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.

DeepC-MVS	78.47 2	84.81 27	86.03 29	83.37 20	89.29 33	90.38 12	88.61 28	76.50 1	86.25 24	77.22 25	75.12 41	80.28 46	77.59 23	88.39 10	88.17 6	91.02 7	93.66 19
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
SED-MVS		88.85 2	91.59 3	85.67 2	90.54 16	92.29 3	91.71 3	76.40 2	92.41 3	83.24 2	92.50 3	90.64 4	81.10 3	89.53 3	88.02 7	91.00 9	95.73 3

DVP-MVS++		89.14 1	91.86 1	85.97 1	92.55 2	92.38 1	91.69 4	76.31 3	93.31 1	83.11 3	92.44 4	91.18 1	81.17 2	89.55 2	87.93 8	91.01 8	96.21 1

DVP-MVS		88.67 3	91.62 2	85.22 4	90.47 18	92.36 2	90.69 10	76.15 4	93.08 2	82.75 5	92.19 6	90.71 3	80.45 6	89.27 6	87.91 9	90.82 12	95.84 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
HPM-MVS++		87.09 9	88.92 13	84.95 6	92.61 1	87.91 41	90.23 16	76.06 5	88.85 13	81.20 11	87.33 14	87.93 12	79.47 9	88.59 9	88.23 5	90.15 36	93.60 21

DPE-MVS		88.63 4	91.29 4	85.53 3	90.87 9	92.20 4	91.98 2	76.00 6	90.55 8	82.09 7	93.85 1	90.75 2	81.25 1	88.62 8	87.59 14	90.96 10	95.48 4
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
MSP-MVS		88.09 5	90.84 5	84.88 7	90.00 24	91.80 6	91.63 5	75.80 7	91.99 4	81.23 10	92.54 2	89.18 6	80.89 4	87.99 15	87.91 9	89.70 46	94.51 7
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
xxxxxxxxxxxxxcwj		85.35 20	85.76 31	84.86 8	91.26 6	91.10 8	90.90 6	75.65 8	89.21 9	81.25 8	91.12 8	61.35 121	78.82 10	87.42 20	86.23 31	91.28 3	93.90 13

SF-MVS		87.47 8	89.70 8	84.86 8	91.26 6	91.10 8	90.90 6	75.65 8	89.21 9	81.25 8	91.12 8	88.93 7	78.82 10	87.42 20	86.23 31	91.28 3	93.90 13

APD-MVS		86.84 12	88.91 14	84.41 11	90.66 12	90.10 13	90.78 8	75.64 10	87.38 18	78.72 20	90.68 11	86.82 17	80.15 7	87.13 26	86.45 29	90.51 22	93.83 15
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
CNVR-MVS		86.36 14	88.19 17	84.23 13	91.33 5	89.84 15	90.34 12	75.56 11	87.36 19	78.97 19	81.19 29	86.76 18	78.74 12	89.30 5	88.58 2	90.45 28	94.33 10

NCCC		85.34 21	86.59 25	83.88 17	91.48 4	88.88 26	89.79 18	75.54 12	86.67 22	77.94 24	76.55 36	84.99 26	78.07 18	88.04 12	87.68 12	90.46 27	93.31 22

APDe-MVS		88.00 6	90.50 6	85.08 5	90.95 8	91.58 7	92.03 1	75.53 13	91.15 5	80.10 16	92.27 5	88.34 11	80.80 5	88.00 14	86.99 19	91.09 6	95.16 6

SMA-MVS		87.56 7	90.17 7	84.52 10	91.71 3	90.57 10	90.77 9	75.19 14	90.67 7	80.50 15	86.59 18	88.86 8	78.09 17	89.92 1	89.41 1	90.84 11	95.19 5
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
SD-MVS		86.96 10	89.45 9	84.05 16	90.13 21	89.23 23	89.77 19	74.59 15	89.17 11	80.70 12	89.93 12	89.67 5	78.47 13	87.57 19	86.79 23	90.67 18	93.76 17
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
SteuartSystems-ACMMP		85.99 16	88.31 16	83.27 22	90.73 11	89.84 15	90.27 15	74.31 16	84.56 31	75.88 31	87.32 15	85.04 25	77.31 25	89.01 7	88.46 3	91.14 5	93.96 12
Skip Steuart: Steuart Systems R&D Blog.
HFP-MVS		86.15 15	87.95 18	84.06 15	90.80 10	89.20 24	89.62 21	74.26 17	87.52 16	80.63 13	86.82 17	84.19 30	78.22 15	87.58 18	87.19 17	90.81 13	93.13 25

DeepC-MVS_fast	78.24 3	84.27 30	85.50 32	82.85 24	90.46 19	89.24 22	87.83 34	74.24 18	84.88 27	76.23 29	75.26 40	81.05 44	77.62 22	88.02 13	87.62 13	90.69 17	92.41 29
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
zzz-MVS		85.71 17	86.88 23	84.34 12	90.54 16	87.11 45	89.77 19	74.17 19	88.54 14	83.08 4	78.60 33	86.10 20	78.11 16	87.80 17	87.46 15	90.35 31	92.56 27

MP-MVS		85.50 19	87.40 21	83.28 21	90.65 13	89.51 20	89.16 25	74.11 20	83.70 35	78.06 23	85.54 21	84.89 28	77.31 25	87.40 23	87.14 18	90.41 29	93.65 20
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
ACMMP_NAP		86.52 13	89.01 11	83.62 18	90.28 20	90.09 14	90.32 14	74.05 21	88.32 15	79.74 17	87.04 16	85.59 24	76.97 30	89.35 4	88.44 4	90.35 31	94.27 11

ACMMPR		85.52 18	87.53 20	83.17 23	90.13 21	89.27 21	89.30 22	73.97 22	86.89 21	77.14 26	86.09 19	83.18 33	77.74 21	87.42 20	87.20 16	90.77 14	92.63 26

CP-MVS		84.74 28	86.43 27	82.77 25	89.48 31	88.13 40	88.64 27	73.93 23	84.92 26	76.77 27	81.94 27	83.50 31	77.29 27	86.92 32	86.49 28	90.49 23	93.14 24

MCST-MVS		85.13 24	86.62 24	83.39 19	90.55 15	89.82 17	89.29 23	73.89 24	84.38 32	76.03 30	79.01 32	85.90 22	78.47 13	87.81 16	86.11 35	92.11 1	93.29 23

X-MVS		83.23 34	85.20 34	80.92 35	89.71 28	88.68 29	88.21 33	73.60 25	82.57 39	71.81 47	77.07 34	81.92 38	71.72 61	86.98 30	86.86 21	90.47 24	92.36 30

SR-MVS					88.99 35			73.57 26				87.54 14

train_agg		84.86 26	87.21 22	82.11 28	90.59 14	85.47 56	89.81 17	73.55 27	83.95 33	73.30 39	89.84 13	87.23 15	75.61 35	86.47 35	85.46 40	89.78 42	92.06 33

TSAR-MVS + MP.		86.88 11	89.23 10	84.14 14	89.78 27	88.67 32	90.59 11	73.46 28	88.99 12	80.52 14	91.26 7	88.65 9	79.91 8	86.96 31	86.22 33	90.59 20	93.83 15
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
DPM-MVS		83.30 33	84.33 36	82.11 28	89.56 29	88.49 35	90.33 13	73.24 29	83.85 34	76.46 28	72.43 52	82.65 34	73.02 50	86.37 37	86.91 20	90.03 38	89.62 54

