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.

MCST-MVS		91.08 1	91.46 2	89.94 4	97.66 2	73.37 8	97.13 2	95.58 10	89.33 1	85.77 51	96.26 30	72.84 26	99.38 1	92.64 19	95.93 9	97.08 9

DVP-MVS++		90.53 3	91.09 4	88.87 14	97.31 4	69.91 37	93.96 70	94.37 46	72.48 175	92.07 8	96.85 16	83.82 2	99.15 2	91.53 29	97.42 4	97.55 4

OPU-MVS				89.97 3	97.52 3	73.15 12	96.89 5				97.00 9	83.82 2	99.15 2	95.72 5	97.63 3	97.62 2

test_0728_SECOND				88.70 16	96.45 12	70.43 29	96.64 9	94.37 46					99.15 2	91.91 27	94.90 21	96.51 21

PC_three_1452									80.91 45	94.07 2	96.83 18	83.57 4	99.12 5	95.70 7	97.42 4	97.55 4

SED-MVS		89.94 8	90.36 9	88.70 16	96.45 12	69.38 47	96.89 5	94.44 40	71.65 204	92.11 6	97.21 4	76.79 9	99.11 6	92.34 21	95.36 13	97.62 2

test_241102_TWO								94.41 42	71.65 204	92.07 8	97.21 4	74.58 17	99.11 6	92.34 21	95.36 13	96.59 16

test_241102_ONE					96.45 12	69.38 47		94.44 40	71.65 204	92.11 6	97.05 7	76.79 9	99.11 6

DPM-MVS		90.70 2	90.52 7	91.24 1	89.68 144	76.68 2	97.29 1	95.35 12	82.87 20	91.58 12	97.22 3	79.93 5	99.10 9	83.12 92	97.64 2	97.94 1

CANet		89.61 11	89.99 11	88.46 21	94.39 39	69.71 43	96.53 12	93.78 59	86.89 6	89.68 27	95.78 40	65.94 61	99.10 9	92.99 16	93.91 40	96.58 18

DVP-MVS		89.41 12	89.73 13	88.45 22	96.40 15	69.99 33	96.64 9	94.52 36	71.92 191	90.55 19	96.93 11	73.77 21	99.08 11	91.91 27	94.90 21	96.29 30
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_THIRD									72.48 175	90.55 19	96.93 11	76.24 11	99.08 11	91.53 29	94.99 17	96.43 26

MSC_two_6792asdad				89.60 8	97.31 4	73.22 10		95.05 21					99.07 13	92.01 24	94.77 25	96.51 21

No_MVS				89.60 8	97.31 4	73.22 10		95.05 21					99.07 13	92.01 24	94.77 25	96.51 21

CNVR-MVS		90.32 5	90.89 6	88.61 19	96.76 8	70.65 26	96.47 13	94.83 25	84.83 11	89.07 31	96.80 19	70.86 34	99.06 15	92.64 19	95.71 10	96.12 35

QAPM		79.95 153	77.39 179	87.64 30	89.63 145	71.41 17	93.30 101	93.70 66	65.34 282	67.39 255	91.75 142	47.83 259	98.96 16	57.71 286	89.81 93	92.54 161

MM				88.92 13		71.10 22	97.02 3	96.04 6	88.70 2	91.57 13	96.19 33	70.12 36	98.91 17	96.83 1	95.06 16	96.76 12

DELS-MVS		90.05 6	90.09 10	89.94 4	93.14 66	73.88 7	97.01 4	94.40 44	88.32 3	85.71 52	94.91 68	74.11 19	98.91 17	87.26 59	95.94 8	97.03 10
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
MVS		84.66 68	82.86 94	90.06 2	90.93 120	74.56 6	87.91 268	95.54 11	68.55 256	72.35 190	94.71 73	59.78 135	98.90 19	81.29 108	94.69 31	96.74 13

API-MVS		82.28 111	80.53 129	87.54 35	96.13 22	70.59 27	93.63 90	91.04 180	65.72 279	75.45 154	92.83 122	56.11 177	98.89 20	64.10 249	89.75 96	93.15 143

MAR-MVS		84.18 78	83.43 80	86.44 66	96.25 21	65.93 135	94.28 55	94.27 50	74.41 133	79.16 113	95.61 45	53.99 201	98.88 21	69.62 196	93.26 52	94.50 100
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
PHI-MVS		86.83 36	86.85 39	86.78 55	93.47 57	65.55 144	95.39 30	95.10 18	71.77 201	85.69 53	96.52 23	62.07 110	98.77 22	86.06 70	95.60 11	96.03 38

NCCC		89.07 14	89.46 14	87.91 25	96.60 10	69.05 56	96.38 15	94.64 33	84.42 12	86.74 43	96.20 32	66.56 57	98.76 23	89.03 46	94.56 32	95.92 41

MVS_0304		90.01 7	90.50 8	88.53 20	90.14 135	70.94 23	96.47 13	95.72 9	87.33 4	89.60 28	96.26 30	68.44 40	98.74 24	95.82 4	94.72 30	95.90 42

DeepPCF-MVS	81.17 1	89.72 9	91.38 3	84.72 123	93.00 69	58.16 295	96.72 8	94.41 42	86.50 8	90.25 21	97.83 1	75.46 14	98.67 25	92.78 18	95.49 12	97.32 6

HPM-MVS++		89.37 13	89.95 12	87.64 30	95.10 30	68.23 77	95.24 33	94.49 38	82.43 25	88.90 32	96.35 27	71.89 33	98.63 26	88.76 47	96.40 6	96.06 36

