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	botani.	boulde.	bridge	door	exhibi.	lectur.	living.	lounge	observ.	old co.	statue	terrac.

CHOSEN 1792x2688		76.24 62	74.03 94	82.88 1	83.09 118	62.84 2	85.73 115	85.39 113	69.79 31	64.87 166	83.49 218	41.52 181	93.69 29	70.55 113	81.82 69	92.12 40

MG-MVS		78.42 28	76.99 47	82.73 2	93.17 1	64.46 1	89.93 29	88.51 53	64.83 103	73.52 68	88.09 149	48.07 80	92.19 55	62.24 180	84.53 52	91.53 63

LFMVS		78.52 25	77.14 44	82.67 3	89.58 13	58.90 8	91.27 19	88.05 60	63.22 138	74.63 56	90.83 86	41.38 182	94.40 20	75.42 82	79.90 92	94.72 2

DVP-MVS++		82.44 3	82.38 6	82.62 4	91.77 4	57.49 17	84.98 147	88.88 37	58.00 239	83.60 6	93.39 22	67.21 2	96.39 4	81.64 38	91.98 4	93.98 5

DPM-MVS		82.39 4	82.36 7	82.49 5	80.12 204	59.50 5	92.24 8	90.72 16	69.37 37	83.22 8	94.47 2	63.81 5	93.18 33	74.02 94	93.25 2	94.80 1

CSCG		80.41 15	79.72 16	82.49 5	89.12 25	57.67 15	89.29 42	91.54 5	59.19 215	71.82 93	90.05 108	59.72 10	96.04 10	78.37 59	88.40 14	93.75 7

SED-MVS		81.92 8	81.75 9	82.44 7	89.48 17	56.89 29	92.48 3	88.94 35	57.50 253	84.61 4	94.09 4	58.81 13	96.37 6	82.28 32	87.60 18	94.06 3

DVP-MVS		81.30 10	81.00 13	82.20 8	89.40 20	57.45 19	92.34 5	89.99 21	57.71 247	81.91 15	93.64 15	55.17 31	96.44 2	81.68 36	87.13 21	92.72 28
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
test_0728_SECOND				82.20 8	89.50 15	57.73 13	92.34 5	88.88 37					96.39 4	81.68 36	87.13 21	92.47 31

MCST-MVS		83.01 1	83.30 2	82.15 10	92.84 2	57.58 16	93.77 1	91.10 12	75.95 3	77.10 42	93.09 31	54.15 40	95.57 12	85.80 11	85.87 38	93.31 11

balanced_conf03		80.28 16	79.73 15	81.90 11	86.47 52	59.34 6	80.45 279	89.51 26	69.76 33	71.05 105	86.66 176	58.68 16	93.24 31	84.64 18	90.40 6	93.14 18

DELS-MVS		82.32 5	82.50 5	81.79 12	86.80 48	56.89 29	92.77 2	86.30 95	77.83 1	77.88 38	92.13 49	60.24 7	94.78 19	78.97 53	89.61 8	93.69 8
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
OPU-MVS				81.71 13	92.05 3	55.97 48	92.48 3				94.01 6	67.21 2	95.10 15	89.82 3	92.55 3	94.06 3

PS-MVSNAJ		80.06 17	79.52 18	81.68 14	85.58 64	60.97 3	91.69 12	87.02 78	70.62 25	80.75 22	93.22 28	37.77 218	92.50 47	82.75 29	86.25 35	91.57 61

MSC_two_6792asdad				81.53 15	91.77 4	56.03 46		91.10 12					96.22 8	81.46 41	86.80 28	92.34 35

No_MVS				81.53 15	91.77 4	56.03 46		91.10 12					96.22 8	81.46 41	86.80 28	92.34 35

xiu_mvs_v2_base		79.86 18	79.31 19	81.53 15	85.03 76	60.73 4	91.65 13	86.86 81	70.30 29	80.77 21	93.07 33	37.63 223	92.28 53	82.73 30	85.71 39	91.57 61

CNVR-MVS		81.76 9	81.90 8	81.33 18	90.04 10	57.70 14	91.71 11	88.87 39	70.31 28	77.64 41	93.87 8	52.58 48	93.91 26	84.17 19	87.92 16	92.39 33

MVS		76.91 51	75.48 68	81.23 19	84.56 83	55.21 65	80.23 285	91.64 4	58.65 229	65.37 158	91.48 71	45.72 114	95.05 16	72.11 108	89.52 10	93.44 9

VDDNet		74.37 97	72.13 123	81.09 20	79.58 210	56.52 37	90.02 26	86.70 85	52.61 310	71.23 101	87.20 167	31.75 309	93.96 25	74.30 92	75.77 141	92.79 27

MVSMamba_PlusPlus		75.28 82	73.39 98	80.96 21	80.85 189	58.25 10	74.47 331	87.61 71	50.53 326	65.24 159	83.41 220	57.38 20	92.83 37	73.92 96	87.13 21	91.80 55

MM		82.69 2	83.29 3	80.89 22	84.38 87	55.40 59	92.16 10	89.85 23	75.28 4	82.41 11	93.86 9	54.30 37	93.98 23	90.29 1	87.13 21	93.30 12

testing91		78.30 32	77.54 38	80.61 23	88.16 35	57.12 25	87.94 61	91.07 15	71.43 20	70.75 108	88.04 153	55.82 28	92.65 43	69.61 121	75.00 155	92.05 44

NCCC		79.57 20	79.23 20	80.59 24	89.50 15	56.99 26	91.38 16	88.17 57	67.71 53	73.81 65	92.75 38	46.88 95	93.28 30	78.79 56	84.07 55	91.50 65

dcpmvs_2		79.33 21	78.94 21	80.49 25	89.75 12	56.54 36	84.83 155	83.68 167	67.85 50	69.36 118	90.24 100	60.20 8	92.10 59	84.14 20	80.40 83	92.82 25

API-MVS		74.17 100	72.07 125	80.49 25	90.02 11	58.55 9	87.30 77	84.27 152	57.51 252	65.77 155	87.77 158	41.61 179	95.97 11	51.71 276	82.63 61	86.94 190

MVS_0304		82.10 7	82.64 4	80.47 27	86.63 50	54.69 84	92.20 9	86.66 86	74.48 5	82.63 10	93.80 11	50.83 63	93.70 28	90.11 2	86.44 33	93.01 21

testing99		78.45 26	77.78 35	80.45 28	88.28 33	56.81 32	87.95 60	91.49 6	71.72 17	70.84 107	88.09 149	57.29 21	92.63 45	69.24 125	75.13 151	91.91 50

3Dnovator	64.70 6	74.46 95	72.48 112	80.41 29	82.84 132	55.40 59	83.08 216	88.61 50	67.61 56	59.85 231	88.66 134	34.57 278	93.97 24	58.42 216	88.70 12	91.85 53

DPE-MVS		79.82 19	79.66 17	80.29 30	89.27 24	55.08 72	88.70 48	87.92 62	55.55 283	81.21 20	93.69 14	56.51 24	94.27 22	78.36 60	85.70 40	91.51 64
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
MAR-MVS		76.76 56	75.60 65	80.21 31	90.87 7	54.68 85	89.14 43	89.11 32	62.95 142	70.54 114	92.33 47	41.05 183	94.95 17	57.90 227	86.55 32	91.00 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
SD-MVS		76.18 63	74.85 82	80.18 32	85.39 68	56.90 28	85.75 113	82.45 192	56.79 267	74.48 59	91.81 60	43.72 147	90.75 94	74.61 88	78.65 103	92.91 22
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
testing11		79.18 22	78.85 23	80.16 33	88.33 30	56.99 26	88.31 53	92.06 1	72.82 11	70.62 113	88.37 140	57.69 19	92.30 51	75.25 84	76.24 134	91.20 74

Effi-MVS+		75.24 84	73.61 97	80.16 33	81.92 152	57.42 21	85.21 134	76.71 310	60.68 189	73.32 71	89.34 121	47.30 89	91.63 66	68.28 132	79.72 94	91.42 66

SMA-MVS		79.10 23	78.76 24	80.12 35	84.42 85	55.87 49	87.58 70	86.76 83	61.48 171	80.26 25	93.10 29	46.53 101	92.41 49	79.97 47	88.77 11	92.08 41
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
MSLP-MVS++		74.21 99	72.25 119	80.11 36	81.45 174	56.47 38	86.32 98	79.65 249	58.19 235	66.36 146	92.29 48	36.11 257	90.66 96	67.39 137	82.49 63	93.18 17

CANet		80.90 11	81.17 12	80.09 37	87.62 41	54.21 96	91.60 14	86.47 91	73.13 9	79.89 27	93.10 29	49.88 72	92.98 34	84.09 21	84.75 50	93.08 19

IB-MVS	68.87 2	74.01 103	72.03 128	79.94 38	83.04 121	55.50 53	90.24 25	88.65 46	67.14 61	61.38 216	81.74 254	53.21 44	94.28 21	60.45 200	62.41 277	90.03 112
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
HPM-MVS++		80.50 14	80.71 14	79.88 39	87.34 44	55.20 67	89.93 29	87.55 72	66.04 87	79.46 29	93.00 35	53.10 45	91.76 64	80.40 46	89.56 9	92.68 29

QAPM		71.88 146	69.33 173	79.52 40	82.20 147	54.30 93	86.30 99	88.77 43	56.61 271	59.72 233	87.48 162	33.90 286	95.36 13	47.48 304	81.49 72	88.90 140

VDD-MVS		76.08 67	74.97 79	79.44 41	84.27 91	53.33 119	91.13 20	85.88 103	65.33 98	72.37 86	89.34 121	32.52 298	92.76 41	77.90 66	75.96 138	92.22 39

MVS_111021_HR		76.39 61	75.38 72	79.42 42	85.33 70	56.47 38	88.15 54	84.97 132	65.15 101	66.06 149	89.88 111	43.79 144	92.16 56	75.03 85	80.03 90	89.64 120

SteuartSystems-ACMMP		77.08 49	76.33 56	79.34 43	80.98 182	55.31 61	89.76 33	86.91 80	62.94 143	71.65 94	91.56 69	42.33 166	92.56 46	77.14 70	83.69 57	90.15 108
Skip Steuart: Steuart Systems R&D Blog.
test12				79.24 44	86.89 47	56.08 45		85.16 127		72.27 88		47.15 91	91.10 84		85.93 37	90.54 94

APDe-MVS		78.44 27	78.20 27	79.19 45	88.56 26	54.55 89	89.76 33	87.77 66	55.91 278	78.56 34	92.49 44	48.20 79	92.65 43	79.49 48	83.04 59	90.39 97
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
lupinMVS		78.38 29	78.11 29	79.19 45	83.02 122	55.24 63	91.57 15	84.82 136	69.12 38	76.67 44	92.02 54	44.82 133	90.23 110	80.83 45	80.09 87	92.08 41

casdiffmvs_mvg		77.75 40	77.28 41	79.16 47	80.42 200	54.44 91	87.76 62	85.46 110	71.67 18	71.38 99	88.35 142	51.58 52	91.22 79	79.02 52	79.89 93	91.83 54
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
testing222		77.70 41	77.22 43	79.14 48	86.95 46	54.89 78	87.18 81	91.96 2	72.29 13	71.17 104	88.70 133	55.19 30	91.24 78	65.18 161	76.32 132	91.29 72

DeepC-MVS_fast	67.50 3	78.00 36	77.63 36	79.13 49	88.52 27	55.12 69	89.95 28	85.98 102	68.31 40	71.33 100	92.75 38	45.52 118	90.37 103	71.15 111	85.14 46	91.91 50
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
sasdasda		78.17 33	77.86 33	79.12 50	84.30 88	54.22 94	87.71 63	84.57 146	67.70 54	77.70 39	92.11 52	50.90 59	89.95 117	78.18 63	77.54 115	93.20 15

canonicalmvs		78.17 33	77.86 33	79.12 50	84.30 88	54.22 94	87.71 63	84.57 146	67.70 54	77.70 39	92.11 52	50.90 59	89.95 117	78.18 63	77.54 115	93.20 15

RRT-MVS		73.29 118	71.37 137	79.07 52	84.63 81	54.16 99	78.16 307	86.64 88	61.67 166	60.17 228	82.35 245	40.63 191	92.26 54	70.19 117	77.87 111	90.81 86

PHI-MVS		77.49 43	77.00 46	78.95 53	85.33 70	50.69 177	88.57 50	88.59 51	58.14 236	73.60 66	93.31 25	43.14 158	93.79 27	73.81 97	88.53 13	92.37 34

test_yl		75.85 72	74.83 83	78.91 54	88.08 37	51.94 153	91.30 17	89.28 29	57.91 241	71.19 102	89.20 124	42.03 173	92.77 39	69.41 122	75.07 153	92.01 46

DCV-MVSNet		75.85 72	74.83 83	78.91 54	88.08 37	51.94 153	91.30 17	89.28 29	57.91 241	71.19 102	89.20 124	42.03 173	92.77 39	69.41 122	75.07 153	92.01 46

casdiffmvs		77.36 46	76.85 48	78.88 56	80.40 201	54.66 87	87.06 84	85.88 103	72.11 15	71.57 96	88.63 138	50.89 62	90.35 104	76.00 75	79.11 100	91.63 58
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
UBG		78.86 24	78.86 22	78.86 57	87.80 40	55.43 55	87.67 65	91.21 11	72.83 10	72.10 89	88.40 139	58.53 17	89.08 144	73.21 104	77.98 110	92.08 41

PAPM		76.76 56	76.07 60	78.81 58	80.20 202	59.11 7	86.86 90	86.23 96	68.60 39	70.18 116	88.84 131	51.57 53	87.16 226	65.48 154	86.68 30	90.15 108