DeepPCF-MVS	79.04 1	85.30 22	88.93 12	81.06 33	88.77 37	90.48 11	85.46 47	73.08 30	90.97 6	73.77 38	84.81 23	85.95 21	77.43 24	88.22 11	87.73 11	87.85 86	94.34 9

OPM-MVS		79.68 49	79.28 61	80.15 39	87.99 40	86.77 48	88.52 30	72.72 31	64.55 100	67.65 65	67.87 75	74.33 65	74.31 41	86.37 37	85.25 42	89.73 45	89.81 52
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
TSAR-MVS + ACMM		85.10 25	88.81 15	80.77 36	89.55 30	88.53 34	88.59 29	72.55 32	87.39 17	71.90 44	90.95 10	87.55 13	74.57 38	87.08 28	86.54 27	87.47 93	93.67 18

EPNet		79.08 57	80.62 53	77.28 54	88.90 36	83.17 81	83.65 56	72.41 33	74.41 59	67.15 68	76.78 35	74.37 64	64.43 100	83.70 62	83.69 54	87.15 97	88.19 63
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
ACMMP		83.42 32	85.27 33	81.26 32	88.47 38	88.49 35	88.31 32	72.09 34	83.42 36	72.77 42	82.65 25	78.22 51	75.18 36	86.24 40	85.76 37	90.74 15	92.13 32
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
AdaColmap		79.74 48	78.62 63	81.05 34	89.23 34	86.06 53	84.95 50	71.96 35	79.39 49	75.51 32	63.16 92	68.84 96	76.51 31	83.55 63	82.85 60	88.13 76	86.46 78

CDPH-MVS		82.64 35	85.03 35	79.86 40	89.41 32	88.31 37	88.32 31	71.84 36	80.11 46	67.47 66	82.09 26	81.44 42	71.85 59	85.89 43	86.15 34	90.24 34	91.25 39

PGM-MVS		84.42 29	86.29 28	82.23 27	90.04 23	88.82 28	89.23 24	71.74 37	82.82 38	74.61 34	84.41 24	82.09 36	77.03 29	87.13 26	86.73 25	90.73 16	92.06 33

3Dnovator+	75.73 4	82.40 36	82.76 41	81.97 30	88.02 39	89.67 18	86.60 38	71.48 38	81.28 44	78.18 22	64.78 86	77.96 53	77.13 28	87.32 24	86.83 22	90.41 29	91.48 37

CSCG		85.28 23	87.68 19	82.49 26	89.95 25	91.99 5	88.82 26	71.20 39	86.41 23	79.63 18	79.26 30	88.36 10	73.94 43	86.64 33	86.67 26	91.40 2	94.41 8

CPTT-MVS		81.77 39	83.10 40	80.21 38	85.93 52	86.45 51	87.72 35	70.98 40	82.54 40	71.53 50	74.23 46	81.49 41	76.31 33	82.85 70	81.87 67	88.79 64	92.26 31

ACMM	72.26 8	78.86 58	78.13 65	79.71 41	86.89 46	83.40 76	86.02 41	70.50 41	75.28 56	71.49 51	63.01 93	69.26 90	73.57 45	84.11 58	83.98 49	89.76 44	87.84 66
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
HQP-MVS		81.19 42	83.27 39	78.76 47	87.40 42	85.45 57	86.95 36	70.47 42	81.31 43	66.91 69	79.24 31	76.63 55	71.67 62	84.43 56	83.78 53	89.19 56	92.05 35

TSAR-MVS + GP.		83.69 31	86.58 26	80.32 37	85.14 56	86.96 46	84.91 51	70.25 43	84.71 30	73.91 37	85.16 22	85.63 23	77.92 19	85.44 44	85.71 38	89.77 43	92.45 28

MSLP-MVS++		82.09 38	82.66 42	81.42 31	87.03 45	87.22 44	85.82 43	70.04 44	80.30 45	78.66 21	68.67 71	81.04 45	77.81 20	85.19 48	84.88 45	89.19 56	91.31 38

PCF-MVS	73.28 6	79.42 51	80.41 56	78.26 49	84.88 62	88.17 38	86.08 40	69.85 45	75.23 58	68.43 61	68.03 74	78.38 49	71.76 60	81.26 88	80.65 89	88.56 67	91.18 40
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
TranMVSNet+NR-MVSNet		69.25 122	70.81 114	67.43 130	77.23 117	79.46 115	73.48 146	69.66 46	60.43 134	39.56 186	58.82 114	53.48 166	55.74 163	79.59 113	81.21 74	88.89 61	82.70 117

UniMVSNet_NR-MVSNet		70.59 106	72.19 105	68.72 115	77.72 112	80.72 103	73.81 141	69.65 47	61.99 120	43.23 178	60.54 103	57.50 139	58.57 138	79.56 115	81.07 76	89.34 52	83.97 107

LGP-MVS_train		79.83 45	81.22 49	78.22 51	86.28 50	85.36 59	86.76 37	69.59 48	77.34 51	65.14 75	75.68 38	70.79 79	71.37 65	84.60 52	84.01 48	90.18 35	90.74 44

ACMP	73.23 7	79.79 46	80.53 54	78.94 45	85.61 54	85.68 54	85.61 44	69.59 48	77.33 52	71.00 53	74.45 44	69.16 91	71.88 57	83.15 67	83.37 56	89.92 39	90.57 47
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
PHI-MVS		82.36 37	85.89 30	78.24 50	86.40 49	89.52 19	85.52 45	69.52 50	82.38 41	65.67 72	81.35 28	82.36 35	73.07 49	87.31 25	86.76 24	89.24 53	91.56 36

MVS_111021_HR		80.13 44	81.46 46	78.58 48	85.77 53	85.17 60	83.45 58	69.28 51	74.08 62	70.31 56	74.31 45	75.26 62	73.13 48	86.46 36	85.15 43	89.53 49	89.81 52

DU-MVS		69.63 117	70.91 113	68.13 121	75.99 123	79.54 113	73.81 141	69.20 52	61.20 128	43.23 178	58.52 115	53.50 164	58.57 138	79.22 119	80.45 92	87.97 81	83.97 107

NR-MVSNet		68.79 127	70.56 115	66.71 146	77.48 115	79.54 113	73.52 145	69.20 52	61.20 128	39.76 185	58.52 115	50.11 190	51.37 178	80.26 106	80.71 86	88.97 59	83.59 113

LS3D		74.08 80	73.39 95	74.88 70	85.05 57	82.62 85	79.71 76	68.66 54	72.82 67	58.80 94	57.61 124	61.31 122	71.07 67	80.32 103	78.87 116	86.00 135	80.18 144

Baseline_NR-MVSNet		67.53 145	68.77 137	66.09 148	75.99 123	74.75 164	72.43 152	68.41 55	61.33 127	38.33 190	51.31 172	54.13 159	56.03 159	79.22 119	78.19 123	85.37 146	82.45 119

abl_6				79.05 44	87.27 43	88.85 27	83.62 57	68.25 56	81.68 42	72.94 41	73.79 48	84.45 29	72.55 53			89.66 48	90.64 45

ACMH	65.37 14	70.71 105	70.00 120	71.54 86	82.51 69	82.47 86	77.78 96	68.13 57	56.19 159	46.06 169	54.30 142	51.20 184	68.68 77	80.66 98	80.72 82	86.07 129	84.45 106
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
ACMH+	66.54 13	71.36 101	70.09 119	72.85 81	82.59 68	81.13 98	78.56 88	68.04 58	61.55 124	52.52 133	51.50 171	54.14 157	68.56 78	78.85 124	79.50 107	86.82 109	83.94 109

