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.

test_0728_SECOND				87.71 32	95.34 1	71.43 58	93.49 9	94.23 3					97.49 4	89.08 15	96.41 12	94.21 49

SED-MVS		90.08 2	90.85 2	87.77 26	95.30 2	70.98 66	93.57 7	94.06 10	77.24 55	93.10 1	95.72 8	82.99 1	97.44 7	89.07 17	96.63 4	94.88 15

IU-MVS					95.30 2	71.25 59		92.95 55	66.81 272	92.39 6				88.94 20	96.63 4	94.85 20

test_241102_ONE					95.30 2	70.98 66		94.06 10	77.17 58	93.10 1	95.39 14	82.99 1	97.27 12

DVP-MVS		89.60 3	90.35 3	87.33 40	95.27 5	71.25 59	93.49 9	92.73 64	77.33 52	92.12 9	95.78 4	80.98 9	97.40 9	89.08 15	96.41 12	93.33 94
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
test0726					95.27 5	71.25 59	93.60 6	94.11 6	77.33 52	92.81 3	95.79 3	80.98 9

test_one_0601					95.07 7	71.46 57		94.14 5	78.27 37	92.05 11	95.74 6	80.83 11

test_part2					95.06 8	72.65 32				91.80 13

HPM-MVS++		89.02 9	89.15 9	88.63 5	95.01 9	76.03 1	92.38 27	92.85 59	80.26 11	87.78 36	94.27 38	75.89 19	96.81 23	87.45 36	96.44 9	93.05 109

FOURS1					95.00 10	72.39 39	95.06 1	93.84 15	74.49 125	91.30 15

DPE-MVS		89.48 5	89.98 4	88.01 16	94.80 11	72.69 31	91.59 43	94.10 8	75.90 92	92.29 7	95.66 10	81.67 6	97.38 11	87.44 37	96.34 15	93.95 61
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
CNVR-MVS		88.93 10	89.13 10	88.33 8	94.77 12	73.82 8	90.51 62	93.00 46	80.90 7	88.06 31	94.06 49	76.43 16	96.84 21	88.48 28	95.99 18	94.34 44

ACMMPR		87.44 25	87.23 31	88.08 15	94.64 13	73.59 12	93.04 12	93.20 34	76.78 70	84.66 76	94.52 24	68.81 92	96.65 30	84.53 58	94.90 41	94.00 58

region2R		87.42 27	87.20 32	88.09 14	94.63 14	73.55 13	93.03 14	93.12 40	76.73 73	84.45 81	94.52 24	69.09 86	96.70 27	84.37 60	94.83 45	94.03 57

OPU-MVS				89.06 3	94.62 15	75.42 4	93.57 7				94.02 51	82.45 3	96.87 20	83.77 68	96.48 8	94.88 15

HFP-MVS		87.58 22	87.47 26	87.94 19	94.58 16	73.54 15	93.04 12	93.24 33	76.78 70	84.91 69	94.44 31	70.78 68	96.61 32	84.53 58	94.89 42	93.66 75

MCST-MVS		87.37 29	87.25 30	87.73 28	94.53 17	72.46 38	89.82 79	93.82 16	73.07 163	84.86 72	92.89 81	76.22 17	96.33 41	84.89 52	95.13 36	94.40 41

APDe-MVS		89.15 7	89.63 6	87.73 28	94.49 18	71.69 52	93.83 4	93.96 13	75.70 96	91.06 16	96.03 1	76.84 14	97.03 17	89.09 14	95.65 27	94.47 38
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
DP-MVS Recon		83.11 104	82.09 112	86.15 63	94.44 19	70.92 71	88.79 120	92.20 89	70.53 208	79.17 151	91.03 132	64.12 137	96.03 50	68.39 220	90.14 110	91.50 160

XVS		87.18 32	86.91 38	88.00 17	94.42 20	73.33 19	92.78 18	92.99 49	79.14 22	83.67 98	94.17 43	67.45 105	96.60 33	83.06 73	94.50 51	94.07 55

X-MVStestdata		80.37 158	77.83 194	88.00 17	94.42 20	73.33 19	92.78 18	92.99 49	79.14 22	83.67 98	12.47 428	67.45 105	96.60 33	83.06 73	94.50 51	94.07 55

mPP-MVS		86.67 41	86.32 44	87.72 30	94.41 22	73.55 13	92.74 20	92.22 88	76.87 67	82.81 110	94.25 40	66.44 115	96.24 44	82.88 78	94.28 58	93.38 91

NCCC		88.06 14	88.01 18	88.24 11	94.41 22	73.62 11	91.22 54	92.83 60	81.50 5	85.79 59	93.47 67	73.02 41	97.00 18	84.90 50	94.94 40	94.10 53

ZNCC-MVS		87.94 18	87.85 19	88.20 12	94.39 24	73.33 19	93.03 14	93.81 17	76.81 68	85.24 64	94.32 36	71.76 53	96.93 19	85.53 47	95.79 22	94.32 45

ZD-MVS					94.38 25	72.22 44		92.67 67	70.98 198	87.75 38	94.07 48	74.01 32	96.70 27	84.66 56	94.84 44

MP-MVS		87.71 19	87.64 21	87.93 21	94.36 26	73.88 6	92.71 22	92.65 70	77.57 44	83.84 94	94.40 33	72.24 47	96.28 43	85.65 45	95.30 35	93.62 82
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
DVP-MVS++		90.23 1	91.01 1	87.89 24	94.34 27	71.25 59	95.06 1	94.23 3	78.38 34	92.78 4	95.74 6	82.45 3	97.49 4	89.42 12	96.68 2	94.95 11

MSC_two_6792asdad				89.16 1	94.34 27	75.53 2		92.99 49					97.53 2	89.67 9	96.44 9	94.41 39

No_MVS				89.16 1	94.34 27	75.53 2		92.99 49					97.53 2	89.67 9	96.44 9	94.41 39

MSP-MVS		89.51 4	89.91 5	88.30 10	94.28 30	73.46 17	92.90 16	94.11 6	80.27 10	91.35 14	94.16 44	78.35 13	96.77 24	89.59 11	94.22 60	94.67 28
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
SMA-MVS		89.08 8	89.23 7	88.61 6	94.25 31	73.73 9	92.40 24	93.63 21	74.77 119	92.29 7	95.97 2	74.28 29	97.24 13	88.58 25	96.91 1	94.87 17
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
APD-MVS		87.44 25	87.52 25	87.19 42	94.24 32	72.39 39	91.86 40	92.83 60	73.01 165	88.58 25	94.52 24	73.36 34	96.49 38	84.26 61	95.01 37	92.70 119
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
PGM-MVS		86.68 40	86.27 46	87.90 22	94.22 33	73.38 18	90.22 73	93.04 41	75.53 98	83.86 93	94.42 32	67.87 102	96.64 31	82.70 83	94.57 50	93.66 75

CP-MVS		87.11 33	86.92 37	87.68 34	94.20 34	73.86 7	93.98 3	92.82 63	76.62 76	83.68 97	94.46 28	67.93 100	95.95 57	84.20 64	94.39 55	93.23 97

MTAPA		87.23 31	87.00 33	87.90 22	94.18 35	74.25 5	86.58 197	92.02 93	79.45 20	85.88 57	94.80 20	68.07 98	96.21 45	86.69 40	95.34 32	93.23 97

GST-MVS		87.42 27	87.26 29	87.89 24	94.12 36	72.97 24	92.39 26	93.43 28	76.89 66	84.68 73	93.99 55	70.67 70	96.82 22	84.18 65	95.01 37	93.90 64

SR-MVS		86.73 38	86.67 40	86.91 49	94.11 37	72.11 47	92.37 28	92.56 75	74.50 124	86.84 52	94.65 23	67.31 107	95.77 59	84.80 54	92.85 72	92.84 117

114514_t		80.68 148	79.51 154	84.20 123	94.09 38	67.27 157	89.64 87	91.11 128	58.75 365	74.08 269	90.72 138	58.10 210	95.04 92	69.70 205	89.42 122	90.30 205

HPM-MVS		87.11 33	86.98 35	87.50 38	93.88 39	72.16 45	92.19 33	93.33 31	76.07 89	83.81 95	93.95 58	69.77 80	96.01 53	85.15 48	94.66 47	94.32 45
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
save fliter					93.80 40	72.35 42	90.47 66	91.17 125	74.31 130

ACMMP_NAP		88.05 16	88.08 17	87.94 19	93.70 41	73.05 22	90.86 57	93.59 23	76.27 86	88.14 29	95.09 17	71.06 65	96.67 29	87.67 33	96.37 14	94.09 54

HPM-MVS_fast		85.35 66	84.95 72	86.57 56	93.69 42	70.58 78	92.15 35	91.62 111	73.89 141	82.67 112	94.09 47	62.60 154	95.54 65	80.93 96	92.93 71	93.57 84

TSAR-MVS + MP.		88.02 17	88.11 16	87.72 30	93.68 43	72.13 46	91.41 50	92.35 82	74.62 123	88.90 23	93.85 59	75.75 20	96.00 54	87.80 32	94.63 48	95.04 9
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
MP-MVS-pluss		87.67 21	87.72 20	87.54 36	93.64 44	72.04 48	89.80 81	93.50 25	75.17 109	86.34 55	95.29 15	70.86 67	96.00 54	88.78 23	96.04 16	94.58 33
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
ACMMP		85.89 56	85.39 63	87.38 39	93.59 45	72.63 33	92.74 20	93.18 39	76.78 70	80.73 134	93.82 60	64.33 135	96.29 42	82.67 84	90.69 101	93.23 97
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
DeepC-MVS_fast	79.65 3	86.91 36	86.62 41	87.76 27	93.52 46	72.37 41	91.26 51	93.04 41	76.62 76	84.22 85	93.36 70	71.44 59	96.76 25	80.82 98	95.33 33	94.16 50
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
CDPH-MVS		85.76 58	85.29 68	87.17 43	93.49 47	71.08 64	88.58 130	92.42 80	68.32 260	84.61 78	93.48 65	72.32 46	96.15 48	79.00 110	95.43 30	94.28 47

DP-MVS		76.78 239	74.57 256	83.42 157	93.29 48	69.46 97	88.55 131	83.70 293	63.98 316	70.20 312	88.89 179	54.01 246	94.80 102	46.66 379	81.88 234	86.01 328

CPTT-MVS		83.73 86	83.33 92	84.92 96	93.28 49	70.86 72	92.09 36	90.38 147	68.75 252	79.57 146	92.83 83	60.60 196	93.04 184	80.92 97	91.56 91	90.86 181

reproduce-ours		87.47 23	87.61 22	87.07 45	93.27 50	71.60 53	91.56 46	93.19 35	74.98 112	88.96 21	95.54 12	71.20 63	96.54 36	86.28 41	93.49 65	93.06 107

our_new_method		87.47 23	87.61 22	87.07 45	93.27 50	71.60 53	91.56 46	93.19 35	74.98 112	88.96 21	95.54 12	71.20 63	96.54 36	86.28 41	93.49 65	93.06 107

TEST9					93.26 52	72.96 25	88.75 122	91.89 101	68.44 258	85.00 67	93.10 74	74.36 28	95.41 73

train_agg		86.43 43	86.20 47	87.13 44	93.26 52	72.96 25	88.75 122	91.89 101	68.69 253	85.00 67	93.10 74	74.43 26	95.41 73	84.97 49	95.71 25	93.02 111

test_8					93.13 54	72.57 35	88.68 127	91.84 105	68.69 253	84.87 71	93.10 74	74.43 26	95.16 83

新几何1				83.42 157	93.13 54	70.71 74		85.48 271	57.43 375	81.80 120	91.98 98	63.28 143	92.27 211	64.60 251	92.99 70	87.27 301

reproduce_model		87.28 30	87.39 28	86.95 48	93.10 56	71.24 63	91.60 42	93.19 35	74.69 120	88.80 24	95.61 11	70.29 74	96.44 39	86.20 43	93.08 69	93.16 102

AdaColmap		80.58 153	79.42 156	84.06 134	93.09 57	68.91 108	89.36 100	88.97 200	69.27 236	75.70 229	89.69 156	57.20 221	95.77 59	63.06 261	88.41 139	87.50 296

SR-MVS-dyc-post		85.77 57	85.61 60	86.23 59	93.06 58	70.63 76	91.88 38	92.27 84	73.53 151	85.69 60	94.45 29	65.00 133	95.56 63	82.75 79	91.87 84	92.50 128

RE-MVS-def			85.48 62		93.06 58	70.63 76	91.88 38	92.27 84	73.53 151	85.69 60	94.45 29	63.87 139		82.75 79	91.87 84	92.50 128

原ACMM1				84.35 114	93.01 60	68.79 110		92.44 77	63.96 317	81.09 130	91.57 112	66.06 121	95.45 68	67.19 230	94.82 46	88.81 264

CSCG		86.41 45	86.19 48	87.07 45	92.91 61	72.48 37	90.81 58	93.56 24	73.95 138	83.16 104	91.07 129	75.94 18	95.19 82	79.94 107	94.38 56	93.55 86

agg_prior					92.85 62	71.94 50		91.78 108		84.41 82			94.93 94

9.14			88.26 15		92.84 63		91.52 48	94.75 1	73.93 140	88.57 26	94.67 22	75.57 22	95.79 58	86.77 39	95.76 23

SF-MVS		88.46 12	88.74 12	87.64 35	92.78 64	71.95 49	92.40 24	94.74 2	75.71 94	89.16 20	95.10 16	75.65 21	96.19 46	87.07 38	96.01 17	94.79 22

