195	25.91 188	8.34 203	51.26 176	52.60 175	63.58 171	52.46 191

UniMVSNet (Re)		46.89 150	51.65 140	41.34 160	45.60 155	62.71 138	44.05 163	47.10 76	37.24 134	13.55 177	36.90 116	34.54 149	26.76 176	57.56 151	59.90 145	70.98 136	72.69 130

FMVSNet1		50.14 130	52.78 130	47.06 125	45.56 156	63.56 133	54.22 116	43.74 110	34.10 150	25.37 141	29.79 161	42.06 121	38.70 138	64.25 85	65.54 74	74.75 85	70.18 146

RPMNet		43.70 166	48.17 159	38.48 169	45.52 157	55.95 169	37.66 177	26.63 198	42.17 107	25.47 140	29.59 163	37.61 132	33.87 150	50.85 178	52.02 177	61.75 182	69.00 154

thisisatest0515		46.88 151	49.57 152	43.74 147	45.33 158	60.46 152	46.19 156	41.06 135	30.34 168	29.73 126	32.50 141	31.63 164	35.43 147	58.75 146	61.71 122	64.70 167	71.59 138

TESTMET0.1,1		53.30 104	58.66 86	47.04 126	44.94 159	65.89 112	47.88 143	35.95 163	42.51 103	29.84 124	41.41 92	48.87 89	45.20 114	62.91 100	64.43 92	78.43 28	84.62 52

V42		52.63 110	55.08 113	49.76 112	44.93 160	67.49 101	60.19 78	42.13 130	37.21 135	34.08 102	34.57 129	37.30 135	47.29 104	63.48 94	64.15 95	69.96 146	81.38 83

TAMVS		44.27 163	49.35 154	38.35 170	44.74 161	61.04 148	39.07 174	31.82 188	29.95 170	18.34 171	33.55 136	39.94 130	30.01 168	56.85 158	57.58 152	66.13 162	66.54 159

pmmvs6		41.90 173	44.01 174	39.43 165	44.45 162	58.77 161	41.92 168	39.22 144	21.74 192	19.08 169	17.40 196	31.33 168	24.28 181	55.94 162	56.67 158	67.60 156	66.24 160

DU-MVS		47.33 145	50.86 146	43.20 149	44.43 163	60.64 149	46.97 150	47.63 67	37.26 132	16.42 174	37.31 114	31.39 167	33.43 156	57.53 152	59.98 143	70.35 140	71.94 132

Baseline_NR-MVSNet		47.14 148	50.83 147	42.84 152	44.43 163	63.31 135	44.50 162	50.36 44	37.71 129	11.25 184	30.84 151	32.09 160	30.96 164	57.53 152	63.73 98	75.53 70	70.60 143

PMMVS		55.74 82	62.68 63	47.64 123	44.34 165	65.58 118	47.22 149	37.96 152	56.43 60	34.11 101	61.51 32	47.41 97	54.55 50	65.88 68	62.49 113	67.67 155	79.48 95

CMPMVS	33.64 16	44.39 161	46.41 167	42.03 155	44.21 166	56.50 167	46.73 153	26.48 199	34.20 149	35.14 95	24.22 179	34.64 148	40.52 136	56.50 160	56.07 163	59.12 185	62.74 170
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
WR-MVS		37.61 178	42.15 177	32.31 187	43.64 167	51.85 176	29.39 195	43.35 117	27.65 179	4.40 202	29.90 159	29.80 174	10.46 196	46.73 184	51.98 178	62.60 178	57.16 182

pmmvs5		47.02 149	50.02 149	43.51 148	43.48 168	62.65 139	47.24 148	37.78 154	30.59 167	24.80 144	35.26 124	30.43 171	34.36 149	59.05 142	60.28 139	73.40 115	71.92 134

LTVRE_ROB	32.83 17	35.10 187	37.46 189	32.35 186	43.12 169	49.99 183	28.52 197	33.23 184	12.73 206	8.18 192	27.71 170	21.34 197	32.64 160	46.92 183	48.11 186	48.41 198	55.45 187
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	49.14 136	51.75 138	46.10 130	42.78 170	55.60 174	53.11 122	34.46 174	55.69 65	32.47 110	34.16 132	41.45 124	48.91 94	57.13 156	54.09 170	64.84 165	64.10 165
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
pmmvs-eth3d		44.67 159	45.27 171	43.98 145	42.56 171	55.72 173	44.97 161	40.81 137	31.96 160	29.13 127	26.09 175	25.27 191	36.69 145	55.13 165	56.62 159	69.68 147	66.12 161