UniMVSNet (Re)		69.53 118	71.90 108	66.76 144	76.42 121	80.93 99	72.59 151	68.03 59	61.75 123	41.68 183	58.34 121	57.23 141	53.27 174	79.53 116	80.62 90	88.57 66	84.90 99

CANet		81.62 41	83.41 38	79.53 42	87.06 44	88.59 33	85.47 46	67.96 60	76.59 54	74.05 35	74.69 42	81.98 37	72.98 51	86.14 41	85.47 39	89.68 47	90.42 48

DTE-MVSNet		61.85 180	64.96 171	58.22 185	74.32 141	74.39 166	61.01 198	67.85 61	51.76 189	21.91 215	53.28 153	48.17 195	37.74 201	72.22 172	76.44 149	86.52 121	78.49 155

test1111		71.56 97	73.44 93	69.38 110	81.16 79	82.95 82	74.99 121	67.68 62	66.89 84	46.33 166	55.19 138	60.91 123	57.99 144	84.59 53	82.70 62	88.12 77	80.85 135

PEN-MVS		62.96 168	65.77 162	59.70 179	73.98 145	75.45 157	63.39 192	67.61 63	52.49 182	25.49 207	53.39 151	49.12 194	40.85 197	71.94 175	77.26 139	86.86 108	80.72 137

test2506		71.72 95	72.95 99	70.29 97	81.49 75	83.27 77	75.74 110	67.59 64	68.19 79	49.81 146	61.15 98	49.73 192	58.82 136	84.76 50	82.94 58	88.27 70	80.63 138

ECVR-MVS		72.20 91	73.91 90	70.20 99	81.49 75	83.27 77	75.74 110	67.59 64	68.19 79	49.31 150	55.77 132	62.00 119	58.82 136	84.76 50	82.94 58	88.27 70	80.41 142

MAR-MVS		79.21 54	80.32 57	77.92 52	87.46 41	88.15 39	83.95 54	67.48 66	74.28 60	68.25 62	64.70 87	77.04 54	72.17 55	85.42 45	85.00 44	88.22 72	87.62 68
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
MVS_0304		81.73 40	83.86 37	79.26 43	86.22 51	89.18 25	86.41 39	67.15 67	75.28 56	70.75 54	74.59 43	83.49 32	74.42 40	87.05 29	86.34 30	90.58 21	91.08 41

CP-MVSNet		62.68 170	65.49 165	59.40 182	71.84 162	75.34 158	62.87 194	67.04 68	52.64 181	27.19 205	53.38 152	48.15 196	41.40 195	71.26 178	75.68 154	86.07 129	82.00 124

PS-CasMVS		62.38 176	65.06 168	59.25 183	71.73 163	75.21 162	62.77 195	66.99 69	51.94 188	26.96 206	52.00 169	47.52 199	41.06 196	71.16 181	75.60 155	85.97 136	81.97 126

UniMVSNet_ETH3D		67.18 149	67.03 154	67.36 132	74.44 140	78.12 128	74.07 136	66.38 70	52.22 184	46.87 161	48.64 183	51.84 181	56.96 152	77.29 139	78.53 118	85.42 145	82.59 118

WR-MVS_H		61.83 182	65.87 161	57.12 189	71.72 164	76.87 144	61.45 197	66.19 71	51.97 187	22.92 212	53.13 158	52.30 179	33.80 205	71.03 182	75.00 159	86.65 117	80.78 136

PVSNet_Blended_VisFu		76.57 67	77.90 66	75.02 68	80.56 87	86.58 50	79.24 81	66.18 72	64.81 97	68.18 63	65.61 80	71.45 74	67.05 83	84.16 57	81.80 68	88.90 60	90.92 42

WR-MVS		63.03 167	67.40 152	57.92 186	75.14 132	77.60 140	60.56 199	66.10 73	54.11 176	23.88 208	53.94 148	53.58 162	34.50 204	73.93 163	77.71 129	87.35 95	80.94 134

PLC	68.99 11	75.68 71	75.31 83	76.12 63	82.94 66	81.26 96	79.94 72	66.10 73	77.15 53	66.86 70	59.13 113	68.53 98	73.73 44	80.38 102	79.04 112	87.13 101	81.68 129
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
QAPM		78.47 60	80.22 58	76.43 61	85.03 58	86.75 49	80.62 67	66.00 75	73.77 64	65.35 74	65.54 82	78.02 52	72.69 52	83.71 61	83.36 57	88.87 62	90.41 49

UA-Net		74.47 77	77.80 67	70.59 94	85.33 55	85.40 58	73.54 144	65.98 76	60.65 132	56.00 111	72.11 53	79.15 47	54.63 169	83.13 68	82.25 64	88.04 80	81.92 127

TSAR-MVS + COLMAP		78.34 61	81.64 45	74.48 75	80.13 94	85.01 61	81.73 60	65.93 77	84.75 29	61.68 86	85.79 20	66.27 106	71.39 64	82.91 69	80.78 80	86.01 134	85.98 80

3Dnovator	73.76 5	79.75 47	80.52 55	78.84 46	84.94 61	87.35 42	84.43 53	65.54 78	78.29 50	73.97 36	63.00 94	75.62 61	74.07 42	85.00 49	85.34 41	90.11 37	89.04 56

Anonymous202405211			72.16 107		80.85 85	81.85 89	76.88 106	65.40 79	62.89 115		46.35 189	67.99 100	62.05 115	81.15 91	80.38 93	85.97 136	84.50 104

MVS_111021_LR		78.13 62	79.85 60	76.13 62	81.12 81	81.50 92	80.28 69	65.25 80	76.09 55	71.32 52	76.49 37	72.87 71	72.21 54	82.79 71	81.29 73	86.59 119	87.91 65

FC-MVSNet-train		72.60 89	75.07 84	69.71 105	81.10 83	78.79 123	73.74 143	65.23 81	66.10 89	53.34 126	70.36 62	63.40 115	56.92 154	81.44 81	80.96 78	87.93 82	84.46 105

OMC-MVS		80.26 43	82.59 43	77.54 53	83.04 64	85.54 55	83.25 59	65.05 82	87.32 20	72.42 43	72.04 54	78.97 48	73.30 47	83.86 59	81.60 71	88.15 75	88.83 58

DELS-MVS		79.15 56	81.07 51	76.91 58	83.54 63	87.31 43	84.45 52	64.92 83	69.98 71	69.34 58	71.62 56	76.26 56	69.84 70	86.57 34	85.90 36	89.39 51	89.88 51
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
CNLPA		77.20 65	77.54 69	76.80 59	82.63 67	84.31 65	79.77 74	64.64 84	85.17 25	73.18 40	56.37 130	69.81 86	74.53 39	81.12 92	78.69 117	86.04 133	87.29 71

MSDG		71.52 98	69.87 121	73.44 79	82.21 73	79.35 116	79.52 78	64.59 85	66.15 88	61.87 85	53.21 156	56.09 147	65.85 97	78.94 123	78.50 119	86.60 118	76.85 166

TDRefinement		66.09 153	65.03 170	67.31 133	69.73 181	76.75 146	75.33 112	64.55 86	60.28 135	49.72 148	45.63 191	42.83 208	60.46 132	75.75 152	75.95 153	84.08 158	78.04 157

baseline1		70.10 113	72.17 106	67.69 126	79.74 95	76.80 145	73.91 137	64.38 87	62.74 116	48.30 154	64.94 84	64.08 112	54.17 171	81.46 80	78.92 114	85.66 141	76.22 168