MG-MVS		83.41 96	83.45 88	83.28 162	92.74 65	62.28 259	88.17 145	89.50 177	75.22 104	81.49 124	92.74 89	66.75 110	95.11 87	72.85 175	91.58 90	92.45 131

APD-MVS_3200maxsize		85.97 52	85.88 55	86.22 60	92.69 66	69.53 92	91.93 37	92.99 49	73.54 150	85.94 56	94.51 27	65.80 125	95.61 62	83.04 75	92.51 76	93.53 88

test12				86.80 52	92.63 67	70.70 75		91.79 107		82.71 111		71.67 56	96.16 47		94.50 51	93.54 87

test_prior				86.33 57	92.61 68	69.59 91		92.97 54					95.48 67			93.91 62

SD-MVS		88.06 14	88.50 14	86.71 54	92.60 69	72.71 29	91.81 41	93.19 35	77.87 38	90.32 17	94.00 53	74.83 23	93.78 141	87.63 34	94.27 59	93.65 79
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
PAPM_NR		83.02 105	82.41 105	84.82 99	92.47 70	66.37 172	87.93 154	91.80 106	73.82 142	77.32 190	90.66 139	67.90 101	94.90 97	70.37 197	89.48 121	93.19 101

DeepPCF-MVS	80.84 1	88.10 13	88.56 13	86.73 53	92.24 71	69.03 103	89.57 90	93.39 30	77.53 48	89.79 19	94.12 46	78.98 12	96.58 35	85.66 44	95.72 24	94.58 33

SteuartSystems-ACMMP		88.72 11	88.86 11	88.32 9	92.14 72	72.96 25	93.73 5	93.67 20	80.19 12	88.10 30	94.80 20	73.76 33	97.11 15	87.51 35	95.82 21	94.90 14
Skip Steuart: Steuart Systems R&D Blog.
UA-Net		85.08 70	84.96 71	85.45 78	92.07 73	68.07 135	89.78 82	90.86 135	82.48 2	84.60 79	93.20 73	69.35 83	95.22 81	71.39 187	90.88 99	93.07 106

旧先验1					91.96 74	65.79 185		86.37 259			93.08 78	69.31 85			92.74 73	88.74 269

MSLP-MVS++		85.43 64	85.76 58	84.45 110	91.93 75	70.24 79	90.71 59	92.86 58	77.46 50	84.22 85	92.81 85	67.16 109	92.94 186	80.36 102	94.35 57	90.16 209

LFMVS		81.82 122	81.23 123	83.57 154	91.89 76	63.43 239	89.84 78	81.85 324	77.04 63	83.21 102	93.10 74	52.26 261	93.43 160	71.98 182	89.95 115	93.85 66

PLC	70.83 11	78.05 212	76.37 232	83.08 174	91.88 77	67.80 141	88.19 144	89.46 178	64.33 309	69.87 321	88.38 194	53.66 248	93.58 149	58.86 302	82.73 223	87.86 287
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
dcpmvs_2		85.63 60	86.15 50	84.06 134	91.71 78	64.94 205	86.47 200	91.87 103	73.63 146	86.60 54	93.02 79	76.57 15	91.87 226	83.36 70	92.15 80	95.35 3

MVS_111021_HR		85.14 68	84.75 73	86.32 58	91.65 79	72.70 30	85.98 213	90.33 151	76.11 88	82.08 115	91.61 111	71.36 61	94.17 124	81.02 95	92.58 75	92.08 147

test222					91.50 80	68.26 130	84.16 260	83.20 305	54.63 386	79.74 143	91.63 109	58.97 205			91.42 92	86.77 314

TSAR-MVS + GP.		85.71 59	85.33 65	86.84 50	91.34 81	72.50 36	89.07 112	87.28 239	76.41 79	85.80 58	90.22 148	74.15 31	95.37 78	81.82 88	91.88 83	92.65 123

MAR-MVS		81.84 121	80.70 131	85.27 82	91.32 82	71.53 56	89.82 79	90.92 131	69.77 227	78.50 164	86.21 257	62.36 160	94.52 111	65.36 244	92.05 82	89.77 233
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
balanced_conf03		86.78 37	86.99 34	86.15 63	91.24 83	67.61 146	90.51 62	92.90 56	77.26 54	87.44 44	91.63 109	71.27 62	96.06 49	85.62 46	95.01 37	94.78 23

DeepC-MVS	79.81 2	87.08 35	86.88 39	87.69 33	91.16 84	72.32 43	90.31 71	93.94 14	77.12 60	82.82 109	94.23 41	72.13 49	97.09 16	84.83 53	95.37 31	93.65 79
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
MVSMamba_PlusPlus		85.99 50	85.96 54	86.05 66	91.09 85	67.64 145	89.63 88	92.65 70	72.89 168	84.64 77	91.71 105	71.85 51	96.03 50	84.77 55	94.45 54	94.49 37

3Dnovator+	77.84 4	85.48 62	84.47 78	88.51 7	91.08 86	73.49 16	93.18 11	93.78 18	80.79 8	76.66 207	93.37 69	60.40 200	96.75 26	77.20 129	93.73 64	95.29 5

Anonymous202405211		78.25 204	77.01 214	81.99 205	91.03 87	60.67 279	84.77 242	83.90 291	70.65 207	80.00 141	91.20 124	41.08 366	91.43 246	65.21 245	85.26 181	93.85 66

SPE-MVS-test		86.29 47	86.48 42	85.71 73	91.02 88	67.21 161	92.36 29	93.78 18	78.97 29	83.51 101	91.20 124	70.65 71	95.15 84	81.96 87	94.89 42	94.77 24

VDD-MVS		83.01 106	82.36 107	84.96 93	91.02 88	66.40 171	88.91 116	88.11 218	77.57 44	84.39 83	93.29 71	52.19 262	93.91 135	77.05 132	88.70 134	94.57 35

API-MVS		81.99 119	81.23 123	84.26 122	90.94 90	70.18 85	91.10 55	89.32 182	71.51 187	78.66 160	88.28 197	65.26 128	95.10 90	64.74 250	91.23 95	87.51 295

testdata				79.97 251	90.90 91	64.21 221		84.71 278	59.27 359	85.40 62	92.91 80	62.02 167	89.08 292	68.95 213	91.37 93	86.63 318

PHI-MVS		86.43 43	86.17 49	87.24 41	90.88 92	70.96 68	92.27 32	94.07 9	72.45 170	85.22 65	91.90 100	69.47 82	96.42 40	83.28 72	95.94 19	94.35 43

VNet		82.21 114	82.41 105	81.62 211	90.82 93	60.93 274	84.47 250	89.78 167	76.36 84	84.07 89	91.88 101	64.71 134	90.26 269	70.68 194	88.89 128	93.66 75

PVSNet_Blended_VisFu		82.62 109	81.83 118	84.96 93	90.80 94	69.76 90	88.74 124	91.70 110	69.39 233	78.96 153	88.46 192	65.47 127	94.87 100	74.42 158	88.57 135	90.24 207

MM		89.16 6	89.23 7	88.97 4	90.79 95	73.65 10	92.66 23	91.17 125	86.57 1	87.39 45	94.97 19	71.70 55	97.68 1	92.19 1	95.63 28	95.57 1

CS-MVS		86.69 39	86.95 36	85.90 71	90.76 96	67.57 148	92.83 17	93.30 32	79.67 17	84.57 80	92.27 93	71.47 58	95.02 93	84.24 63	93.46 67	95.13 8

Anonymous20240529		80.19 162	78.89 170	84.10 126	90.60 97	64.75 210	88.95 115	90.90 132	65.97 289	80.59 135	91.17 126	49.97 293	93.73 147	69.16 211	82.70 225	93.81 70

h-mvs33		83.15 101	82.19 109	86.02 69	90.56 98	70.85 73	88.15 147	89.16 190	76.02 90	84.67 74	91.39 118	61.54 173	95.50 66	82.71 81	75.48 315	91.72 154

Anonymous20231211		78.97 190	77.69 202	82.81 187	90.54 99	64.29 220	90.11 75	91.51 115	65.01 301	76.16 224	88.13 206	50.56 287	93.03 185	69.68 206	77.56 285	91.11 171

LS3D		76.95 236	74.82 254	83.37 160	90.45 100	67.36 154	89.15 108	86.94 248	61.87 340	69.52 324	90.61 140	51.71 275	94.53 110	46.38 382	86.71 162	88.21 281

VDDNet		81.52 129	80.67 132	84.05 137	90.44 101	64.13 223	89.73 84	85.91 266	71.11 194	83.18 103	93.48 65	50.54 288	93.49 155	73.40 169	88.25 140	94.54 36

testing3-2		75.12 268	75.19 250	74.91 326	90.40 102	45.09 407	80.29 319	78.42 359	78.37 36	76.54 212	87.75 209	44.36 344	87.28 316	57.04 321	83.49 212	92.37 133

CNLPA		78.08 210	76.79 221	81.97 206	90.40 102	71.07 65	87.59 163	84.55 281	66.03 288	72.38 292	89.64 158	57.56 216	86.04 327	59.61 294	83.35 215	88.79 265

PAPR		81.66 127	80.89 130	83.99 142	90.27 104	64.00 224	86.76 193	91.77 109	68.84 251	77.13 200	89.50 162	67.63 103	94.88 99	67.55 225	88.52 137	93.09 105

Vis-MVSNet		83.46 95	82.80 101	85.43 79	90.25 105	68.74 114	90.30 72	90.13 159	76.33 85	80.87 133	92.89 81	61.00 187	94.20 122	72.45 181	90.97 97	93.35 93
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
DPM-MVS		84.93 72	84.29 79	86.84 50	90.20 106	73.04 23	87.12 177	93.04 41	69.80 225	82.85 108	91.22 123	73.06 40	96.02 52	76.72 137	94.63 48	91.46 164

EPP-MVSNet		83.40 97	83.02 96	84.57 105	90.13 107	64.47 216	92.32 30	90.73 137	74.45 127	79.35 149	91.10 127	69.05 89	95.12 85	72.78 176	87.22 154	94.13 52

CANet		86.45 42	86.10 51	87.51 37	90.09 108	70.94 70	89.70 85	92.59 74	81.78 4	81.32 125	91.43 117	70.34 72	97.23 14	84.26 61	93.36 68	94.37 42

test2506		77.30 231	76.49 228	79.74 256	90.08 109	52.02 372	87.86 158	63.10 414	74.88 115	80.16 140	92.79 86	38.29 380	92.35 208	68.74 216	92.50 77	94.86 18

ECVR-MVS		79.61 169	79.26 162	80.67 238	90.08 109	54.69 355	87.89 156	77.44 367	74.88 115	80.27 137	92.79 86	48.96 309	92.45 202	68.55 217	92.50 77	94.86 18

HQP_MVS		83.64 89	83.14 93	85.14 85	90.08 109	68.71 116	91.25 52	92.44 77	79.12 24	78.92 155	91.00 134	60.42 198	95.38 75	78.71 114	86.32 167	91.33 165

plane_prior7					90.08 109	68.51 124

patch_mono-2		83.65 88	84.54 75	80.99 230	90.06 113	65.83 183	84.21 259	88.74 209	71.60 185	85.01 66	92.44 91	74.51 25	83.50 351	82.15 86	92.15 80	93.64 81

test1111		79.43 176	79.18 165	80.15 248	89.99 114	53.31 368	87.33 172	77.05 371	75.04 110	80.23 139	92.77 88	48.97 308	92.33 210	68.87 214	92.40 79	94.81 21

CHOSEN 1792x2688		77.63 225	75.69 237	83.44 156	89.98 115	68.58 122	78.70 341	87.50 235	56.38 380	75.80 228	86.84 234	58.67 206	91.40 247	61.58 279	85.75 179	90.34 202

IS-MVSNet		83.15 101	82.81 100	84.18 124	89.94 116	63.30 241	91.59 43	88.46 215	79.04 26	79.49 147	92.16 95	65.10 130	94.28 117	67.71 223	91.86 86	94.95 11

plane_prior1					89.90 117

sasdasda		85.91 54	85.87 56	86.04 67	89.84 118	69.44 98	90.45 68	93.00 46	76.70 74	88.01 33	91.23 121	73.28 36	93.91 135	81.50 90	88.80 130	94.77 24

canonicalmvs		85.91 54	85.87 56	86.04 67	89.84 118	69.44 98	90.45 68	93.00 46	76.70 74	88.01 33	91.23 121	73.28 36	93.91 135	81.50 90	88.80 130	94.77 24

plane_prior6					89.84 118	68.70 118						60.42 198

mvsmamba		80.60 150	79.38 157	84.27 120	89.74 121	67.24 159	87.47 166	86.95 247	70.02 218	75.38 239	88.93 177	51.24 279	92.56 198	75.47 151	89.22 124	93.00 113

NP-MVS					89.62 122	68.32 128					90.24 146

EIA-MVS		83.31 100	82.80 101	84.82 99	89.59 123	65.59 189	88.21 143	92.68 66	74.66 122	78.96 153	86.42 253	69.06 88	95.26 80	75.54 149	90.09 111	93.62 82

HyFIR lowres test		77.53 226	75.40 245	83.94 145	89.59 123	66.62 168	80.36 317	88.64 212	56.29 381	76.45 213	85.17 282	57.64 215	93.28 164	61.34 282	83.10 219	91.91 150

