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.

xxxxxxxxxxxxxcwj		73.17 12	74.44 21	71.69 2	82.90 1	86.54 1	82.08 1	64.58 1	81.67 11	59.82 5	86.26 4	35.82 150	61.11 15	71.81 27	70.75 34	79.63 12	88.22 24

SF-MVS		76.41 3	80.45 6	71.69 2	82.90 1	86.54 1	82.08 1	64.58 1	81.67 11	59.82 5	86.26 4	77.90 8	61.11 15	71.81 27	70.75 34	79.63 12	88.22 24

SED-MVS		78.97 1	84.56 1	72.45 1	81.70 3	86.20 3	77.82 4	59.97 6	88.89 1	65.96 1	86.00 6	84.02 1	70.03 1	76.19 4	76.17 5	79.22 19	94.46 1

DVP-MVS		77.54 2	84.41 2	69.54 7	79.93 4	86.08 4	77.20 9	60.31 4	88.62 2	62.54 2	86.67 3	83.77 2	58.04 33	75.84 7	75.69 8	79.21 20	94.17 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
MCST-MVS		74.06 9	77.71 14	69.79 5	78.95 5	81.99 9	76.33 11	62.16 3	75.89 22	52.96 26	64.37 32	73.30 22	65.66 5	77.49 2	77.43 3	82.67 1	93.51 4

CSCG		72.98 13	76.86 16	68.46 9	78.23 6	81.74 11	77.26 8	60.00 5	75.61 25	59.06 7	62.72 34	77.42 9	56.63 47	74.24 11	77.18 4	79.56 14	89.13 18

DPE-MVS		75.74 6	82.82 4	67.49 12	77.07 7	82.01 8	77.05 10	57.70 12	86.55 5	55.44 16	90.50 2	82.52 3	60.33 20	72.99 15	72.98 16	77.33 48	92.19 6
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
APDe-MVS		74.59 8	80.23 7	68.01 11	76.51 8	80.20 16	77.39 7	58.18 10	85.31 6	56.84 13	84.89 7	76.08 14	60.66 18	71.85 26	71.76 21	78.47 29	91.49 9

DPM-MVS		74.63 7	78.53 11	70.07 4	76.10 9	82.56 7	79.30 3	59.89 7	80.49 14	57.75 11	66.98 26	76.16 13	65.95 4	79.35 1	78.47 1	81.45 5	85.71 47

3Dnovator	58.39 4	65.97 36	66.85 52	64.94 16	73.72 10	79.03 21	67.73 40	54.25 26	61.52 54	52.79 28	42.27 94	60.73 55	62.01 9	71.29 30	71.75 22	79.12 22	81.34 89

MAR-MVS		66.85 31	69.81 40	63.39 25	73.56 11	80.51 15	69.87 30	51.51 38	67.78 45	46.44 46	51.09 68	61.60 52	60.38 19	72.67 22	73.61 14	78.59 26	81.44 86
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 21	74.76 20	63.98 20	73.45 12	78.56 25	73.13 18	55.24 22	70.68 35	48.93 38	70.43 21	69.10 29	54.00 59	72.78 21	72.98 16	79.14 21	88.74 21
Skip Steuart: Steuart Systems R&D Blog.
CNVR-MVS		73.87 10	78.60 10	68.35 10	73.32 13	81.97 10	76.19 12	59.29 9	80.12 15	56.70 14	67.09 25	76.48 11	64.26 7	75.88 6	75.75 7	80.32 7	92.93 5

QAPM		65.47 39	67.82 46	62.72 28	72.56 14	81.17 14	67.43 43	55.38 21	56.07 70	43.29 63	43.60 89	65.38 37	59.10 28	72.20 23	70.76 33	78.56 27	85.59 50

CHOSEN 1792x2688		62.48 58	64.06 65	60.64 41	72.50 15	84.18 6	62.43 71	53.77 29	47.90 93	39.85 85	25.15 188	44.76 116	53.72 60	77.29 3	77.61 2	81.60 4	91.53 8

NCCC		71.36 17	75.44 18	66.60 13	72.46 16	79.18 20	74.16 14	57.83 11	76.93 20	54.19 21	63.47 33	71.08 27	61.30 14	73.56 13	73.70 13	79.69 11	90.19 11

OpenMVS	55.62 8	62.57 54	63.76 66	61.19 38	72.13 17	78.84 23	64.42 62	50.51 47	56.44 66	45.67 51	36.88 124	56.51 67	56.66 46	68.28 57	68.96 49	77.73 42	80.44 97

MSP-MVS		76.38 4	82.99 3	68.68 8	71.93 18	78.65 24	77.61 6	55.44 19	88.04 3	60.25 4	92.24 1	77.08 10	69.84 2	75.48 8	75.69 8	76.99 57	93.75 3
Zhenlong Yuan, Cong Liu, Fei Shen, Zhaoxin Li, Jingguo luo, Tianlu Mao and Zhaoqi Wang: MSP-MVS: Multi-granularity Segmentation Prior Guided Multi-View Stereo. AAAI2025
HPM-MVS++		72.44 14	78.73 9	65.11 15	71.88 19	77.31 33	71.98 21	55.67 17	83.11 9	53.59 23	75.90 13	78.49 7	61.00 17	73.99 12	73.31 15	76.55 60	88.97 19

DVP-MVS++		75.99 5	81.32 5	69.77 6	71.86 20	85.13 5	77.62 5	59.87 8	82.69 10	61.55 3	83.05 10	79.63 6	69.78 3	76.01 5	75.89 6	77.92 39	86.86 36

SMA-MVS		73.31 11	79.53 8	66.05 14	71.25 21	80.13 17	74.99 13	56.09 15	84.14 7	54.48 19	73.74 17	80.23 4	61.43 12	74.96 9	74.09 12	78.08 36	89.42 14
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
MVS_111021_HR		64.66 43	67.11 50	61.80 33	71.04 22	77.91 29	62.75 70	54.78 24	51.43 80	47.54 44	53.77 59	54.85 71	56.84 42	70.59 34	71.50 24	77.86 40	89.70 12

AdaColmap		62.79 52	62.63 69	62.98 27	70.82 23	72.90 67	67.84 39	54.09 28	65.14 49	50.71 32	41.78 96	47.64 103	60.17 22	67.41 64	66.83 67	74.28 107	76.69 114

abl_6				63.79 24	70.80 24	81.22 13	65.26 61	53.25 31	77.02 19	53.02 25	65.14 31	73.74 20	60.30 21			80.13 8	90.27 10

MS-PatchMatch		61.41 65	61.88 77	60.85 39	70.57 25	75.98 39	66.29 55	46.91 82	50.56 82	48.28 42	36.30 127	51.64 78	50.95 83	72.89 18	70.65 36	82.13 3	75.17 124

APD-MVS		71.86 15	77.91 13	64.80 17	70.39 26	75.69 43	74.02 15	56.14 14	83.59 8	52.92 27	84.67 8	73.46 21	59.30 27	69.47 42	69.66 42	76.02 68	88.84 20
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
train_agg		70.74 18	76.53 17	63.98 20	70.33 27	75.16 47	72.33 20	55.78 16	75.74 23	50.41 35	80.08 12	73.15 23	57.75 37	71.96 25	70.94 31	77.25 52	88.69 22

ACMMP_NAP		71.50 16	77.27 15	64.77 18	69.64 28	79.26 18	73.53 16	54.73 25	79.32 17	54.23 20	74.81 14	74.61 18	59.40 26	73.00 14	72.17 19	77.10 56	87.72 29