MSP-MVS		82.30 6	83.47 1	78.80 59	82.99 124	52.71 136	85.04 144	88.63 48	66.08 84	86.77 3	92.75 38	72.05 1	91.46 71	83.35 25	93.53 1	92.23 37
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
DeepC-MVS	67.15 4	76.90 53	76.27 57	78.80 59	80.70 193	55.02 73	86.39 96	86.71 84	66.96 67	67.91 132	89.97 110	48.03 81	91.41 72	75.60 79	84.14 54	89.96 114
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
ACMMP_NAP		76.43 60	75.66 64	78.73 61	81.92 152	54.67 86	84.06 182	85.35 115	61.10 178	72.99 75	91.50 70	40.25 193	91.00 86	76.84 71	86.98 25	90.51 95

baseline		76.86 54	76.24 58	78.71 62	80.47 199	54.20 98	83.90 188	84.88 135	71.38 22	71.51 97	89.15 126	50.51 64	90.55 100	75.71 77	78.65 103	91.39 67

jason		77.01 50	76.45 54	78.69 63	79.69 209	54.74 80	90.56 24	83.99 163	68.26 41	74.10 62	90.91 83	42.14 170	89.99 115	79.30 50	79.12 99	91.36 69
jason: jason.
ET-MVSNet_ETH3D		75.23 85	74.08 92	78.67 64	84.52 84	55.59 51	88.92 45	89.21 31	68.06 47	53.13 327	90.22 102	49.71 73	87.62 212	72.12 107	70.82 197	92.82 25

CostFormer		73.89 107	72.30 118	78.66 65	82.36 144	56.58 33	75.56 321	85.30 118	66.06 85	70.50 115	76.88 311	57.02 22	89.06 145	68.27 133	68.74 214	90.33 99

patch_mono-2		80.84 12	81.59 10	78.62 66	90.34 9	53.77 104	88.08 55	88.36 55	76.17 2	79.40 31	91.09 73	55.43 29	90.09 113	85.01 14	80.40 83	91.99 49

MVS_Test		75.85 72	74.93 80	78.62 66	84.08 93	55.20 67	83.99 184	85.17 125	68.07 46	73.38 70	82.76 229	50.44 65	89.00 149	65.90 150	80.61 79	91.64 57

CDPH-MVS		76.05 68	75.19 74	78.62 66	86.51 51	54.98 75	87.32 75	84.59 145	58.62 230	70.75 108	90.85 85	43.10 160	90.63 98	70.50 115	84.51 53	90.24 102

TSAR-MVS + GP.		77.82 38	77.59 37	78.49 69	85.25 72	50.27 196	90.02 26	90.57 17	56.58 272	74.26 61	91.60 68	54.26 38	92.16 56	75.87 76	79.91 91	93.05 20

ETV-MVS		77.17 48	76.74 50	78.48 70	81.80 155	54.55 89	86.13 102	85.33 116	68.20 42	73.10 74	90.52 92	45.23 123	90.66 96	79.37 49	80.95 74	90.22 103

TSAR-MVS + MP.		78.31 31	78.26 26	78.48 70	81.33 177	56.31 42	81.59 258	86.41 92	69.61 35	81.72 17	88.16 148	55.09 33	88.04 193	74.12 93	86.31 34	91.09 78
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
train_agg		76.91 51	76.40 55	78.45 72	85.68 60	55.42 56	87.59 68	84.00 161	57.84 244	72.99 75	90.98 77	44.99 127	88.58 167	78.19 61	85.32 44	91.34 71

SymmetryMVS		77.43 45	77.09 45	78.44 73	82.56 140	52.32 145	89.31 40	84.15 158	72.20 14	73.23 73	91.05 74	46.52 102	91.00 86	76.23 73	78.55 105	92.00 48

PAPR		75.20 86	74.13 90	78.41 74	88.31 32	55.10 71	84.31 173	85.66 107	63.76 125	67.55 134	90.73 88	43.48 152	89.40 132	66.36 145	77.03 119	90.73 88

alignmvs		78.08 35	77.98 30	78.39 75	83.53 104	53.22 122	89.77 32	85.45 111	66.11 82	76.59 46	91.99 56	54.07 41	89.05 146	77.34 69	77.00 120	92.89 23

test_prior				78.39 75	86.35 54	54.91 77		85.45 111					89.70 126			90.55 92

SF-MVS		77.64 42	77.42 40	78.32 77	83.75 101	52.47 141	86.63 94	87.80 63	58.78 227	74.63 56	92.38 46	47.75 85	91.35 73	78.18 63	86.85 27	91.15 77

ZNCC-MVS		75.82 75	75.02 78	78.23 78	83.88 99	53.80 103	86.91 89	86.05 101	59.71 201	67.85 133	90.55 90	42.23 168	91.02 85	72.66 106	85.29 45	89.87 117

VNet		77.99 37	77.92 32	78.19 79	87.43 43	50.12 197	90.93 22	91.41 8	67.48 57	75.12 51	90.15 106	46.77 98	91.00 86	73.52 99	78.46 106	93.44 9

EIA-MVS		75.92 70	75.18 75	78.13 80	85.14 73	51.60 162	87.17 82	85.32 117	64.69 104	68.56 126	90.53 91	45.79 113	91.58 68	67.21 139	82.18 66	91.20 74

HFP-MVS		74.37 97	73.13 106	78.10 81	84.30 88	53.68 106	85.58 119	84.36 150	56.82 265	65.78 154	90.56 89	40.70 190	90.90 91	69.18 126	80.88 75	89.71 118

tpm2		70.82 168	68.44 186	77.98 82	80.78 191	56.11 44	74.21 333	81.28 216	60.24 194	68.04 131	75.27 329	52.26 50	88.50 174	55.82 248	68.03 219	89.33 129

thisisatest0515		73.64 114	72.20 120	77.97 83	81.63 164	53.01 129	86.69 93	88.81 42	62.53 150	64.06 180	85.65 186	52.15 51	92.50 47	58.43 214	69.84 205	88.39 160

EPNet		78.36 30	78.49 25	77.97 83	85.49 66	52.04 151	89.36 39	84.07 160	73.22 8	77.03 43	91.72 63	49.32 76	90.17 112	73.46 100	82.77 60	91.69 56
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
GDP-MVS		75.27 83	74.38 88	77.95 85	79.04 222	52.86 134	85.22 133	86.19 98	62.43 154	70.66 111	90.40 97	53.51 42	91.60 67	69.25 124	72.68 177	89.39 128

DeepPCF-MVS	69.37 1	80.65 13	81.56 11	77.94 86	85.46 67	49.56 210	90.99 21	86.66 86	70.58 26	80.07 26	95.30 1	56.18 26	90.97 90	82.57 31	86.22 36	93.28 13

GST-MVS		74.87 93	73.90 95	77.77 87	83.30 111	53.45 112	85.75 113	85.29 119	59.22 214	66.50 145	89.85 112	40.94 185	90.76 93	70.94 112	83.35 58	89.10 137

GG-mvs-BLEND				77.77 87	86.68 49	50.61 178	68.67 372	88.45 54		68.73 125	87.45 163	59.15 11	90.67 95	54.83 253	87.67 17	92.03 45

BP-MVS1		76.09 66	75.55 66	77.71 89	79.49 211	52.27 148	84.70 158	90.49 18	64.44 106	69.86 117	90.31 99	55.05 34	91.35 73	70.07 118	75.58 144	89.53 124

cascas		69.01 203	66.13 235	77.66 90	79.36 213	55.41 58	86.99 85	83.75 166	56.69 269	58.92 251	81.35 258	24.31 360	92.10 59	53.23 263	70.61 199	85.46 227

3Dnovator+	62.71 7	72.29 137	70.50 149	77.65 91	83.40 109	51.29 171	87.32 75	86.40 93	59.01 222	58.49 263	88.32 144	32.40 299	91.27 76	57.04 236	82.15 67	90.38 98

MVSFormer		73.53 115	72.19 121	77.57 92	83.02 122	55.24 63	81.63 255	81.44 212	50.28 327	76.67 44	90.91 83	44.82 133	86.11 258	60.83 192	80.09 87	91.36 69

APD-MVS		76.15 65	75.68 63	77.54 93	88.52 27	53.44 113	87.26 80	85.03 131	53.79 300	74.91 54	91.68 65	43.80 143	90.31 106	74.36 90	81.82 69	88.87 142
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
Fast-Effi-MVS+		72.73 127	71.15 141	77.48 94	82.75 134	54.76 79	86.77 92	80.64 227	63.05 141	65.93 151	84.01 207	44.42 138	89.03 147	56.45 243	76.36 131	88.64 149

EPMVS		68.45 216	65.44 254	77.47 95	84.91 77	56.17 43	71.89 358	81.91 203	61.72 165	60.85 221	72.49 355	36.21 256	87.06 229	47.32 305	71.62 187	89.17 135

lecture		74.14 101	73.05 107	77.44 96	81.66 163	50.39 187	87.43 71	84.22 157	51.38 321	72.10 89	90.95 82	38.31 214	93.23 32	70.51 114	80.83 77	88.69 147

PatchmatchNet		67.07 252	63.63 273	77.40 97	83.10 116	58.03 11	72.11 356	77.77 289	58.85 225	59.37 241	70.83 368	37.84 217	84.93 287	42.96 331	69.83 206	89.26 130
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
region2R		73.75 110	72.55 111	77.33 98	83.90 98	52.98 130	85.54 123	84.09 159	56.83 264	65.10 161	90.45 93	37.34 232	90.24 109	68.89 128	80.83 77	88.77 146

WTY-MVS		77.47 44	77.52 39	77.30 99	88.33 30	46.25 304	88.46 51	90.32 19	71.40 21	72.32 87	91.72 63	53.44 43	92.37 50	66.28 146	75.42 145	93.28 13

OpenMVS	61.00 11	69.99 185	67.55 206	77.30 99	78.37 241	54.07 101	84.36 170	85.76 106	57.22 258	56.71 294	87.67 160	30.79 316	92.83 37	43.04 330	84.06 56	85.01 234

myMVS_eth3d28		77.77 39	77.94 31	77.27 101	87.58 42	52.89 133	86.06 104	91.33 10	74.15 7	68.16 130	88.24 146	58.17 18	88.31 183	69.88 120	77.87 111	90.61 91

MTAPA		72.73 127	71.22 139	77.27 101	81.54 170	53.57 108	67.06 379	81.31 214	59.41 208	68.39 127	90.96 79	36.07 259	89.01 148	73.80 98	82.45 64	89.23 132

PAPM_NR		71.80 148	69.98 163	77.26 103	81.54 170	53.34 118	78.60 305	85.25 122	53.46 303	60.53 226	88.66 134	45.69 115	89.24 138	56.49 240	79.62 97	89.19 134

ACMMPR		73.76 109	72.61 109	77.24 104	83.92 97	52.96 131	85.58 119	84.29 151	56.82 265	65.12 160	90.45 93	37.24 235	90.18 111	69.18 126	80.84 76	88.58 152

h-mvs33		73.95 104	72.89 108	77.15 105	80.17 203	50.37 190	84.68 160	83.33 173	68.08 44	71.97 91	88.65 137	42.50 164	91.15 82	78.82 54	57.78 318	89.91 116

SPE-MVS-test		77.20 47	77.25 42	77.05 106	84.60 82	49.04 227	89.42 36	85.83 105	65.90 88	72.85 78	91.98 58	45.10 124	91.27 76	75.02 86	84.56 51	90.84 85

MP-MVS-pluss		75.54 80	75.03 77	77.04 107	81.37 176	52.65 138	84.34 172	84.46 148	61.16 175	69.14 121	91.76 61	39.98 200	88.99 151	78.19 61	84.89 49	89.48 127
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
HyFIR lowres test		69.94 187	67.58 204	77.04 107	77.11 265	57.29 22	81.49 263	79.11 263	58.27 234	58.86 253	80.41 265	42.33 166	86.96 232	61.91 183	68.68 215	86.87 192

DP-MVS Recon		71.99 143	70.31 156	77.01 109	90.65 8	53.44 113	89.37 37	82.97 184	56.33 275	63.56 191	89.47 118	34.02 284	92.15 58	54.05 259	72.41 179	85.43 228

Anonymous20240529		69.71 190	67.28 212	77.00 110	83.78 100	50.36 191	88.87 47	85.10 130	47.22 349	64.03 181	83.37 221	27.93 331	92.10 59	57.78 230	67.44 224	88.53 155

CS-MVS		76.77 55	76.70 51	76.99 111	83.55 103	48.75 237	88.60 49	85.18 124	66.38 75	72.47 85	91.62 67	45.53 117	90.99 89	74.48 89	82.51 62	91.23 73

baseline2		75.15 87	74.54 87	76.98 112	81.67 162	51.74 159	83.84 190	91.94 3	69.97 30	58.98 248	86.02 182	59.73 9	91.73 65	68.37 131	70.40 202	87.48 180

MP-MVS		74.99 90	74.33 89	76.95 113	82.89 129	53.05 128	85.63 118	83.50 172	57.86 243	67.25 136	90.24 100	43.38 155	88.85 160	76.03 74	82.23 65	88.96 139
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
mvs_anonymous		72.29 137	70.74 145	76.94 114	82.85 131	54.72 82	78.43 306	81.54 210	63.77 124	61.69 213	79.32 278	51.11 56	85.31 278	62.15 182	75.79 140	90.79 87

ETVMVS		75.80 76	75.44 69	76.89 115	86.23 55	50.38 189	85.55 122	91.42 7	71.30 23	68.80 124	87.94 155	56.42 25	89.24 138	56.54 239	74.75 159	91.07 79

KinetiMVS		71.15 158	69.25 176	76.82 116	77.99 245	50.49 182	85.05 143	86.51 89	59.78 199	64.10 179	85.34 191	32.16 302	91.33 75	58.82 210	73.54 167	88.64 149

XVS		72.92 123	71.62 131	76.81 117	83.41 106	52.48 139	84.88 152	83.20 179	58.03 237	63.91 183	89.63 116	35.50 264	89.78 122	65.50 152	80.50 81	88.16 163

X-MVStestdata		65.85 271	62.20 281	76.81 117	83.41 106	52.48 139	84.88 152	83.20 179	58.03 237	63.91 183	4.82 447	35.50 264	89.78 122	65.50 152	80.50 81	88.16 163