TAPA-MVS	73.13 9	79.15 184	77.94 190	82.79 190	89.59 123	62.99 251	88.16 146	91.51 115	65.77 290	77.14 199	91.09 128	60.91 188	93.21 169	50.26 361	87.05 156	92.17 144
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
thres100view900		76.50 243	75.55 242	79.33 264	89.52 126	56.99 323	85.83 220	83.23 302	73.94 139	76.32 217	87.12 230	51.89 271	91.95 221	48.33 370	83.75 204	89.07 247

GeoE		81.71 124	81.01 128	83.80 149	89.51 127	64.45 217	88.97 114	88.73 210	71.27 191	78.63 161	89.76 155	66.32 117	93.20 172	69.89 203	86.02 174	93.74 73

alignmvs		85.48 62	85.32 66	85.96 70	89.51 127	69.47 95	89.74 83	92.47 76	76.17 87	87.73 40	91.46 116	70.32 73	93.78 141	81.51 89	88.95 127	94.63 32

PS-MVSNAJ		81.69 125	81.02 127	83.70 150	89.51 127	68.21 132	84.28 258	90.09 160	70.79 200	81.26 129	85.62 271	63.15 148	94.29 116	75.62 147	88.87 129	88.59 273

MVS_0304		87.69 20	87.55 24	88.12 13	89.45 130	71.76 51	91.47 49	89.54 175	82.14 3	86.65 53	94.28 37	68.28 97	97.46 6	90.81 3	95.31 34	95.15 7

MGCFI-Net		85.06 71	85.51 61	83.70 150	89.42 131	63.01 247	89.43 94	92.62 73	76.43 78	87.53 41	91.34 119	72.82 44	93.42 161	81.28 93	88.74 133	94.66 31

ACMP	74.13 6	81.51 131	80.57 133	84.36 113	89.42 131	68.69 119	89.97 77	91.50 118	74.46 126	75.04 255	90.41 143	53.82 247	94.54 109	77.56 125	82.91 220	89.86 229
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
thres600view7		76.50 243	75.44 243	79.68 258	89.40 133	57.16 320	85.53 228	83.23 302	73.79 143	76.26 218	87.09 231	51.89 271	91.89 224	48.05 375	83.72 207	90.00 221

ETV-MVS		84.90 74	84.67 74	85.59 75	89.39 134	68.66 120	88.74 124	92.64 72	79.97 15	84.10 88	85.71 266	69.32 84	95.38 75	80.82 98	91.37 93	92.72 118

BH-RMVSNet		79.61 169	78.44 178	83.14 170	89.38 135	65.93 180	84.95 239	87.15 244	73.56 149	78.19 172	89.79 154	56.67 225	93.36 162	59.53 295	86.74 161	90.13 211

HQP-NCC					89.33 136		89.17 104		76.41 79	77.23 193

ACMP_Plane					89.33 136		89.17 104		76.41 79	77.23 193

HQP-MVS		82.61 110	82.02 114	84.37 112	89.33 136	66.98 164	89.17 104	92.19 90	76.41 79	77.23 193	90.23 147	60.17 201	95.11 87	77.47 126	85.99 175	91.03 175

EC-MVSNet		86.01 49	86.38 43	84.91 97	89.31 139	66.27 174	92.32 30	93.63 21	79.37 21	84.17 87	91.88 101	69.04 90	95.43 70	83.93 67	93.77 63	93.01 112

ACMM	73.20 8	80.78 147	79.84 148	83.58 153	89.31 139	68.37 127	89.99 76	91.60 112	70.28 213	77.25 191	89.66 157	53.37 252	93.53 154	74.24 161	82.85 221	88.85 262
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
Test_1112_low_res		76.40 248	75.44 243	79.27 265	89.28 141	58.09 303	81.69 295	87.07 245	59.53 357	72.48 290	86.67 243	61.30 180	89.33 286	60.81 286	80.15 255	90.41 200

F-COLMAP		76.38 249	74.33 262	82.50 197	89.28 141	66.95 167	88.41 134	89.03 195	64.05 314	66.83 349	88.61 187	46.78 320	92.89 187	57.48 315	78.55 270	87.67 290

LPG-MVS_test		82.08 116	81.27 122	84.50 107	89.23 143	68.76 112	90.22 73	91.94 99	75.37 101	76.64 208	91.51 113	54.29 242	94.91 95	78.44 116	83.78 201	89.83 230

LGP-MVS_train				84.50 107	89.23 143	68.76 112		91.94 99	75.37 101	76.64 208	91.51 113	54.29 242	94.91 95	78.44 116	83.78 201	89.83 230

BH-untuned		79.47 174	78.60 174	82.05 203	89.19 145	65.91 181	86.07 212	88.52 214	72.18 175	75.42 237	87.69 212	61.15 184	93.54 153	60.38 287	86.83 160	86.70 316

xiu_mvs_v2_base		81.69 125	81.05 126	83.60 152	89.15 146	68.03 137	84.46 252	90.02 161	70.67 203	81.30 128	86.53 251	63.17 147	94.19 123	75.60 148	88.54 136	88.57 274

test_yl		81.17 134	80.47 136	83.24 165	89.13 147	63.62 230	86.21 208	89.95 164	72.43 173	81.78 121	89.61 159	57.50 217	93.58 149	70.75 192	86.90 158	92.52 126

DCV-MVSNet		81.17 134	80.47 136	83.24 165	89.13 147	63.62 230	86.21 208	89.95 164	72.43 173	81.78 121	89.61 159	57.50 217	93.58 149	70.75 192	86.90 158	92.52 126

tfpn200view9		76.42 247	75.37 247	79.55 263	89.13 147	57.65 314	85.17 231	83.60 294	73.41 155	76.45 213	86.39 254	52.12 263	91.95 221	48.33 370	83.75 204	89.07 247

thres400		76.50 243	75.37 247	79.86 253	89.13 147	57.65 314	85.17 231	83.60 294	73.41 155	76.45 213	86.39 254	52.12 263	91.95 221	48.33 370	83.75 204	90.00 221

1112_ss		77.40 229	76.43 230	80.32 245	89.11 151	60.41 284	83.65 268	87.72 231	62.13 337	73.05 282	86.72 238	62.58 156	89.97 275	62.11 274	80.80 246	90.59 193

SDMVSNet		80.38 156	80.18 142	80.99 230	89.03 152	64.94 205	80.45 316	89.40 179	75.19 107	76.61 210	89.98 150	60.61 195	87.69 313	76.83 135	83.55 210	90.33 203

sd_testset		77.70 223	77.40 207	78.60 276	89.03 152	60.02 288	79.00 336	85.83 267	75.19 107	76.61 210	89.98 150	54.81 234	85.46 335	62.63 267	83.55 210	90.33 203

Fast-Effi-MVS+		80.81 142	79.92 145	83.47 155	88.85 154	64.51 213	85.53 228	89.39 180	70.79 200	78.49 165	85.06 285	67.54 104	93.58 149	67.03 233	86.58 163	92.32 136

PVSNet_BlendedMVS		80.60 150	80.02 143	82.36 200	88.85 154	65.40 192	86.16 210	92.00 95	69.34 235	78.11 174	86.09 261	66.02 122	94.27 118	71.52 184	82.06 231	87.39 297

PVSNet_Blended		80.98 137	80.34 138	82.90 183	88.85 154	65.40 192	84.43 254	92.00 95	67.62 266	78.11 174	85.05 286	66.02 122	94.27 118	71.52 184	89.50 120	89.01 254

MVS_111021_LR		82.61 110	82.11 110	84.11 125	88.82 157	71.58 55	85.15 233	86.16 263	74.69 120	80.47 136	91.04 130	62.29 161	90.55 267	80.33 103	90.08 112	90.20 208

BH-w/o		78.21 206	77.33 210	80.84 234	88.81 158	65.13 200	84.87 240	87.85 228	69.75 228	74.52 264	84.74 292	61.34 179	93.11 179	58.24 310	85.84 177	84.27 354

FIs		82.07 117	82.42 104	81.04 229	88.80 159	58.34 301	88.26 142	93.49 26	76.93 65	78.47 166	91.04 130	69.92 78	92.34 209	69.87 204	84.97 183	92.44 132

OPM-MVS		83.50 94	82.95 98	85.14 85	88.79 160	70.95 69	89.13 109	91.52 114	77.55 47	80.96 132	91.75 104	60.71 190	94.50 112	79.67 109	86.51 165	89.97 225
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
WR-MVS		79.49 173	79.22 164	80.27 246	88.79 160	58.35 300	85.06 236	88.61 213	78.56 31	77.65 183	88.34 195	63.81 141	90.66 266	64.98 248	77.22 287	91.80 153

OMC-MVS		82.69 108	81.97 116	84.85 98	88.75 162	67.42 151	87.98 150	90.87 134	74.92 114	79.72 144	91.65 107	62.19 164	93.96 128	75.26 153	86.42 166	93.16 102

hse-mvs2		81.72 123	80.94 129	84.07 132	88.72 163	67.68 144	85.87 217	87.26 241	76.02 90	84.67 74	88.22 200	61.54 173	93.48 156	82.71 81	73.44 343	91.06 173

AUN-MVS		79.21 183	77.60 204	84.05 137	88.71 164	67.61 146	85.84 219	87.26 241	69.08 244	77.23 193	88.14 205	53.20 254	93.47 157	75.50 150	73.45 342	91.06 173

ACMH	67.68 16	75.89 255	73.93 266	81.77 209	88.71 164	66.61 169	88.62 129	89.01 197	69.81 224	66.78 350	86.70 242	41.95 362	91.51 242	55.64 330	78.14 277	87.17 303
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
Vis-MVSNet (Re-imp)		78.36 203	78.45 177	78.07 289	88.64 166	51.78 378	86.70 194	79.63 350	74.14 136	75.11 252	90.83 137	61.29 181	89.75 279	58.10 311	91.60 88	92.69 121

PatchMatch-RL		72.38 299	70.90 303	76.80 307	88.60 167	67.38 153	79.53 327	76.17 377	62.75 330	69.36 326	82.00 346	45.51 336	84.89 341	53.62 340	80.58 249	78.12 395

ACMH+	68.96 14	76.01 254	74.01 264	82.03 204	88.60 167	65.31 196	88.86 118	87.55 233	70.25 215	67.75 338	87.47 220	41.27 364	93.19 174	58.37 308	75.94 308	87.60 292

LTVRE_ROB	69.57 13	76.25 250	74.54 258	81.41 217	88.60 167	64.38 219	79.24 331	89.12 194	70.76 202	69.79 323	87.86 208	49.09 306	93.20 172	56.21 329	80.16 254	86.65 317
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
DELS-MVS		85.41 65	85.30 67	85.77 72	88.49 170	67.93 138	85.52 230	93.44 27	78.70 30	83.63 100	89.03 176	74.57 24	95.71 61	80.26 104	94.04 61	93.66 75
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
CLD-MVS		82.31 113	81.65 119	84.29 117	88.47 171	67.73 143	85.81 221	92.35 82	75.78 93	78.33 169	86.58 248	64.01 138	94.35 115	76.05 142	87.48 150	90.79 182
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
UniMVSNet_NR-MVSNet		81.88 120	81.54 120	82.92 182	88.46 172	63.46 237	87.13 176	92.37 81	80.19 12	78.38 167	89.14 172	71.66 57	93.05 182	70.05 200	76.46 298	92.25 139

ab-mvs		79.51 172	78.97 169	81.14 226	88.46 172	60.91 275	83.84 264	89.24 187	70.36 210	79.03 152	88.87 180	63.23 146	90.21 271	65.12 246	82.57 226	92.28 138

testing91		76.54 241	75.66 240	79.18 268	88.43 174	55.89 341	81.08 303	83.00 309	73.76 144	75.34 241	84.29 300	46.20 328	90.07 273	64.33 252	84.50 189	91.58 157

FC-MVSNet-test		81.52 129	82.02 114	80.03 250	88.42 175	55.97 340	87.95 152	93.42 29	77.10 61	77.38 188	90.98 136	69.96 77	91.79 227	68.46 219	84.50 189	92.33 135

Effi-MVS+		83.62 91	83.08 94	85.24 83	88.38 176	67.45 150	88.89 117	89.15 191	75.50 99	82.27 113	88.28 197	69.61 81	94.45 114	77.81 123	87.84 144	93.84 68

UniMVSNet (Re)		81.60 128	81.11 125	83.09 172	88.38 176	64.41 218	87.60 162	93.02 45	78.42 33	78.56 163	88.16 201	69.78 79	93.26 165	69.58 207	76.49 297	91.60 155

VPNet		78.69 196	78.66 173	78.76 273	88.31 178	55.72 344	84.45 253	86.63 254	76.79 69	78.26 170	90.55 141	59.30 203	89.70 281	66.63 234	77.05 289	90.88 180

FA-MVS(test-final)		80.96 138	79.91 146	84.10 126	88.30 179	65.01 202	84.55 249	90.01 162	73.25 160	79.61 145	87.57 215	58.35 209	94.72 105	71.29 188	86.25 169	92.56 125

TR-MVS		77.44 227	76.18 233	81.20 224	88.24 180	63.24 242	84.61 247	86.40 258	67.55 267	77.81 180	86.48 252	54.10 244	93.15 176	57.75 314	82.72 224	87.20 302

myMVS_eth3d28		73.62 282	73.53 272	73.90 338	88.20 181	47.41 397	78.06 351	79.37 352	74.29 132	73.98 270	84.29 300	44.67 340	83.54 350	51.47 351	87.39 151	90.74 186