PVSNet_BlendedMVS		76.21 68	77.52 70	74.69 72	79.46 97	83.79 71	77.50 99	64.34 88	69.88 72	71.88 45	68.54 72	70.42 81	67.05 83	83.48 64	79.63 102	87.89 84	86.87 74

PVSNet_Blended		76.21 68	77.52 70	74.69 72	79.46 97	83.79 71	77.50 99	64.34 88	69.88 72	71.88 45	68.54 72	70.42 81	67.05 83	83.48 64	79.63 102	87.89 84	86.87 74

ETV-MVS		77.32 64	78.81 62	75.58 64	82.24 72	83.64 74	79.98 70	64.02 90	69.64 76	63.90 80	70.89 60	69.94 85	73.41 46	85.39 47	83.91 52	89.92 39	88.31 62

CDS-MVSNet		67.65 142	69.83 123	65.09 151	75.39 130	76.55 148	74.42 129	63.75 91	53.55 177	49.37 149	59.41 111	62.45 117	44.44 189	79.71 112	79.82 100	83.17 164	77.36 162
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
CS-MVS-test		78.79 59	80.72 52	76.53 60	81.11 82	83.88 69	79.69 77	63.72 92	73.80 63	69.95 57	75.40 39	76.17 57	74.85 37	84.50 55	82.78 61	89.87 41	88.54 61

DROMVSNet		79.44 50	81.35 47	77.22 55	82.95 65	84.67 63	81.31 62	63.65 93	72.47 69	68.75 59	73.15 49	78.33 50	75.99 34	86.06 42	83.96 50	90.67 18	90.79 43

UGNet		72.78 87	77.67 68	67.07 139	71.65 166	83.24 79	75.20 115	63.62 94	64.93 96	56.72 107	71.82 55	73.30 67	49.02 182	81.02 93	80.70 87	86.22 125	88.67 59
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
IS_MVSNet		73.33 84	77.34 74	68.65 117	81.29 78	83.47 75	74.45 126	63.58 95	65.75 92	48.49 152	67.11 79	70.61 80	54.63 169	84.51 54	83.58 55	89.48 50	86.34 79

EPNet_dtu		68.08 133	71.00 112	64.67 155	79.64 96	68.62 186	75.05 120	63.30 96	66.36 87	45.27 173	67.40 77	66.84 105	43.64 191	75.37 154	74.98 160	81.15 170	77.44 161
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
CS-MVS		79.22 53	81.11 50	77.01 57	81.36 77	84.03 66	80.35 68	63.25 97	73.43 66	70.37 55	74.10 47	76.03 59	76.40 32	86.32 39	83.95 51	90.34 33	89.93 50

casdiffmvs		76.76 66	78.46 64	74.77 71	80.32 91	83.73 73	80.65 66	63.24 98	73.58 65	66.11 71	69.39 66	74.09 66	69.49 73	82.52 73	79.35 111	88.84 63	86.52 77

canonicalmvs		79.16 55	82.37 44	75.41 65	82.33 71	86.38 52	80.80 65	63.18 99	82.90 37	67.34 67	72.79 51	76.07 58	69.62 71	83.46 66	84.41 47	89.20 55	90.60 46

TAPA-MVS	71.42 9	77.69 63	80.05 59	74.94 69	80.68 86	84.52 64	81.36 61	63.14 100	84.77 28	64.82 77	68.72 69	75.91 60	71.86 58	81.62 77	79.55 106	87.80 88	85.24 92
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
Effi-MVS+		75.28 74	76.20 80	74.20 76	81.15 80	83.24 79	81.11 63	63.13 101	66.37 86	60.27 90	64.30 90	68.88 95	70.93 68	81.56 79	81.69 69	88.61 65	87.35 69

Vis-MVSNet (Re-imp)		67.83 138	73.52 92	61.19 171	78.37 105	76.72 147	66.80 176	62.96 102	65.50 93	34.17 197	67.19 78	69.68 88	39.20 200	79.39 118	79.44 109	85.68 140	76.73 167

COLMAP_ROB	62.73 15	67.66 141	66.76 157	68.70 116	80.49 89	77.98 133	75.29 114	62.95 103	63.62 109	49.96 144	47.32 188	50.72 187	58.57 138	76.87 145	75.50 157	84.94 153	75.33 177
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
Anonymous20231211		71.90 93	72.48 104	71.21 87	80.14 93	81.53 91	76.92 104	62.89 104	64.46 102	58.94 92	43.80 193	70.98 78	62.22 112	80.70 97	80.19 96	86.18 126	85.73 82

tfpn200view9		68.11 132	68.72 138	67.40 131	77.83 110	78.93 119	74.28 131	62.81 105	56.64 154	46.82 162	52.65 164	53.47 167	56.59 155	80.41 99	78.43 120	86.11 127	80.52 140

thres600view7		67.68 140	68.43 142	66.80 143	77.90 107	78.86 121	73.84 139	62.75 106	56.07 160	44.70 176	52.85 162	52.81 174	55.58 164	80.41 99	77.77 128	86.05 131	80.28 143

thres200		67.98 134	68.55 141	67.30 134	77.89 109	78.86 121	74.18 135	62.75 106	56.35 157	46.48 165	52.98 160	53.54 163	56.46 156	80.41 99	77.97 126	86.05 131	79.78 148

thres400		67.95 135	68.62 140	67.17 136	77.90 107	78.59 126	74.27 132	62.72 108	56.34 158	45.77 171	53.00 159	53.35 170	56.46 156	80.21 108	78.43 120	85.91 138	80.43 141

GBi-Net		70.78 103	73.37 96	67.76 122	72.95 154	78.00 130	75.15 116	62.72 108	64.13 103	51.44 135	58.37 118	69.02 92	57.59 146	81.33 84	80.72 82	86.70 113	82.02 121

test1		70.78 103	73.37 96	67.76 122	72.95 154	78.00 130	75.15 116	62.72 108	64.13 103	51.44 135	58.37 118	69.02 92	57.59 146	81.33 84	80.72 82	86.70 113	82.02 121

FMVSNet3		70.49 107	72.90 101	67.67 127	72.88 157	77.98 133	74.96 123	62.72 108	64.13 103	51.44 135	58.37 118	69.02 92	57.43 149	79.43 117	79.57 105	86.59 119	81.81 128

FMVSNet2		70.39 109	72.67 103	67.72 125	72.95 154	78.00 130	75.15 116	62.69 112	63.29 111	51.25 139	55.64 133	68.49 99	57.59 146	80.91 95	80.35 94	86.70 113	82.02 121

EPP-MVSNet		74.00 81	77.41 72	70.02 102	80.53 88	83.91 68	74.99 121	62.68 113	65.06 95	49.77 147	68.68 70	72.09 73	63.06 108	82.49 74	80.73 81	89.12 58	88.91 57

TransMVSNet (Re)		64.74 160	65.66 163	63.66 162	77.40 116	75.33 159	69.86 159	62.67 114	47.63 199	41.21 184	50.01 177	52.33 177	45.31 188	79.57 114	77.69 130	85.49 143	77.07 165