PGM-MVS		72.60 129	71.20 140	76.80 119	82.95 125	52.82 135	83.07 217	82.14 194	56.51 273	63.18 193	89.81 113	35.68 263	89.76 124	67.30 138	80.19 86	87.83 172

Anonymous202405211		70.11 179	67.88 197	76.79 120	87.20 45	47.24 288	89.49 35	77.38 297	54.88 292	66.14 147	86.84 172	20.93 380	91.54 69	56.45 243	71.62 187	91.59 59

tpm cat1		66.28 265	62.78 275	76.77 121	81.40 175	57.14 24	70.03 365	77.19 299	53.00 307	58.76 256	70.73 371	46.17 105	86.73 239	43.27 329	64.46 252	86.44 207

PVSNet_Blended		76.53 58	76.54 53	76.50 122	85.91 57	51.83 157	88.89 46	84.24 155	67.82 51	69.09 122	89.33 123	46.70 99	88.13 189	75.43 80	81.48 73	89.55 122

diffmvs		75.11 88	74.65 85	76.46 123	78.52 237	53.35 117	83.28 209	79.94 241	70.51 27	71.64 95	88.72 132	46.02 110	86.08 263	77.52 67	75.75 142	89.96 114
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
PVSNet_Blended_VisFu		73.40 117	72.44 113	76.30 124	81.32 178	54.70 83	85.81 109	78.82 267	63.70 126	64.53 172	85.38 190	47.11 92	87.38 221	67.75 136	77.55 114	86.81 200

BH-RMVSNet		70.08 181	68.01 193	76.27 125	84.21 92	51.22 173	87.29 78	79.33 260	58.96 224	63.63 189	86.77 173	33.29 292	90.30 108	44.63 322	73.96 163	87.30 186

CLD-MVS		75.60 78	75.39 71	76.24 126	80.69 194	52.40 142	90.69 23	86.20 97	74.40 6	65.01 164	88.93 128	42.05 172	90.58 99	76.57 72	73.96 163	85.73 221
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
GeoE		69.96 186	67.88 197	76.22 127	81.11 180	51.71 160	84.15 178	76.74 309	59.83 198	60.91 220	84.38 202	41.56 180	88.10 191	51.67 277	70.57 200	88.84 143

1314		71.11 161	69.41 170	76.22 127	79.32 215	50.49 182	80.23 285	85.14 129	59.44 207	58.93 250	88.89 130	33.83 288	89.60 129	61.49 187	77.42 117	88.57 153

thisisatest0530		70.47 176	68.56 182	76.20 129	79.78 208	51.52 165	83.49 201	88.58 52	57.62 250	58.60 259	82.79 228	51.03 58	91.48 70	52.84 268	62.36 279	85.59 226

FA-MVS(test-final)		69.00 204	66.60 226	76.19 130	83.48 105	47.96 270	74.73 328	82.07 198	57.27 257	62.18 205	78.47 287	36.09 258	92.89 35	53.76 262	71.32 193	87.73 175

HY-MVS	67.03 5	73.90 106	73.14 104	76.18 131	84.70 80	47.36 285	75.56 321	86.36 94	66.27 77	70.66 111	83.91 209	51.05 57	89.31 135	67.10 140	72.61 178	91.88 52

gg-mvs-nofinetune		67.43 239	64.53 265	76.13 132	85.95 56	47.79 276	64.38 386	88.28 56	39.34 388	66.62 141	41.27 428	58.69 15	89.00 149	49.64 289	86.62 31	91.59 59

原ACMM1				76.13 132	84.89 78	54.59 88		85.26 121	51.98 314	66.70 139	87.07 170	40.15 196	89.70 126	51.23 280	85.06 48	84.10 248

GA-MVS		69.04 202	66.70 223	76.06 134	75.11 298	52.36 143	83.12 215	80.23 235	63.32 136	60.65 224	79.22 280	30.98 315	88.37 177	61.25 188	66.41 234	87.46 181

mPP-MVS		71.79 149	70.38 154	76.04 135	82.65 138	52.06 150	84.45 168	81.78 206	55.59 282	62.05 210	89.68 115	33.48 290	88.28 186	65.45 157	78.24 109	87.77 174

MVSTER		73.25 119	72.33 116	76.01 136	85.54 65	53.76 105	83.52 195	87.16 76	67.06 65	63.88 185	81.66 255	52.77 46	90.44 101	64.66 166	64.69 250	83.84 259

CP-MVS		72.59 131	71.46 134	76.00 137	82.93 127	52.32 145	86.93 88	82.48 191	55.15 287	63.65 188	90.44 96	35.03 271	88.53 173	68.69 129	77.83 113	87.15 187

fmvsm_s_conf0.5_n_8		76.50 59	76.68 52	75.94 138	78.67 231	47.92 271	85.18 136	74.71 328	68.09 43	80.67 23	94.26 3	47.09 93	89.26 137	86.62 8	74.85 157	90.65 89

HPM-MVS		72.60 129	71.50 133	75.89 139	82.02 148	51.42 167	80.70 277	83.05 181	56.12 277	64.03 181	89.53 117	37.55 226	88.37 177	70.48 116	80.04 89	87.88 171
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
114514_t		69.87 188	67.88 197	75.85 140	88.38 29	52.35 144	86.94 87	83.68 167	53.70 301	55.68 304	85.60 187	30.07 321	91.20 80	55.84 247	71.02 195	83.99 252

reproduce-ours		71.77 150	70.43 151	75.78 141	81.96 150	49.54 213	82.54 230	81.01 221	48.77 339	69.21 119	90.96 79	37.13 238	89.40 132	66.28 146	76.01 136	88.39 160

our_new_method		71.77 150	70.43 151	75.78 141	81.96 150	49.54 213	82.54 230	81.01 221	48.77 339	69.21 119	90.96 79	37.13 238	89.40 132	66.28 146	76.01 136	88.39 160

PMMVS		72.98 122	72.05 126	75.78 141	83.57 102	48.60 241	84.08 180	82.85 186	61.62 167	68.24 129	90.33 98	28.35 327	87.78 204	72.71 105	76.69 126	90.95 83

SDMVSNet		71.89 145	70.62 148	75.70 144	81.70 159	51.61 161	73.89 334	88.72 45	66.58 70	61.64 214	82.38 242	37.63 223	89.48 130	77.44 68	65.60 243	86.01 213

EC-MVSNet		75.30 81	75.20 73	75.62 145	80.98 182	49.00 228	87.43 71	84.68 143	63.49 133	70.97 106	90.15 106	42.86 163	91.14 83	74.33 91	81.90 68	86.71 201

fmvsm_l_conf0.5_n_3		75.73 77	75.78 62	75.61 146	76.03 284	48.33 254	85.34 126	72.92 349	67.16 60	78.55 35	93.85 10	46.22 104	87.53 215	85.61 12	76.30 133	90.98 82

test_fmvsm_n_1920		75.56 79	75.54 67	75.61 146	74.60 307	49.51 215	81.82 249	74.08 334	66.52 73	80.40 24	93.46 20	46.95 94	89.72 125	86.69 7	75.30 146	87.61 178

MS-PatchMatch		72.34 134	71.26 138	75.61 146	82.38 143	55.55 52	88.00 56	89.95 22	65.38 96	56.51 298	80.74 264	32.28 301	92.89 35	57.95 225	88.10 15	78.39 338

fmvsm_s_conf0.5_n		74.48 94	74.12 91	75.56 149	76.96 267	47.85 273	85.32 130	69.80 374	64.16 114	78.74 32	93.48 19	45.51 119	89.29 136	86.48 9	66.62 230	89.55 122

WBMVS		73.93 105	73.39 98	75.55 150	87.82 39	55.21 65	89.37 37	87.29 74	67.27 58	63.70 187	80.30 266	60.32 6	86.47 247	61.58 186	62.85 274	84.97 235

xiu_mvs_v1_base_debu		71.60 152	70.29 157	75.55 150	77.26 260	53.15 123	85.34 126	79.37 254	55.83 279	72.54 81	90.19 103	22.38 371	86.66 241	73.28 101	76.39 128	86.85 195

xiu_mvs_v1_base		71.60 152	70.29 157	75.55 150	77.26 260	53.15 123	85.34 126	79.37 254	55.83 279	72.54 81	90.19 103	22.38 371	86.66 241	73.28 101	76.39 128	86.85 195

xiu_mvs_v1_base_debi		71.60 152	70.29 157	75.55 150	77.26 260	53.15 123	85.34 126	79.37 254	55.83 279	72.54 81	90.19 103	22.38 371	86.66 241	73.28 101	76.39 128	86.85 195

test_fmvsmconf_n		74.41 96	74.05 93	75.49 154	74.16 315	48.38 250	82.66 224	72.57 350	67.05 66	75.11 52	92.88 37	46.35 103	87.81 199	83.93 22	71.71 186	90.28 101

fmvsm_s_conf0.1_n		73.80 108	73.26 101	75.43 155	73.28 323	47.80 275	84.57 166	69.43 376	63.34 135	78.40 36	93.29 26	44.73 136	89.22 140	85.99 10	66.28 239	89.26 130

CANet_DTU		73.71 111	73.14 104	75.40 156	82.61 139	50.05 198	84.67 162	79.36 257	69.72 34	75.39 50	90.03 109	29.41 323	85.93 271	67.99 135	79.11 100	90.22 103

ACMMP		70.81 169	69.29 174	75.39 157	81.52 172	51.92 155	83.43 202	83.03 182	56.67 270	58.80 255	88.91 129	31.92 307	88.58 167	65.89 151	73.39 168	85.67 222
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
test_fmvsmconf0.1_n		73.69 112	73.15 102	75.34 158	70.71 355	48.26 256	82.15 238	71.83 355	66.75 69	74.47 60	92.59 43	44.89 130	87.78 204	83.59 24	71.35 192	89.97 113

SCA		63.84 282	60.01 303	75.32 159	78.58 236	57.92 12	61.61 398	77.53 293	56.71 268	57.75 275	70.77 369	31.97 305	79.91 341	48.80 295	56.36 325	88.13 166

fmvsm_l_conf0.5_n_a		75.88 71	76.07 60	75.31 160	76.08 281	48.34 252	85.24 132	70.62 367	63.13 140	81.45 19	93.62 17	49.98 70	87.40 220	87.76 6	76.77 125	90.20 105

fmvsm_l_conf0.5_n		75.95 69	76.16 59	75.31 160	76.01 286	48.44 249	84.98 147	71.08 364	63.50 132	81.70 18	93.52 18	50.00 68	87.18 225	87.80 5	76.87 123	90.32 100

FE-MVS		64.15 279	60.43 299	75.30 162	80.85 189	49.86 203	68.28 374	78.37 279	50.26 330	59.31 243	73.79 340	26.19 344	91.92 62	40.19 339	66.67 229	84.12 247

fmvsm_s_conf0.5_n_a		73.68 113	73.15 102	75.29 163	75.45 295	48.05 265	83.88 189	68.84 379	63.43 134	78.60 33	93.37 24	45.32 121	88.92 156	85.39 13	64.04 254	88.89 141

ab-mvs		70.65 171	69.11 178	75.29 163	80.87 188	46.23 305	73.48 338	85.24 123	59.99 196	66.65 140	80.94 261	43.13 159	88.69 162	63.58 171	68.07 218	90.95 83

reproduce_model		71.07 162	69.67 167	75.28 165	81.51 173	48.82 235	81.73 252	80.57 230	47.81 345	68.26 128	90.78 87	36.49 253	88.60 166	65.12 162	74.76 158	88.42 159

TR-MVS		69.71 190	67.85 200	75.27 166	82.94 126	48.48 247	87.40 74	80.86 224	57.15 260	64.61 170	87.08 169	32.67 297	89.64 128	46.38 313	71.55 189	87.68 177

v2v482		69.55 196	67.64 203	75.26 167	72.32 337	53.83 102	84.93 151	81.94 200	65.37 97	60.80 222	79.25 279	41.62 178	88.98 152	63.03 175	59.51 293	82.98 277

PCF-MVS	61.03 10	70.10 180	68.40 187	75.22 168	77.15 264	51.99 152	79.30 300	82.12 195	56.47 274	61.88 212	86.48 180	43.98 140	87.24 224	55.37 251	72.79 176	86.43 208
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
fmvsm_s_conf0.1_n_a		72.82 126	72.05 126	75.12 169	70.95 354	47.97 268	82.72 223	68.43 381	62.52 151	78.17 37	93.08 32	44.21 139	88.86 157	84.82 15	63.54 261	88.54 154

test_fmvsmconf0.01_n		71.97 144	70.95 144	75.04 170	66.21 384	47.87 272	80.35 282	70.08 371	65.85 89	72.69 80	91.68 65	39.99 199	87.67 208	82.03 34	69.66 207	89.58 121

fmvsm_s_conf0.5_n_4		74.92 92	74.88 81	75.03 171	75.96 287	47.53 279	85.84 108	73.19 348	67.07 64	79.43 30	92.60 42	46.12 106	88.03 194	84.70 16	69.01 211	89.53 124

HQP-MVS		72.34 134	71.44 135	75.03 171	79.02 223	51.56 163	88.00 56	83.68 167	65.45 92	64.48 173	85.13 192	37.35 230	88.62 164	66.70 141	73.12 171	84.91 237

AdaColmap		67.86 227	65.48 251	75.00 173	88.15 36	54.99 74	86.10 103	76.63 312	49.30 334	57.80 272	86.65 177	29.39 324	88.94 155	45.10 319	70.21 203	81.06 308

EI-MVSNet-Vis-set		73.19 120	72.60 110	74.99 174	82.56 140	49.80 205	82.55 229	89.00 34	66.17 80	65.89 152	88.98 127	43.83 142	92.29 52	65.38 160	69.01 211	82.87 279

mvsmamba		69.38 198	67.52 208	74.95 175	82.86 130	52.22 149	67.36 377	76.75 307	61.14 176	49.43 348	82.04 251	37.26 234	84.14 295	73.93 95	76.91 121	88.50 157

fmvsm_s_conf0.5_n_5		75.02 89	75.07 76	74.88 176	74.33 312	47.83 274	83.99 184	73.54 342	67.10 62	76.32 47	92.43 45	45.42 120	86.35 253	82.98 27	79.50 98	90.47 96

tpmrst		71.04 164	69.77 165	74.86 177	83.19 115	55.86 50	75.64 320	78.73 271	67.88 49	64.99 165	73.73 341	49.96 71	79.56 345	65.92 149	67.85 222	89.14 136