EI-MVSNet-Vis-set		84.19 78	83.81 83	85.31 81	88.18 182	67.85 139	87.66 161	89.73 170	80.05 14	82.95 105	89.59 161	70.74 69	94.82 101	80.66 101	84.72 186	93.28 96

testing11		75.14 267	74.01 264	78.53 280	88.16 183	56.38 334	80.74 310	80.42 341	70.67 203	72.69 288	83.72 315	43.61 350	89.86 276	62.29 270	83.76 203	89.36 243

testing99		76.09 253	75.12 252	79.00 269	88.16 183	55.50 347	80.79 307	81.40 329	73.30 158	75.17 249	84.27 303	44.48 343	90.02 274	64.28 253	84.22 198	91.48 162

GDP-MVS		83.52 93	82.64 103	86.16 62	88.14 185	68.45 125	89.13 109	92.69 65	72.82 169	83.71 96	91.86 103	55.69 229	95.35 79	80.03 105	89.74 118	94.69 27

baseline1		76.98 235	76.75 224	77.66 294	88.13 186	55.66 345	85.12 234	81.89 322	73.04 164	76.79 203	88.90 178	62.43 159	87.78 312	63.30 260	71.18 359	89.55 239

test_0402		72.79 297	70.44 308	79.84 254	88.13 186	65.99 179	85.93 215	84.29 285	65.57 293	67.40 344	85.49 274	46.92 319	92.61 194	35.88 407	74.38 333	80.94 386

tttt0517		79.40 178	77.91 191	83.90 146	88.10 188	63.84 227	88.37 138	84.05 289	71.45 188	76.78 204	89.12 173	49.93 296	94.89 98	70.18 199	83.18 218	92.96 115

FE-MVS		77.78 219	75.68 238	84.08 131	88.09 189	66.00 178	83.13 279	87.79 229	68.42 259	78.01 177	85.23 280	45.50 337	95.12 85	59.11 299	85.83 178	91.11 171

VPA-MVSNet		80.60 150	80.55 134	80.76 236	88.07 190	60.80 277	86.86 187	91.58 113	75.67 97	80.24 138	89.45 168	63.34 142	90.25 270	70.51 196	79.22 267	91.23 168

UGNet		80.83 141	79.59 153	84.54 106	88.04 191	68.09 134	89.42 96	88.16 217	76.95 64	76.22 219	89.46 166	49.30 303	93.94 131	68.48 218	90.31 106	91.60 155
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
UBG		73.08 293	72.27 288	75.51 318	88.02 192	51.29 383	78.35 348	77.38 368	65.52 294	73.87 272	82.36 338	45.55 335	86.48 323	55.02 332	84.39 195	88.75 267

WR-MVS_H		78.51 200	78.49 176	78.56 278	88.02 192	56.38 334	88.43 133	92.67 67	77.14 59	73.89 271	87.55 217	66.25 118	89.24 289	58.92 301	73.55 341	90.06 219

QAPM		80.88 139	79.50 155	85.03 90	88.01 194	68.97 107	91.59 43	92.00 95	66.63 281	75.15 251	92.16 95	57.70 214	95.45 68	63.52 256	88.76 132	90.66 189

RRT-MVS		82.60 112	82.10 111	84.10 126	87.98 195	62.94 252	87.45 168	91.27 121	77.42 51	79.85 142	90.28 144	56.62 226	94.70 107	79.87 108	88.15 142	94.67 28

3Dnovator	76.31 5	83.38 98	82.31 108	86.59 55	87.94 196	72.94 28	90.64 60	92.14 92	77.21 57	75.47 233	92.83 83	58.56 207	94.72 105	73.24 172	92.71 74	92.13 146

WBMVS		73.43 285	72.81 281	75.28 322	87.91 197	50.99 385	78.59 344	81.31 331	65.51 296	74.47 265	84.83 289	46.39 322	86.68 320	58.41 307	77.86 279	88.17 282

testing222		74.04 277	72.66 283	78.19 286	87.89 198	55.36 348	81.06 304	79.20 355	71.30 190	74.65 262	83.57 319	39.11 375	88.67 301	51.43 353	85.75 179	90.53 195

EI-MVSNet-UG-set		83.81 83	83.38 90	85.09 89	87.87 199	67.53 149	87.44 169	89.66 171	79.74 16	82.23 114	89.41 170	70.24 75	94.74 104	79.95 106	83.92 200	92.99 114

TranMVSNet+NR-MVSNet		80.84 140	80.31 139	82.42 198	87.85 200	62.33 257	87.74 160	91.33 120	80.55 9	77.99 178	89.86 152	65.23 129	92.62 193	67.05 232	75.24 325	92.30 137

BP-MVS1		84.32 77	83.71 85	86.17 61	87.84 201	67.85 139	89.38 99	89.64 173	77.73 40	83.98 91	92.12 97	56.89 224	95.43 70	84.03 66	91.75 87	95.24 6

CP-MVSNet		78.22 205	78.34 181	77.84 291	87.83 202	54.54 357	87.94 153	91.17 125	77.65 41	73.48 277	88.49 191	62.24 163	88.43 304	62.19 271	74.07 334	90.55 194

DU-MVS		81.12 136	80.52 135	82.90 183	87.80 203	63.46 237	87.02 181	91.87 103	79.01 27	78.38 167	89.07 174	65.02 131	93.05 182	70.05 200	76.46 298	92.20 142

NR-MVSNet		80.23 160	79.38 157	82.78 191	87.80 203	63.34 240	86.31 205	91.09 129	79.01 27	72.17 295	89.07 174	67.20 108	92.81 191	66.08 239	75.65 311	92.20 142

TAMVS		78.89 192	77.51 206	83.03 177	87.80 203	67.79 142	84.72 243	85.05 276	67.63 265	76.75 205	87.70 211	62.25 162	90.82 262	58.53 306	87.13 155	90.49 197

thres200		75.55 259	74.47 259	78.82 272	87.78 206	57.85 310	83.07 282	83.51 297	72.44 172	75.84 227	84.42 295	52.08 266	91.75 229	47.41 377	83.64 209	86.86 312

ETVMVS		72.25 302	71.05 301	75.84 312	87.77 207	51.91 375	79.39 329	74.98 380	69.26 237	73.71 273	82.95 329	40.82 368	86.14 326	46.17 383	84.43 194	89.47 240

PS-CasMVS		78.01 214	78.09 187	77.77 293	87.71 208	54.39 359	88.02 149	91.22 122	77.50 49	73.26 279	88.64 186	60.73 189	88.41 305	61.88 275	73.88 338	90.53 195

PCF-MVS	73.52 7	80.38 156	78.84 171	85.01 91	87.71 208	68.99 106	83.65 268	91.46 119	63.00 324	77.77 182	90.28 144	66.10 119	95.09 91	61.40 280	88.22 141	90.94 179
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
thisisatest0530		79.40 178	77.76 199	84.31 116	87.69 210	65.10 201	87.36 170	84.26 287	70.04 217	77.42 187	88.26 199	49.94 294	94.79 103	70.20 198	84.70 187	93.03 110

casdiffmvs_mvg		85.99 50	86.09 52	85.70 74	87.65 211	67.22 160	88.69 126	93.04 41	79.64 19	85.33 63	92.54 90	73.30 35	94.50 112	83.49 69	91.14 96	95.37 2
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
GBi-Net		78.40 201	77.40 207	81.40 218	87.60 212	63.01 247	88.39 135	89.28 183	71.63 182	75.34 241	87.28 222	54.80 235	91.11 253	62.72 263	79.57 260	90.09 215

test1		78.40 201	77.40 207	81.40 218	87.60 212	63.01 247	88.39 135	89.28 183	71.63 182	75.34 241	87.28 222	54.80 235	91.11 253	62.72 263	79.57 260	90.09 215

FMVSNet2		78.20 207	77.21 211	81.20 224	87.60 212	62.89 253	87.47 166	89.02 196	71.63 182	75.29 247	87.28 222	54.80 235	91.10 256	62.38 268	79.38 264	89.61 237

CDS-MVSNet		79.07 187	77.70 201	83.17 169	87.60 212	68.23 131	84.40 256	86.20 262	67.49 268	76.36 216	86.54 250	61.54 173	90.79 263	61.86 276	87.33 152	90.49 197
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
HY-MVS	69.67 12	77.95 215	77.15 212	80.36 243	87.57 216	60.21 287	83.37 275	87.78 230	66.11 285	75.37 240	87.06 233	63.27 144	90.48 268	61.38 281	82.43 227	90.40 201

xiu_mvs_v1_base_debu		80.80 144	79.72 150	84.03 139	87.35 217	70.19 82	85.56 223	88.77 205	69.06 245	81.83 117	88.16 201	50.91 282	92.85 188	78.29 120	87.56 147	89.06 249

xiu_mvs_v1_base		80.80 144	79.72 150	84.03 139	87.35 217	70.19 82	85.56 223	88.77 205	69.06 245	81.83 117	88.16 201	50.91 282	92.85 188	78.29 120	87.56 147	89.06 249

xiu_mvs_v1_base_debi		80.80 144	79.72 150	84.03 139	87.35 217	70.19 82	85.56 223	88.77 205	69.06 245	81.83 117	88.16 201	50.91 282	92.85 188	78.29 120	87.56 147	89.06 249

MVSFormer		82.85 107	82.05 113	85.24 83	87.35 217	70.21 80	90.50 64	90.38 147	68.55 255	81.32 125	89.47 164	61.68 170	93.46 158	78.98 111	90.26 108	92.05 148

lupinMVS		81.39 132	80.27 141	84.76 102	87.35 217	70.21 80	85.55 226	86.41 257	62.85 327	81.32 125	88.61 187	61.68 170	92.24 213	78.41 118	90.26 108	91.83 151

testing3		68.56 335	67.67 335	71.22 362	87.33 222	42.87 412	83.06 283	71.54 392	70.36 210	69.08 329	84.38 297	30.33 400	85.69 331	37.50 405	75.45 318	85.09 346

baseline		84.93 72	84.98 70	84.80 101	87.30 223	65.39 194	87.30 173	92.88 57	77.62 42	84.04 90	92.26 94	71.81 52	93.96 128	81.31 92	90.30 107	95.03 10

PAPM		77.68 224	76.40 231	81.51 214	87.29 224	61.85 264	83.78 265	89.59 174	64.74 303	71.23 304	88.70 183	62.59 155	93.66 148	52.66 345	87.03 157	89.01 254

fmvsm_l_conf0.5_n_3		86.02 48	86.32 44	85.14 85	87.20 225	68.54 123	89.57 90	90.44 145	75.31 103	87.49 42	94.39 34	72.86 42	92.72 192	89.04 19	90.56 103	94.16 50

LCM-MVSNet-Re		77.05 233	76.94 217	77.36 300	87.20 225	51.60 379	80.06 321	80.46 340	75.20 106	67.69 339	86.72 238	62.48 157	88.98 294	63.44 258	89.25 123	91.51 159

casdiffmvs		85.11 69	85.14 69	85.01 91	87.20 225	65.77 186	87.75 159	92.83 60	77.84 39	84.36 84	92.38 92	72.15 48	93.93 134	81.27 94	90.48 104	95.33 4
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
COLMAP_ROB	66.92 17	73.01 294	70.41 309	80.81 235	87.13 228	65.63 188	88.30 141	84.19 288	62.96 325	63.80 376	87.69 212	38.04 381	92.56 198	46.66 379	74.91 328	84.24 355
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
fmvsm_s_conf0.5_n_3		86.36 46	87.46 27	83.09 172	87.08 229	65.21 197	89.09 111	90.21 156	79.67 17	89.98 18	95.02 18	73.17 38	91.71 232	91.30 2	91.60 88	92.34 134

PEN-MVS		77.73 220	77.69 202	77.84 291	87.07 230	53.91 362	87.91 155	91.18 124	77.56 46	73.14 281	88.82 181	61.23 182	89.17 290	59.95 290	72.37 349	90.43 199

MVS_Test		83.15 101	83.06 95	83.41 159	86.86 231	63.21 243	86.11 211	92.00 95	74.31 130	82.87 107	89.44 169	70.03 76	93.21 169	77.39 128	88.50 138	93.81 70

UniMVSNet_ETH3D		79.10 186	78.24 184	81.70 210	86.85 232	60.24 286	87.28 174	88.79 204	74.25 133	76.84 201	90.53 142	49.48 299	91.56 237	67.98 221	82.15 229	93.29 95

FMVSNet3		77.88 217	76.85 219	80.97 232	86.84 233	62.36 256	86.52 199	88.77 205	71.13 193	75.34 241	86.66 244	54.07 245	91.10 256	62.72 263	79.57 260	89.45 241

FMVSNet1		77.44 227	76.12 234	81.40 218	86.81 234	63.01 247	88.39 135	89.28 183	70.49 209	74.39 266	87.28 222	49.06 307	91.11 253	60.91 284	78.52 271	90.09 215

nrg030		83.88 82	83.53 87	84.96 93	86.77 235	69.28 102	90.46 67	92.67 67	74.79 118	82.95 105	91.33 120	72.70 45	93.09 180	80.79 100	79.28 266	92.50 128

ET-MVSNet_ETH3D		78.63 197	76.63 227	84.64 104	86.73 236	69.47 95	85.01 237	84.61 280	69.54 231	66.51 357	86.59 246	50.16 291	91.75 229	76.26 139	84.24 197	92.69 121

fmvsm_s_conf0.5_n		83.80 84	83.71 85	84.07 132	86.69 237	67.31 155	89.46 93	83.07 307	71.09 195	86.96 51	93.70 62	69.02 91	91.47 244	88.79 22	84.62 188	93.44 90