DI_MVS_plusplus_trai		75.13 75	76.12 81	73.96 77	78.18 106	81.55 90	80.97 64	62.54 115	68.59 77	65.13 76	61.43 97	74.81 63	69.32 74	81.01 94	79.59 104	87.64 91	85.89 81

thres100view900		67.60 144	68.02 145	67.12 138	77.83 110	77.75 137	73.90 138	62.52 116	56.64 154	46.82 162	52.65 164	53.47 167	55.92 160	78.77 125	77.62 131	85.72 139	79.23 151

tfpnnormal		64.27 163	63.64 179	65.02 152	75.84 126	75.61 156	71.24 157	62.52 116	47.79 198	42.97 180	42.65 196	44.49 206	52.66 176	78.77 125	76.86 143	84.88 154	79.29 150

ET-MVSNet_ETH3D		72.46 90	74.19 88	70.44 95	62.50 201	81.17 97	79.90 73	62.46 118	64.52 101	57.52 103	71.49 58	59.15 132	72.08 56	78.61 127	81.11 75	88.16 74	83.29 115

test_part1		74.24 78	73.44 93	75.18 67	82.02 74	82.34 87	83.88 55	62.40 119	60.93 130	68.68 60	49.25 182	69.71 87	65.73 98	81.26 88	81.98 66	88.35 68	88.60 60

FMVSNet1		68.84 126	70.47 117	66.94 141	71.35 171	77.68 138	74.71 124	62.35 120	56.93 152	49.94 145	50.01 177	64.59 110	57.07 151	81.33 84	80.72 82	86.25 124	82.00 124

EIA-MVS		75.64 72	76.60 79	74.53 74	82.43 70	83.84 70	78.32 92	62.28 121	65.96 90	63.28 84	68.95 67	67.54 101	71.61 63	82.55 72	81.63 70	89.24 53	85.72 83

OpenMVS	70.44 10	76.15 70	76.82 78	75.37 66	85.01 59	84.79 62	78.99 85	62.07 122	71.27 70	67.88 64	57.91 123	72.36 72	70.15 69	82.23 75	81.41 72	88.12 77	87.78 67

test-LLR		64.42 161	64.36 174	64.49 156	75.02 133	63.93 199	66.61 178	61.96 123	54.41 172	47.77 157	57.46 125	60.25 125	55.20 167	70.80 184	69.33 182	80.40 174	74.38 181

test0.0.03 1		58.80 191	61.58 192	55.56 194	75.02 133	68.45 187	59.58 203	61.96 123	52.74 180	29.57 201	49.75 180	54.56 155	31.46 207	71.19 179	69.77 180	75.75 191	64.57 202

PatchMatch-RL		67.78 139	66.65 158	69.10 112	73.01 153	72.69 171	68.49 166	61.85 125	62.93 114	60.20 91	56.83 129	50.42 188	69.52 72	75.62 153	74.46 163	81.51 168	73.62 185

IB-MVS	66.94 12	71.21 102	71.66 110	70.68 91	79.18 99	82.83 84	72.61 150	61.77 126	59.66 137	63.44 83	53.26 154	59.65 130	59.16 135	76.78 147	82.11 65	87.90 83	87.33 70
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
Vis-MVSNet		72.77 88	77.20 75	67.59 129	74.19 142	84.01 67	76.61 109	61.69 127	60.62 133	50.61 142	70.25 63	71.31 77	55.57 165	83.85 60	82.28 63	86.90 106	88.08 64
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
DCV-MVSNet		73.65 83	75.78 82	71.16 88	80.19 92	79.27 117	77.45 101	61.68 128	66.73 85	58.72 95	65.31 83	69.96 84	62.19 113	81.29 87	80.97 77	86.74 112	86.91 73

Effi-MVS+-dtu		71.82 94	71.86 109	71.78 85	78.77 101	80.47 105	78.55 89	61.67 129	60.68 131	55.49 112	58.48 117	65.48 108	68.85 76	76.92 144	75.55 156	87.35 95	85.46 88

test20.03		53.93 203	56.28 204	51.19 203	72.19 161	65.83 194	53.20 210	61.08 130	42.74 207	22.08 213	37.07 205	45.76 204	24.29 215	70.44 188	69.04 184	74.31 199	63.05 206

GeoE		74.23 79	74.84 86	73.52 78	80.42 90	81.46 93	79.77 74	61.06 131	67.23 83	63.67 81	59.56 110	68.74 97	67.90 80	80.25 107	79.37 110	88.31 69	87.26 72

pmmvs4		67.89 136	67.39 153	68.48 118	71.60 168	73.57 168	74.45 126	60.98 132	64.65 98	57.97 101	54.95 140	51.73 182	61.88 119	73.78 164	75.11 158	83.99 160	77.91 158

CLD-MVS		79.35 52	81.23 48	77.16 56	85.01 59	86.92 47	85.87 42	60.89 133	80.07 48	75.35 33	72.96 50	73.21 69	68.43 79	85.41 46	84.63 46	87.41 94	85.44 89
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
pm-mvs1		65.62 154	67.42 151	63.53 163	73.66 150	76.39 149	69.66 160	60.87 134	49.73 194	43.97 177	51.24 173	57.00 144	48.16 183	79.89 110	77.84 127	84.85 155	79.82 147

v1144		69.93 115	69.36 129	70.61 93	74.89 135	80.93 99	79.11 83	60.64 135	55.97 161	55.31 114	53.85 149	54.14 157	66.54 92	78.10 132	77.44 135	87.14 100	85.09 94

v2v482		70.05 114	69.46 128	70.74 89	74.62 138	80.32 109	79.00 84	60.62 136	57.41 150	56.89 106	55.43 137	55.14 152	66.39 94	77.25 140	77.14 140	86.90 106	83.57 114

v144192		69.34 121	68.68 139	70.12 100	74.06 143	80.54 104	78.08 95	60.54 137	54.99 169	54.13 119	52.92 161	52.80 175	66.73 90	77.13 142	76.72 145	87.15 97	85.63 84

v1192		69.50 119	68.83 135	70.29 97	74.49 139	80.92 101	78.55 89	60.54 137	55.04 167	54.21 117	52.79 163	52.33 177	66.92 87	77.88 134	77.35 138	87.04 104	85.51 86

IterMVS-LS		71.69 96	72.82 102	70.37 96	77.54 114	76.34 150	75.13 119	60.46 139	61.53 125	57.57 102	64.89 85	67.33 102	66.04 96	77.09 143	77.37 137	85.48 144	85.18 93
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
USDC		67.36 147	67.90 147	66.74 145	71.72 164	75.23 161	71.58 154	60.28 140	67.45 82	50.54 143	60.93 99	45.20 205	62.08 114	76.56 149	74.50 162	84.25 157	75.38 176

v1921920		69.03 124	68.32 143	69.86 103	74.03 144	80.37 107	77.55 97	60.25 141	54.62 171	53.59 125	52.36 167	51.50 183	66.75 89	77.17 141	76.69 147	86.96 105	85.56 85

HyFIR lowres test		69.47 120	68.94 134	70.09 101	76.77 120	82.93 83	76.63 108	60.17 142	59.00 140	54.03 120	40.54 202	65.23 109	67.89 81	76.54 150	78.30 122	85.03 151	80.07 145

diffmvs		74.86 76	77.37 73	71.93 84	75.62 128	80.35 108	79.42 80	60.15 143	72.81 68	64.63 78	71.51 57	73.11 70	66.53 93	79.02 122	77.98 125	85.25 148	86.83 76

MVS_Test		75.37 73	77.13 76	73.31 80	79.07 100	81.32 95	79.98 70	60.12 144	69.72 74	64.11 79	70.53 61	73.22 68	68.90 75	80.14 109	79.48 108	87.67 90	85.50 87