TSAR-MVS + ACMM		65.95 37	72.83 24	57.93 57	69.35 29	65.85 124	73.36 17	39.84 150	76.00 21	48.69 41	82.54 11	75.03 17	49.38 96	65.33 77	63.42 111	66.94 171	81.67 83

TSAR-MVS + MP.		70.28 19	75.09 19	64.66 19	69.34 30	64.61 132	72.60 19	56.29 13	80.73 13	58.36 9	84.56 9	75.22 16	55.37 54	69.11 49	69.45 43	75.97 70	81.97 78
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 23	72.58 25	63.31 26	69.24 31	67.85 105	70.81 27	53.65 30	79.64 16	58.52 8	74.31 15	75.37 15	53.52 65	65.63 74	63.56 109	74.13 112	81.73 82
Zhenlong Yuan, Jiakai Cao, Zhaoxin Li, Hao Jiang and Zhaoqi Wang: SD-MVS: Segmentation-driven Deformation Multi-View Stereo with Spherical Refinement and EM optimization. AAAI2024
DELS-MVS		67.36 25	70.34 39	63.89 23	69.12 32	81.55 12	70.82 26	55.02 23	53.38 77	48.83 39	56.45 48	59.35 57	60.05 24	74.93 10	74.78 10	79.51 15	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 30	71.64 31	61.65 35	69.10 33	76.84 37	71.35 25	55.42 20	67.02 46	42.83 65	65.27 30	64.60 39	53.16 68	69.70 41	71.40 25	78.02 38	86.67 38

HFP-MVS		68.75 22	72.84 23	63.98 20	68.87 34	75.09 48	71.87 22	51.22 39	73.50 29	58.17 10	68.05 24	68.67 30	57.79 36	70.49 36	69.23 45	75.98 69	84.84 56

MSLP-MVS++		61.81 63	62.19 74	61.37 37	68.33 35	63.08 146	70.75 28	38.89 156	63.96 52	57.51 12	48.59 76	61.66 51	53.67 63	62.04 119	59.92 154	79.03 23	76.08 117

CLD-MVS		64.69 42	67.25 47	61.69 34	68.22 36	78.33 26	63.09 67	47.59 72	69.64 39	53.98 22	54.87 56	53.94 74	57.87 34	72.79 19	71.34 26	79.40 17	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 28	72.08 28	61.56 36	66.76 37	73.58 60	71.41 23	52.98 32	69.92 38	43.85 60	70.58 20	58.75 59	56.76 44	72.90 17	71.88 20	77.57 44	86.94 35

OPM-MVS		61.59 64	62.30 73	60.76 40	66.53 38	73.35 62	71.41 23	54.18 27	40.82 123	41.57 77	45.70 84	54.84 72	54.43 58	69.92 40	69.19 46	76.45 61	82.25 72
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
MP-MVS		67.34 26	73.08 22	60.64 41	66.20 39	76.62 38	69.22 33	50.92 41	70.07 36	48.81 40	69.66 22	70.12 28	53.68 62	68.41 54	69.13 47	74.98 90	87.53 31
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
zzz-MVS		67.78 24	72.46 26	62.33 31	66.09 40	74.21 53	70.05 29	51.54 37	77.27 18	54.61 18	60.30 42	71.51 26	56.73 45	69.19 47	68.63 54	74.96 91	86.11 43

3Dnovator+	55.76 7	62.70 53	65.10 61	59.90 48	65.89 41	72.15 73	62.94 69	49.82 50	62.77 53	49.06 37	43.62 88	61.47 54	58.60 31	68.51 53	66.75 68	73.08 133	80.40 98

PGM-MVS		65.35 40	70.43 38	59.43 52	65.78 42	73.75 57	69.41 31	48.18 65	68.80 42	45.37 52	65.88 29	64.04 41	52.68 75	68.94 50	68.68 53	75.18 85	82.93 69

MSDG		52.58 119	51.40 152	53.95 86	65.48 43	64.31 140	61.44 74	44.02 113	44.17 102	32.92 115	30.40 164	31.81 173	46.35 115	62.13 117	62.55 121	73.49 123	64.41 173

ACMMPR		66.20 35	71.51 34	60.00 47	65.34 44	74.04 55	69.39 32	50.92 41	71.97 33	46.04 48	66.79 27	65.68 34	53.07 69	68.93 51	69.12 48	75.21 84	84.05 62

X-MVS		63.53 49	68.62 42	57.60 61	64.77 45	73.06 64	65.82 57	50.53 46	65.77 48	42.02 73	58.20 45	63.42 44	47.83 108	68.25 58	68.50 55	74.61 101	83.16 68

CANet		67.21 29	71.83 30	61.83 32	64.51 46	79.25 19	66.72 51	48.73 57	68.49 43	50.63 34	61.40 38	66.47 33	61.44 11	69.31 46	69.90 38	78.94 25	88.00 26

SR-MVS					63.74 47			48.51 62				73.80 19

FC-MVSNet-train		55.68 91	57.00 107	54.13 85	63.37 48	66.16 120	46.77 162	52.14 35	42.36 114	37.67 92	48.50 77	41.42 133	51.28 79	61.58 124	63.22 113	73.56 121	75.76 121

ACMH	47.82 13	50.10 141	49.60 161	50.69 106	63.36 49	66.99 113	56.83 105	52.13 36	31.06 175	17.74 184	28.22 177	26.24 197	45.17 123	60.88 133	63.80 107	68.91 159	70.00 158
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
CostFormer		62.45 59	65.68 58	58.67 53	63.29 50	77.65 30	67.62 41	38.42 159	54.04 75	46.00 49	48.27 78	57.89 61	56.97 41	67.03 67	67.79 61	79.74 9	87.09 34

ACMM	53.73 9	57.91 77	58.27 96	57.49 62	63.10 51	66.45 118	65.65 58	49.02 54	53.69 76	42.67 69	36.41 126	46.07 112	50.38 86	64.74 85	64.63 97	74.14 111	75.91 118
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
mPP-MVS					63.08 52							62.34 47

PHI-MVS		65.17 41	72.07 29	57.11 66	63.02 53	77.35 32	67.04 48	48.14 67	68.03 44	37.56 93	66.00 28	65.39 36	53.19 67	70.68 33	70.57 37	73.72 119	86.46 42

DROMVSNet		64.30 46	68.19 43	59.76 49	62.97 54	75.31 46	67.26 45	44.19 112	60.73 57	47.52 45	55.84 50	62.12 48	57.67 38	70.71 32	67.47 63	78.97 24	85.13 53

DeepC-MVS_fast	60.18 3	66.84 32	70.69 37	62.36 30	62.76 55	73.21 63	67.96 37	52.31 33	72.26 32	51.03 29	56.50 47	64.26 40	63.37 8	71.64 29	70.85 32	76.70 59	86.10 44
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 56	73.06 64	61.80 72			42.02 73		63.42 44				74.68 99

X-MVStestdata					62.70 56	73.06 64	61.80 72			42.02 73		63.42 44				74.68 99

ACMMP		63.27 50	67.85 45	57.93 57	62.64 58	72.30 72	68.23 35	48.77 56	66.50 47	43.05 64	62.07 35	57.84 62	49.98 88	66.58 69	66.46 75	74.93 92	83.17 66
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 34	71.61 32	60.14 45	62.59 59	78.98 22	67.13 47	45.75 96	64.35 51	45.23 53	60.69 40	67.67 32	61.73 10	71.09 31	71.03 29	78.41 32	87.44 32

baseline1		57.21 83	60.53 84	53.33 88	62.50 60	69.86 87	57.33 101	50.59 44	43.39 106	30.00 130	48.60 75	51.09 82	42.36 140	69.38 45	68.03 57	77.20 53	73.39 132