UWE-MVS		72.13 303	71.49 294	74.03 336	86.66 238	47.70 395	81.40 301	76.89 373	63.60 319	75.59 230	84.22 304	39.94 371	85.62 332	48.98 367	86.13 172	88.77 266

jason		81.39 132	80.29 140	84.70 103	86.63 239	69.90 88	85.95 214	86.77 252	63.24 320	81.07 131	89.47 164	61.08 186	92.15 215	78.33 119	90.07 113	92.05 148
jason: jason.
PS-MVSNAJss		82.07 117	81.31 121	84.34 115	86.51 240	67.27 157	89.27 102	91.51 115	71.75 180	79.37 148	90.22 148	63.15 148	94.27 118	77.69 124	82.36 228	91.49 161

WTY-MVS		75.65 258	75.68 238	75.57 316	86.40 241	56.82 325	77.92 354	82.40 317	65.10 298	76.18 221	87.72 210	63.13 151	80.90 367	60.31 288	81.96 232	89.00 256

DTE-MVSNet		76.99 234	76.80 220	77.54 299	86.24 242	53.06 371	87.52 164	90.66 138	77.08 62	72.50 289	88.67 185	60.48 197	89.52 283	57.33 318	70.74 361	90.05 220

PVSNet	64.34 18	72.08 304	70.87 304	75.69 314	86.21 243	56.44 332	74.37 378	80.73 335	62.06 338	70.17 314	82.23 342	42.86 354	83.31 353	54.77 334	84.45 193	87.32 300

fmvsm_s_conf0.5_n_2		84.04 80	84.11 81	83.81 148	86.17 244	65.00 203	86.96 182	87.28 239	74.35 128	88.25 28	94.23 41	61.82 168	92.60 195	89.85 7	88.09 143	93.84 68

fmvsm_s_conf0.5_n_a		83.63 90	83.41 89	84.28 118	86.14 245	68.12 133	89.43 94	82.87 312	70.27 214	87.27 47	93.80 61	69.09 86	91.58 235	88.21 30	83.65 208	93.14 104

test_fmvsm_n_1920		85.29 67	85.34 64	85.13 88	86.12 246	69.93 86	88.65 128	90.78 136	69.97 221	88.27 27	93.98 56	71.39 60	91.54 239	88.49 27	90.45 105	93.91 62

mamv4		76.81 238	78.23 186	72.54 351	86.12 246	65.75 187	78.76 340	82.07 321	64.12 311	72.97 283	91.02 133	67.97 99	68.08 416	83.04 75	78.02 278	83.80 362

tfpnnormal		74.39 271	73.16 277	78.08 288	86.10 248	58.05 304	84.65 246	87.53 234	70.32 212	71.22 305	85.63 270	54.97 233	89.86 276	43.03 393	75.02 327	86.32 320

IterMVS-LS		80.06 163	79.38 157	82.11 202	85.89 249	63.20 244	86.79 190	89.34 181	74.19 134	75.45 236	86.72 238	66.62 111	92.39 205	72.58 178	76.86 292	90.75 185
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
Baseline_NR-MVSNet		78.15 209	78.33 182	77.61 296	85.79 250	56.21 338	86.78 191	85.76 268	73.60 148	77.93 179	87.57 215	65.02 131	88.99 293	67.14 231	75.33 322	87.63 291

cascas		76.72 240	74.64 255	82.99 179	85.78 251	65.88 182	82.33 288	89.21 188	60.85 346	72.74 285	81.02 351	47.28 316	93.75 145	67.48 226	85.02 182	89.34 244

MVS		78.19 208	76.99 216	81.78 208	85.66 252	66.99 163	84.66 244	90.47 144	55.08 385	72.02 297	85.27 278	63.83 140	94.11 126	66.10 238	89.80 117	84.24 355

XVG-OURS		80.41 155	79.23 163	83.97 143	85.64 253	69.02 105	83.03 284	90.39 146	71.09 195	77.63 184	91.49 115	54.62 241	91.35 248	75.71 145	83.47 213	91.54 158

fmvsm_s_conf0.1_n_2		83.80 84	83.79 84	83.83 147	85.62 254	64.94 205	87.03 180	86.62 255	74.32 129	87.97 35	94.33 35	60.67 192	92.60 195	89.72 8	87.79 145	93.96 59

CANet_DTU		80.61 149	79.87 147	82.83 185	85.60 255	63.17 246	87.36 170	88.65 211	76.37 83	75.88 226	88.44 193	53.51 250	93.07 181	73.30 170	89.74 118	92.25 139

XVG-OURS-SEG-HR		80.81 142	79.76 149	83.96 144	85.60 255	68.78 111	83.54 273	90.50 143	70.66 206	76.71 206	91.66 106	60.69 191	91.26 250	76.94 133	81.58 236	91.83 151

TransMVSNet (Re)		75.39 265	74.56 257	77.86 290	85.50 257	57.10 322	86.78 191	86.09 265	72.17 176	71.53 302	87.34 221	63.01 152	89.31 287	56.84 324	61.83 388	87.17 303

fmvsm_l_conf0.5_n		84.47 76	84.54 75	84.27 120	85.42 258	68.81 109	88.49 132	87.26 241	68.08 262	88.03 32	93.49 64	72.04 50	91.77 228	88.90 21	89.14 126	92.24 141

fmvsm_l_conf0.5_n_a		84.13 79	84.16 80	84.06 134	85.38 259	68.40 126	88.34 139	86.85 251	67.48 269	87.48 43	93.40 68	70.89 66	91.61 233	88.38 29	89.22 124	92.16 145

MVP-Stereo		76.12 251	74.46 260	81.13 227	85.37 260	69.79 89	84.42 255	87.95 224	65.03 300	67.46 342	85.33 277	53.28 253	91.73 231	58.01 312	83.27 216	81.85 381
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
SSC-MVS3.2		73.35 289	73.39 273	73.23 342	85.30 261	49.01 393	74.58 377	81.57 326	75.21 105	73.68 274	85.58 272	52.53 255	82.05 360	54.33 337	77.69 283	88.63 272

thisisatest0515		77.33 230	75.38 246	83.18 168	85.27 262	63.80 228	82.11 291	83.27 301	65.06 299	75.91 225	83.84 310	49.54 298	94.27 118	67.24 229	86.19 170	91.48 162

tt0805		78.73 194	77.83 194	81.43 216	85.17 263	60.30 285	89.41 97	90.90 132	71.21 192	77.17 198	88.73 182	46.38 323	93.21 169	72.57 179	78.96 268	90.79 182

OpenMVS	72.83 10	79.77 167	78.33 182	84.09 130	85.17 263	69.91 87	90.57 61	90.97 130	66.70 275	72.17 295	91.91 99	54.70 239	93.96 128	61.81 277	90.95 98	88.41 278

AllTest		70.96 311	68.09 326	79.58 261	85.15 265	63.62 230	84.58 248	79.83 347	62.31 334	60.32 388	86.73 236	32.02 394	88.96 296	50.28 359	71.57 357	86.15 324

TestCases				79.58 261	85.15 265	63.62 230		79.83 347	62.31 334	60.32 388	86.73 236	32.02 394	88.96 296	50.28 359	71.57 357	86.15 324

Effi-MVS+-dtu		80.03 164	78.57 175	84.42 111	85.13 267	68.74 114	88.77 121	88.10 219	74.99 111	74.97 256	83.49 320	57.27 220	93.36 162	73.53 166	80.88 244	91.18 169

SixPastTwentyTwo		73.37 286	71.26 300	79.70 257	85.08 268	57.89 309	85.57 222	83.56 296	71.03 197	65.66 361	85.88 263	42.10 360	92.57 197	59.11 299	63.34 386	88.65 271

test_fmvsmconf_n		85.92 53	86.04 53	85.57 76	85.03 269	69.51 93	89.62 89	90.58 140	73.42 154	87.75 38	94.02 51	72.85 43	93.24 166	90.37 4	90.75 100	93.96 59

EG-PatchMatch MVS		74.04 277	71.82 291	80.71 237	84.92 270	67.42 151	85.86 218	88.08 220	66.04 287	64.22 371	83.85 309	35.10 389	92.56 198	57.44 316	80.83 245	82.16 380

fmvsm_s_conf0.1_n		83.56 92	83.38 90	84.10 126	84.86 271	67.28 156	89.40 98	83.01 308	70.67 203	87.08 48	93.96 57	68.38 95	91.45 245	88.56 26	84.50 189	93.56 85

IB-MVS	68.01 15	75.85 256	73.36 275	83.31 161	84.76 272	66.03 176	83.38 274	85.06 275	70.21 216	69.40 325	81.05 350	45.76 333	94.66 108	65.10 247	75.49 314	89.25 246
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
mvs_tets		79.13 185	77.77 198	83.22 167	84.70 273	66.37 172	89.17 104	90.19 157	69.38 234	75.40 238	89.46 166	44.17 346	93.15 176	76.78 136	80.70 248	90.14 210

Syy-MVS		68.05 339	67.85 329	68.67 375	84.68 274	40.97 418	78.62 342	73.08 389	66.65 279	66.74 351	79.46 367	52.11 265	82.30 358	32.89 410	76.38 303	82.75 374

myMVS_eth3d		67.02 345	66.29 346	69.21 370	84.68 274	42.58 413	78.62 342	73.08 389	66.65 279	66.74 351	79.46 367	31.53 397	82.30 358	39.43 402	76.38 303	82.75 374

jajsoiax		79.29 181	77.96 189	83.27 163	84.68 274	66.57 170	89.25 103	90.16 158	69.20 241	75.46 235	89.49 163	45.75 334	93.13 178	76.84 134	80.80 246	90.11 213

WB-MVSnew		71.96 305	71.65 293	72.89 347	84.67 277	51.88 376	82.29 289	77.57 364	62.31 334	73.67 275	83.00 328	53.49 251	81.10 366	45.75 386	82.13 230	85.70 334

MIMVSNet		70.69 315	69.30 314	74.88 327	84.52 278	56.35 336	75.87 366	79.42 351	64.59 304	67.76 337	82.41 337	41.10 365	81.54 363	46.64 381	81.34 237	86.75 315

MSDG		73.36 288	70.99 302	80.49 241	84.51 279	65.80 184	80.71 311	86.13 264	65.70 291	65.46 362	83.74 313	44.60 341	90.91 261	51.13 354	76.89 291	84.74 350

mvs_anonymous		79.42 177	79.11 166	80.34 244	84.45 280	57.97 307	82.59 286	87.62 232	67.40 270	76.17 223	88.56 190	68.47 94	89.59 282	70.65 195	86.05 173	93.47 89

EI-MVSNet		80.52 154	79.98 144	82.12 201	84.28 281	63.19 245	86.41 201	88.95 201	74.18 135	78.69 158	87.54 218	66.62 111	92.43 203	72.57 179	80.57 250	90.74 186

CVMVSNet		72.99 295	72.58 284	74.25 334	84.28 281	50.85 386	86.41 201	83.45 299	44.56 405	73.23 280	87.54 218	49.38 301	85.70 330	65.90 240	78.44 273	86.19 323

pm-mvs1		77.25 232	76.68 226	78.93 271	84.22 283	58.62 298	86.41 201	88.36 216	71.37 189	73.31 278	88.01 207	61.22 183	89.15 291	64.24 254	73.01 346	89.03 253

EPNet		83.72 87	82.92 99	86.14 65	84.22 283	69.48 94	91.05 56	85.27 272	81.30 6	76.83 202	91.65 107	66.09 120	95.56 63	76.00 143	93.85 62	93.38 91
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
test_fmvsmvis_n_1920		84.02 81	83.87 82	84.49 109	84.12 285	69.37 101	88.15 147	87.96 223	70.01 219	83.95 92	93.23 72	68.80 93	91.51 242	88.61 24	89.96 114	92.57 124

v8		79.97 166	79.02 168	82.80 188	84.09 286	64.50 215	87.96 151	90.29 154	74.13 137	75.24 248	86.81 235	62.88 153	93.89 138	74.39 159	75.40 320	90.00 221

v10		79.74 168	78.67 172	82.97 181	84.06 287	64.95 204	87.88 157	90.62 139	73.11 162	75.11 252	86.56 249	61.46 176	94.05 127	73.68 164	75.55 313	89.90 227

SCA		74.22 274	72.33 287	79.91 252	84.05 288	62.17 260	79.96 324	79.29 354	66.30 284	72.38 292	80.13 361	51.95 269	88.60 302	59.25 297	77.67 284	88.96 258

test_djsdf		80.30 159	79.32 160	83.27 163	83.98 289	65.37 195	90.50 64	90.38 147	68.55 255	76.19 220	88.70 183	56.44 227	93.46 158	78.98 111	80.14 256	90.97 178

1314		76.53 242	75.30 249	80.21 247	83.93 290	62.32 258	84.66 244	88.81 203	60.23 350	70.16 315	84.07 307	55.30 232	90.73 265	67.37 227	83.21 217	87.59 294

reproduce_monomvs		75.40 264	74.38 261	78.46 283	83.92 291	57.80 312	83.78 265	86.94 248	73.47 153	72.25 294	84.47 294	38.74 376	89.27 288	75.32 152	70.53 362	88.31 279