OMC-MVS		55.48 86	61.85 73	48.04 122	41.55 172	60.32 153	56.80 99	31.78 189	75.67 20	42.30 66	51.52 60	54.15 67	49.91 84	60.28 132	57.59 151	65.91 163	73.42 121

DTE-MVSNet		36.91 181	40.44 181	32.79 183	40.74 173	47.55 189	30.71 193	44.39 100	27.03 182	4.32 203	30.88 150	25.99 187	12.73 194	45.58 186	50.80 180	63.86 170	55.23 188

UGNet		51.04 122	58.79 85	42.00 156	40.59 174	65.32 119	46.65 154	39.26 143	39.90 118	27.30 133	54.12 51	52.03 70	30.93 165	59.85 138	59.62 146	67.23 159	80.70 89
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		38.23 177	41.72 178	34.15 178	40.56 175	50.07 182	33.17 186	44.35 103	27.64 180	5.54 200	30.84 151	26.67 184	14.99 190	45.64 185	52.38 176	66.29 161	58.83 178

ambc			35.52 195		38.36 176	40.40 200	28.38 198		25.20 189	14.87 176	13.22 202	7.54 210	19.34 185	55.63 163	47.79 189	47.91 199	58.89 177

UniMVSNet_ETH3D		43.97 165	46.01 168	41.59 157	38.31 177	56.20 168	49.69 137	38.18 151	28.18 174	19.88 164	27.82 169	30.20 172	33.41 158	54.18 167	56.30 161	70.05 144	69.17 153

MIMVSNet		45.62 155	49.56 153	41.02 161	38.17 178	64.43 128	49.48 138	35.43 166	36.53 137	20.06 162	22.58 183	35.16 144	28.75 173	61.97 110	62.20 116	74.20 98	64.07 166

PatchMatch-RL		43.37 167	44.93 172	41.56 158	37.94 179	51.70 177	40.02 172	35.75 164	39.04 123	30.71 119	35.14 125	27.43 183	46.58 107	51.99 175	50.55 181	58.38 187	58.64 179

WR-MVS_H		36.29 183	40.35 183	31.55 189	37.80 180	49.94 184	30.57 194	41.11 134	26.90 183	4.14 204	30.72 153	28.85 178	10.45 197	42.47 194	47.99 188	65.24 164	55.54 186

CP-MVSNet		37.09 180	40.62 180	32.99 180	37.56 181	48.25 187	32.75 187	43.05 122	27.88 177	5.93 196	31.27 149	25.82 189	15.09 188	43.37 192	48.82 182	63.54 173	58.90 176

PS-CasMVS		36.84 182	40.23 184	32.89 181	37.44 182	48.09 188	32.68 188	42.97 124	27.36 181	5.89 197	30.08 158	25.48 190	14.96 191	43.28 193	48.71 183	63.39 174	58.63 180

FC-MVSNet-test		30.97 195	37.38 191	23.49 198	37.42 183	33.68 203	19.43 206	39.27 142	31.37 164	1.67 210	38.56 111	28.85 178	6.06 207	41.40 195	43.80 195	37.10 203	44.03 200

N_pmnet		34.09 191	35.74 194	32.17 188	37.25 184	43.17 196	32.26 191	35.57 165	26.22 186	10.60 187	20.44 188	19.38 200	20.20 184	44.59 189	47.00 192	57.13 190	49.35 198

SixPastTwentyTwo		36.11 184	37.80 188	34.13 179	37.13 185	46.72 191	34.58 181	34.96 168	21.20 195	11.66 181	29.15 165	19.88 199	29.77 170	44.93 187	48.34 185	56.67 191	54.41 190

new-patchmatchnet		30.47 196	32.80 199	27.75 194	36.81 186	43.98 194	24.85 202	39.29 141	20.52 196	4.06 205	15.94 199	16.05 203	9.57 198	41.32 196	42.05 197	51.94 197	49.74 197