DeepPCF-MVS	62.48 1	70.07 20	78.36 12	60.39 44	62.38 61	76.96 36	65.54 59	52.23 34	87.46 4	49.07 36	74.05 16	76.19 12	59.01 29	72.79 19	71.61 23	74.13 112	89.49 13

CP-MVS		64.37 45	69.48 41	58.39 54	62.21 62	71.81 75	67.27 44	49.51 51	69.40 41	45.76 50	60.41 41	64.96 38	51.84 77	67.33 65	67.57 62	73.78 118	84.89 54

canonicalmvs		65.55 38	70.75 36	59.49 51	62.11 63	78.26 28	66.52 52	43.82 118	71.54 34	47.84 43	61.30 39	61.68 50	58.48 32	67.56 61	69.67 41	78.16 35	85.25 52

LGP-MVS_train		59.69 70	62.59 70	56.31 74	61.94 64	68.15 102	66.90 49	48.15 66	59.75 58	38.47 89	50.38 71	48.34 100	46.87 113	65.39 76	64.93 91	75.51 80	81.21 91

test_part1		56.55 87	56.50 112	56.60 72	61.77 65	69.59 91	66.45 53	43.70 120	38.22 135	44.13 58	29.53 173	49.96 87	47.92 106	63.09 106	64.59 98	75.61 78	80.54 96

Effi-MVS+		59.63 71	61.78 80	57.12 65	61.56 66	71.63 77	63.61 65	47.59 72	47.18 94	37.79 90	45.29 85	49.93 88	56.27 49	67.45 62	67.06 65	75.91 71	83.93 63

HyFIR lowres test		57.12 84	59.11 86	54.80 80	61.55 67	77.55 31	59.02 91	45.00 101	41.84 120	33.93 110	22.44 195	49.16 95	51.02 82	68.39 55	68.71 52	78.26 34	85.70 48

GeoE		58.97 74	60.94 82	56.67 70	61.27 68	72.71 68	61.35 75	45.69 97	49.19 88	41.22 78	39.55 111	49.58 91	52.79 74	64.79 83	65.89 79	77.73 42	84.87 55

TSAR-MVS + GP.		66.77 33	72.21 27	60.44 43	61.23 69	70.00 85	64.26 64	47.79 69	72.98 30	56.32 15	71.35 19	72.33 24	55.68 53	65.49 75	66.66 69	77.35 46	86.62 39

ACMP	56.21 5	59.78 69	61.81 79	57.41 63	61.15 70	68.88 96	65.98 56	48.85 55	58.56 61	44.19 57	48.89 74	46.31 109	48.56 101	63.61 101	64.49 101	75.75 75	81.91 79
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
Anonymous202405211			56.81 110		60.91 71	73.48 61	59.82 86	48.68 59	39.26 130		24.00 191	46.77 107	50.73 85	65.28 79	65.72 81	75.37 83	83.17 66

casdiffmvs		63.87 47	67.08 51	60.12 46	60.90 72	78.29 27	67.91 38	48.01 68	55.89 72	44.97 54	50.45 70	56.94 64	59.54 25	70.17 39	69.81 39	79.41 16	87.99 27

IB-MVS	53.15 10	57.33 81	59.02 88	55.37 78	60.83 73	77.11 34	54.51 121	50.10 49	43.22 107	42.82 67	40.50 101	37.61 142	44.67 128	59.27 151	69.81 39	79.29 18	85.59 50
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 80	58.26 97	56.42 73	60.80 74	72.56 70	64.35 63	38.43 158	49.18 89	46.36 47	36.69 125	43.50 122	54.47 56	61.39 127	62.64 119	74.11 114	81.81 80

gg-mvs-nofinetune		50.82 134	55.83 117	44.97 148	60.63 75	75.69 43	53.40 130	34.48 184	20.05 211	6.93 206	18.27 203	52.70 75	33.57 161	70.50 35	72.93 18	80.84 6	80.68 95

EPNet		64.39 44	70.93 35	56.77 68	60.58 76	75.77 40	59.28 90	50.58 45	69.93 37	40.73 80	68.59 23	61.60 52	53.72 60	68.65 52	68.07 56	75.75 75	83.87 64
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
MVS_Test		63.75 48	67.24 48	59.68 50	60.01 77	76.99 35	68.13 36	45.17 99	57.45 63	43.74 61	53.07 62	56.16 69	61.33 13	70.27 37	71.11 28	79.72 10	85.63 49

DCV-MVSNet		56.80 86	58.96 89	54.28 83	59.96 78	66.74 116	60.37 82	44.87 103	41.01 122	36.81 96	47.57 79	47.87 102	48.23 104	64.41 88	65.17 87	75.45 81	79.95 100

tpmrst		57.23 82	59.08 87	55.06 79	59.91 79	70.65 82	60.71 79	35.38 178	47.91 92	42.58 70	39.78 106	45.45 114	54.44 57	62.19 116	62.82 116	77.37 45	84.73 57

dps		52.84 116	52.92 139	52.74 92	59.89 80	69.49 92	54.47 122	37.38 166	42.49 113	39.53 86	35.33 129	32.71 166	51.83 78	60.45 138	61.12 140	73.33 127	68.86 165

DeepC-MVS	60.65 2	67.33 27	71.52 33	62.44 29	59.79 81	74.84 50	68.89 34	55.56 18	73.91 28	53.50 24	55.00 55	65.63 35	60.08 23	71.99 24	71.33 27	76.85 58	87.94 28
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 88	57.00 107	55.70 77	59.78 82	72.49 71	61.29 78	46.83 84	40.50 125	40.46 81	22.12 197	49.73 89	51.07 81	64.39 89	65.30 86	74.74 95	84.44 60

baseline2		59.20 73	61.72 81	56.27 75	59.61 83	74.12 54	58.65 93	49.42 52	48.10 91	40.12 84	49.10 73	44.15 118	51.24 80	66.65 68	67.88 60	78.56 27	82.06 74

EG-PatchMatch MVS		50.23 138	50.89 155	49.47 120	59.54 84	70.88 79	52.46 138	44.01 114	26.22 197	31.91 119	24.97 189	31.45 177	33.48 163	64.79 83	66.51 74	75.40 82	71.39 148

tpm		54.94 94	57.86 102	51.54 99	59.48 85	67.04 112	58.34 94	34.60 182	41.93 119	34.41 105	42.40 93	47.14 105	49.07 99	61.46 125	61.67 135	73.31 128	83.39 65

Effi-MVS+-dtu		53.63 105	54.85 125	52.20 96	59.32 86	61.33 157	56.42 112	40.24 148	43.84 103	34.22 107	39.49 112	46.18 111	53.00 72	58.72 157	57.49 163	69.99 155	76.91 112

EIA-MVS		60.56 68	64.29 64	56.20 76	59.14 87	72.68 69	59.55 88	43.56 122	51.78 79	41.01 79	55.47 51	51.93 77	55.87 50	65.01 81	66.57 71	78.06 37	86.60 41