MS-PatchMatch		73.83 280	72.67 282	77.30 302	83.87 292	66.02 177	81.82 292	84.66 279	61.37 344	68.61 333	82.82 333	47.29 315	88.21 306	59.27 296	84.32 196	77.68 396

fmvsm_s_conf0.1_n_a		83.32 99	82.99 97	84.28 118	83.79 293	68.07 135	89.34 101	82.85 313	69.80 225	87.36 46	94.06 49	68.34 96	91.56 237	87.95 31	83.46 214	93.21 100

v1144		80.03 164	79.03 167	83.01 178	83.78 294	64.51 213	87.11 178	90.57 142	71.96 179	78.08 176	86.20 258	61.41 177	93.94 131	74.93 154	77.23 286	90.60 192

OurMVSNet-221017-0		74.26 273	72.42 286	79.80 255	83.76 295	59.59 293	85.92 216	86.64 253	66.39 283	66.96 347	87.58 214	39.46 372	91.60 234	65.76 242	69.27 367	88.22 280

mmtdpeth		74.16 275	73.01 279	77.60 298	83.72 296	61.13 271	85.10 235	85.10 274	72.06 178	77.21 197	80.33 359	43.84 348	85.75 329	77.14 131	52.61 406	85.91 331

v2v482		80.23 160	79.29 161	83.05 176	83.62 297	64.14 222	87.04 179	89.97 163	73.61 147	78.18 173	87.22 226	61.10 185	93.82 139	76.11 140	76.78 295	91.18 169

XXY-MVS		75.41 263	75.56 241	74.96 325	83.59 298	57.82 311	80.59 313	83.87 292	66.54 282	74.93 257	88.31 196	63.24 145	80.09 370	62.16 272	76.85 293	86.97 310

v1192		79.59 171	78.43 179	83.07 175	83.55 299	64.52 212	86.93 185	90.58 140	70.83 199	77.78 181	85.90 262	59.15 204	93.94 131	73.96 163	77.19 288	90.76 184

EGC-MVSNET		52.07 381	47.05 385	67.14 381	83.51 300	60.71 278	80.50 315	67.75 403	0.07 431	0.43 432	75.85 393	24.26 409	81.54 363	28.82 414	62.25 387	59.16 414

v7n		78.97 190	77.58 205	83.14 170	83.45 301	65.51 190	88.32 140	91.21 123	73.69 145	72.41 291	86.32 256	57.93 211	93.81 140	69.18 210	75.65 311	90.11 213

v144192		79.47 174	78.37 180	82.78 191	83.35 302	63.96 225	86.96 182	90.36 150	69.99 220	77.50 185	85.67 269	60.66 193	93.77 143	74.27 160	76.58 296	90.62 190

tpm2		73.26 290	71.46 295	78.63 274	83.34 303	56.71 328	80.65 312	80.40 342	56.63 379	73.55 276	82.02 345	51.80 273	91.24 251	56.35 328	78.42 274	87.95 284

v1921920		79.22 182	78.03 188	82.80 188	83.30 304	63.94 226	86.80 189	90.33 151	69.91 223	77.48 186	85.53 273	58.44 208	93.75 145	73.60 165	76.85 293	90.71 188

baseline2		75.70 257	73.83 269	81.30 221	83.26 305	61.79 266	82.57 287	80.65 336	66.81 272	66.88 348	83.42 321	57.86 213	92.19 214	63.47 257	79.57 260	89.91 226

v1240		78.99 189	77.78 197	82.64 194	83.21 306	63.54 234	86.62 196	90.30 153	69.74 230	77.33 189	85.68 268	57.04 222	93.76 144	73.13 173	76.92 290	90.62 190

XVG-ACMP-BASELINE		76.11 252	74.27 263	81.62 211	83.20 307	64.67 211	83.60 271	89.75 169	69.75 228	71.85 298	87.09 231	32.78 393	92.11 216	69.99 202	80.43 252	88.09 283

MDTV_nov1_ep13			69.97 313		83.18 308	53.48 365	77.10 360	80.18 346	60.45 347	69.33 327	80.44 357	48.89 310	86.90 318	51.60 350	78.51 272

PatchmatchNet		73.12 292	71.33 298	78.49 282	83.18 308	60.85 276	79.63 326	78.57 358	64.13 310	71.73 299	79.81 366	51.20 280	85.97 328	57.40 317	76.36 305	88.66 270
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
Fast-Effi-MVS+-dtu		78.02 213	76.49 228	82.62 195	83.16 310	66.96 166	86.94 184	87.45 237	72.45 170	71.49 303	84.17 305	54.79 238	91.58 235	67.61 224	80.31 253	89.30 245

gg-mvs-nofinetune		69.95 323	67.96 327	75.94 311	83.07 311	54.51 358	77.23 359	70.29 395	63.11 322	70.32 311	62.33 409	43.62 349	88.69 300	53.88 339	87.76 146	84.62 352

MVSTER		79.01 188	77.88 193	82.38 199	83.07 311	64.80 209	84.08 263	88.95 201	69.01 248	78.69 158	87.17 229	54.70 239	92.43 203	74.69 155	80.57 250	89.89 228

K. test v3		71.19 308	68.51 320	79.21 267	83.04 313	57.78 313	84.35 257	76.91 372	72.90 167	62.99 379	82.86 332	39.27 373	91.09 258	61.65 278	52.66 405	88.75 267

eth_miper_zixun_eth		77.92 216	76.69 225	81.61 213	83.00 314	61.98 262	83.15 278	89.20 189	69.52 232	74.86 258	84.35 299	61.76 169	92.56 198	71.50 186	72.89 347	90.28 206

diffmvs		82.10 115	81.88 117	82.76 193	83.00 314	63.78 229	83.68 267	89.76 168	72.94 166	82.02 116	89.85 153	65.96 124	90.79 263	82.38 85	87.30 153	93.71 74
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
test_fmvsmconf0.1_n		85.61 61	85.65 59	85.50 77	82.99 316	69.39 100	89.65 86	90.29 154	73.31 157	87.77 37	94.15 45	71.72 54	93.23 167	90.31 5	90.67 102	93.89 65

FMVSNet5		69.50 326	67.96 327	74.15 335	82.97 317	55.35 349	80.01 323	82.12 320	62.56 332	63.02 377	81.53 347	36.92 384	81.92 361	48.42 369	74.06 335	85.17 344

c3_l		78.75 193	77.91 191	81.26 222	82.89 318	61.56 268	84.09 262	89.13 193	69.97 221	75.56 231	84.29 300	66.36 116	92.09 217	73.47 168	75.48 315	90.12 212

sss		73.60 283	73.64 271	73.51 341	82.80 319	55.01 353	76.12 362	81.69 325	62.47 333	74.68 261	85.85 265	57.32 219	78.11 378	60.86 285	80.93 242	87.39 297

GA-MVS		76.87 237	75.17 251	81.97 206	82.75 320	62.58 254	81.44 300	86.35 260	72.16 177	74.74 259	82.89 331	46.20 328	92.02 219	68.85 215	81.09 241	91.30 167

v148		78.72 195	77.80 196	81.47 215	82.73 321	61.96 263	86.30 206	88.08 220	73.26 159	76.18 221	85.47 275	62.46 158	92.36 207	71.92 183	73.82 339	90.09 215

IterMVS-SCA-FT		75.43 262	73.87 268	80.11 249	82.69 322	64.85 208	81.57 297	83.47 298	69.16 242	70.49 309	84.15 306	51.95 269	88.15 307	69.23 209	72.14 353	87.34 299

miper_ehance_all_eth		78.59 199	77.76 199	81.08 228	82.66 323	61.56 268	83.65 268	89.15 191	68.87 250	75.55 232	83.79 312	66.49 114	92.03 218	73.25 171	76.39 300	89.64 236

CostFormer		75.24 266	73.90 267	79.27 265	82.65 324	58.27 302	80.80 306	82.73 315	61.57 341	75.33 245	83.13 326	55.52 230	91.07 259	64.98 248	78.34 276	88.45 276

EPNet_dtu		75.46 261	74.86 253	77.23 303	82.57 325	54.60 356	86.89 186	83.09 306	71.64 181	66.25 359	85.86 264	55.99 228	88.04 309	54.92 333	86.55 164	89.05 252
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
RPSCF		73.23 291	71.46 295	78.54 279	82.50 326	59.85 289	82.18 290	82.84 314	58.96 362	71.15 306	89.41 170	45.48 338	84.77 342	58.82 303	71.83 355	91.02 177

cl____		77.72 221	76.76 222	80.58 239	82.49 327	60.48 282	83.09 280	87.87 226	69.22 239	74.38 267	85.22 281	62.10 165	91.53 240	71.09 189	75.41 319	89.73 235

DIV-MVS_self_test		77.72 221	76.76 222	80.58 239	82.48 328	60.48 282	83.09 280	87.86 227	69.22 239	74.38 267	85.24 279	62.10 165	91.53 240	71.09 189	75.40 320	89.74 234

tpm cat1		70.57 316	68.31 322	77.35 301	82.41 329	57.95 308	78.08 350	80.22 345	52.04 392	68.54 334	77.66 383	52.00 268	87.84 311	51.77 348	72.07 354	86.25 321

cl22		78.07 211	77.01 214	81.23 223	82.37 330	61.83 265	83.55 272	87.98 222	68.96 249	75.06 254	83.87 308	61.40 178	91.88 225	73.53 166	76.39 300	89.98 224

tpm		72.37 300	71.71 292	74.35 333	82.19 331	52.00 373	79.22 332	77.29 369	64.56 305	72.95 284	83.68 317	51.35 277	83.26 354	58.33 309	75.80 309	87.81 288

tpmvs		71.09 310	69.29 315	76.49 308	82.04 332	56.04 339	78.92 338	81.37 330	64.05 314	67.18 346	78.28 378	49.74 297	89.77 278	49.67 364	72.37 349	83.67 363

dmvs_re		71.14 309	70.58 305	72.80 348	81.96 333	59.68 291	75.60 368	79.34 353	68.55 255	69.27 328	80.72 356	49.42 300	76.54 386	52.56 346	77.79 280	82.19 379

pmmvs4		74.03 279	71.91 290	80.39 242	81.96 333	68.32 128	81.45 299	82.14 319	59.32 358	69.87 321	85.13 283	52.40 259	88.13 308	60.21 289	74.74 330	84.73 351

TinyColmap		67.30 344	64.81 350	74.76 329	81.92 335	56.68 329	80.29 319	81.49 328	60.33 348	56.27 402	83.22 323	24.77 408	87.66 314	45.52 387	69.47 366	79.95 391

ITE_SJBPF				78.22 285	81.77 336	60.57 280		83.30 300	69.25 238	67.54 340	87.20 227	36.33 386	87.28 316	54.34 336	74.62 331	86.80 313

miper_enhance_ethall		77.87 218	76.86 218	80.92 233	81.65 337	61.38 270	82.68 285	88.98 198	65.52 294	75.47 233	82.30 340	65.76 126	92.00 220	72.95 174	76.39 300	89.39 242

MVS-HIRNet		59.14 369	57.67 371	63.57 387	81.65 337	43.50 411	71.73 385	65.06 410	39.59 412	51.43 407	57.73 415	38.34 379	82.58 357	39.53 400	73.95 336	64.62 411

GG-mvs-BLEND				75.38 321	81.59 339	55.80 343	79.32 330	69.63 397		67.19 345	73.67 398	43.24 351	88.90 298	50.41 356	84.50 189	81.45 383

MonoMVSNet		76.49 246	75.80 235	78.58 277	81.55 340	58.45 299	86.36 204	86.22 261	74.87 117	74.73 260	83.73 314	51.79 274	88.73 299	70.78 191	72.15 352	88.55 275

IterMVS		74.29 272	72.94 280	78.35 284	81.53 341	63.49 236	81.58 296	82.49 316	68.06 263	69.99 318	83.69 316	51.66 276	85.54 333	65.85 241	71.64 356	86.01 328
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
CHOSEN 280x420		66.51 349	64.71 351	71.90 354	81.45 342	63.52 235	57.98 418	68.95 401	53.57 388	62.59 381	76.70 386	46.22 327	75.29 401	55.25 331	79.68 259	76.88 398

gm-plane-assit					81.40 343	53.83 363			62.72 331		80.94 353		92.39 205	63.40 259

pmmvs6		74.69 270	73.39 273	78.61 275	81.38 344	57.48 317	86.64 195	87.95 224	64.99 302	70.18 313	86.61 245	50.43 289	89.52 283	62.12 273	70.18 364	88.83 263

test-LLR		72.94 296	72.43 285	74.48 331	81.35 345	58.04 305	78.38 345	77.46 365	66.66 276	69.95 319	79.00 372	48.06 312	79.24 372	66.13 236	84.83 184	86.15 324

test-mter		71.41 307	70.39 310	74.48 331	81.35 345	58.04 305	78.38 345	77.46 365	60.32 349	69.95 319	79.00 372	36.08 387	79.24 372	66.13 236	84.83 184	86.15 324

CR-MVSNet		73.37 286	71.27 299	79.67 259	81.32 347	65.19 198	75.92 364	80.30 343	59.92 353	72.73 286	81.19 348	52.50 257	86.69 319	59.84 291	77.71 281	87.11 307

RPMNet		73.51 284	70.49 307	82.58 196	81.32 347	65.19 198	75.92 364	92.27 84	57.60 373	72.73 286	76.45 388	52.30 260	95.43 70	48.14 374	77.71 281	87.11 307

V42		79.38 180	78.24 184	82.83 185	81.10 349	65.50 191	85.55 226	89.82 166	71.57 186	78.21 171	86.12 260	60.66 193	93.18 175	75.64 146	75.46 317	89.81 232

lessismore_v0				78.97 270	81.01 350	57.15 321		65.99 407		61.16 385	82.82 333	39.12 374	91.34 249	59.67 293	46.92 412	88.43 277