AstraMVS		70.12 178	68.56 182	74.81 178	76.48 272	47.48 281	84.35 171	82.58 190	63.80 123	62.09 209	84.54 200	31.39 312	89.96 116	68.24 134	63.58 260	87.00 189

v1144		68.81 208	66.82 219	74.80 179	72.34 336	53.46 110	84.68 160	81.77 207	64.25 111	60.28 227	77.91 291	40.23 194	88.95 153	60.37 201	59.52 292	81.97 287

guyue		70.53 173	69.12 177	74.76 180	77.61 251	47.53 279	84.86 154	85.17 125	62.70 147	62.18 205	83.74 212	34.72 274	89.86 119	64.69 165	66.38 235	86.87 192

v1192		67.96 226	65.74 246	74.63 181	71.79 341	53.43 115	84.06 182	80.99 223	63.19 139	59.56 237	77.46 298	37.50 229	88.65 163	58.20 220	58.93 299	81.79 290

BH-w/o		70.02 183	68.51 185	74.56 182	82.77 133	50.39 187	86.60 95	78.14 283	59.77 200	59.65 234	85.57 188	39.27 205	87.30 222	49.86 287	74.94 156	85.99 215

SR-MVS		70.92 167	69.73 166	74.50 183	83.38 110	50.48 184	84.27 174	79.35 258	48.96 337	66.57 144	90.45 93	33.65 289	87.11 227	66.42 143	74.56 160	85.91 218

tttt0517		68.33 219	66.29 231	74.46 184	78.08 243	49.06 224	80.88 273	89.08 33	54.40 298	54.75 312	80.77 263	51.31 55	90.33 105	49.35 291	58.01 312	83.99 252

TESTMET0.1,1		72.86 125	72.33 116	74.46 184	81.98 149	50.77 175	85.13 138	85.47 109	66.09 83	67.30 135	83.69 215	37.27 233	83.57 304	65.06 163	78.97 102	89.05 138

Elysia		65.59 272	62.65 276	74.42 186	69.85 364	49.46 217	80.04 288	82.11 196	46.32 359	58.74 257	79.64 273	20.30 382	88.57 170	55.48 249	71.37 190	85.22 230

StellarMVS		65.59 272	62.65 276	74.42 186	69.85 364	49.46 217	80.04 288	82.11 196	46.32 359	58.74 257	79.64 273	20.30 382	88.57 170	55.48 249	71.37 190	85.22 230

nrg030		72.27 139	71.56 132	74.42 186	75.93 288	50.60 179	86.97 86	83.21 178	62.75 145	67.15 137	84.38 202	50.07 67	86.66 241	71.19 110	62.37 278	85.99 215

RPMNet		59.29 315	54.25 339	74.42 186	73.97 318	56.57 34	60.52 401	76.98 303	35.72 403	57.49 281	58.87 413	37.73 221	85.26 280	27.01 401	59.93 288	81.42 298

Vis-MVSNet		70.61 172	69.34 172	74.42 186	80.95 187	48.49 246	86.03 106	77.51 294	58.74 228	65.55 157	87.78 157	34.37 281	85.95 270	52.53 274	80.61 79	88.80 144
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
EPP-MVSNet		71.14 159	70.07 162	74.33 191	79.18 219	46.52 296	83.81 191	86.49 90	56.32 276	57.95 269	84.90 198	54.23 39	89.14 143	58.14 221	69.65 208	87.33 184

test2506		72.91 124	72.43 114	74.32 192	80.12 204	44.18 331	83.19 212	84.77 139	64.02 116	65.97 150	87.43 164	47.67 86	88.72 161	59.08 206	79.66 95	90.08 110

EI-MVSNet-UG-set		72.37 133	71.73 129	74.29 193	81.60 166	49.29 222	81.85 247	88.64 47	65.29 100	65.05 162	88.29 145	43.18 156	91.83 63	63.74 170	67.97 220	81.75 291

ECVR-MVS		71.81 147	71.00 143	74.26 194	80.12 204	43.49 337	84.69 159	82.16 193	64.02 116	64.64 168	87.43 164	35.04 270	89.21 141	61.24 189	79.66 95	90.08 110

OPM-MVS		70.75 170	69.58 168	74.26 194	75.55 294	51.34 169	86.05 105	83.29 177	61.94 162	62.95 197	85.77 185	34.15 283	88.44 175	65.44 158	71.07 194	82.99 275
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
v144192		67.86 227	65.76 245	74.16 196	71.68 343	53.09 126	84.14 179	80.83 225	62.85 144	59.21 246	77.28 302	39.30 204	88.00 195	58.67 212	57.88 316	81.40 300

fmvsm_s_conf0.5_n_6		76.17 64	76.84 49	74.15 197	77.42 257	46.46 297	85.53 124	77.86 287	69.78 32	79.78 28	92.90 36	46.80 96	84.81 289	84.67 17	76.86 124	91.17 76

HQP_MVS		70.96 166	69.91 164	74.12 198	77.95 246	49.57 207	85.76 111	82.59 188	63.60 129	62.15 207	83.28 223	36.04 260	88.30 184	65.46 155	72.34 181	84.49 241

v1921920		67.45 238	65.23 258	74.10 199	71.51 346	52.90 132	83.75 193	80.44 231	62.48 153	59.12 247	77.13 303	36.98 242	87.90 197	57.53 232	58.14 310	81.49 295

v8		67.25 245	64.99 261	74.04 200	72.89 330	53.31 120	82.37 236	80.11 237	61.54 169	54.29 318	76.02 325	42.89 162	88.41 176	58.43 214	56.36 325	80.39 317

VPNet		72.07 141	71.42 136	74.04 200	78.64 235	47.17 289	89.91 31	87.97 61	72.56 12	64.66 167	85.04 195	41.83 177	88.33 181	61.17 190	60.97 284	86.62 202

test_fmvsmvis_n_1920		71.29 157	70.38 154	74.00 202	71.04 353	48.79 236	79.19 301	64.62 391	62.75 145	66.73 138	91.99 56	40.94 185	88.35 179	83.00 26	73.18 170	84.85 239

MonoMVSNet		66.80 258	64.41 266	73.96 203	76.21 279	48.07 264	76.56 318	78.26 281	64.34 108	54.32 317	74.02 338	37.21 236	86.36 252	64.85 164	53.96 349	87.45 182

v1240		66.99 253	64.68 263	73.93 204	71.38 350	52.66 137	83.39 206	79.98 239	61.97 161	58.44 266	77.11 304	35.25 266	87.81 199	56.46 242	58.15 308	81.33 303

BH-untuned		68.28 220	66.40 228	73.91 205	81.62 165	50.01 199	85.56 121	77.39 296	57.63 249	57.47 283	83.69 215	36.36 254	87.08 228	44.81 320	73.08 174	84.65 240

v148		68.24 222	66.35 229	73.88 206	71.76 342	51.47 166	84.23 175	81.90 204	63.69 127	58.94 249	76.44 316	43.72 147	87.78 204	60.63 194	55.86 335	82.39 284

V42		67.66 232	65.60 250	73.86 207	70.69 357	53.63 107	81.50 261	78.61 274	63.85 122	59.49 240	77.49 297	37.98 215	87.65 209	62.33 178	58.43 303	80.29 318

Fast-Effi-MVS+-dtu		66.53 262	64.10 271	73.84 208	72.41 335	52.30 147	84.73 157	75.66 319	59.51 205	56.34 299	79.11 282	28.11 329	85.85 272	57.74 231	63.29 266	83.35 265

v10		66.61 260	64.20 270	73.83 209	72.59 333	53.37 116	81.88 246	79.91 243	61.11 177	54.09 320	75.60 327	40.06 198	88.26 187	56.47 241	56.10 331	79.86 323

APD-MVS_3200maxsize		69.62 195	68.23 191	73.80 210	81.58 168	48.22 257	81.91 245	79.50 252	48.21 343	64.24 178	89.75 114	31.91 308	87.55 214	63.08 173	73.85 165	85.64 224

AUN-MVS		68.20 223	66.35 229	73.76 211	76.37 273	47.45 283	79.52 297	79.52 251	60.98 181	62.34 202	86.02 182	36.59 252	86.94 233	62.32 179	53.47 355	86.89 191

PVSNet_BlendedMVS		73.42 116	73.30 100	73.76 211	85.91 57	51.83 157	86.18 101	84.24 155	65.40 95	69.09 122	80.86 262	46.70 99	88.13 189	75.43 80	65.92 242	81.33 303

hse-mvs2		71.44 156	70.68 146	73.73 213	76.34 274	47.44 284	79.45 298	79.47 253	68.08 44	71.97 91	86.01 184	42.50 164	86.93 234	78.82 54	53.46 356	86.83 198

baseline1		72.51 132	72.12 124	73.69 214	85.05 74	44.46 324	83.51 199	86.13 100	71.61 19	64.64 168	87.97 154	55.00 35	89.48 130	59.07 207	56.05 332	87.13 188

CDS-MVSNet		70.48 175	69.43 169	73.64 215	77.56 254	48.83 234	83.51 199	77.45 295	63.27 137	62.33 203	85.54 189	43.85 141	83.29 309	57.38 235	74.00 162	88.79 145
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
PVSNet	62.49 8	69.27 200	67.81 201	73.64 215	84.41 86	51.85 156	84.63 163	77.80 288	66.42 74	59.80 232	84.95 197	22.14 375	80.44 333	55.03 252	75.11 152	88.62 151

fmvsm_s_conf0.5_n_3		74.97 91	75.42 70	73.62 217	76.99 266	46.67 293	83.13 214	71.14 363	66.20 79	82.13 13	93.76 12	47.49 87	84.00 297	81.95 35	76.02 135	90.19 107

PS-MVSNAJss		68.78 210	67.17 214	73.62 217	73.01 327	48.33 254	84.95 150	84.81 137	59.30 213	58.91 252	79.84 271	37.77 218	88.86 157	62.83 176	63.12 271	83.67 263

TAMVS		69.51 197	68.16 192	73.56 219	76.30 277	48.71 240	82.57 227	77.17 300	62.10 157	61.32 217	84.23 204	41.90 175	83.46 306	54.80 255	73.09 173	88.50 157

UGNet		68.71 211	67.11 215	73.50 220	80.55 198	47.61 278	84.08 180	78.51 276	59.45 206	65.68 156	82.73 232	23.78 362	85.08 285	52.80 269	76.40 127	87.80 173
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
VortexMVS		68.49 215	66.84 218	73.46 221	81.10 181	48.75 237	84.63 163	84.73 141	62.05 158	57.22 288	77.08 306	34.54 280	89.20 142	63.08 173	57.12 322	82.43 283

sd_testset		67.79 230	65.95 240	73.32 222	81.70 159	46.33 302	68.99 370	80.30 234	66.58 70	61.64 214	82.38 242	30.45 318	87.63 210	55.86 246	65.60 243	86.01 213

Anonymous20231211		66.08 269	63.67 272	73.31 223	83.07 119	48.75 237	86.01 107	84.67 144	45.27 365	56.54 296	76.67 314	28.06 330	88.95 153	52.78 270	59.95 287	82.23 285

新几何1				73.30 224	83.10 116	53.48 109		71.43 361	45.55 363	66.14 147	87.17 168	33.88 287	80.54 331	48.50 298	80.33 85	85.88 220

reproduce_monomvs		69.71 190	68.52 184	73.29 225	86.43 53	48.21 258	83.91 187	86.17 99	68.02 48	54.91 309	77.46 298	42.96 161	88.86 157	68.44 130	48.38 369	82.80 280

LuminaMVS		66.60 261	64.37 267	73.27 226	70.06 363	49.57 207	80.77 276	81.76 208	50.81 324	60.56 225	78.41 288	24.50 358	87.26 223	64.24 167	68.25 216	82.99 275

FMVSNet3		68.84 206	67.40 210	73.19 227	85.05 74	48.53 244	85.71 117	85.36 114	60.90 185	57.58 278	79.15 281	42.16 169	86.77 237	47.25 306	63.40 262	84.27 245

thres200		68.71 211	67.27 213	73.02 228	84.73 79	46.76 292	85.03 145	87.73 67	62.34 155	59.87 230	83.45 219	43.15 157	88.32 182	31.25 383	67.91 221	83.98 254

PVSNet_0	57.04 13	61.19 306	57.24 319	73.02 228	77.45 256	50.31 194	79.43 299	77.36 298	63.96 121	47.51 363	72.45 357	25.03 353	83.78 301	52.76 272	19.22 435	84.96 236

test1111		71.06 163	70.42 153	72.97 230	79.48 212	41.49 362	84.82 156	82.74 187	64.20 113	62.98 196	87.43 164	35.20 267	87.92 196	58.54 213	78.42 107	89.49 126

fmvsm_s_conf0.5_n_2		72.02 142	71.72 130	72.92 231	76.79 269	45.90 308	84.48 167	66.11 387	64.26 110	76.12 48	93.40 21	36.26 255	86.04 264	81.47 40	66.54 233	86.82 199

dp		64.41 277	61.58 285	72.90 232	82.40 142	54.09 100	72.53 346	76.59 313	60.39 192	55.68 304	70.39 372	35.18 268	76.90 369	39.34 342	61.71 281	87.73 175

FMVSNet2		67.57 235	65.79 244	72.90 232	82.71 135	47.97 268	85.15 137	84.93 133	58.55 231	56.71 294	78.26 289	36.72 249	86.67 240	46.15 315	62.94 273	84.07 249