PCF-MVS	55.99 6	62.31 60	66.60 53	57.32 64	59.12 88	73.68 59	67.53 42	48.71 58	61.35 55	42.83 65	51.33 67	63.48 43	53.48 66	65.64 73	64.87 92	72.22 138	85.83 45
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
ETV-MVS		62.88 51	68.18 44	56.70 69	58.47 89	74.89 49	60.26 83	43.96 115	58.27 62	42.37 71	61.47 37	56.56 66	57.80 35	68.00 59	68.74 51	77.34 47	89.33 17

PVSNet_BlendedMVS		62.53 55	66.37 54	58.05 55	58.17 90	75.70 41	61.30 76	48.67 60	58.67 59	50.93 30	55.43 52	49.39 92	53.01 70	69.46 43	66.55 72	76.24 66	89.39 15

PVSNet_Blended		62.53 55	66.37 54	58.05 55	58.17 90	75.70 41	61.30 76	48.67 60	58.67 59	50.93 30	55.43 52	49.39 92	53.01 70	69.46 43	66.55 72	76.24 66	89.39 15

TransMVSNet (Re)		47.46 154	48.94 166	45.74 142	57.96 92	64.29 141	48.26 152	48.47 63	26.33 196	19.33 176	29.45 174	31.28 180	25.31 190	63.05 107	62.70 117	75.10 88	65.47 171

DI_MVS_plusplus_trai		61.86 62	65.26 60	57.90 60	57.93 93	74.51 52	66.30 54	46.49 89	49.96 84	41.62 76	42.69 92	61.77 49	58.74 30	70.25 38	69.32 44	76.31 63	88.30 23

NR-MVSNet		48.84 148	51.76 147	45.44 145	57.66 94	60.64 159	47.39 156	47.63 70	37.26 142	13.31 190	37.31 121	29.64 187	33.53 162	63.52 102	62.09 128	73.10 132	71.89 144

CS-MVS		60.58 67	65.95 57	54.33 82	57.44 95	71.15 78	58.13 96	37.47 165	57.06 64	40.34 82	58.92 44	57.68 63	56.28 48	65.95 71	65.05 89	76.31 63	85.81 46

diffmvs		62.30 61	66.05 56	57.92 59	57.08 96	75.60 45	66.90 49	47.06 81	55.45 74	43.37 62	53.45 61	55.60 70	57.21 40	66.57 70	68.00 58	75.89 73	87.70 30

PVSNet_Blended_VisFu		58.56 76	62.33 72	54.16 84	56.90 97	73.92 56	57.72 97	46.16 94	44.23 101	42.73 68	46.26 81	51.06 83	46.28 116	67.99 60	65.38 85	75.18 85	87.44 32

ACMH+	47.85 12	49.13 147	48.86 167	49.44 121	56.75 98	62.01 153	56.62 110	47.55 74	37.49 141	23.98 153	26.68 182	29.46 188	43.12 135	57.45 164	58.85 158	68.62 161	70.05 157

EPMVS		54.07 99	56.06 114	51.75 98	56.74 99	70.80 80	55.32 117	34.20 188	46.46 97	36.59 97	40.38 103	42.55 125	49.77 92	61.25 131	60.90 143	77.86 40	70.08 156

gm-plane-assit		45.41 166	48.03 170	42.34 164	56.49 100	40.48 210	24.54 214	34.15 191	14.44 217	6.59 207	17.82 204	35.32 154	49.82 91	72.93 16	74.11 11	82.47 2	81.12 92

Fast-Effi-MVS+-dtu		52.47 121	55.89 115	48.48 129	56.25 101	65.07 131	58.75 92	23.79 211	41.27 121	27.07 143	37.95 119	41.34 134	50.85 84	62.90 112	62.34 125	74.17 110	80.37 99

MVS_111021_LR		57.06 85	60.60 83	52.93 90	56.25 101	65.14 130	55.16 119	41.21 142	52.32 78	44.89 55	53.92 58	49.27 94	52.16 76	61.46 125	60.54 147	67.92 164	81.53 85

CS-MVS-test		61.36 66	65.42 59	56.63 71	56.23 103	71.71 76	67.26 45	43.28 128	56.42 68	39.08 87	55.14 54	56.92 65	57.67 38	65.28 79	65.78 80	76.25 65	86.68 37

thres100view900		52.33 123	53.91 130	50.48 109	56.10 104	67.79 106	56.18 114	49.18 53	35.86 154	25.22 149	34.74 134	34.10 162	42.41 139	64.45 87	62.62 120	73.81 117	77.85 108

tfpn200view9		50.91 132	52.45 144	49.11 124	56.10 104	64.53 135	53.06 133	47.31 77	35.86 154	25.22 149	34.74 134	34.10 162	41.08 142	60.84 134	61.37 137	71.90 141	75.70 122

SCA		50.88 133	53.70 132	47.59 133	55.99 106	55.81 182	43.14 176	33.45 194	45.16 98	37.14 95	41.83 95	43.82 120	44.43 130	60.37 139	60.02 152	71.38 143	68.90 164

thres200		50.76 135	52.52 142	48.70 126	55.98 107	64.60 133	55.29 118	47.34 75	33.91 161	24.36 152	34.33 138	33.90 164	37.27 149	60.84 134	62.41 124	71.99 139	77.63 109

IS_MVSNet		51.53 127	57.98 100	44.01 154	55.96 108	66.16 120	47.65 155	42.84 135	39.82 128	19.09 179	44.97 86	50.28 85	27.20 186	63.43 104	63.84 106	71.33 144	77.33 110

PatchmatchNet		53.37 109	55.62 119	50.75 104	55.93 109	70.54 83	51.39 142	36.41 171	44.85 99	37.26 94	39.40 114	42.54 126	47.83 108	60.29 141	60.88 145	75.69 77	70.87 150
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
LS3D		49.59 143	49.75 160	49.40 122	55.88 110	59.86 165	56.31 113	45.33 98	48.57 90	28.32 138	31.54 155	36.81 147	46.27 117	57.17 165	55.88 174	64.29 179	58.42 191

test2506		53.36 110	57.36 103	48.68 127	55.53 111	68.11 103	54.31 123	46.25 92	43.54 104	22.21 163	40.19 104	43.69 121	36.56 153	64.15 96	65.94 77	77.20 53	75.91 118

ECVR-MVS		52.52 120	55.88 116	48.60 128	55.53 111	68.11 103	54.31 123	46.25 92	43.54 104	21.75 165	32.76 148	39.83 140	36.56 153	64.15 96	65.94 77	77.20 53	76.81 113

IterMVS-LS		53.36 110	55.65 118	50.68 107	55.34 113	59.04 168	55.00 120	39.98 149	38.72 133	33.22 114	44.52 87	47.05 106	49.63 94	61.82 122	61.77 130	70.92 147	76.61 116
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
UA-Net		47.19 157	53.02 138	40.38 174	55.31 114	60.02 164	38.41 187	38.68 157	36.42 148	22.47 162	51.95 64	58.72 60	25.62 189	54.11 178	53.40 184	61.79 192	56.51 194

MVSTER		62.51 57	67.22 49	57.02 67	55.05 115	69.23 94	63.02 68	46.88 83	61.11 56	43.95 59	59.20 43	58.86 58	56.80 43	69.13 48	70.98 30	76.41 62	82.04 75

thres400		50.39 137	52.22 145	48.26 130	55.02 116	66.32 119	52.97 134	48.33 64	32.68 165	22.94 158	33.21 145	33.38 165	37.27 149	62.74 113	61.38 136	73.04 134	75.81 120