Patchmtry		70.74 314	69.16 317	75.49 319	80.72 351	54.07 361	74.94 375	80.30 343	58.34 366	70.01 316	81.19 348	52.50 257	86.54 321	53.37 342	71.09 360	85.87 333

PatchT		68.46 337	67.85 329	70.29 366	80.70 352	43.93 410	72.47 383	74.88 381	60.15 351	70.55 307	76.57 387	49.94 294	81.59 362	50.58 355	74.83 329	85.34 339

USDC		70.33 319	68.37 321	76.21 310	80.60 353	56.23 337	79.19 333	86.49 256	60.89 345	61.29 384	85.47 275	31.78 396	89.47 285	53.37 342	76.21 306	82.94 373

tpmrst		72.39 298	72.13 289	73.18 346	80.54 354	49.91 390	79.91 325	79.08 356	63.11 322	71.69 300	79.95 363	55.32 231	82.77 356	65.66 243	73.89 337	86.87 311

anonymousdsp		78.60 198	77.15 212	82.98 180	80.51 355	67.08 162	87.24 175	89.53 176	65.66 292	75.16 250	87.19 228	52.52 256	92.25 212	77.17 130	79.34 265	89.61 237

OpenMVS_ROB	64.09 19	70.56 317	68.19 323	77.65 295	80.26 356	59.41 295	85.01 237	82.96 311	58.76 364	65.43 363	82.33 339	37.63 383	91.23 252	45.34 389	76.03 307	82.32 377

test_fmvsmconf0.01_n		84.73 75	84.52 77	85.34 80	80.25 357	69.03 103	89.47 92	89.65 172	73.24 161	86.98 50	94.27 38	66.62 111	93.23 167	90.26 6	89.95 115	93.78 72

Anonymous20231206		68.60 333	67.80 332	71.02 363	80.23 358	50.75 387	78.30 349	80.47 339	56.79 378	66.11 360	82.63 336	46.35 325	78.95 374	43.62 392	75.70 310	83.36 366

miper_lstm_enhance		74.11 276	73.11 278	77.13 304	80.11 359	59.62 292	72.23 384	86.92 250	66.76 274	70.40 310	82.92 330	56.93 223	82.92 355	69.06 212	72.63 348	88.87 261

MIMVSNet1		68.58 334	66.78 344	73.98 337	80.07 360	51.82 377	80.77 308	84.37 282	64.40 307	59.75 391	82.16 343	36.47 385	83.63 349	42.73 394	70.33 363	86.48 319

ADS-MVSNet2		66.20 354	63.33 358	74.82 328	79.92 361	58.75 297	67.55 403	75.19 379	53.37 389	65.25 365	75.86 391	42.32 357	80.53 369	41.57 397	68.91 369	85.18 342

ADS-MVSNet		64.36 359	62.88 362	68.78 374	79.92 361	47.17 398	67.55 403	71.18 393	53.37 389	65.25 365	75.86 391	42.32 357	73.99 405	41.57 397	68.91 369	85.18 342

test_vis1_n_1920		75.52 260	75.78 236	74.75 330	79.84 363	57.44 318	83.26 276	85.52 270	62.83 328	79.34 150	86.17 259	45.10 339	79.71 371	78.75 113	81.21 240	87.10 309

D2MVS		74.82 269	73.21 276	79.64 260	79.81 364	62.56 255	80.34 318	87.35 238	64.37 308	68.86 330	82.66 335	46.37 324	90.10 272	67.91 222	81.24 239	86.25 321

our_test_3		69.14 329	67.00 342	75.57 316	79.80 365	58.80 296	77.96 352	77.81 362	59.55 356	62.90 380	78.25 379	47.43 314	83.97 346	51.71 349	67.58 374	83.93 360

ppachtmachnet_test		70.04 322	67.34 340	78.14 287	79.80 365	61.13 271	79.19 333	80.59 337	59.16 360	65.27 364	79.29 369	46.75 321	87.29 315	49.33 365	66.72 375	86.00 330

dp		66.80 346	65.43 348	70.90 365	79.74 367	48.82 394	75.12 373	74.77 382	59.61 355	64.08 373	77.23 384	42.89 353	80.72 368	48.86 368	66.58 377	83.16 368

EPMVS		69.02 330	68.16 324	71.59 356	79.61 368	49.80 392	77.40 357	66.93 405	62.82 329	70.01 316	79.05 370	45.79 332	77.86 380	56.58 326	75.26 324	87.13 306

PVSNet_0	57.27 20	61.67 366	59.27 369	68.85 373	79.61 368	57.44 318	68.01 401	73.44 388	55.93 382	58.54 394	70.41 405	44.58 342	77.55 381	47.01 378	35.91 417	71.55 405

CL-MVSNet_self_test		72.37 300	71.46 295	75.09 324	79.49 370	53.53 364	80.76 309	85.01 277	69.12 243	70.51 308	82.05 344	57.92 212	84.13 345	52.27 347	66.00 380	87.60 292

Patchmatch-test		64.82 358	63.24 359	69.57 368	79.42 371	49.82 391	63.49 415	69.05 400	51.98 394	59.95 390	80.13 361	50.91 282	70.98 409	40.66 399	73.57 340	87.90 286

MDA-MVSNet-bldmvs		66.68 347	63.66 357	75.75 313	79.28 372	60.56 281	73.92 380	78.35 360	64.43 306	50.13 410	79.87 365	44.02 347	83.67 348	46.10 384	56.86 396	83.03 371

TESTMET0.1,1		69.89 324	69.00 318	72.55 350	79.27 373	56.85 324	78.38 345	74.71 384	57.64 372	68.09 336	77.19 385	37.75 382	76.70 385	63.92 255	84.09 199	84.10 358

N_pmnet		52.79 379	53.26 377	51.40 403	78.99 374	7.68 437	69.52 395	3.89 436	51.63 395	57.01 399	74.98 395	40.83 367	65.96 418	37.78 404	64.67 383	80.56 390

UWE-MVS-28		65.32 355	64.93 349	66.49 383	78.70 375	38.55 420	77.86 355	64.39 412	62.00 339	64.13 372	83.60 318	41.44 363	76.00 393	31.39 412	80.89 243	84.92 347

dmvs_testset		62.63 363	64.11 354	58.19 393	78.55 376	24.76 431	75.28 369	65.94 408	67.91 264	60.34 387	76.01 390	53.56 249	73.94 406	31.79 411	67.65 373	75.88 400

EU-MVSNet		68.53 336	67.61 336	71.31 361	78.51 377	47.01 399	84.47 250	84.27 286	42.27 408	66.44 358	84.79 291	40.44 369	83.76 347	58.76 304	68.54 372	83.17 367

pmmvs5		71.55 306	70.20 312	75.61 315	77.83 378	56.39 333	81.74 294	80.89 332	57.76 371	67.46 342	84.49 293	49.26 304	85.32 337	57.08 320	75.29 323	85.11 345

test0.0.03 1		68.00 340	67.69 334	68.90 372	77.55 379	47.43 396	75.70 367	72.95 391	66.66 276	66.56 353	82.29 341	48.06 312	75.87 395	44.97 390	74.51 332	83.41 365

Patchmatch-RL test		70.24 320	67.78 333	77.61 296	77.43 380	59.57 294	71.16 388	70.33 394	62.94 326	68.65 332	72.77 400	50.62 286	85.49 334	69.58 207	66.58 377	87.77 289

pmmvs-eth3d		70.50 318	67.83 331	78.52 281	77.37 381	66.18 175	81.82 292	81.51 327	58.90 363	63.90 375	80.42 358	42.69 355	86.28 325	58.56 305	65.30 382	83.11 369

JIA-IIPM		66.32 351	62.82 363	76.82 306	77.09 382	61.72 267	65.34 411	75.38 378	58.04 370	64.51 369	62.32 410	42.05 361	86.51 322	51.45 352	69.22 368	82.21 378

Gipuma		45.18 388	41.86 391	55.16 400	77.03 383	51.52 380	32.50 424	80.52 338	32.46 420	27.12 423	35.02 424	9.52 427	75.50 397	22.31 421	60.21 394	38.45 423
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
MDA-MVSNet_test_wron		65.03 356	62.92 360	71.37 358	75.93 384	56.73 326	69.09 400	74.73 383	57.28 376	54.03 405	77.89 380	45.88 330	74.39 404	49.89 363	61.55 389	82.99 372

test_cas_vis1_n_1920		73.76 281	73.74 270	73.81 339	75.90 385	59.77 290	80.51 314	82.40 317	58.30 367	81.62 123	85.69 267	44.35 345	76.41 389	76.29 138	78.61 269	85.23 341

YYNet1		65.03 356	62.91 361	71.38 357	75.85 386	56.60 330	69.12 399	74.66 385	57.28 376	54.12 404	77.87 381	45.85 331	74.48 403	49.95 362	61.52 390	83.05 370

PMMVS		69.34 328	68.67 319	71.35 360	75.67 387	62.03 261	75.17 370	73.46 387	50.00 398	68.68 331	79.05 370	52.07 267	78.13 377	61.16 283	82.77 222	73.90 402

testgi		66.67 348	66.53 345	67.08 382	75.62 388	41.69 417	75.93 363	76.50 374	66.11 285	65.20 367	86.59 246	35.72 388	74.71 402	43.71 391	73.38 344	84.84 349

test20.03		67.45 342	66.95 343	68.94 371	75.48 389	44.84 408	77.50 356	77.67 363	66.66 276	63.01 378	83.80 311	47.02 318	78.40 376	42.53 396	68.86 371	83.58 364

KD-MVS_2432*1600		66.22 352	63.89 355	73.21 343	75.47 390	53.42 366	70.76 391	84.35 283	64.10 312	66.52 355	78.52 376	34.55 390	84.98 339	50.40 357	50.33 409	81.23 384

miper_refine_blended		66.22 352	63.89 355	73.21 343	75.47 390	53.42 366	70.76 391	84.35 283	64.10 312	66.52 355	78.52 376	34.55 390	84.98 339	50.40 357	50.33 409	81.23 384

Anonymous20240521		68.80 332	67.22 341	73.55 340	74.33 392	54.11 360	83.18 277	85.61 269	58.15 368	61.68 383	80.94 353	30.71 399	81.27 365	57.00 322	73.34 345	85.28 340

KD-MVS_self_test		68.81 331	67.59 337	72.46 352	74.29 393	45.45 402	77.93 353	87.00 246	63.12 321	63.99 374	78.99 374	42.32 357	84.77 342	56.55 327	64.09 385	87.16 305

mvs5depth		69.45 327	67.45 339	75.46 320	73.93 394	55.83 342	79.19 333	83.23 302	66.89 271	71.63 301	83.32 322	33.69 392	85.09 338	59.81 292	55.34 402	85.46 337

PM-MVS		66.41 350	64.14 353	73.20 345	73.92 395	56.45 331	78.97 337	64.96 411	63.88 318	64.72 368	80.24 360	19.84 416	83.44 352	66.24 235	64.52 384	79.71 392

test_fmvs1		70.93 312	70.52 306	72.16 353	73.71 396	55.05 352	80.82 305	78.77 357	51.21 397	78.58 162	84.41 296	31.20 398	76.94 384	75.88 144	80.12 257	84.47 353

UnsupCasMVSNet_bld		63.70 361	61.53 367	70.21 367	73.69 397	51.39 382	72.82 382	81.89 322	55.63 383	57.81 397	71.80 402	38.67 377	78.61 375	49.26 366	52.21 407	80.63 388

WB-MVS		54.94 373	54.72 374	55.60 399	73.50 398	20.90 433	74.27 379	61.19 416	59.16 360	50.61 408	74.15 396	47.19 317	75.78 396	17.31 424	35.07 418	70.12 406

UnsupCasMVSNet_eth		67.33 343	65.99 347	71.37 358	73.48 399	51.47 381	75.16 371	85.19 273	65.20 297	60.78 386	80.93 355	42.35 356	77.20 382	57.12 319	53.69 404	85.44 338

TDRefinement		67.49 341	64.34 352	76.92 305	73.47 400	61.07 273	84.86 241	82.98 310	59.77 354	58.30 395	85.13 283	26.06 404	87.89 310	47.92 376	60.59 393	81.81 382

dongtai		45.42 387	45.38 388	45.55 405	73.36 401	26.85 429	67.72 402	34.19 431	54.15 387	49.65 411	56.41 418	25.43 405	62.94 421	19.45 422	28.09 422	46.86 421

ambc				75.24 323	73.16 402	50.51 388	63.05 416	87.47 236		64.28 370	77.81 382	17.80 418	89.73 280	57.88 313	60.64 392	85.49 336

CMPMVS	51.72 21	70.19 321	68.16 324	76.28 309	73.15 403	57.55 316	79.47 328	83.92 290	48.02 401	56.48 401	84.81 290	43.13 352	86.42 324	62.67 266	81.81 235	84.89 348
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
SSC-MVS		53.88 376	53.59 376	54.75 401	72.87 404	19.59 434	73.84 381	60.53 418	57.58 374	49.18 412	73.45 399	46.34 326	75.47 399	16.20 427	32.28 420	69.20 407

new-patchmatchnet		61.73 365	61.73 366	61.70 389	72.74 405	24.50 432	69.16 398	78.03 361	61.40 342	56.72 400	75.53 394	38.42 378	76.48 388	45.95 385	57.67 395	84.13 357

test_vis1_n		69.85 325	69.21 316	71.77 355	72.66 406	55.27 351	81.48 298	76.21 376	52.03 393	75.30 246	83.20 325	28.97 401	76.22 391	74.60 156	78.41 275	83.81 361

test_fmvs1_n		70.86 313	70.24 311	72.73 349	72.51 407	55.28 350	81.27 302	79.71 349	51.49 396	78.73 157	84.87 288	27.54 403	77.02 383	76.06 141	79.97 258	85.88 332