XXY-MVS		70.18 177	69.28 175	72.89 234	77.64 250	42.88 347	85.06 142	87.50 73	62.58 149	62.66 201	82.34 246	43.64 149	89.83 121	58.42 216	63.70 259	85.96 217

fmvsm_s_conf0.1_n_2		71.45 155	71.01 142	72.78 235	75.37 296	45.82 312	84.18 177	64.59 392	64.02 116	75.67 49	93.02 34	34.99 272	85.99 266	81.18 44	66.04 241	86.52 205

CR-MVSNet		62.47 298	59.04 310	72.77 236	73.97 318	56.57 34	60.52 401	71.72 357	60.04 195	57.49 281	65.86 388	38.94 207	80.31 334	42.86 332	59.93 288	81.42 298

WB-MVSnew		69.36 199	68.24 190	72.72 237	79.26 217	49.40 219	85.72 116	88.85 40	61.33 172	64.59 171	82.38 242	34.57 278	87.53 215	46.82 310	70.63 198	81.22 307

EI-MVSNet		69.70 193	68.70 181	72.68 238	75.00 301	48.90 232	79.54 295	87.16 76	61.05 179	63.88 185	83.74 212	45.87 111	90.44 101	57.42 234	64.68 251	78.70 331

HPM-MVS_fast		67.86 227	66.28 232	72.61 239	80.67 195	48.34 252	81.18 266	75.95 318	50.81 324	59.55 238	88.05 152	27.86 332	85.98 267	58.83 209	73.58 166	83.51 264

MVP-Stereo		70.97 165	70.44 150	72.59 240	76.03 284	51.36 168	85.02 146	86.99 79	60.31 193	56.53 297	78.92 283	40.11 197	90.00 114	60.00 204	90.01 7	76.41 361
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
MVS_111021_LR		69.07 201	67.91 195	72.54 241	77.27 259	49.56 210	79.77 293	73.96 337	59.33 212	60.73 223	87.82 156	30.19 320	81.53 318	69.94 119	72.19 183	86.53 204

IS-MVSNet		68.80 209	67.55 206	72.54 241	78.50 238	43.43 339	81.03 268	79.35 258	59.12 220	57.27 286	86.71 174	46.05 109	87.70 207	44.32 325	75.60 143	86.49 206

VPA-MVSNet		71.12 160	70.66 147	72.49 243	78.75 229	44.43 326	87.64 66	90.02 20	63.97 120	65.02 163	81.58 257	42.14 170	87.42 219	63.42 172	63.38 265	85.63 225

SR-MVS-dyc-post		68.27 221	66.87 217	72.48 244	80.96 184	48.14 261	81.54 259	76.98 303	46.42 356	62.75 199	89.42 119	31.17 314	86.09 262	60.52 198	72.06 184	83.19 271

dmvs_re		67.61 233	66.00 238	72.42 245	81.86 154	43.45 338	64.67 385	80.00 238	69.56 36	60.07 229	85.00 196	34.71 275	87.63 210	51.48 278	66.68 228	86.17 212

miper_enhance_ethall		69.77 189	68.90 180	72.38 246	78.93 226	49.91 201	83.29 208	78.85 265	64.90 102	59.37 241	79.46 276	52.77 46	85.16 283	63.78 169	58.72 300	82.08 286

cl22		68.85 205	67.69 202	72.35 247	78.07 244	49.98 200	82.45 234	78.48 277	62.50 152	58.46 264	77.95 290	49.99 69	85.17 282	62.55 177	58.72 300	81.90 289

MGCFI-Net		74.07 102	74.64 86	72.34 248	82.90 128	43.33 342	80.04 288	79.96 240	65.61 90	74.93 53	91.85 59	48.01 82	80.86 325	71.41 109	77.10 118	92.84 24

MSDG		59.44 314	55.14 334	72.32 249	74.69 304	50.71 176	74.39 332	73.58 340	44.44 372	43.40 381	77.52 296	19.45 386	90.87 92	31.31 382	57.49 320	75.38 367

UWE-MVS		72.17 140	72.15 122	72.21 250	82.26 145	44.29 328	86.83 91	89.58 25	65.58 91	65.82 153	85.06 194	45.02 126	84.35 294	54.07 258	75.18 148	87.99 170

v7n		62.50 297	59.27 308	72.20 251	67.25 383	49.83 204	77.87 310	80.12 236	52.50 311	48.80 353	73.07 349	32.10 303	87.90 197	46.83 309	54.92 341	78.86 329

testing3-2		72.30 136	72.35 115	72.15 252	83.07 119	47.64 277	85.46 125	89.81 24	66.17 80	61.96 211	84.88 199	58.93 12	82.27 312	55.87 245	64.97 246	86.54 203

1112_ss		70.05 182	69.37 171	72.10 253	80.77 192	42.78 348	85.12 141	76.75 307	59.69 202	61.19 218	92.12 50	47.48 88	83.84 299	53.04 266	68.21 217	89.66 119

miper_ehance_all_eth		68.70 213	67.58 204	72.08 254	76.91 268	49.48 216	82.47 233	78.45 278	62.68 148	58.28 268	77.88 292	50.90 59	85.01 286	61.91 183	58.72 300	81.75 291

eth_miper_zixun_eth		66.98 254	65.28 257	72.06 255	75.61 293	50.40 186	81.00 269	76.97 306	62.00 159	56.99 290	76.97 307	44.84 132	85.58 273	58.75 211	54.42 346	80.21 319

LPG-MVS_test		66.44 264	64.58 264	72.02 256	74.42 309	48.60 241	83.07 217	80.64 227	54.69 294	53.75 323	83.83 210	25.73 348	86.98 230	60.33 202	64.71 248	80.48 315

LGP-MVS_train				72.02 256	74.42 309	48.60 241		80.64 227	54.69 294	53.75 323	83.83 210	25.73 348	86.98 230	60.33 202	64.71 248	80.48 315

ACMP	61.11 9	66.24 267	64.33 268	72.00 258	74.89 303	49.12 223	83.18 213	79.83 244	55.41 285	52.29 332	82.68 233	25.83 346	86.10 260	60.89 191	63.94 257	80.78 311
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
GBi-Net		67.09 250	65.47 252	71.96 259	82.71 135	46.36 299	83.52 195	83.31 174	58.55 231	57.58 278	76.23 320	36.72 249	86.20 254	47.25 306	63.40 262	83.32 266

test1		67.09 250	65.47 252	71.96 259	82.71 135	46.36 299	83.52 195	83.31 174	58.55 231	57.58 278	76.23 320	36.72 249	86.20 254	47.25 306	63.40 262	83.32 266

FMVSNet1		64.57 276	62.11 282	71.96 259	77.32 258	46.36 299	83.52 195	83.31 174	52.43 312	54.42 315	76.23 320	27.80 333	86.20 254	42.59 334	61.34 283	83.32 266

cl____		67.43 239	65.93 241	71.95 262	76.33 275	48.02 266	82.58 226	79.12 262	61.30 174	56.72 293	76.92 309	46.12 106	86.44 249	57.98 223	56.31 327	81.38 302

DIV-MVS_self_test		67.43 239	65.93 241	71.94 263	76.33 275	48.01 267	82.57 227	79.11 263	61.31 173	56.73 292	76.92 309	46.09 108	86.43 250	57.98 223	56.31 327	81.39 301

Patchmatch-RL test		58.72 325	54.32 338	71.92 264	63.91 399	44.25 329	61.73 397	55.19 409	57.38 255	49.31 350	54.24 419	37.60 225	80.89 323	62.19 181	47.28 377	90.63 90

c3_l		67.97 225	66.66 224	71.91 265	76.20 280	49.31 221	82.13 240	78.00 285	61.99 160	57.64 277	76.94 308	49.41 74	84.93 287	60.62 195	57.01 323	81.49 295

tfpn200view9		67.57 235	66.13 235	71.89 266	84.05 94	45.07 319	83.40 204	87.71 69	60.79 186	57.79 273	82.76 229	43.53 150	87.80 201	28.80 390	66.36 236	82.78 281

SSC-MVS3.2		68.13 224	66.89 216	71.85 267	82.26 145	43.97 332	82.09 241	89.29 28	71.74 16	61.12 219	79.83 272	34.60 277	87.45 217	41.23 336	59.85 290	84.14 246

MIMVSNet		63.12 290	60.29 300	71.61 268	75.92 289	46.65 294	65.15 382	81.94 200	59.14 219	54.65 313	69.47 375	25.74 347	80.63 329	41.03 338	69.56 210	87.55 179

test-LLR		69.65 194	69.01 179	71.60 269	78.67 231	48.17 259	85.13 138	79.72 246	59.18 217	63.13 194	82.58 236	36.91 244	80.24 335	60.56 196	75.17 149	86.39 209

test-mter		68.36 217	67.29 211	71.60 269	78.67 231	48.17 259	85.13 138	79.72 246	53.38 304	63.13 194	82.58 236	27.23 337	80.24 335	60.56 196	75.17 149	86.39 209

sss		70.49 174	70.13 161	71.58 271	81.59 167	39.02 374	80.78 275	84.71 142	59.34 210	66.61 142	88.09 149	37.17 237	85.52 274	61.82 185	71.02 195	90.20 105

tpmvs		62.45 299	59.42 306	71.53 272	83.93 96	54.32 92	70.03 365	77.61 292	51.91 315	53.48 326	68.29 381	37.91 216	86.66 241	33.36 373	58.27 306	73.62 383

ACMM	58.35 12	64.35 278	62.01 283	71.38 273	74.21 313	48.51 245	82.25 237	79.66 248	47.61 347	54.54 314	80.11 267	25.26 351	86.00 265	51.26 279	63.16 269	79.64 324
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
ACMH	53.70 16	59.78 312	55.94 330	71.28 274	76.59 271	48.35 251	80.15 287	76.11 316	49.74 332	41.91 387	73.45 348	16.50 405	90.31 106	31.42 381	57.63 319	75.17 370
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
ppachtmachnet_test		58.56 327	54.34 337	71.24 275	71.42 348	54.74 80	81.84 248	72.27 352	49.02 336	45.86 373	68.99 379	26.27 342	83.30 308	30.12 385	43.23 391	75.69 364

thres100view900		66.87 256	65.42 255	71.24 275	83.29 112	43.15 344	81.67 254	87.78 64	59.04 221	55.92 302	82.18 248	43.73 145	87.80 201	28.80 390	66.36 236	82.78 281

thres400		67.40 243	66.13 235	71.19 277	84.05 94	45.07 319	83.40 204	87.71 69	60.79 186	57.79 273	82.76 229	43.53 150	87.80 201	28.80 390	66.36 236	80.71 313

our_test_3		59.11 319	55.08 335	71.18 278	71.42 348	53.29 121	81.96 243	74.52 329	48.32 341	42.08 385	69.28 378	28.14 328	82.15 314	34.35 369	45.68 386	78.11 343

CPTT-MVS		67.15 248	65.84 243	71.07 279	80.96 184	50.32 193	81.94 244	74.10 333	46.18 361	57.91 270	87.64 161	29.57 322	81.31 320	64.10 168	70.18 204	81.56 294

NR-MVSNet		67.25 245	65.99 239	71.04 280	73.27 324	43.91 333	85.32 130	84.75 140	66.05 86	53.65 325	82.11 249	45.05 125	85.97 269	47.55 303	56.18 330	83.24 269

tpm		68.36 217	67.48 209	70.97 281	79.93 207	51.34 169	76.58 317	78.75 270	67.73 52	63.54 192	74.86 331	48.33 78	72.36 394	53.93 260	63.71 258	89.21 133

TranMVSNet+NR-MVSNet		66.94 255	65.61 249	70.93 282	73.45 320	43.38 340	83.02 219	84.25 153	65.31 99	58.33 267	81.90 253	39.92 201	85.52 274	49.43 290	54.89 342	83.89 258

EG-PatchMatch MVS		62.40 300	59.59 304	70.81 283	73.29 322	49.05 225	85.81 109	84.78 138	51.85 317	44.19 376	73.48 347	15.52 408	89.85 120	40.16 340	67.24 225	73.54 384

fmvsm_s_conf0.5_n_7		73.10 121	73.89 96	70.72 284	74.17 314	46.03 307	83.28 209	74.19 332	67.10 62	73.94 64	91.73 62	43.42 154	77.61 363	83.92 23	73.26 169	88.53 155

test_djsdf		63.84 282	61.56 286	70.70 285	68.78 372	44.69 323	81.63 255	81.44 212	50.28 327	52.27 333	76.26 319	26.72 340	86.11 258	60.83 192	55.84 336	81.29 306

UA-Net		67.32 244	66.23 233	70.59 286	78.85 227	41.23 365	73.60 336	75.45 322	61.54 169	66.61 142	84.53 201	38.73 210	86.57 246	42.48 335	74.24 161	83.98 254

thres600view7		66.46 263	65.12 259	70.47 287	83.41 106	43.80 335	82.15 238	87.78 64	59.37 209	56.02 301	82.21 247	43.73 145	86.90 235	26.51 402	64.94 247	80.71 313

UniMVSNet (Re)		67.71 231	66.80 220	70.45 288	74.44 308	42.93 346	82.42 235	84.90 134	63.69 127	59.63 235	80.99 260	47.18 90	85.23 281	51.17 281	56.75 324	83.19 271

IterMVS-LS		66.63 259	65.36 256	70.42 289	75.10 299	48.90 232	81.45 264	76.69 311	61.05 179	55.71 303	77.10 305	45.86 112	83.65 303	57.44 233	57.88 316	78.70 331
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
UniMVSNet_NR-MVSNet		68.82 207	68.29 189	70.40 290	75.71 291	42.59 350	84.23 175	86.78 82	66.31 76	58.51 260	82.45 239	51.57 53	84.64 292	53.11 264	55.96 333	83.96 256

jajsoiax		63.21 289	60.84 294	70.32 291	68.33 377	44.45 325	81.23 265	81.05 218	53.37 305	50.96 342	77.81 294	17.49 399	85.49 276	59.31 205	58.05 311	81.02 309

mvs_tets		62.96 292	60.55 296	70.19 292	68.22 380	44.24 330	80.90 272	80.74 226	52.99 308	50.82 344	77.56 295	16.74 403	85.44 277	59.04 208	57.94 313	80.89 310

pmmvs4		63.34 288	61.07 293	70.16 293	70.14 360	50.53 181	79.97 292	71.41 362	55.08 288	54.12 319	78.58 285	32.79 296	82.09 316	50.33 284	57.22 321	77.86 344