CPTT-MVS		59.54 72	64.47 63	53.79 87	54.99 117	67.63 108	65.48 60	44.59 106	64.81 50	37.74 91	51.55 65	59.90 56	49.77 92	61.83 121	61.26 139	70.18 152	84.31 61

EPP-MVSNet		52.91 115	58.91 90	45.91 140	54.99 117	68.84 97	49.27 148	42.71 136	37.53 140	20.20 171	46.09 82	56.19 68	36.90 151	61.37 128	60.90 143	71.41 142	81.41 87

baseline		58.65 75	61.99 75	54.75 81	54.70 119	71.85 74	60.20 84	43.91 116	55.99 71	40.13 83	53.50 60	50.91 84	55.76 51	61.29 129	61.73 131	73.83 116	78.68 106

Fast-Effi-MVS+		55.73 90	58.26 97	52.76 91	54.33 120	68.19 101	57.05 102	34.66 180	46.92 95	38.96 88	40.53 100	41.55 131	55.69 52	65.31 78	65.99 76	75.90 72	79.34 102

MDTV_nov1_ep13		52.99 114	55.59 120	49.95 116	54.08 121	70.69 81	56.47 111	38.42 159	42.78 109	30.19 129	39.56 110	43.31 124	45.78 118	60.07 146	62.11 127	74.74 95	70.62 151

thres600view7		48.44 150	50.23 158	46.35 138	54.05 122	64.60 133	50.18 145	47.34 75	31.73 171	20.74 169	32.28 152	32.62 168	33.79 160	60.84 134	56.11 172	71.99 139	73.40 131

test1111		50.62 136	54.98 124	45.55 143	53.84 123	68.48 99	48.99 150	47.25 78	40.60 124	15.64 187	31.51 156	38.32 141	33.01 168	64.34 91	66.62 70	74.55 103	74.95 125

EPNet_dtu		49.85 142	56.99 109	41.52 169	52.79 124	57.06 176	41.44 181	43.13 130	56.13 69	19.24 178	52.11 63	48.38 99	22.14 193	58.19 159	58.38 159	70.35 150	68.71 166
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
tfpnnormal		46.61 162	46.82 175	46.37 137	52.70 125	62.31 150	50.39 144	47.17 79	25.74 199	21.80 164	23.13 193	24.15 205	33.45 164	60.28 142	60.77 146	72.70 136	71.39 148

CANet_DTU		57.87 78	63.63 67	51.15 101	52.18 126	70.20 84	58.14 95	37.32 167	56.49 65	31.06 124	57.38 46	50.05 86	53.67 63	64.98 82	65.04 90	74.57 102	81.29 90

v8		53.77 103	54.82 126	52.54 94	52.12 127	66.95 115	60.56 81	43.23 129	37.17 146	35.35 100	34.96 133	37.50 144	49.51 95	63.67 100	64.59 98	74.48 104	78.91 105

v10		53.44 108	54.40 128	52.31 95	52.08 128	66.99 113	59.68 87	43.41 123	35.90 152	34.30 106	33.98 140	35.56 151	50.10 87	64.39 89	64.67 96	74.32 105	79.30 103

v1144		53.47 107	54.65 127	52.10 97	51.93 129	69.81 88	59.32 89	44.77 105	33.21 164	32.52 116	33.55 143	34.34 161	49.29 97	64.58 86	64.81 95	74.74 95	82.27 71

Vis-MVSNet (Re-imp)		44.31 172	51.67 149	35.72 187	51.82 130	55.24 186	34.57 193	41.63 140	39.10 131	8.84 203	45.93 83	46.63 108	14.45 203	54.09 179	57.03 166	63.00 187	63.65 177

v2v482		54.00 100	55.12 121	52.69 93	51.73 131	69.42 93	60.65 80	45.09 100	34.56 157	33.73 113	35.29 130	35.36 153	49.92 89	64.05 98	65.16 88	75.00 89	81.98 77

test-LLR		54.62 97	58.66 92	49.89 117	51.68 132	65.89 122	47.88 153	46.35 90	42.51 111	29.84 131	41.41 97	48.87 96	45.20 121	62.91 110	64.43 102	78.43 30	84.62 58

test0.0.03 1		43.07 179	46.95 174	38.54 179	51.68 132	58.77 171	35.28 189	46.35 90	32.05 169	12.44 192	28.53 176	35.52 152	14.40 204	57.12 167	56.93 167	71.11 145	59.69 185

GA-MVS		53.77 103	56.41 113	50.70 105	51.63 134	69.96 86	57.55 99	44.39 107	34.31 158	27.15 141	40.99 99	36.40 148	47.65 110	67.45 62	67.16 64	75.83 74	78.60 107

UniMVSNet_NR-MVSNet		49.56 144	53.04 137	45.49 144	51.59 135	64.42 139	46.97 160	51.01 40	37.87 136	16.42 185	39.87 105	34.91 157	33.43 165	59.59 149	62.70 117	73.52 122	71.94 141

thisisatest0530		53.61 106	57.22 105	49.40 122	51.30 136	68.22 100	52.72 137	43.34 126	42.72 110	35.31 101	43.57 90	44.14 119	44.37 131	63.00 108	64.86 93	69.34 158	74.00 126

v1192		52.69 117	53.86 131	51.31 100	51.22 137	69.76 89	57.37 100	44.39 107	32.21 167	31.39 123	32.41 151	32.44 169	49.19 98	64.25 92	64.17 104	74.31 106	81.81 80

v144192		52.43 122	53.63 133	51.03 102	51.06 138	69.60 90	56.94 104	44.84 104	32.15 168	30.88 125	32.45 150	32.71 166	48.36 102	62.98 109	63.52 110	74.10 115	82.02 76

v1921920		51.95 124	53.19 135	50.51 108	50.82 139	69.14 95	55.45 116	44.34 111	31.53 172	30.53 127	31.96 153	31.67 174	48.31 103	63.12 105	63.28 112	73.59 120	81.60 84

FMVSNet3		55.66 92	59.68 85	50.96 103	50.59 140	66.49 117	57.57 98	46.61 86	49.30 85	28.77 135	39.61 107	51.42 79	43.85 133	68.29 56	68.80 50	78.35 33	73.86 127

TranMVSNet+NR-MVSNet		48.06 153	51.36 153	44.21 152	50.38 141	62.09 152	47.28 157	50.88 43	36.11 149	13.25 191	37.51 120	31.60 176	30.70 176	59.34 150	62.53 122	72.81 135	70.31 153

tttt0517		53.05 113	56.73 111	48.76 125	50.35 142	67.51 109	51.96 141	43.34 126	42.00 118	33.88 111	43.19 91	43.49 123	44.37 131	62.58 115	64.86 93	68.67 160	73.46 129

v1240		51.42 128	52.66 141	49.97 115	50.31 143	68.70 98	54.05 127	43.85 117	30.78 176	30.22 128	31.43 157	31.03 181	47.98 105	62.62 114	63.16 114	73.40 125	80.93 93

v148		51.72 125	53.15 136	50.05 113	50.15 144	67.51 109	56.98 103	42.85 134	32.60 166	32.41 118	33.88 141	34.71 158	44.45 129	61.06 132	63.00 115	73.45 124	79.24 104

PatchT		48.11 152	51.27 154	44.43 149	50.13 145	61.58 155	33.59 194	32.92 196	40.38 126	31.74 120	30.60 163	36.93 146	45.00 125	58.80 154	61.11 141	73.19 130	69.47 160