TAPA-MVS	47.92 11	51.66 117	57.88 95	44.40 140	36.46 187	58.42 163	53.82 119	30.83 190	69.51 36	34.97 96	46.90 75	49.67 84	46.99 105	58.00 150	54.64 169	63.33 175	68.00 158
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
COLMAP_ROB	34.79 15	38.65 176	40.72 179	36.23 175	36.41 188	49.22 186	45.51 159	27.60 196	37.81 127	20.54 159	23.37 181	24.25 193	28.11 174	51.02 177	48.55 184	59.22 184	50.82 195
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
anonymousdsp		43.03 170	47.19 162	38.18 171	36.00 189	56.92 166	38.44 175	34.56 172	24.22 190	22.53 153	29.69 162	29.92 173	35.21 148	53.96 171	58.98 147	62.32 179	76.66 108

CVMVSNet		38.91 175	44.49 173	32.40 185	34.57 190	47.20 190	34.81 180	34.20 177	31.45 163	8.95 190	38.86 109	36.38 139	24.30 180	47.77 182	46.94 193	57.59 189	62.85 169

USDC		42.80 171	45.57 170	39.58 164	34.55 191	51.13 178	42.61 167	36.21 161	39.59 120	23.65 148	33.13 139	20.87 198	37.86 141	55.35 164	57.16 155	62.61 177	61.75 172

TSAR-MVS + COLMAP		54.37 91	62.43 66	44.98 137	34.33 192	58.94 160	54.11 117	34.15 180	74.06 23	34.57 97	71.63 14	42.03 122	47.88 100	61.26 120	57.33 154	64.83 166	71.74 136

test-mter		48.31 141	55.04 114	40.45 162	34.12 193	59.02 159	41.77 169	28.05 194	38.43 125	22.67 151	39.35 108	44.40 110	41.88 134	60.30 130	61.68 124	74.20 98	82.12 68

CHOSEN 280x420		42.39 172	47.40 161	36.54 174	33.56 194	39.66 202	40.67 171	26.88 197	34.66 146	18.03 172	30.09 157	45.59 106	44.82 120	54.46 166	54.00 171	55.28 194	73.32 124

EU-MVSNet		33.00 193	36.49 193	28.92 192	33.10 195	42.86 197	29.32 196	35.99 162	22.94 191	5.83 198	25.29 176	24.43 192	15.21 187	41.22 197	41.65 198	54.08 195	57.01 183

ET-MVSNet_ETH3D		57.84 73	61.91 71	53.09 82	32.91 196	74.53 47	63.51 59	46.80 81	46.52 90	36.14 91	56.00 45	46.20 103	64.41 4	60.75 127	66.99 63	74.79 84	82.35 65

TinyColmap		37.18 179	37.37 192	36.95 173	31.17 197	45.21 193	39.71 173	34.65 170	29.83 171	20.20 160	18.54 191	13.72 206	38.27 139	50.33 179	51.57 179	57.71 188	52.42 192

FMVSNet5		43.29 168	47.07 163	38.87 167	30.46 198	50.99 179	45.87 157	37.19 158	42.17 107	19.32 166	26.77 171	40.51 127	30.26 167	56.82 159	55.81 165	70.10 143	56.46 185

FPMVS		26.87 198	28.19 200	25.32 196	27.09 199	29.49 205	32.28 190	17.79 205	28.09 176	11.33 182	19.38 190	14.69 204	20.88 183	35.11 200	32.82 201	42.56 200	37.75 202

MDA-MVSNet-bldmvs		34.31 190	34.11 196	34.54 177	24.73 200	49.66 185	33.42 185	43.03 123	21.59 194	11.10 185	19.81 189	12.68 207	31.41 163	35.59 199	48.05 187	63.56 172	51.39 194

pmmvs3		31.22 194	33.62 197	28.43 193	22.82 201	40.26 201	26.40 200	22.05 203	16.89 203	10.99 186	14.72 200	16.26 202	29.70 171	44.82 188	47.39 190	58.61 186	54.98 189

PM-MVS		34.96 188	38.17 187	31.22 190	22.78 202	40.82 198	33.56 184	23.61 201	29.16 172	21.43 156	28.00 168	21.43 196	31.90 162	44.33 190	42.12 196	54.07 196	61.34 173

PMVS	18.18 18	21.95 199	22.85 201	20.90 200	21.92 203	14.78 207	19.95 205	17.31 206	15.69 204	11.32 183	13.70 201	13.91 205	15.02 189	34.92 201	31.72 202	39.85 202	35.20 203
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
E-PMN		10.66 203	8.30 206	13.42 203	19.91 204	7.87 211	4.30 212	29.47 192	8.37 210	1.70 209	3.67 207	1.29 216	9.12 200	8.98 208	13.59 206	16.03 208	14.30 209