DU-MVS		66.84 257	65.74 246	70.16 293	73.27 324	42.59 350	81.50 261	82.92 185	63.53 131	58.51 260	82.11 249	40.75 187	84.64 292	53.11 264	55.96 333	83.24 269

Effi-MVS+-dtu		66.24 267	64.96 262	70.08 295	75.17 297	49.64 206	82.01 242	74.48 330	62.15 156	57.83 271	76.08 324	30.59 317	83.79 300	65.40 159	60.93 285	76.81 354

IterMVS		63.77 284	61.67 284	70.08 295	72.68 332	51.24 172	80.44 280	75.51 320	60.51 191	51.41 337	73.70 344	32.08 304	78.91 346	54.30 257	54.35 347	80.08 321
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
WR-MVS		67.58 234	66.76 221	70.04 297	75.92 289	45.06 322	86.23 100	85.28 120	64.31 109	58.50 262	81.00 259	44.80 135	82.00 317	49.21 293	55.57 338	83.06 274

Test_1112_low_res		67.18 247	66.23 233	70.02 298	78.75 229	41.02 366	83.43 202	73.69 339	57.29 256	58.45 265	82.39 241	45.30 122	80.88 324	50.50 283	66.26 240	88.16 163

D2MVS		63.49 286	61.39 288	69.77 299	69.29 369	48.93 231	78.89 303	77.71 291	60.64 190	49.70 347	72.10 363	27.08 338	83.48 305	54.48 256	62.65 275	76.90 352

tt0805		63.39 287	61.31 290	69.64 300	69.36 368	38.87 375	78.00 308	85.48 108	48.82 338	55.66 306	81.66 255	24.38 359	86.37 251	49.04 294	59.36 296	83.68 262

XVG-OURS		61.88 302	59.34 307	69.49 301	65.37 389	46.27 303	64.80 384	73.49 343	47.04 351	57.41 285	82.85 227	25.15 352	78.18 351	53.00 267	64.98 245	84.01 251

XVG-OURS-SEG-HR		62.02 301	59.54 305	69.46 302	65.30 390	45.88 309	65.06 383	73.57 341	46.45 355	57.42 284	83.35 222	26.95 339	78.09 353	53.77 261	64.03 255	84.42 243

test_vis1_n_1920		68.59 214	68.31 188	69.44 303	69.16 370	41.51 361	84.63 163	68.58 380	58.80 226	73.26 72	88.37 140	25.30 350	80.60 330	79.10 51	67.55 223	86.23 211

FIs		70.00 184	70.24 160	69.30 304	77.93 248	38.55 377	83.99 184	87.72 68	66.86 68	57.66 276	84.17 205	52.28 49	85.31 278	52.72 273	68.80 213	84.02 250

Baseline_NR-MVSNet		65.49 275	64.27 269	69.13 305	74.37 311	41.65 359	83.39 206	78.85 265	59.56 204	59.62 236	76.88 311	40.75 187	87.44 218	49.99 285	55.05 340	78.28 340

TransMVSNet (Re)		62.82 293	60.76 295	69.02 306	73.98 317	41.61 360	86.36 97	79.30 261	56.90 262	52.53 330	76.44 316	41.85 176	87.60 213	38.83 343	40.61 396	77.86 344

anonymousdsp		60.46 310	57.65 316	68.88 307	63.63 401	45.09 318	72.93 342	78.63 273	46.52 354	51.12 339	72.80 353	21.46 378	83.07 310	57.79 229	53.97 348	78.47 335

ADS-MVSNet		56.17 342	51.95 352	68.84 308	80.60 196	53.07 127	55.03 413	70.02 372	44.72 369	51.00 340	61.19 405	22.83 367	78.88 347	28.54 393	53.63 351	74.57 377

OpenMVS_ROB	53.19 17	59.20 317	56.00 329	68.83 309	71.13 352	44.30 327	83.64 194	75.02 325	46.42 356	46.48 370	73.03 350	18.69 391	88.14 188	27.74 398	61.80 280	74.05 380

Patchmatch-test		53.33 358	48.17 370	68.81 310	73.31 321	42.38 354	42.98 425	58.23 404	32.53 409	38.79 402	70.77 369	39.66 202	73.51 388	25.18 405	52.06 361	90.55 92

pm-mvs1		64.12 280	62.56 278	68.78 311	71.68 343	38.87 375	82.89 221	81.57 209	55.54 284	53.89 322	77.82 293	37.73 221	86.74 238	48.46 299	53.49 354	80.72 312

miper_lstm_enhance		63.91 281	62.30 280	68.75 312	75.06 300	46.78 291	69.02 369	81.14 217	59.68 203	52.76 329	72.39 358	40.71 189	77.99 357	56.81 238	53.09 357	81.48 297

OMC-MVS		65.97 270	65.06 260	68.71 313	72.97 328	42.58 352	78.61 304	75.35 323	54.72 293	59.31 243	86.25 181	33.30 291	77.88 359	57.99 222	67.05 226	85.66 223

DP-MVS		59.24 316	56.12 328	68.63 314	88.24 34	50.35 192	82.51 232	64.43 393	41.10 385	46.70 368	78.77 284	24.75 356	88.57 170	22.26 414	56.29 329	66.96 406

tfpnnormal		61.47 305	59.09 309	68.62 315	76.29 278	41.69 358	81.14 267	85.16 127	54.48 296	51.32 338	73.63 345	32.32 300	86.89 236	21.78 416	55.71 337	77.29 350

test_cas_vis1_n_1920		67.10 249	66.60 226	68.59 316	65.17 392	43.23 343	83.23 211	69.84 373	55.34 286	70.67 110	87.71 159	24.70 357	76.66 371	78.57 58	64.20 253	85.89 219

UniMVSNet_ETH3D		62.51 296	60.49 297	68.57 317	68.30 378	40.88 368	73.89 334	79.93 242	51.81 318	54.77 311	79.61 275	24.80 355	81.10 321	49.93 286	61.35 282	83.73 260

CL-MVSNet_self_test		62.98 291	61.14 292	68.50 318	65.86 387	42.96 345	84.37 169	82.98 183	60.98 181	53.95 321	72.70 354	40.43 192	83.71 302	41.10 337	47.93 372	78.83 330

ACMH+	54.58 15	58.55 328	55.24 332	68.50 318	74.68 305	45.80 313	80.27 283	70.21 370	47.15 350	42.77 384	75.48 328	16.73 404	85.98 267	35.10 367	54.78 343	73.72 382

lessismore_v0				67.98 320	64.76 396	41.25 364		45.75 419		36.03 409	65.63 391	19.29 389	84.11 296	35.67 358	21.24 432	78.59 334

K. test v3		54.04 352	49.42 365	67.92 321	68.55 374	42.57 353	75.51 323	63.07 397	52.07 313	39.21 399	64.59 394	19.34 387	82.21 313	37.11 349	25.31 426	78.97 328

pmmvs5		62.80 294	61.18 291	67.66 322	69.53 367	42.37 355	82.65 225	75.19 324	54.30 299	52.03 335	78.51 286	31.64 310	80.67 328	48.60 297	58.15 308	79.95 322

PatchT		56.60 338	52.97 345	67.48 323	72.94 329	46.16 306	57.30 409	73.78 338	38.77 390	54.37 316	57.26 416	37.52 227	78.06 354	32.02 378	52.79 358	78.23 342

Patchmtry		56.56 339	52.95 346	67.42 324	72.53 334	50.59 180	59.05 405	71.72 357	37.86 395	46.92 366	65.86 388	38.94 207	80.06 338	36.94 352	46.72 382	71.60 396

mmtdpeth		57.93 332	54.78 336	67.39 325	72.32 337	43.38 340	72.72 344	68.93 378	54.45 297	56.85 291	62.43 399	17.02 401	83.46 306	57.95 225	30.31 420	75.31 368

SixPastTwentyTwo		54.37 349	50.10 358	67.21 326	70.70 356	41.46 363	74.73 328	64.69 390	47.56 348	39.12 400	69.49 374	18.49 394	84.69 291	31.87 379	34.20 414	75.48 366

pmmvs6		59.64 313	57.15 320	67.09 327	66.01 385	36.86 385	80.50 278	78.64 272	45.05 367	49.05 351	73.94 339	27.28 336	86.10 260	43.96 327	49.94 366	78.31 339

testdata				67.08 328	77.59 253	45.46 316		69.20 377	44.47 371	71.50 98	88.34 143	31.21 313	70.76 399	52.20 275	75.88 139	85.03 233

CNLPA		60.59 309	58.44 313	67.05 329	79.21 218	47.26 287	79.75 294	64.34 394	42.46 383	51.90 336	83.94 208	27.79 334	75.41 379	37.12 348	59.49 294	78.47 335

KD-MVS_2432*1600		59.04 321	56.44 325	66.86 330	79.07 220	45.87 310	72.13 354	80.42 232	55.03 289	48.15 355	71.01 366	36.73 247	78.05 355	35.21 363	30.18 421	76.67 355

miper_refine_blended		59.04 321	56.44 325	66.86 330	79.07 220	45.87 310	72.13 354	80.42 232	55.03 289	48.15 355	71.01 366	36.73 247	78.05 355	35.21 363	30.18 421	76.67 355

TAPA-MVS	56.12 14	61.82 303	60.18 302	66.71 332	78.48 239	37.97 381	75.19 326	76.41 315	46.82 352	57.04 289	86.52 179	27.67 335	77.03 366	26.50 403	67.02 227	85.14 232
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
test_0402		56.45 340	53.03 344	66.69 333	76.78 270	50.31 194	81.76 250	69.61 375	42.79 381	43.88 377	72.13 361	22.82 369	86.46 248	16.57 428	50.94 363	63.31 415

PLC	52.38 18	60.89 307	58.97 311	66.68 334	81.77 156	45.70 314	78.96 302	74.04 336	43.66 377	47.63 360	83.19 225	23.52 365	77.78 362	37.47 345	60.46 286	76.55 360
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
ADS-MVSNet2		55.21 348	51.44 353	66.51 335	80.60 196	49.56 210	55.03 413	65.44 388	44.72 369	51.00 340	61.19 405	22.83 367	75.41 379	28.54 393	53.63 351	74.57 377

FC-MVSNet-test		67.49 237	67.91 195	66.21 336	76.06 282	33.06 399	80.82 274	87.18 75	64.44 106	54.81 310	82.87 226	50.40 66	82.60 311	48.05 301	66.55 232	82.98 277

JIA-IIPM		52.33 364	47.77 373	66.03 337	71.20 351	46.92 290	40.00 430	76.48 314	37.10 397	46.73 367	37.02 430	32.96 293	77.88 359	35.97 357	52.45 360	73.29 386

UWE-MVS-28		67.43 239	67.98 194	65.75 338	75.66 292	34.74 389	80.00 291	88.17 57	64.21 112	57.27 286	84.14 206	45.68 116	78.82 348	44.33 323	72.40 180	83.70 261

LCM-MVSNet-Re		58.82 324	56.54 323	65.68 339	79.31 216	29.09 418	61.39 400	45.79 418	60.73 188	37.65 405	72.47 356	31.42 311	81.08 322	49.66 288	70.41 201	86.87 192

XVG-ACMP-BASELINE		56.03 343	52.85 347	65.58 340	61.91 406	40.95 367	63.36 389	72.43 351	45.20 366	46.02 371	74.09 336	9.20 421	78.12 352	45.13 318	58.27 306	77.66 347

pmmvs-eth3d		55.97 344	52.78 348	65.54 341	61.02 408	46.44 298	75.36 325	67.72 383	49.61 333	43.65 379	67.58 383	21.63 377	77.04 365	44.11 326	44.33 388	73.15 388

MDA-MVSNet_test_wron		53.82 354	49.95 361	65.43 342	70.13 361	49.05 225	72.30 350	71.65 360	44.23 375	31.85 421	63.13 397	23.68 364	74.01 383	33.25 375	39.35 401	73.23 387

YYNet1		53.82 354	49.96 360	65.41 343	70.09 362	48.95 229	72.30 350	71.66 359	44.25 374	31.89 420	63.07 398	23.73 363	73.95 384	33.26 374	39.40 400	73.34 385

PatchMatch-RL		56.66 337	53.75 342	65.37 344	77.91 249	45.28 317	69.78 367	60.38 400	41.35 384	47.57 361	73.73 341	16.83 402	76.91 367	36.99 351	59.21 297	73.92 381

Vis-MVSNet (Re-imp)		65.52 274	65.63 248	65.17 345	77.49 255	30.54 406	75.49 324	77.73 290	59.34 210	52.26 334	86.69 175	49.38 75	80.53 332	37.07 350	75.28 147	84.42 243

FMVSNet5		58.61 326	56.45 324	65.10 346	77.20 263	39.74 370	74.77 327	77.12 301	50.27 329	43.28 382	67.71 382	26.15 345	76.90 369	36.78 354	54.78 343	78.65 333

EPNet_dtu		66.25 266	66.71 222	64.87 347	78.66 234	34.12 394	82.80 222	75.51 320	61.75 164	64.47 176	86.90 171	37.06 240	72.46 393	43.65 328	69.63 209	88.02 169
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
UnsupCasMVSNet_eth		57.56 334	55.15 333	64.79 348	64.57 397	33.12 398	73.17 341	83.87 165	58.98 223	41.75 388	70.03 373	22.54 370	79.92 339	46.12 316	35.31 408	81.32 305

sc_t1		53.51 357	49.92 362	64.29 349	70.33 359	39.55 373	72.93 342	59.60 403	38.74 391	47.16 365	66.47 386	17.59 398	76.50 372	36.83 353	39.62 399	76.82 353