CNLPA		54.00 100	57.08 106	50.40 110	49.83 146	61.75 154	53.47 129	37.27 168	74.55 26	44.85 56	33.58 142	45.42 115	52.94 73	58.89 153	53.66 183	64.06 180	71.68 146

our_test_3					49.68 147	61.50 156	45.84 168

pmmvs4		51.28 129	52.50 143	49.85 118	49.54 148	63.02 147	52.83 136	43.41 123	44.65 100	35.71 99	34.38 137	32.25 170	45.14 124	60.21 145	60.03 151	72.44 137	72.98 138

GBi-Net		54.66 95	58.42 94	50.26 111	49.36 149	65.81 125	56.80 106	46.61 86	49.30 85	28.77 135	39.61 107	51.42 79	42.71 136	64.25 92	65.54 82	77.32 49	73.03 135

test1		54.66 95	58.42 94	50.26 111	49.36 149	65.81 125	56.80 106	46.61 86	49.30 85	28.77 135	39.61 107	51.42 79	42.71 136	64.25 92	65.54 82	77.32 49	73.03 135

FMVSNet2		53.94 102	57.29 104	50.03 114	49.36 149	65.81 125	56.80 106	45.95 95	43.13 108	28.04 139	35.68 128	48.18 101	42.71 136	67.23 66	67.95 59	77.32 49	73.03 135

pm-mvs1		46.14 163	49.34 165	42.41 163	48.93 152	62.22 151	44.98 170	42.68 137	27.66 189	20.76 168	29.88 169	34.96 156	26.41 188	60.03 147	60.42 148	70.70 149	70.20 154

Anonymous20231206		40.63 185	43.29 186	37.53 183	48.88 153	55.81 182	34.99 190	44.98 102	28.16 186	10.16 200	17.26 208	27.50 193	18.28 197	54.00 180	55.07 177	67.85 165	65.23 172

ADS-MVSNet		45.39 167	46.42 176	44.19 153	48.74 154	57.52 174	43.91 174	31.93 197	35.89 153	27.11 142	30.12 165	32.06 172	45.30 119	53.13 184	55.19 176	68.15 163	61.07 183

v7n		47.22 156	48.38 168	45.87 141	48.20 155	63.58 142	50.69 143	40.93 146	26.60 195	26.44 145	26.52 183	29.65 186	38.19 147	58.22 158	60.23 150	70.79 148	73.83 128

Vis-MVSNet		51.13 130	58.04 99	43.06 160	47.68 156	67.71 107	49.10 149	39.09 155	37.75 138	22.57 160	51.03 69	48.78 98	32.42 171	62.12 118	61.80 129	67.49 168	77.12 111
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
MVS-HIRNet		43.98 174	43.63 185	44.39 151	47.66 157	59.31 167	32.66 200	33.88 193	30.15 179	33.75 112	16.82 209	28.39 191	45.25 120	53.92 182	55.00 178	73.16 131	61.80 180

IterMVS		50.23 138	53.27 134	46.68 136	47.59 158	60.58 161	53.10 132	36.62 170	36.07 150	25.89 146	39.42 113	40.05 137	43.65 134	60.22 144	61.35 138	73.23 129	75.23 123
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
CDS-MVSNet		49.25 145	53.97 129	43.75 156	47.53 159	64.53 135	48.59 151	42.27 138	33.77 162	26.64 144	40.46 102	42.26 128	30.01 178	61.77 123	61.71 132	67.48 169	73.28 134
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
testgi		34.51 200	37.42 201	31.12 202	47.37 160	50.34 192	24.38 215	41.21 142	20.32 209	5.64 212	20.56 198	26.55 196	8.06 216	49.28 191	52.65 185	60.05 194	42.23 211

CR-MVSNet		48.82 149	51.85 146	45.29 146	46.74 161	55.95 180	52.06 139	34.21 186	42.17 115	31.74 120	32.92 147	42.53 127	45.00 125	58.80 154	61.11 141	61.99 191	69.47 160

IterMVS-SCA-FT		45.87 164	51.55 151	39.24 177	46.22 162	59.43 166	52.89 135	31.93 197	36.01 151	23.68 154	38.86 116	39.88 139	39.05 144	56.25 171	58.17 160	41.70 212	72.25 140

MDTV_nov1_ep13_2view		44.44 170	45.75 179	42.91 161	46.13 163	63.43 144	46.53 165	34.20 188	29.08 184	19.95 174	26.23 184	27.89 192	35.88 155	53.36 183	56.43 170	74.74 95	63.86 176

test20.03		36.00 196	38.92 196	32.60 195	45.92 164	50.99 190	28.05 210	43.69 121	21.62 205	6.03 208	17.61 206	25.91 199	8.34 215	51.26 187	52.60 186	63.58 182	52.46 201

pmnet_mix02		42.41 182	43.24 187	41.44 170	45.80 165	57.46 175	42.19 178	41.57 141	29.38 182	23.39 156	26.08 186	23.96 206	27.31 185	51.50 186	53.76 182	68.36 162	60.58 184

UniMVSNet (Re)		46.89 160	51.65 150	41.34 171	45.60 166	62.71 148	44.05 173	47.10 80	37.24 144	13.55 189	36.90 123	34.54 160	26.76 187	57.56 161	59.90 155	70.98 146	72.69 139

FMVSNet1		50.14 140	52.78 140	47.06 134	45.56 167	63.56 143	54.22 125	43.74 119	34.10 160	25.37 148	29.79 170	42.06 129	38.70 145	64.25 92	65.54 82	74.75 94	70.18 155

RPMNet		43.70 176	48.17 169	38.48 180	45.52 168	55.95 180	37.66 188	26.63 209	42.17 115	25.47 147	29.59 172	37.61 142	33.87 159	50.85 189	52.02 188	61.75 193	69.00 163

thisisatest0515		46.88 161	49.57 162	43.74 157	45.33 169	60.46 162	46.19 166	41.06 145	30.34 178	29.73 133	32.50 149	31.63 175	35.43 156	58.75 156	61.71 132	64.70 178	71.59 147

TESTMET0.1,1		53.30 112	58.66 92	47.04 135	44.94 170	65.89 122	47.88 153	35.95 174	42.51 111	29.84 131	41.41 97	48.87 96	45.20 121	62.91 110	64.43 102	78.43 30	84.62 58

V42		52.63 118	55.08 122	49.76 119	44.93 171	67.49 111	60.19 85	42.13 139	37.21 145	34.08 109	34.57 136	37.30 145	47.29 111	63.48 103	64.15 105	69.96 156	81.38 88

TAMVS		44.27 173	49.35 164	38.35 181	44.74 172	61.04 158	39.07 185	31.82 199	29.95 180	18.34 182	33.55 143	39.94 138	30.01 178	56.85 168	57.58 162	66.13 173	66.54 168

pmmvs6		41.90 184	44.01 184	39.43 176	44.45 173	58.77 171	41.92 179	39.22 154	21.74 204	19.08 180	17.40 207	31.33 179	24.28 192	55.94 172	56.67 168	67.60 167	66.24 169

DU-MVS		47.33 155	50.86 156	43.20 159	44.43 174	60.64 159	46.97 160	47.63 70	37.26 142	16.42 185	37.31 121	31.39 178	33.43 165	57.53 162	59.98 153	70.35 150	71.94 141

Baseline_NR-MVSNet		47.14 158	50.83 157	42.84 162	44.43 174	63.31 145	44.50 172	50.36 48	37.71 139	11.25 196	30.84 160	32.09 171	30.96 174	57.53 162	63.73 108	75.53 79	70.60 152