LF4IMVS		64.02 360	62.19 364	69.50 369	70.90 408	53.29 369	76.13 361	77.18 370	52.65 391	58.59 393	80.98 352	23.55 411	76.52 387	53.06 344	66.66 376	78.68 394

mvsany_test1		62.30 364	61.26 368	65.41 385	69.52 409	54.86 354	66.86 405	49.78 425	46.65 402	68.50 335	83.21 324	49.15 305	66.28 417	56.93 323	60.77 391	75.11 401

test_fmvs2		68.35 338	67.48 338	70.98 364	69.50 410	51.95 374	80.05 322	76.38 375	49.33 399	74.65 262	84.38 297	23.30 412	75.40 400	74.51 157	75.17 326	85.60 335

new_pmnet		50.91 382	50.29 382	52.78 402	68.58 411	34.94 424	63.71 413	56.63 422	39.73 411	44.95 413	65.47 408	21.93 413	58.48 422	34.98 408	56.62 397	64.92 410

DSMNet-mixed		57.77 371	56.90 373	60.38 391	67.70 412	35.61 422	69.18 397	53.97 423	32.30 421	57.49 398	79.88 364	40.39 370	68.57 415	38.78 403	72.37 349	76.97 397

test_vis1_rt		60.28 367	58.42 370	65.84 384	67.25 413	55.60 346	70.44 393	60.94 417	44.33 406	59.00 392	66.64 407	24.91 407	68.67 414	62.80 262	69.48 365	73.25 403

ttmdpeth		59.91 368	57.10 372	68.34 377	67.13 414	46.65 401	74.64 376	67.41 404	48.30 400	62.52 382	85.04 287	20.40 414	75.93 394	42.55 395	45.90 415	82.44 376

APD_test1		53.31 378	49.93 383	63.42 388	65.68 415	50.13 389	71.59 387	66.90 406	34.43 418	40.58 417	71.56 403	8.65 429	76.27 390	34.64 409	55.36 401	63.86 412

FPMVS		53.68 377	51.64 379	59.81 392	65.08 416	51.03 384	69.48 396	69.58 398	41.46 409	40.67 416	72.32 401	16.46 420	70.00 413	24.24 420	65.42 381	58.40 416

kuosan		39.70 391	40.40 392	37.58 408	64.52 417	26.98 427	65.62 410	33.02 432	46.12 403	42.79 415	48.99 421	24.10 410	46.56 429	12.16 430	26.30 423	39.20 422

pmmvs3		57.79 370	54.26 375	68.37 376	64.02 418	56.72 327	75.12 373	65.17 409	40.20 410	52.93 406	69.86 406	20.36 415	75.48 398	45.45 388	55.25 403	72.90 404

test_fmvs3		63.36 362	61.82 365	67.98 379	62.51 419	46.96 400	77.37 358	74.03 386	45.24 404	67.50 341	78.79 375	12.16 424	72.98 408	72.77 177	66.02 379	83.99 359

MVStest1		56.63 372	52.76 378	68.25 378	61.67 420	53.25 370	71.67 386	68.90 402	38.59 413	50.59 409	83.05 327	25.08 406	70.66 410	36.76 406	38.56 416	80.83 387

wuyk23d		16.82 398	15.94 401	19.46 412	58.74 421	31.45 425	39.22 422	3.74 437	6.84 428	6.04 431	2.70 431	1.27 436	24.29 431	10.54 431	14.40 430	2.63 428

testf1		45.72 385	41.96 389	57.00 394	56.90 422	45.32 403	66.14 408	59.26 419	26.19 422	30.89 421	60.96 413	4.14 432	70.64 411	26.39 418	46.73 413	55.04 417

APD_test2		45.72 385	41.96 389	57.00 394	56.90 422	45.32 403	66.14 408	59.26 419	26.19 422	30.89 421	60.96 413	4.14 432	70.64 411	26.39 418	46.73 413	55.04 417

mvsany_test3		53.99 375	51.45 380	61.61 390	55.51 424	44.74 409	63.52 414	45.41 429	43.69 407	58.11 396	76.45 388	17.99 417	63.76 420	54.77 334	47.59 411	76.34 399

test_vis3_rt		49.26 384	47.02 386	56.00 396	54.30 425	45.27 406	66.76 407	48.08 426	36.83 415	44.38 414	53.20 419	7.17 431	64.07 419	56.77 325	55.66 399	58.65 415

PMMVS2		40.82 390	38.86 394	46.69 404	53.84 426	16.45 435	48.61 421	49.92 424	37.49 414	31.67 419	60.97 412	8.14 430	56.42 424	28.42 415	30.72 421	67.19 409

test_f		52.09 380	50.82 381	55.90 397	53.82 427	42.31 416	59.42 417	58.31 421	36.45 416	56.12 403	70.96 404	12.18 423	57.79 423	53.51 341	56.57 398	67.60 408

LCM-MVSNet		54.25 374	49.68 384	67.97 380	53.73 428	45.28 405	66.85 406	80.78 334	35.96 417	39.45 418	62.23 411	8.70 428	78.06 379	48.24 373	51.20 408	80.57 389

E-PMN		31.77 392	30.64 395	35.15 409	52.87 429	27.67 426	57.09 419	47.86 427	24.64 424	16.40 429	33.05 425	11.23 425	54.90 425	14.46 428	18.15 426	22.87 425

EMVS		30.81 394	29.65 396	34.27 410	50.96 430	25.95 430	56.58 420	46.80 428	24.01 425	15.53 430	30.68 426	12.47 422	54.43 426	12.81 429	17.05 427	22.43 426

ANet_high		50.57 383	46.10 387	63.99 386	48.67 431	39.13 419	70.99 390	80.85 333	61.39 343	31.18 420	57.70 416	17.02 419	73.65 407	31.22 413	15.89 428	79.18 393

MVE	26.22 23	30.37 395	25.89 399	43.81 406	44.55 432	35.46 423	28.87 425	39.07 430	18.20 426	18.58 428	40.18 423	2.68 435	47.37 428	17.07 426	23.78 425	48.60 420
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
PMVS	37.38 22	44.16 389	40.28 393	55.82 398	40.82 433	42.54 415	65.12 412	63.99 413	34.43 418	24.48 424	57.12 417	3.92 434	76.17 392	17.10 425	55.52 400	48.75 419
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
DeepMVS_CX				27.40 411	40.17 434	26.90 428		24.59 435	17.44 427	23.95 425	48.61 422	9.77 426	26.48 430	18.06 423	24.47 424	28.83 424

test_method		31.52 393	29.28 397	38.23 407	27.03 435	6.50 438	20.94 426	62.21 415	4.05 429	22.35 427	52.50 420	13.33 421	47.58 427	27.04 417	34.04 419	60.62 413

tmp_tt		18.61 397	21.40 400	10.23 413	4.82 436	10.11 436	34.70 423	30.74 434	1.48 430	23.91 426	26.07 427	28.42 402	13.41 432	27.12 416	15.35 429	7.17 427

testmvs		6.04 401	8.02 404	0.10 415	0.08 437	0.03 440	69.74 394	0.04 438	0.05 432	0.31 433	1.68 432	0.02 438	0.04 433	0.24 432	0.02 431	0.25 430

test123		6.12 400	8.11 403	0.14 414	0.06 438	0.09 439	71.05 389	0.03 439	0.04 433	0.25 434	1.30 433	0.05 437	0.03 434	0.21 433	0.01 432	0.29 429

mmdepth		0.00 403	0.00 406	0.00 416	0.00 439	0.00 441	0.00 427	0.00 440	0.00 434	0.00 435	0.00 434	0.00 439	0.00 435	0.00 434	0.00 433	0.00 431

monomultidepth		0.00 403	0.00 406	0.00 416	0.00 439	0.00 441	0.00 427	0.00 440	0.00 434	0.00 435	0.00 434	0.00 439	0.00 435	0.00 434	0.00 433	0.00 431

test_blank		0.00 403	0.00 406	0.00 416	0.00 439	0.00 441	0.00 427	0.00 440	0.00 434	0.00 435	0.00 434	0.00 439	0.00 435	0.00 434	0.00 433	0.00 431

eth-test2					0.00 439

eth-test					0.00 439

uanet_test		0.00 403	0.00 406	0.00 416	0.00 439	0.00 441	0.00 427	0.00 440	0.00 434	0.00 435	0.00 434	0.00 439	0.00 435	0.00 434	0.00 433	0.00 431

DCPMVS		0.00 403	0.00 406	0.00 416	0.00 439	0.00 441	0.00 427	0.00 440	0.00 434	0.00 435	0.00 434	0.00 439	0.00 435	0.00 434	0.00 433	0.00 431

cdsmvs_eth3d_5k		19.96 396	26.61 398	0.00 416	0.00 439	0.00 441	0.00 427	89.26 186	0.00 434	0.00 435	88.61 187	61.62 172	0.00 435	0.00 434	0.00 433	0.00 431

pcd_1.5k_mvsjas		5.26 402	7.02 405	0.00 416	0.00 439	0.00 441	0.00 427	0.00 440	0.00 434	0.00 435	0.00 434	63.15 148	0.00 435	0.00 434	0.00 433	0.00 431

sosnet-low-res		0.00 403	0.00 406	0.00 416	0.00 439	0.00 441	0.00 427	0.00 440	0.00 434	0.00 435	0.00 434	0.00 439	0.00 435	0.00 434	0.00 433	0.00 431

sosnet		0.00 403	0.00 406	0.00 416	0.00 439	0.00 441	0.00 427	0.00 440	0.00 434	0.00 435	0.00 434	0.00 439	0.00 435	0.00 434	0.00 433	0.00 431

uncertanet		0.00 403	0.00 406	0.00 416	0.00 439	0.00 441	0.00 427	0.00 440	0.00 434	0.00 435	0.00 434	0.00 439	0.00 435	0.00 434	0.00 433	0.00 431

Regformer		0.00 403	0.00 406	0.00 416	0.00 439	0.00 441	0.00 427	0.00 440	0.00 434	0.00 435	0.00 434	0.00 439	0.00 435	0.00 434	0.00 433	0.00 431

ab-mvs-re		7.23 399	9.64 402	0.00 416	0.00 439	0.00 441	0.00 427	0.00 440	0.00 434	0.00 435	86.72 238	0.00 439	0.00 435	0.00 434	0.00 433	0.00 431

uanet		0.00 403	0.00 406	0.00 416	0.00 439	0.00 441	0.00 427	0.00 440	0.00 434	0.00 435	0.00 434	0.00 439	0.00 435	0.00 434	0.00 433	0.00 431

WAC-MVS						42.58 413								39.46 401

PC_three_1452									68.21 261	92.02 12	94.00 53	82.09 5	95.98 56	84.58 57	96.68 2	94.95 11

test_241102_TWO								94.06 10	77.24 55	92.78 4	95.72 8	81.26 8	97.44 7	89.07 17	96.58 6	94.26 48

test_0728_THIRD									78.38 34	92.12 9	95.78 4	81.46 7	97.40 9	89.42 12	96.57 7	94.67 28

GSMVS																88.96 258

sam_mvs1												51.32 278				88.96 258

sam_mvs												50.01 292

MTGPA								92.02 93

test_post1							78.90 339				5.43 430	48.81 311	85.44 336	59.25 297

test_post											5.46 429	50.36 290	84.24 344

patchmatchnet-post											74.00 397	51.12 281	88.60 302

MTMP							92.18 34	32.83 433

test9_res														84.90 50	95.70 26	92.87 116

agg_prior2														82.91 77	95.45 29	92.70 119

test_prior4						72.60 34	89.01 113

test_prior2							88.85 119		75.41 100	84.91 69	93.54 63	74.28 29		83.31 71	95.86 20

旧先验2							86.56 198		58.10 369	87.04 49			88.98 294	74.07 162

新几何2							86.29 207

无先验							87.48 165	88.98 198	60.00 352				94.12 125	67.28 228		88.97 257

原ACMM2							86.86 187

testdata2													91.01 260	62.37 269

segment_acmp												73.08 39

testdata1							84.14 261		75.71 94

plane_prior5								92.44 77					95.38 75	78.71 114	86.32 167	91.33 165

plane_prior4											91.00 134

plane_prior3						68.60 121			78.44 32	78.92 155

plane_prior2							91.25 52		79.12 24

plane_prior						68.71 116	90.38 70		77.62 42						86.16 171

n2								0.00 440

nn								0.00 440

door-mid								69.98 396

test11								92.23 87

door								69.44 399

HQP5-MVS						66.98 164

BP-MVS														77.47 126

HQP4-MVS										77.24 192			95.11 87			91.03 175

HQP3-MVS								92.19 90							85.99 175

HQP2-MVS												60.17 201

MDTV_nov1_ep13_2view						37.79 421	75.16 371		55.10 384	66.53 354		49.34 302		53.98 338		87.94 285

ACMMP++_ref															81.95 233

ACMMP++															81.25 238

Test By Simon												64.33 135

High-resolution multi-view benchmark