LS3D		56.40 341	53.82 341	64.12 350	81.12 179	45.69 315	73.42 339	66.14 386	35.30 407	43.24 383	79.88 269	22.18 374	79.62 344	19.10 423	64.00 256	67.05 405

UnsupCasMVSNet_bld		53.86 353	50.53 357	63.84 351	63.52 402	34.75 388	71.38 359	81.92 202	46.53 353	38.95 401	57.93 414	20.55 381	80.20 337	39.91 341	34.09 415	76.57 359

USDC		54.36 350	51.23 354	63.76 352	64.29 398	37.71 382	62.84 394	73.48 345	56.85 263	35.47 410	71.94 364	9.23 420	78.43 349	38.43 344	48.57 368	75.13 371

tt0320-xc		52.22 365	48.38 369	63.75 353	72.19 340	42.25 356	72.19 353	57.59 406	37.24 396	44.41 375	61.56 402	17.90 396	75.89 376	35.60 359	36.73 404	73.12 389

tt0320		52.45 362	48.75 366	63.55 354	71.47 347	41.85 357	72.42 348	59.73 402	36.33 402	44.52 374	61.55 403	19.34 387	76.45 373	33.53 371	39.85 398	72.36 391

Anonymous20231206		59.08 320	57.59 317	63.55 354	68.77 373	32.14 404	80.26 284	79.78 245	50.00 331	49.39 349	72.39 358	26.64 341	78.36 350	33.12 376	57.94 313	80.14 320

CMPMVS	40.41 21	55.34 346	52.64 349	63.46 356	60.88 409	43.84 334	61.58 399	71.06 365	30.43 415	36.33 407	74.63 333	24.14 361	75.44 378	48.05 301	66.62 230	71.12 399
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
myMVS_eth3d		63.52 285	63.56 274	63.40 357	81.73 157	34.28 391	80.97 270	81.02 219	60.93 183	55.06 307	82.64 234	48.00 84	80.81 326	23.42 412	58.32 304	75.10 372

OurMVSNet-221017-0		52.39 363	48.73 367	63.35 358	65.21 391	38.42 378	68.54 373	64.95 389	38.19 392	39.57 398	71.43 365	13.23 411	79.92 339	37.16 347	40.32 397	71.72 395

MDA-MVSNet-bldmvs		51.56 367	47.75 374	63.00 359	71.60 345	47.32 286	69.70 368	72.12 353	43.81 376	27.65 428	63.38 396	21.97 376	75.96 375	27.30 400	32.19 416	65.70 411

mvs5depth		50.97 369	46.98 375	62.95 360	56.63 416	34.23 393	62.73 395	67.35 385	45.03 368	48.00 357	65.41 392	10.40 417	79.88 343	36.00 356	31.27 419	74.73 375

F-COLMAP		55.96 345	53.65 343	62.87 361	72.76 331	42.77 349	74.70 330	70.37 369	40.03 386	41.11 393	79.36 277	17.77 397	73.70 387	32.80 377	53.96 349	72.15 392

test0.0.03 1		62.54 295	62.44 279	62.86 362	72.28 339	29.51 415	82.93 220	78.78 268	59.18 217	53.07 328	82.41 240	36.91 244	77.39 364	37.45 346	58.96 298	81.66 293

CVMVSNet		60.85 308	60.44 298	62.07 363	75.00 301	32.73 401	79.54 295	73.49 343	36.98 398	56.28 300	83.74 212	29.28 325	69.53 402	46.48 312	63.23 267	83.94 257

ambc				62.06 364	53.98 420	29.38 416	35.08 433	79.65 249		41.37 389	59.96 409	6.27 432	82.15 314	35.34 362	38.22 402	74.65 376

Syy-MVS		61.51 304	61.35 289	62.00 365	81.73 157	30.09 410	80.97 270	81.02 219	60.93 183	55.06 307	82.64 234	35.09 269	80.81 326	16.40 429	58.32 304	75.10 372

PEN-MVS		58.35 330	57.15 320	61.94 366	67.55 382	34.39 390	77.01 313	78.35 280	51.87 316	47.72 359	76.73 313	33.91 285	73.75 386	34.03 370	47.17 378	77.68 346

MVS-HIRNet		49.01 374	44.71 378	61.92 367	76.06 282	46.61 295	63.23 391	54.90 410	24.77 423	33.56 415	36.60 432	21.28 379	75.88 377	29.49 387	62.54 276	63.26 416

LTVRE_ROB	45.45 19	52.73 359	49.74 363	61.69 368	69.78 366	34.99 387	44.52 422	67.60 384	43.11 380	43.79 378	74.03 337	18.54 393	81.45 319	28.39 395	57.94 313	68.62 403
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
WR-MVS_H		58.91 323	58.04 315	61.54 369	69.07 371	33.83 396	76.91 314	81.99 199	51.40 320	48.17 354	74.67 332	40.23 194	74.15 382	31.78 380	48.10 370	76.64 358

CP-MVSNet		58.54 329	57.57 318	61.46 370	68.50 375	33.96 395	76.90 315	78.60 275	51.67 319	47.83 358	76.60 315	34.99 272	72.79 391	35.45 360	47.58 374	77.64 348

PS-CasMVS		58.12 331	57.03 322	61.37 371	68.24 379	33.80 397	76.73 316	78.01 284	51.20 322	47.54 362	76.20 323	32.85 294	72.76 392	35.17 365	47.37 376	77.55 349

Anonymous20240521		51.65 366	48.42 368	61.34 372	56.43 417	39.65 372	73.57 337	73.47 346	36.64 400	36.59 406	63.98 395	10.75 416	72.25 395	35.35 361	49.01 367	72.11 393

CHOSEN 280x420		57.53 335	56.38 327	60.97 373	74.01 316	48.10 263	46.30 421	54.31 411	48.18 344	50.88 343	77.43 300	38.37 213	59.16 417	54.83 253	63.14 270	75.66 365

DTE-MVSNet		57.03 336	55.73 331	60.95 374	65.94 386	32.57 402	75.71 319	77.09 302	51.16 323	46.65 369	76.34 318	32.84 295	73.22 390	30.94 384	44.87 387	77.06 351

IterMVS-SCA-FT		59.12 318	58.81 312	60.08 375	70.68 358	45.07 319	80.42 281	74.25 331	43.54 378	50.02 346	73.73 341	31.97 305	56.74 421	51.06 282	53.60 353	78.42 337

COLMAP_ROB	43.60 20	50.90 370	48.05 371	59.47 376	67.81 381	40.57 369	71.25 360	62.72 399	36.49 401	36.19 408	73.51 346	13.48 410	73.92 385	20.71 418	50.26 365	63.92 414
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
testing3		59.97 311	60.19 301	59.32 377	77.60 252	30.01 412	81.75 251	81.79 205	53.54 302	50.34 345	79.94 268	48.99 77	76.91 367	17.19 427	50.59 364	71.03 400

testgi		54.25 351	52.57 350	59.29 378	62.76 404	21.65 433	72.21 352	70.47 368	53.25 306	41.94 386	77.33 301	14.28 409	77.95 358	29.18 389	51.72 362	78.28 340

TinyColmap		48.15 376	44.49 380	59.13 379	65.73 388	38.04 379	63.34 390	62.86 398	38.78 389	29.48 423	67.23 385	6.46 431	73.30 389	24.59 407	41.90 394	66.04 409

test20.03		55.22 347	54.07 340	58.68 380	63.14 403	25.00 424	77.69 311	74.78 327	52.64 309	43.43 380	72.39 358	26.21 343	74.76 381	29.31 388	47.05 380	76.28 362

EU-MVSNet		52.63 360	50.72 356	58.37 381	62.69 405	28.13 421	72.60 345	75.97 317	30.94 414	40.76 395	72.11 362	20.16 384	70.80 398	35.11 366	46.11 384	76.19 363

MIMVSNet1		50.35 371	47.81 372	57.96 382	61.53 407	27.80 422	67.40 376	74.06 335	43.25 379	33.31 419	65.38 393	16.03 406	71.34 396	21.80 415	47.55 375	74.75 374

pmmvs3		45.53 381	41.55 387	57.44 383	48.97 430	39.68 371	70.06 364	57.66 405	28.32 418	34.06 413	57.29 415	8.50 424	66.85 405	34.86 368	34.26 413	65.80 410

test_fmvs1		53.60 356	52.54 351	56.78 384	58.07 412	30.26 408	68.95 371	42.19 424	32.46 410	63.59 190	82.56 238	11.55 413	60.81 411	58.25 219	55.27 339	79.28 325

test_fmvs1_n		52.55 361	51.19 355	56.65 385	51.90 423	30.14 409	67.66 375	42.84 423	32.27 411	62.30 204	82.02 252	9.12 422	60.84 410	57.82 228	54.75 345	78.99 327

KD-MVS_self_test		49.24 373	46.85 376	56.44 386	54.32 418	22.87 427	57.39 408	73.36 347	44.36 373	37.98 404	59.30 412	18.97 390	71.17 397	33.48 372	42.44 392	75.26 369

PM-MVS		46.92 378	43.76 385	56.41 387	52.18 422	32.26 403	63.21 392	38.18 430	37.99 394	40.78 394	66.20 387	5.09 435	65.42 406	48.19 300	41.99 393	71.54 397

dmvs_testset		57.65 333	58.21 314	55.97 388	74.62 306	9.82 449	63.75 388	63.34 396	67.23 59	48.89 352	83.68 217	39.12 206	76.14 374	23.43 411	59.80 291	81.96 288

test_vis1_n		51.19 368	49.66 364	55.76 389	51.26 425	29.85 413	67.20 378	38.86 429	32.12 412	59.50 239	79.86 270	8.78 423	58.23 418	56.95 237	52.46 359	79.19 326

AllTest		47.32 377	44.66 379	55.32 390	65.08 393	37.50 383	62.96 393	54.25 412	35.45 405	33.42 416	72.82 351	9.98 418	59.33 414	24.13 408	43.84 389	69.13 401

TestCases				55.32 390	65.08 393	37.50 383		54.25 412	35.45 405	33.42 416	72.82 351	9.98 418	59.33 414	24.13 408	43.84 389	69.13 401

new-patchmatchnet		48.21 375	46.55 377	53.18 392	57.73 414	18.19 441	70.24 363	71.02 366	45.70 362	33.70 414	60.23 408	18.00 395	69.86 401	27.97 397	34.35 412	71.49 398

ITE_SJBPF				51.84 393	58.03 413	31.94 405		53.57 414	36.67 399	41.32 391	75.23 330	11.17 415	51.57 426	25.81 404	48.04 371	72.02 394

RPSCF		45.77 380	44.13 382	50.68 394	57.67 415	29.66 414	54.92 415	45.25 420	26.69 420	45.92 372	75.92 326	17.43 400	45.70 432	27.44 399	45.95 385	76.67 355

test_fmvs2		45.89 379	44.32 381	50.62 395	45.85 434	24.70 425	58.87 407	37.84 432	25.22 421	52.46 331	74.56 334	7.07 426	54.69 422	49.28 292	47.70 373	72.48 390

kuosan		50.20 372	50.09 359	50.52 396	73.09 326	29.09 418	65.25 381	74.89 326	48.27 342	41.34 390	60.85 407	43.45 153	67.48 404	18.59 425	25.07 427	55.01 421

ttmdpeth		40.58 387	37.50 391	49.85 397	49.40 428	22.71 428	56.65 410	46.78 416	28.35 417	40.29 397	69.42 376	5.35 434	61.86 409	20.16 420	21.06 433	64.96 412

MVStest1		38.35 389	34.53 395	49.82 398	51.43 424	30.41 407	50.39 417	55.25 408	17.56 431	26.45 429	65.85 390	11.72 412	57.00 420	14.79 430	17.31 437	62.05 417

ANet_high		34.39 395	29.59 401	48.78 399	30.34 444	22.28 429	55.53 412	63.79 395	38.11 393	15.47 436	36.56 433	6.94 427	59.98 413	13.93 432	5.64 447	64.08 413

TDRefinement		40.91 386	38.37 390	48.55 400	50.45 427	33.03 400	58.98 406	50.97 415	28.50 416	29.89 422	67.39 384	6.21 433	54.51 423	17.67 426	35.25 409	58.11 418

DSMNet-mixed		38.35 389	35.36 394	47.33 401	48.11 432	14.91 445	37.87 431	36.60 433	19.18 428	34.37 412	59.56 411	15.53 407	53.01 425	20.14 421	46.89 381	74.07 379

mvsany_test1		43.38 383	42.57 386	45.82 402	50.96 426	26.10 423	55.80 411	27.74 442	27.15 419	47.41 364	74.39 335	18.67 392	44.95 433	44.66 321	36.31 406	66.40 408

N_pmnet		41.25 385	39.77 388	45.66 403	68.50 375	0.82 455	72.51 347	0.38 454	35.61 404	35.26 411	61.51 404	20.07 385	67.74 403	23.51 410	40.63 395	68.42 404

test_vis1_rt		40.29 388	38.64 389	45.25 404	48.91 431	30.09 410	59.44 404	27.07 443	24.52 424	38.48 403	51.67 424	6.71 429	49.44 427	44.33 323	46.59 383	56.23 419

test_fmvs3		37.95 391	35.75 393	44.55 405	35.50 440	18.92 437	48.32 418	34.00 437	18.36 430	41.31 392	61.58 401	2.29 442	48.06 431	42.72 333	37.71 403	66.66 407

EGC-MVSNET		33.75 396	30.42 400	43.75 406	64.94 395	36.21 386	60.47 403	40.70 427	0.02 448	0.10 449	53.79 420	7.39 425	60.26 412	11.09 435	35.23 410	34.79 434

dongtai		43.51 382	44.07 383	41.82 407	63.75 400	21.90 431	63.80 387	72.05 354	39.59 387	33.35 418	54.54 418	41.04 184	57.30 419	10.75 436	17.77 436	46.26 430