PMMVS		55.74 89	62.68 68	47.64 132	44.34 176	65.58 128	47.22 159	37.96 162	56.43 67	34.11 108	61.51 36	47.41 104	54.55 55	65.88 72	62.49 123	67.67 166	79.48 101

CMPMVS	33.64 16	44.39 171	46.41 177	42.03 165	44.21 177	56.50 178	46.73 163	26.48 210	34.20 159	35.14 102	24.22 190	34.64 159	40.52 143	56.50 170	56.07 173	59.12 196	62.74 179
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
WR-MVS		37.61 189	42.15 188	32.31 198	43.64 178	51.85 187	29.39 206	43.35 125	27.65 190	4.40 215	29.90 168	29.80 185	10.46 208	46.73 195	51.98 189	62.60 189	57.16 192

pmmvs5		47.02 159	50.02 159	43.51 158	43.48 179	62.65 149	47.24 158	37.78 164	30.59 177	24.80 151	35.26 131	30.43 182	34.36 158	59.05 152	60.28 149	73.40 125	71.92 143

LTVRE_ROB	32.83 17	35.10 198	37.46 200	32.35 197	43.12 180	49.99 194	28.52 208	33.23 195	12.73 218	8.18 204	27.71 180	21.34 209	32.64 170	46.92 194	48.11 197	48.41 209	55.45 197
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	49.14 146	51.75 148	46.10 139	42.78 181	55.60 185	53.11 131	34.46 185	55.69 73	32.47 117	34.16 139	41.45 132	48.91 100	57.13 166	54.09 180	64.84 176	64.10 174
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
pmmvs-eth3d		44.67 169	45.27 181	43.98 155	42.56 182	55.72 184	44.97 171	40.81 147	31.96 170	29.13 134	26.09 185	25.27 202	36.69 152	55.13 175	56.62 169	69.68 157	66.12 170

OMC-MVS		55.48 93	61.85 78	48.04 131	41.55 183	60.32 163	56.80 106	31.78 200	75.67 24	42.30 72	51.52 66	54.15 73	49.91 90	60.28 142	57.59 161	65.91 174	73.42 130

DTE-MVSNet		36.91 192	40.44 192	32.79 194	40.74 184	47.55 200	30.71 204	44.39 107	27.03 193	4.32 216	30.88 159	25.99 198	12.73 206	45.58 197	50.80 191	63.86 181	55.23 198

UGNet		51.04 131	58.79 91	42.00 166	40.59 185	65.32 129	46.65 164	39.26 153	39.90 127	27.30 140	54.12 57	52.03 76	30.93 175	59.85 148	59.62 156	67.23 170	80.70 94
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		38.23 188	41.72 189	34.15 189	40.56 186	50.07 193	33.17 197	44.35 110	27.64 191	5.54 213	30.84 160	26.67 195	14.99 201	45.64 196	52.38 187	66.29 172	58.83 188

ambc			35.52 206		38.36 187	40.40 211	28.38 209		25.20 200	14.87 188	13.22 213	7.54 223	19.34 196	55.63 173	47.79 200	47.91 210	58.89 187

UniMVSNet_ETH3D		43.97 175	46.01 178	41.59 167	38.31 188	56.20 179	49.69 146	38.18 161	28.18 185	19.88 175	27.82 179	30.20 183	33.41 167	54.18 177	56.30 171	70.05 154	69.17 162

MIMVSNet		45.62 165	49.56 163	41.02 172	38.17 189	64.43 138	49.48 147	35.43 177	36.53 147	20.06 173	22.58 194	35.16 155	28.75 183	61.97 120	62.20 126	74.20 108	64.07 175

PatchMatch-RL		43.37 177	44.93 182	41.56 168	37.94 190	51.70 188	40.02 183	35.75 175	39.04 132	30.71 126	35.14 132	27.43 194	46.58 114	51.99 185	50.55 192	58.38 198	58.64 189

WR-MVS_H		36.29 194	40.35 194	31.55 200	37.80 191	49.94 195	30.57 205	41.11 144	26.90 194	4.14 217	30.72 162	28.85 189	10.45 209	42.47 205	47.99 199	65.24 175	55.54 196

CP-MVSNet		37.09 191	40.62 191	32.99 191	37.56 192	48.25 198	32.75 198	43.05 131	27.88 188	5.93 209	31.27 158	25.82 200	15.09 199	43.37 203	48.82 193	63.54 184	58.90 186

PS-CasMVS		36.84 193	40.23 195	32.89 192	37.44 193	48.09 199	32.68 199	42.97 133	27.36 192	5.89 210	30.08 167	25.48 201	14.96 202	43.28 204	48.71 194	63.39 185	58.63 190

FC-MVSNet-test		30.97 206	37.38 202	23.49 209	37.42 194	33.68 214	19.43 217	39.27 152	31.37 174	1.67 223	38.56 118	28.85 189	6.06 219	41.40 206	43.80 206	37.10 214	44.03 210

N_pmnet		34.09 202	35.74 205	32.17 199	37.25 195	43.17 207	32.26 202	35.57 176	26.22 197	10.60 199	20.44 199	19.38 213	20.20 195	44.59 200	47.00 203	57.13 201	49.35 208

SixPastTwentyTwo		36.11 195	37.80 199	34.13 190	37.13 196	46.72 202	34.58 192	34.96 179	21.20 207	11.66 193	29.15 175	19.88 212	29.77 180	44.93 198	48.34 196	56.67 202	54.41 200

new-patchmatchnet		30.47 207	32.80 210	27.75 205	36.81 197	43.98 205	24.85 213	39.29 151	20.52 208	4.06 218	15.94 210	16.05 216	9.57 210	41.32 207	42.05 208	51.94 208	49.74 207

TAPA-MVS	47.92 11	51.66 126	57.88 101	44.40 150	36.46 198	58.42 173	53.82 128	30.83 201	69.51 40	34.97 103	46.90 80	49.67 90	46.99 112	58.00 160	54.64 179	63.33 186	68.00 167
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
COLMAP_ROB	34.79 15	38.65 187	40.72 190	36.23 186	36.41 199	49.22 197	45.51 169	27.60 207	37.81 137	20.54 170	23.37 192	24.25 204	28.11 184	51.02 188	48.55 195	59.22 195	50.82 205
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
anonymousdsp		43.03 180	47.19 172	38.18 182	36.00 200	56.92 177	38.44 186	34.56 183	24.22 201	22.53 161	29.69 171	29.92 184	35.21 157	53.96 181	58.98 157	62.32 190	76.66 115

CVMVSNet		38.91 186	44.49 183	32.40 196	34.57 201	47.20 201	34.81 191	34.20 188	31.45 173	8.95 202	38.86 116	36.38 149	24.30 191	47.77 193	46.94 204	57.59 200	62.85 178

USDC		42.80 181	45.57 180	39.58 175	34.55 202	51.13 189	42.61 177	36.21 172	39.59 129	23.65 155	33.13 146	20.87 211	37.86 148	55.35 174	57.16 165	62.61 188	61.75 181

TSAR-MVS + COLMAP		54.37 98	62.43 71	44.98 147	34.33 203	58.94 170	54.11 126	34.15 191	74.06 27	34.57 104	71.63 18	42.03 130	47.88 107	61.26 130	57.33 164	64.83 177	71.74 145

test-mter		48.31 151	55.04 123	40.45 173	34.12 204	59.02 169	41.77 180	28.05 205	38.43 134	22.67 159	39.35 115	44.40 117	41.88 141	60.30 140	61.68 134	74.20 108	82.12 73