CHOSEN 1792x2688		69.20 123	69.26 130	69.13 111	76.86 119	78.93 119	77.27 102	60.12 144	61.86 122	54.42 116	42.54 197	61.61 120	66.91 88	78.55 128	78.14 124	79.23 178	83.23 116

v1240		68.64 129	67.89 148	69.51 108	73.89 146	80.26 111	76.73 107	59.97 146	53.43 179	53.08 128	51.82 170	50.84 186	66.62 91	76.79 146	76.77 144	86.78 111	85.34 90

v10		70.22 111	69.76 124	70.74 89	74.79 136	80.30 110	79.22 82	59.81 147	57.71 148	56.58 109	54.22 147	55.31 150	66.95 86	78.28 130	77.47 134	87.12 103	85.07 95

TinyColmap		62.84 169	61.03 194	64.96 153	69.61 182	71.69 174	68.48 167	59.76 148	55.41 163	47.69 159	47.33 187	34.20 217	62.76 110	74.52 159	72.59 172	81.44 169	71.47 188

EG-PatchMatch MVS		67.24 148	66.94 155	67.60 128	78.73 102	81.35 94	73.28 148	59.49 149	46.89 201	51.42 138	43.65 194	53.49 165	55.50 166	81.38 83	80.66 88	87.15 97	81.17 133

pmmvs-eth3d		63.52 166	62.44 188	64.77 154	66.82 192	70.12 180	69.41 162	59.48 150	54.34 175	52.71 129	46.24 190	44.35 207	56.93 153	72.37 168	73.77 166	83.30 162	75.91 170

pmmvs6		62.41 174	62.88 182	61.87 168	71.38 170	75.18 163	67.76 169	59.45 151	41.64 209	42.52 182	37.33 204	52.91 173	46.87 185	77.67 136	76.26 151	83.23 163	79.18 152

v8		70.23 110	69.86 122	70.67 92	74.69 137	79.82 112	78.79 87	59.18 152	58.80 141	58.20 100	55.00 139	57.33 140	66.31 95	77.51 137	76.71 146	86.82 109	83.88 110

thisisatest0530		71.48 99	73.01 98	69.70 106	73.83 147	78.62 125	74.53 125	59.12 153	64.13 103	58.63 96	64.60 88	58.63 134	64.27 101	80.28 105	80.17 97	87.82 87	84.64 103

tttt0517		71.41 100	72.95 99	69.60 107	73.70 149	78.70 124	74.42 129	59.12 153	63.89 107	58.35 99	64.56 89	58.39 136	64.27 101	80.29 104	80.17 97	87.74 89	84.69 102

LTVRE_ROB	59.44 16	61.82 183	62.64 185	60.87 173	72.83 158	77.19 142	64.37 188	58.97 155	33.56 218	28.00 204	52.59 166	42.21 209	63.93 104	74.52 159	76.28 150	77.15 185	82.13 120
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
MS-PatchMatch		70.17 112	70.49 116	69.79 104	80.98 84	77.97 135	77.51 98	58.95 156	62.33 118	55.22 115	53.14 157	65.90 107	62.03 116	79.08 121	77.11 141	84.08 158	77.91 158

baseline2		69.69 116	70.27 118	69.01 113	75.72 127	77.13 143	73.82 140	58.94 157	61.35 126	57.09 105	61.68 96	57.17 142	61.99 117	78.10 132	76.58 148	86.48 122	79.85 146

v7n		67.05 150	66.94 155	67.17 136	72.35 159	78.97 118	73.26 149	58.88 158	51.16 190	50.90 140	48.21 185	50.11 190	60.96 127	77.70 135	77.38 136	86.68 116	85.05 96

Fast-Effi-MVS+		73.11 86	73.66 91	72.48 82	77.72 112	80.88 102	78.55 89	58.83 159	65.19 94	60.36 89	59.98 107	62.42 118	71.22 66	81.66 76	80.61 91	88.20 73	84.88 100

FC-MVSNet-test		56.90 196	65.20 167	47.21 207	66.98 189	63.20 204	49.11 215	58.60 160	59.38 139	11.50 222	65.60 81	56.68 145	24.66 214	71.17 180	71.36 177	72.38 204	69.02 195

GA-MVS		68.14 131	69.17 132	66.93 142	73.77 148	78.50 127	74.45 126	58.28 161	55.11 166	48.44 153	60.08 105	53.99 160	61.50 124	78.43 129	77.57 132	85.13 149	80.54 139

MDA-MVSNet-bldmvs		53.37 204	53.01 207	53.79 200	43.67 219	67.95 188	59.69 202	57.92 162	43.69 205	32.41 199	41.47 198	27.89 222	52.38 177	56.97 214	65.99 200	76.68 188	67.13 198

Anonymous20231206		56.36 197	57.80 201	54.67 197	70.08 178	66.39 193	60.46 200	57.54 163	49.50 196	29.30 202	33.86 209	46.64 200	35.18 203	70.44 188	68.88 186	75.47 194	68.88 196

SixPastTwentyTwo		61.84 181	62.45 187	61.12 172	69.20 185	72.20 172	62.03 196	57.40 164	46.54 202	38.03 192	57.14 128	41.72 210	58.12 142	69.67 192	71.58 175	81.94 166	78.30 156

thisisatest0515		67.40 146	68.78 136	65.80 149	70.02 179	75.24 160	69.36 163	57.37 165	54.94 170	53.67 124	55.53 136	54.85 153	58.00 143	78.19 131	78.91 115	86.39 123	83.78 111

v148		67.85 137	67.53 149	68.23 119	73.25 152	77.57 141	74.26 133	57.36 166	55.70 162	57.45 104	53.53 150	55.42 149	61.96 118	75.23 155	73.92 164	85.08 150	81.32 132

MVSTER		72.06 92	74.24 87	69.51 108	70.39 177	75.97 153	76.91 105	57.36 166	64.64 99	61.39 88	68.86 68	63.76 113	63.46 105	81.44 81	79.70 101	87.56 92	85.31 91

V42		68.76 128	69.63 125	67.74 124	64.93 197	78.01 129	78.30 93	56.48 168	58.65 142	56.30 110	54.26 145	57.03 143	64.85 99	77.47 138	77.01 142	85.60 142	84.96 98

CANet_DTU		73.29 85	76.96 77	69.00 114	77.04 118	82.06 88	79.49 79	56.30 169	67.85 81	53.29 127	71.12 59	70.37 83	61.81 122	81.59 78	80.96 78	86.09 128	84.73 101

CVMVSNet		62.55 171	65.89 160	58.64 184	66.95 190	69.15 183	66.49 180	56.29 170	52.46 183	32.70 198	59.27 112	58.21 138	50.09 180	71.77 176	71.39 176	79.31 177	78.99 153

Fast-Effi-MVS+-dtu		68.34 130	69.47 127	67.01 140	75.15 131	77.97 135	77.12 103	55.40 171	57.87 143	46.68 164	56.17 131	60.39 124	62.36 111	76.32 151	76.25 152	85.35 147	81.34 131

FA-MVS(training)		73.66 82	74.95 85	72.15 83	78.63 104	80.46 106	78.92 86	54.79 172	69.71 75	65.37 73	62.04 95	66.89 104	67.10 82	80.72 96	79.87 99	88.10 79	84.97 97

gg-mvs-nofinetune		62.55 171	65.05 169	59.62 180	78.72 103	77.61 139	70.83 158	53.63 173	39.71 213	22.04 214	36.36 206	64.32 111	47.53 184	81.16 90	79.03 113	85.00 152	77.17 163

baseline		70.45 108	74.09 89	66.20 147	70.95 174	75.67 154	74.26 133	53.57 174	68.33 78	58.42 97	69.87 64	71.45 74	61.55 123	74.84 158	74.76 161	78.42 180	83.72 112