LCM-MVSNet		28.07 399	23.85 407	40.71 408	27.46 449	18.93 436	30.82 437	46.19 417	12.76 436	16.40 434	34.70 435	1.90 445	48.69 430	20.25 419	24.22 428	54.51 422

FPMVS		35.40 393	33.67 397	40.57 409	46.34 433	28.74 420	41.05 427	57.05 407	20.37 427	22.27 432	53.38 421	6.87 428	44.94 434	8.62 437	47.11 379	48.01 428

WB-MVS		37.41 392	36.37 392	40.54 410	54.23 419	10.43 448	65.29 380	43.75 421	34.86 408	27.81 427	54.63 417	24.94 354	63.21 407	6.81 443	15.00 438	47.98 429

new_pmnet		33.56 397	31.89 399	38.59 411	49.01 429	20.42 434	51.01 416	37.92 431	20.58 425	23.45 431	46.79 426	6.66 430	49.28 429	20.00 422	31.57 418	46.09 431

mamv4		42.60 384	44.05 384	38.26 412	59.21 411	38.00 380	44.14 424	39.03 428	25.03 422	40.61 396	68.39 380	37.01 241	24.28 446	46.62 311	36.43 405	52.50 424

SSC-MVS		35.20 394	34.30 396	37.90 413	52.58 421	8.65 451	61.86 396	41.64 425	31.81 413	25.54 430	52.94 423	23.39 366	59.28 416	6.10 444	12.86 439	45.78 432

PMMVS2		26.71 403	22.98 408	37.87 414	36.89 438	8.51 452	42.51 426	29.32 441	19.09 429	13.01 438	37.54 429	2.23 443	53.11 424	14.54 431	11.71 440	51.99 426

Gipuma		27.47 401	24.26 406	37.12 415	60.55 410	29.17 417	11.68 442	60.00 401	14.18 434	10.52 443	15.12 444	2.20 444	63.01 408	8.39 438	35.65 407	19.18 440
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
LF4IMVS		33.04 398	32.55 398	34.52 416	40.96 435	22.03 430	44.45 423	35.62 434	20.42 426	28.12 426	62.35 400	5.03 436	31.88 445	21.61 417	34.42 411	49.63 427

mvsany_test3		28.00 400	25.98 402	34.05 417	28.97 445	15.31 443	34.54 434	18.17 448	16.24 432	29.30 424	53.37 422	2.79 440	33.38 444	30.01 386	20.41 434	53.45 423

test_f		27.12 402	24.85 403	33.93 418	26.17 450	15.25 444	30.24 438	22.38 447	12.53 437	28.23 425	49.43 425	2.59 441	34.34 443	25.12 406	26.99 424	52.20 425

test_method		24.09 407	21.07 411	33.16 419	27.67 448	8.35 453	26.63 439	35.11 436	3.40 445	14.35 437	36.98 431	3.46 439	35.31 440	19.08 424	22.95 429	55.81 420

PMVS	19.57 22	25.07 405	22.43 410	32.99 420	23.12 451	22.98 426	40.98 428	35.19 435	15.99 433	11.95 442	35.87 434	1.47 448	49.29 428	5.41 446	31.90 417	26.70 439
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
APD_test1		26.46 404	24.41 405	32.62 421	37.58 437	21.74 432	40.50 429	30.39 439	11.45 438	16.33 435	43.76 427	1.63 447	41.62 435	11.24 434	26.82 425	34.51 435

test_vis3_rt		24.79 406	22.95 409	30.31 422	28.59 446	18.92 437	37.43 432	17.27 450	12.90 435	21.28 433	29.92 439	1.02 449	36.35 438	28.28 396	29.82 423	35.65 433

MVE	16.60 23	17.34 413	13.39 416	29.16 423	28.43 447	19.72 435	13.73 441	23.63 446	7.23 444	7.96 444	21.41 440	0.80 450	36.08 439	6.97 441	10.39 441	31.69 436
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
testf1		21.11 408	19.08 412	27.18 424	30.56 442	18.28 439	33.43 435	24.48 444	8.02 442	12.02 440	33.50 436	0.75 451	35.09 441	7.68 439	21.32 430	28.17 437

APD_test2		21.11 408	19.08 412	27.18 424	30.56 442	18.28 439	33.43 435	24.48 444	8.02 442	12.02 440	33.50 436	0.75 451	35.09 441	7.68 439	21.32 430	28.17 437

E-PMN		19.16 410	18.40 414	21.44 426	36.19 439	13.63 446	47.59 419	30.89 438	10.73 439	5.91 446	16.59 442	3.66 438	39.77 436	5.95 445	8.14 442	10.92 442

EMVS		18.42 411	17.66 415	20.71 427	34.13 441	12.64 447	46.94 420	29.94 440	10.46 441	5.58 447	14.93 445	4.23 437	38.83 437	5.24 447	7.51 444	10.67 443

DeepMVS_CX				13.10 428	21.34 452	8.99 450		10.02 452	10.59 440	7.53 445	30.55 438	1.82 446	14.55 447	6.83 442	7.52 443	15.75 441

wuyk23d		9.11 415	8.77 419	10.15 429	40.18 436	16.76 442	20.28 440	1.01 453	2.58 446	2.66 448	0.98 448	0.23 453	12.49 448	4.08 448	6.90 445	1.19 445

tmp_tt		9.44 414	10.68 417	5.73 430	2.49 453	4.21 454	10.48 443	18.04 449	0.34 447	12.59 439	20.49 441	11.39 414	7.03 449	13.84 433	6.46 446	5.95 444

testmvs		6.14 417	8.18 420	0.01 431	0.01 454	0.00 457	73.40 340	0.00 455	0.00 449	0.02 450	0.15 449	0.00 454	0.00 450	0.02 449	0.00 448	0.02 446

test123		6.01 418	8.01 421	0.01 431	0.00 455	0.01 456	71.93 357	0.00 455	0.00 449	0.02 450	0.11 450	0.00 454	0.00 450	0.02 449	0.00 448	0.02 446

mmdepth		0.00 420	0.00 423	0.00 433	0.00 455	0.00 457	0.00 444	0.00 455	0.00 449	0.00 452	0.00 451	0.00 454	0.00 450	0.00 451	0.00 448	0.00 448

monomultidepth		0.00 420	0.00 423	0.00 433	0.00 455	0.00 457	0.00 444	0.00 455	0.00 449	0.00 452	0.00 451	0.00 454	0.00 450	0.00 451	0.00 448	0.00 448

test_blank		0.00 420	0.00 423	0.00 433	0.00 455	0.00 457	0.00 444	0.00 455	0.00 449	0.00 452	0.00 451	0.00 454	0.00 450	0.00 451	0.00 448	0.00 448

uanet_test		0.00 420	0.00 423	0.00 433	0.00 455	0.00 457	0.00 444	0.00 455	0.00 449	0.00 452	0.00 451	0.00 454	0.00 450	0.00 451	0.00 448	0.00 448

DCPMVS		0.00 420	0.00 423	0.00 433	0.00 455	0.00 457	0.00 444	0.00 455	0.00 449	0.00 452	0.00 451	0.00 454	0.00 450	0.00 451	0.00 448	0.00 448

cdsmvs_eth3d_5k		18.33 412	24.44 404	0.00 433	0.00 455	0.00 457	0.00 444	89.40 27	0.00 449	0.00 452	92.02 54	38.55 211	0.00 450	0.00 451	0.00 448	0.00 448

pcd_1.5k_mvsjas		3.15 419	4.20 422	0.00 433	0.00 455	0.00 457	0.00 444	0.00 455	0.00 449	0.00 452	0.00 451	37.77 218	0.00 450	0.00 451	0.00 448	0.00 448

sosnet-low-res		0.00 420	0.00 423	0.00 433	0.00 455	0.00 457	0.00 444	0.00 455	0.00 449	0.00 452	0.00 451	0.00 454	0.00 450	0.00 451	0.00 448	0.00 448

sosnet		0.00 420	0.00 423	0.00 433	0.00 455	0.00 457	0.00 444	0.00 455	0.00 449	0.00 452	0.00 451	0.00 454	0.00 450	0.00 451	0.00 448	0.00 448

uncertanet		0.00 420	0.00 423	0.00 433	0.00 455	0.00 457	0.00 444	0.00 455	0.00 449	0.00 452	0.00 451	0.00 454	0.00 450	0.00 451	0.00 448	0.00 448

Regformer		0.00 420	0.00 423	0.00 433	0.00 455	0.00 457	0.00 444	0.00 455	0.00 449	0.00 452	0.00 451	0.00 454	0.00 450	0.00 451	0.00 448	0.00 448

ab-mvs-re		7.68 416	10.24 418	0.00 433	0.00 455	0.00 457	0.00 444	0.00 455	0.00 449	0.00 452	92.12 50	0.00 454	0.00 450	0.00 451	0.00 448	0.00 448

uanet		0.00 420	0.00 423	0.00 433	0.00 455	0.00 457	0.00 444	0.00 455	0.00 449	0.00 452	0.00 451	0.00 454	0.00 450	0.00 451	0.00 448	0.00 448

WAC-MVS						34.28 391								22.56 413

FOURS1					83.24 113	49.90 202	84.98 147	78.76 269	47.71 346	73.42 69

PC_three_1452									66.58 70	87.27 2	93.70 13	66.82 4	94.95 17	89.74 4	91.98 4	93.98 5

test_one_0601					89.39 22	57.29 22		88.09 59	57.21 259	82.06 14	93.39 22	54.94 36

eth-test2					0.00 455

eth-test					0.00 455

ZD-MVS					89.55 14	53.46 110		84.38 149	57.02 261	73.97 63	91.03 75	44.57 137	91.17 81	75.41 83	81.78 71

RE-MVS-def			66.66 224		80.96 184	48.14 261	81.54 259	76.98 303	46.42 356	62.75 199	89.42 119	29.28 325		60.52 198	72.06 184	83.19 271

IU-MVS					89.48 17	57.49 17		91.38 9	66.22 78	88.26 1				82.83 28	87.60 18	92.44 32

test_241102_TWO								88.76 44	57.50 253	83.60 6	94.09 4	56.14 27	96.37 6	82.28 32	87.43 20	92.55 30

test_241102_ONE					89.48 17	56.89 29		88.94 35	57.53 251	84.61 4	93.29 26	58.81 13	96.45 1

9.14			78.19 28		85.67 62		88.32 52	88.84 41	59.89 197	74.58 58	92.62 41	46.80 96	92.66 42	81.40 43	85.62 41

save fliter					85.35 69	56.34 41	89.31 40	81.46 211	61.55 168

test_0728_THIRD									58.00 239	81.91 15	93.64 15	56.54 23	96.44 2	81.64 38	86.86 26	92.23 37

test0726					89.40 20	57.45 19	92.32 7	88.63 48	57.71 247	83.14 9	93.96 7	55.17 31

GSMVS																88.13 166

test_part2					89.33 23	55.48 54				82.27 12

sam_mvs1												38.86 209				88.13 166

sam_mvs												35.99 262

MTGPA								81.31 214

test_post1							70.84 362				14.72 446	34.33 282	83.86 298	48.80 295

test_post											16.22 443	37.52 227	84.72 290

patchmatchnet-post											59.74 410	38.41 212	79.91 341

MTMP							87.27 79	15.34 451

gm-plane-assit					83.24 113	54.21 96			70.91 24		88.23 147		95.25 14	66.37 144

test9_res														78.72 57	85.44 43	91.39 67

TEST9					85.68 60	55.42 56	87.59 68	84.00 161	57.72 246	72.99 75	90.98 77	44.87 131	88.58 167

test_8					85.72 59	55.31 61	87.60 67	83.88 164	57.84 244	72.84 79	90.99 76	44.99 127	88.34 180

agg_prior2														75.65 78	85.11 47	91.01 80

agg_prior					85.64 63	54.92 76		83.61 171		72.53 84			88.10 191

test_prior4						56.39 40	87.15 83

test_prior2							89.04 44		61.88 163	73.55 67	91.46 72	48.01 82		74.73 87	85.46 42

旧先验2							81.73 252		45.53 364	74.66 55			70.48 400	58.31 218

新几何2							81.61 257

旧先验1					81.57 169	47.48 281		71.83 355			88.66 134	36.94 243			78.34 108	88.67 148

无先验							85.19 135	78.00 285	49.08 335				85.13 284	52.78 270		87.45 182

原ACMM2							83.77 192

test222					79.36 213	50.97 174	77.99 309	67.84 382	42.54 382	62.84 198	86.53 178	30.26 319			76.91 121	85.23 229

testdata2													77.81 361	45.64 317

segment_acmp												44.97 129

testdata1							77.55 312		64.14 115

plane_prior7					77.95 246	48.46 248

plane_prior6					78.42 240	49.39 220						36.04 260

plane_prior5								82.59 188					88.30 184	65.46 155	72.34 181	84.49 241

plane_prior4											83.28 223

plane_prior3						48.95 229			64.01 119	62.15 207

plane_prior2							85.76 111		63.60 129

plane_prior1					78.31 242

plane_prior						49.57 207	87.43 71		64.57 105						72.84 175

n2								0.00 455

nn								0.00 455

door-mid								41.31 426

test11								84.25 153

door								43.27 422

HQP5-MVS						51.56 163

HQP-NCC					79.02 223		88.00 56		65.45 92	64.48 173

ACMP_Plane					79.02 223		88.00 56		65.45 92	64.48 173

BP-MVS														66.70 141

HQP4-MVS										64.47 176			88.61 165			84.91 237

HQP3-MVS								83.68 167							73.12 171

HQP2-MVS												37.35 230

NP-MVS					78.76 228	50.43 185					85.12 193

MDTV_nov1_ep13_2view						43.62 336	71.13 361		54.95 291	59.29 245		36.76 246		46.33 314		87.32 185

MDTV_nov1_ep13			61.56 286		81.68 161	55.12 69	72.41 349	78.18 282	59.19 215	58.85 254	69.29 377	34.69 276	86.16 257	36.76 355	62.96 272

ACMMP++_ref															63.20 268

ACMMP++															59.38 295

Test By Simon												39.38 203

High-resolution multi-view benchmark