MIMVSNet1		29.60 197	33.37 198	25.20 197	19.52 205	43.94 195	26.29 201	37.92 153	19.95 200	3.79 206	12.64 204	21.99 195	7.70 205	43.83 191	46.32 194	55.97 193	44.92 199

EMVS		10.15 204	7.67 207	13.05 204	19.22 206	7.77 212	4.48 210	29.34 193	8.65 209	1.67 210	3.55 208	1.36 215	9.15 199	8.15 209	11.79 208	14.44 209	12.43 210

TDRefinement		35.76 186	38.23 186	32.88 182	19.09 207	46.04 192	43.29 165	29.49 191	33.49 153	19.04 170	22.29 185	17.82 201	29.69 172	48.60 181	47.24 191	56.65 192	52.12 193

Gipuma		17.16 201	17.83 203	16.36 201	18.76 208	12.15 210	11.97 208	27.78 195	17.94 202	4.86 201	2.53 210	2.73 213	8.90 201	34.32 202	36.09 200	25.92 206	19.06 206
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
RPSCF		33.61 192	40.43 182	25.65 195	16.00 209	32.41 204	31.73 192	13.33 208	50.13 78	23.12 149	31.56 146	40.09 128	32.73 159	41.14 198	37.05 199	36.99 204	50.63 196

PMMVS2		12.25 202	14.17 204	10.00 205	11.39 210	14.35 208	8.21 209	19.29 204	9.31 207	0.19 213	7.38 206	6.19 211	1.10 209	19.26 204	21.13 205	19.85 207	21.56 205

new_pmnet		19.10 200	22.71 202	14.89 202	10.93 211	24.08 206	14.22 207	13.94 207	18.68 201	2.93 207	12.84 203	11.27 208	11.94 195	30.57 203	30.58 203	35.38 205	30.93 204

MVE	10.35 19	9.76 205	11.08 205	8.22 206	4.43 212	13.04 209	3.36 213	23.57 202	5.74 211	1.76 208	3.09 209	1.75 214	6.78 206	12.78 206	23.04 204	9.44 210	18.09 207
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
tmp_tt				4.41 207	2.56 213	1.81 214	2.61 214	0.27 210	20.12 198	9.81 189	17.69 194	9.04 209	1.96 208	12.88 205	12.11 207	9.23 211

GG-mvs-BLEND		44.87 158	64.59 56	21.86 199	0.01 214	73.70 55	55.99 108	0.01 211	50.70 76	0.01 214	49.18 66	63.61 38	0.01 210	63.83 90	64.50 90	75.13 78	86.62 36

sosnet-low-res		0.00 208	0.00 210	0.00 208	0.00 215	0.00 215	0.00 216	0.00 212	0.00 214	0.00 215	0.00 213	0.00 217	0.00 212	0.00 211	0.00 211	0.00 213	0.00 213

sosnet		0.00 208	0.00 210	0.00 208	0.00 215	0.00 215	0.00 216	0.00 212	0.00 214	0.00 215	0.00 213	0.00 217	0.00 212	0.00 211	0.00 211	0.00 213	0.00 213

testmvs		0.01 206	0.01 208	0.00 208	0.00 215	0.00 215	0.00 216	0.00 212	0.01 212	0.00 215	0.02 211	0.00 217	0.00 212	0.01 210	0.01 209	0.00 213	0.03 211

test123		0.01 206	0.01 208	0.00 208	0.00 215	0.00 215	0.00 216	0.00 212	0.01 212	0.00 215	0.02 211	0.00 217	0.01 210	0.00 211	0.01 209	0.00 213	0.03 211

test_part1																	92.54 5

MTAPA										54.82 13		71.98 21

MTMP										50.64 29		68.31 27

Patchmatch-RL test							0.69 215

NP-MVS									72.62 27

Patchmtry						64.49 127	52.06 130	34.21 175		31.74 113

DeepMVS_CX						5.87 213	4.32 211	1.74 209	9.04 208	1.30 212	7.97 205	3.16 212	8.56 202	9.74 207		6.30 212	14.51 208

High-resolution multi-view benchmark