PMVS	39.38 18	46.06 211	43.30 213	49.28 206	62.93 199	38.75 219	41.88 218	53.50 175	33.33 219	35.46 195	28.90 214	31.01 220	33.04 206	58.61 213	54.63 214	68.86 211	57.88 213
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
SCA		65.40 156	66.58 159	64.02 159	70.65 175	73.37 169	67.35 170	53.46 176	63.66 108	54.14 118	60.84 100	60.20 127	61.50 124	69.96 191	68.14 192	77.01 187	69.91 191

testgi		54.39 202	57.86 200	50.35 204	71.59 169	67.24 190	54.95 208	53.25 177	43.36 206	23.78 209	44.64 192	47.87 197	24.96 212	70.45 187	68.66 188	73.60 201	62.78 207

IterMVS-SCA-FT		66.89 151	69.22 131	64.17 157	71.30 172	75.64 155	71.33 155	53.17 178	57.63 149	49.08 151	60.72 101	60.05 128	63.09 107	74.99 157	73.92 164	77.07 186	81.57 130

dps		64.00 165	62.99 181	65.18 150	73.29 151	72.07 173	68.98 165	53.07 179	57.74 147	58.41 98	55.55 135	47.74 198	60.89 130	69.53 193	67.14 196	76.44 190	71.19 189

tpm cat1		65.41 155	63.81 178	67.28 135	75.61 129	72.88 170	75.32 113	52.85 180	62.97 113	63.66 82	53.24 155	53.29 172	61.83 121	65.54 201	64.14 203	74.43 198	74.60 179

CR-MVSNet		64.83 159	65.54 164	64.01 160	70.64 176	69.41 181	65.97 181	52.74 181	57.81 145	52.65 130	54.27 143	56.31 146	60.92 128	72.20 173	73.09 169	81.12 171	75.69 173

Patchmtry						65.80 195	65.97 181	52.74 181		52.65 130

pmmvs5		62.37 177	64.04 176	60.42 174	65.03 195	71.67 175	67.17 172	52.70 183	50.30 191	44.80 174	54.23 146	51.19 185	49.37 181	72.88 167	73.48 168	83.45 161	74.55 180

MIMVSNet1		49.27 206	53.25 206	44.62 209	44.61 217	61.52 209	53.61 209	52.18 184	41.62 210	18.68 218	28.14 215	41.58 211	25.50 210	68.46 198	69.04 184	73.15 202	62.37 208

new-patchmatchnet		46.97 209	49.47 211	44.05 211	62.82 200	56.55 213	45.35 217	52.01 185	42.47 208	17.04 220	35.73 208	35.21 216	21.84 218	61.27 209	54.83 213	65.26 214	60.26 209

CostFormer		68.92 125	69.58 126	68.15 120	75.98 125	76.17 152	78.22 94	51.86 186	65.80 91	61.56 87	63.57 91	62.83 116	61.85 120	70.40 190	68.67 187	79.42 176	79.62 149

CMPMVS	47.78 17	62.49 173	62.52 186	62.46 166	70.01 180	70.66 179	62.97 193	51.84 187	51.98 186	56.71 108	42.87 195	53.62 161	57.80 145	72.23 171	70.37 179	75.45 195	75.91 170
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
PatchmatchNet		64.21 164	64.65 172	63.69 161	71.29 173	68.66 185	69.63 161	51.70 188	63.04 112	53.77 123	59.83 109	58.34 137	60.23 133	68.54 197	66.06 199	75.56 193	68.08 197
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
PM-MVS		60.48 187	60.94 195	59.94 177	58.85 208	66.83 192	64.27 189	51.39 189	55.03 168	48.03 156	50.00 179	40.79 212	58.26 141	69.20 195	67.13 197	78.84 179	77.60 160

FPMVS		51.87 205	50.00 210	54.07 198	66.83 191	57.25 212	60.25 201	50.91 190	50.25 192	34.36 196	36.04 207	32.02 219	41.49 194	58.98 212	56.07 211	70.56 209	59.36 212

RPSCF		67.64 143	71.25 111	63.43 164	61.86 203	70.73 178	67.26 171	50.86 191	74.20 61	58.91 93	67.49 76	69.33 89	64.10 103	71.41 177	68.45 191	77.61 182	77.17 163

IterMVS		66.36 152	68.30 144	64.10 158	69.48 184	74.61 165	73.41 147	50.79 192	57.30 151	48.28 155	60.64 102	59.92 129	60.85 131	74.14 162	72.66 171	81.80 167	78.82 154
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
anonymousdsp		65.28 157	67.98 146	62.13 167	58.73 209	73.98 167	67.10 173	50.69 193	48.41 197	47.66 160	54.27 143	52.75 176	61.45 126	76.71 148	80.20 95	87.13 101	89.53 55

EU-MVSNet		54.63 200	58.69 198	49.90 205	56.99 211	62.70 207	56.41 207	50.64 194	45.95 204	23.14 211	50.42 176	46.51 201	36.63 202	65.51 202	64.85 201	75.57 192	74.91 178

MDTV_nov1_ep13		64.37 162	65.24 166	63.37 165	68.94 186	70.81 177	72.40 153	50.29 195	60.10 136	53.91 122	60.07 106	59.15 132	57.21 150	69.43 194	67.30 194	77.47 183	69.78 193

pmnet_mix02		55.30 199	57.01 203	53.30 202	64.14 198	59.09 210	58.39 205	50.24 196	53.47 178	38.68 189	49.75 180	45.86 203	40.14 199	65.38 203	60.22 208	68.19 212	65.33 201

RPMNet		61.71 184	62.88 182	60.34 175	69.51 183	69.41 181	63.48 191	49.23 197	57.81 145	45.64 172	50.51 175	50.12 189	53.13 175	68.17 199	68.49 190	81.07 172	75.62 175

MVS-HIRNet		54.41 201	52.10 208	57.11 190	58.99 207	56.10 214	49.68 214	49.10 198	46.18 203	52.15 134	33.18 210	46.11 202	56.10 158	63.19 207	59.70 210	76.64 189	60.25 210

MIMVSNet		58.52 193	61.34 193	55.22 195	60.76 204	67.01 191	66.81 175	49.02 199	56.43 156	38.90 188	40.59 201	54.54 156	40.57 198	73.16 166	71.65 174	75.30 196	66.00 200

TAMVS		59.58 190	62.81 184	55.81 193	66.03 193	65.64 196	63.86 190	48.74 200	49.95 193	37.07 194	54.77 141	58.54 135	44.44 189	72.29 170	71.79 173	74.70 197	66.66 199

PatchT		61.97 179	64.04 176	59.55 181	60.49 205	67.40 189	56.54 206	48.65 201	56.69 153	52.65 130	51.10 174	52.14 180	60.92 128	72.20 173	73.09 169	78.03 181	75.69 173

Gipuma		36.38 213	35.80 215	37.07 212	45.76 216	33.90 220	29.81 220	48.47 202	39.91 212	18.02 219	8.00 223	8.14 227	25.14 211	59.29 211	61.02 207	55.19 218	40.31 216
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
MDTV_nov1_ep13_2view		60.16 188	60.51 196	59.75 178	65.39 194	69.05 184	68.00 168	48.29 203	51.99 185	45.95 170	48.01 186	49.64 193	53.39 173	68.83 196	66.52 198	77.47 183	69.55 194