CHOSEN 280x420		42.39 183	47.40 171	36.54 185	33.56 205	39.66 213	40.67 182	26.88 208	34.66 156	18.03 183	30.09 166	45.59 113	44.82 127	54.46 176	54.00 181	55.28 205	73.32 133

EU-MVSNet		33.00 204	36.49 204	28.92 203	33.10 206	42.86 208	29.32 207	35.99 173	22.94 202	5.83 211	25.29 187	24.43 203	15.21 198	41.22 208	41.65 209	54.08 206	57.01 193

ET-MVSNet_ETH3D		57.84 79	61.91 76	53.09 89	32.91 207	74.53 51	63.51 66	46.80 85	46.52 96	36.14 98	56.00 49	46.20 110	64.41 6	60.75 137	66.99 66	74.79 93	82.35 70

TinyColmap		37.18 190	37.37 203	36.95 184	31.17 208	45.21 204	39.71 184	34.65 181	29.83 181	20.20 171	18.54 202	13.72 219	38.27 146	50.33 190	51.57 190	57.71 199	52.42 202

FMVSNet5		43.29 178	47.07 173	38.87 178	30.46 209	50.99 190	45.87 167	37.19 169	42.17 115	19.32 177	26.77 181	40.51 135	30.26 177	56.82 169	55.81 175	70.10 153	56.46 195

FPMVS		26.87 209	28.19 211	25.32 207	27.09 210	29.49 216	32.28 201	17.79 216	28.09 187	11.33 194	19.38 201	14.69 217	20.88 194	35.11 211	32.82 212	42.56 211	37.75 212

MDA-MVSNet-bldmvs		34.31 201	34.11 207	34.54 188	24.73 211	49.66 196	33.42 196	43.03 132	21.59 206	11.10 197	19.81 200	12.68 220	31.41 173	35.59 210	48.05 198	63.56 183	51.39 204

pmmvs3		31.22 205	33.62 208	28.43 204	22.82 212	40.26 212	26.40 211	22.05 214	16.89 215	10.99 198	14.72 211	16.26 215	29.70 181	44.82 199	47.39 201	58.61 197	54.98 199

PM-MVS		34.96 199	38.17 198	31.22 201	22.78 213	40.82 209	33.56 195	23.61 212	29.16 183	21.43 167	28.00 178	21.43 208	31.90 172	44.33 201	42.12 207	54.07 207	61.34 182

PMVS	18.18 18	21.95 210	22.85 212	20.90 211	21.92 214	14.78 218	19.95 216	17.31 217	15.69 216	11.32 195	13.70 212	13.91 218	15.02 200	34.92 212	31.72 213	39.85 213	35.20 213
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
E-PMN		10.66 215	8.30 218	13.42 214	19.91 215	7.87 222	4.30 224	29.47 203	8.37 222	1.70 222	3.67 219	1.29 229	9.12 212	8.98 220	13.59 218	16.03 220	14.30 220

MIMVSNet1		29.60 208	33.37 209	25.20 208	19.52 216	43.94 206	26.29 212	37.92 163	19.95 212	3.79 219	12.64 215	21.99 207	7.70 217	43.83 202	46.32 205	55.97 204	44.92 209

EMVS		10.15 216	7.67 219	13.05 215	19.22 217	7.77 223	4.48 222	29.34 204	8.65 221	1.67 223	3.55 220	1.36 228	9.15 211	8.15 221	11.79 220	14.44 221	12.43 221

TDRefinement		35.76 197	38.23 197	32.88 193	19.09 218	46.04 203	43.29 175	29.49 202	33.49 163	19.04 181	22.29 196	17.82 214	29.69 182	48.60 192	47.24 202	56.65 203	52.12 203

Gipuma		17.16 212	17.83 214	16.36 212	18.76 219	12.15 221	11.97 219	27.78 206	17.94 214	4.86 214	2.53 222	2.73 226	8.90 213	34.32 213	36.09 211	25.92 217	19.06 217
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
RPSCF		33.61 203	40.43 193	25.65 206	16.00 220	32.41 215	31.73 203	13.33 219	50.13 83	23.12 157	31.56 154	40.09 136	32.73 169	41.14 209	37.05 210	36.99 215	50.63 206

PMMVS2		12.25 214	14.17 216	10.00 217	11.39 221	14.35 219	8.21 221	19.29 215	9.31 219	0.19 226	7.38 218	6.19 224	1.10 221	19.26 216	21.13 216	19.85 219	21.56 216

new_pmnet		19.10 211	22.71 213	14.89 213	10.93 222	24.08 217	14.22 218	13.94 218	18.68 213	2.93 220	12.84 214	11.27 221	11.94 207	30.57 214	30.58 214	35.38 216	30.93 214

MVE	10.35 19	9.76 217	11.08 217	8.22 218	4.43 223	13.04 220	3.36 225	23.57 213	5.74 223	1.76 221	3.09 221	1.75 227	6.78 218	12.78 218	23.04 215	9.44 222	18.09 218
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
tmp_tt				4.41 219	2.56 224	1.81 226	2.61 226	0.27 222	20.12 210	9.81 201	17.69 205	9.04 222	1.96 220	12.88 217	12.11 219	9.23 223

test_method		13.92 213	17.14 215	10.16 216	1.69 225	6.92 224	11.25 220	5.74 220	22.41 203	8.11 205	10.40 216	20.91 210	13.73 205	22.17 215	13.98 217	20.44 218	23.18 215

GG-mvs-BLEND		44.87 168	64.59 62	21.86 210	0.01 226	73.70 58	55.99 115	0.01 223	50.70 81	0.01 227	49.18 72	63.61 42	0.01 222	63.83 99	64.50 100	75.13 87	86.62 39

uanet_test		0.00 220	0.00 222	0.00 220	0.00 227	0.00 227	0.00 228	0.00 224	0.00 226	0.00 228	0.00 225	0.00 230	0.00 224	0.00 223	0.00 223	0.00 225	0.00 224

sosnet-low-res		0.00 220	0.00 222	0.00 220	0.00 227	0.00 227	0.00 228	0.00 224	0.00 226	0.00 228	0.00 225	0.00 230	0.00 224	0.00 223	0.00 223	0.00 225	0.00 224

sosnet		0.00 220	0.00 222	0.00 220	0.00 227	0.00 227	0.00 228	0.00 224	0.00 226	0.00 228	0.00 225	0.00 230	0.00 224	0.00 223	0.00 223	0.00 225	0.00 224

testmvs		0.01 218	0.01 220	0.00 220	0.00 227	0.00 227	0.00 228	0.00 224	0.01 224	0.00 228	0.02 223	0.00 230	0.00 224	0.01 222	0.01 221	0.00 225	0.03 222

test123		0.01 218	0.01 220	0.00 220	0.00 227	0.00 227	0.00 228	0.00 224	0.01 224	0.00 228	0.02 223	0.00 230	0.01 222	0.00 223	0.01 221	0.00 225	0.03 222

RE-MVS-def										21.59 166

9.14												80.07 5

MTAPA										54.82 17		71.98 25

MTMP										50.64 33		68.31 31

Patchmatch-RL test							0.69 227

NP-MVS									72.62 31

Patchmtry						64.49 137	52.06 139	34.21 186		31.74 120

DeepMVS_CX						5.87 225	4.32 223	1.74 221	9.04 220	1.30 225	7.97 217	3.16 225	8.56 214	9.74 219		6.30 224	14.51 219

High-resolution multi-view benchmark