EPMVS		60.00 189	61.97 190	57.71 187	68.46 187	63.17 205	64.54 187	48.23 204	63.30 110	44.72 175	60.19 104	56.05 148	50.85 179	65.27 204	62.02 206	69.44 210	63.81 204

tpmrst		62.00 178	62.35 189	61.58 169	71.62 167	64.14 198	69.07 164	48.22 205	62.21 119	53.93 121	58.26 122	55.30 151	55.81 162	63.22 206	62.62 205	70.85 207	70.70 190

FMVSNet5		57.24 194	60.02 197	53.99 199	56.45 212	62.74 206	65.27 184	47.03 206	55.14 165	39.55 187	40.88 199	53.42 169	41.83 192	72.35 169	71.10 178	73.79 200	64.50 203

gm-plane-assit		57.00 195	57.62 202	56.28 192	76.10 122	62.43 208	47.62 216	46.57 207	33.84 217	23.24 210	37.52 203	40.19 213	59.61 134	79.81 111	77.55 133	84.55 156	72.03 187

ADS-MVSNet		55.94 198	58.01 199	53.54 201	62.48 202	58.48 211	59.12 204	46.20 208	59.65 138	42.88 181	52.34 168	53.31 171	46.31 186	62.00 208	60.02 209	64.23 215	60.24 211

tpm		62.41 174	63.15 180	61.55 170	72.24 160	63.79 201	71.31 156	46.12 209	57.82 144	55.33 113	59.90 108	54.74 154	53.63 172	67.24 200	64.29 202	70.65 208	74.25 183

N_pmnet		47.35 208	50.13 209	44.11 210	59.98 206	51.64 216	51.86 211	44.80 210	49.58 195	20.76 216	40.65 200	40.05 214	29.64 208	59.84 210	55.15 212	57.63 216	54.00 214

PMMVS		65.06 158	69.17 132	60.26 176	55.25 215	63.43 202	66.71 177	43.01 211	62.41 117	50.64 141	69.44 65	67.04 103	63.29 106	74.36 161	73.54 167	82.68 165	73.99 184

CHOSEN 280x420		58.70 192	61.88 191	54.98 196	55.45 214	50.55 217	64.92 185	40.36 212	55.21 164	38.13 191	48.31 184	63.76 113	63.03 109	73.73 165	68.58 189	68.00 213	73.04 186

E-PMN		21.77 216	18.24 219	25.89 214	40.22 220	19.58 223	12.46 225	39.87 213	18.68 223	6.71 224	9.57 220	4.31 230	22.36 217	19.89 221	27.28 219	33.73 221	28.34 220

EMVS		20.98 217	17.15 220	25.44 215	39.51 221	19.37 224	12.66 224	39.59 214	19.10 222	6.62 225	9.27 221	4.40 229	22.43 216	17.99 222	24.40 220	31.81 222	25.53 221

TESTMET0.1,1		61.10 185	64.36 174	57.29 188	57.53 210	63.93 199	66.61 178	36.22 215	54.41 172	47.77 157	57.46 125	60.25 125	55.20 167	70.80 184	69.33 182	80.40 174	74.38 181

test-mter		60.84 186	64.62 173	56.42 191	55.99 213	64.18 197	65.39 183	34.23 216	54.39 174	46.21 168	57.40 127	59.49 131	55.86 161	71.02 183	69.65 181	80.87 173	76.20 169

MVE	19.12 19	20.47 218	23.27 218	17.20 219	12.66 225	25.41 222	10.52 226	34.14 217	14.79 224	6.53 226	8.79 222	4.68 228	16.64 220	29.49 219	41.63 216	22.73 224	38.11 217
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
new_pmnet		38.40 212	42.64 214	33.44 213	37.54 222	45.00 218	36.60 219	32.72 218	40.27 211	12.72 221	29.89 212	28.90 221	24.78 213	53.17 215	52.90 215	56.31 217	48.34 215

pmmvs3		47.65 207	49.08 212	45.99 208	44.61 217	54.79 215	50.04 212	31.95 219	33.91 216	29.90 200	30.37 211	33.53 218	46.31 186	63.50 205	63.67 204	73.14 203	63.77 205

PMMVS2		25.60 214	29.75 216	20.76 217	28.00 223	30.93 221	23.10 222	29.18 220	23.14 221	1.46 227	18.23 219	16.54 224	5.08 221	40.22 216	41.40 217	37.76 219	37.79 218

DeepMVS_CX						18.74 225	18.55 223	8.02 221	26.96 220	7.33 223	23.81 217	13.05 226	25.99 209	25.17 220		22.45 225	36.25 219

test_method		22.26 215	25.94 217	17.95 218	3.24 226	7.17 226	23.83 221	7.27 222	37.35 215	20.44 217	21.87 218	39.16 215	18.67 219	34.56 217	20.84 221	34.28 220	20.64 222

tmp_tt				14.50 220	14.68 224	7.17 226	10.46 227	2.21 223	37.73 214	28.71 203	25.26 216	16.98 223	4.37 222	31.49 218	29.77 218	26.56 223

GG-mvs-BLEND		46.86 210	67.51 150	22.75 216	0.05 227	76.21 151	64.69 186	0.04 224	61.90 121	0.09 228	55.57 134	71.32 76	0.08 223	70.54 186	67.19 195	71.58 205	69.86 192

testmvs		0.09 219	0.15 221	0.02 221	0.01 228	0.02 228	0.05 229	0.01 225	0.11 225	0.01 229	0.26 225	0.01 231	0.06 225	0.10 223	0.10 222	0.01 226	0.43 224

test123		0.09 219	0.14 222	0.02 221	0.00 229	0.02 228	0.02 230	0.01 225	0.09 226	0.00 230	0.30 224	0.00 232	0.08 223	0.03 224	0.09 223	0.01 226	0.45 223

uanet_test		0.00 221	0.00 223	0.00 223	0.00 229	0.00 230	0.00 231	0.00 227	0.00 227	0.00 230	0.00 226	0.00 232	0.00 226	0.00 225	0.00 224	0.00 228	0.00 225

sosnet-low-res		0.00 221	0.00 223	0.00 223	0.00 229	0.00 230	0.00 231	0.00 227	0.00 227	0.00 230	0.00 226	0.00 232	0.00 226	0.00 225	0.00 224	0.00 228	0.00 225

sosnet		0.00 221	0.00 223	0.00 223	0.00 229	0.00 230	0.00 231	0.00 227	0.00 227	0.00 230	0.00 226	0.00 232	0.00 226	0.00 225	0.00 224	0.00 228	0.00 225

RE-MVS-def										46.24 167

9.14												86.88 16

our_test_3					67.93 188	70.99 176	66.89 174

ambc			53.42 205		64.99 196	63.36 203	49.96 213		47.07 200	37.12 193	28.97 213	16.36 225	41.82 193	75.10 156	67.34 193	71.55 206	75.72 172

MTAPA										83.48 1		86.45 19

MTMP										82.66 6		84.91 27

Patchmatch-RL test							2.85 228

XVS					86.63 47	88.68 29	85.00 48			71.81 47		81.92 38				90.47 24

X-MVStestdata					86.63 47	88.68 29	85.00 48			71.81 47		81.92 38				90.47 24

mPP-MVS					89.90 26							81.29 43

NP-MVS									80.10 47

High-resolution multi-view benchmark