CHOSEN 1792x2688		84.98 64	83.45 79	89.57 10	89.94 139	75.14 5	92.07 148	92.32 117	81.87 31	75.68 149	88.27 194	60.18 129	98.60 27	80.46 113	90.27 91	94.96 77

3Dnovator	73.91 6	82.69 107	80.82 122	88.31 23	89.57 146	71.26 18	92.60 128	94.39 45	78.84 77	67.89 247	92.48 129	48.42 252	98.52 28	68.80 206	94.40 34	95.15 71

DPE-MVS		88.77 15	89.21 15	87.45 37	96.26 20	67.56 93	94.17 57	94.15 53	68.77 254	90.74 17	97.27 2	76.09 12	98.49 29	90.58 37	94.91 20	96.30 29
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
CSCG		86.87 34	86.26 42	88.72 15	95.05 31	70.79 25	93.83 82	95.33 13	68.48 258	77.63 130	94.35 86	73.04 24	98.45 30	84.92 79	93.71 45	96.92 11

DeepC-MVS	77.85 3	85.52 57	85.24 57	86.37 69	88.80 168	66.64 117	92.15 142	93.68 67	81.07 43	76.91 140	93.64 104	62.59 105	98.44 31	85.50 72	92.84 57	94.03 117
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
DeepC-MVS_fast	79.48 2	87.95 20	88.00 23	87.79 28	95.86 27	68.32 72	95.74 21	94.11 54	83.82 15	83.49 73	96.19 33	64.53 79	98.44 31	83.42 91	94.88 24	96.61 15
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
SMA-MVS		88.14 16	88.29 20	87.67 29	93.21 63	68.72 64	93.85 77	94.03 55	74.18 138	91.74 11	96.67 21	65.61 65	98.42 33	89.24 43	96.08 7	95.88 43
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
TSAR-MVS + GP.		87.96 19	88.37 19	86.70 57	93.51 56	65.32 148	95.15 36	93.84 58	78.17 85	85.93 50	94.80 71	75.80 13	98.21 34	89.38 40	88.78 101	96.59 16

DP-MVS Recon		82.73 104	81.65 111	85.98 77	97.31 4	67.06 106	95.15 36	91.99 131	69.08 251	76.50 144	93.89 99	54.48 196	98.20 35	70.76 185	85.66 133	92.69 156

MVS_111021_HR		86.19 45	85.80 52	87.37 38	93.17 65	69.79 40	93.99 69	93.76 62	79.08 72	78.88 118	93.99 97	62.25 109	98.15 36	85.93 71	91.15 82	94.15 110

OpenMVS	70.45 11	78.54 180	75.92 198	86.41 68	85.93 235	71.68 16	92.74 119	92.51 114	66.49 273	64.56 277	91.96 138	43.88 285	98.10 37	54.61 295	90.65 87	89.44 218

ZNCC-MVS		85.33 59	85.08 60	86.06 75	93.09 68	65.65 140	93.89 75	93.41 80	73.75 149	79.94 103	94.68 74	60.61 126	98.03 38	82.63 95	93.72 44	94.52 98

test_fmvsm_n_1920		87.69 24	88.50 17	85.27 103	87.05 214	63.55 200	93.69 87	91.08 176	84.18 13	90.17 23	97.04 8	67.58 49	97.99 39	95.72 5	90.03 92	94.26 104

SteuartSystems-ACMMP		86.82 37	86.90 37	86.58 61	90.42 129	66.38 123	96.09 17	93.87 57	77.73 92	84.01 71	95.66 43	63.39 95	97.94 40	87.40 57	93.55 48	95.42 53
Skip Steuart: Steuart Systems R&D Blog.
ACMMP_NAP		86.05 47	85.80 52	86.80 54	91.58 106	67.53 95	91.79 162	93.49 76	74.93 129	84.61 63	95.30 53	59.42 139	97.92 41	86.13 68	94.92 19	94.94 79

EI-MVSNet-Vis-set		83.77 87	83.67 73	84.06 148	92.79 76	63.56 199	91.76 165	94.81 26	79.65 60	77.87 127	94.09 94	63.35 97	97.90 42	79.35 119	79.36 179	90.74 197

PS-MVSNAJ		88.14 16	87.61 27	89.71 6	92.06 90	76.72 1	95.75 20	93.26 83	83.86 14	89.55 29	96.06 36	53.55 206	97.89 43	91.10 31	93.31 51	94.54 96

9.14			87.63 26		93.86 47		94.41 52	94.18 51	72.76 170	86.21 46	96.51 24	66.64 55	97.88 44	90.08 38	94.04 37

GST-MVS		84.63 69	84.29 69	85.66 90	92.82 73	65.27 149	93.04 109	93.13 90	73.20 158	78.89 115	94.18 93	59.41 140	97.85 45	81.45 104	92.48 61	93.86 125

fmvsm_s_conf0.5_n		86.39 41	86.91 36	84.82 116	87.36 207	63.54 201	94.74 47	90.02 215	82.52 24	90.14 24	96.92 13	62.93 103	97.84 46	95.28 8	82.26 154	93.07 147

SF-MVS		87.03 33	87.09 33	86.84 51	92.70 77	67.45 98	93.64 89	93.76 62	70.78 228	86.25 45	96.44 26	66.98 52	97.79 47	88.68 48	94.56 32	95.28 65

EI-MVSNet-UG-set		83.14 98	82.96 90	83.67 159	92.28 85	63.19 208	91.38 181	94.68 31	79.22 67	76.60 142	93.75 100	62.64 104	97.76 48	78.07 132	78.01 190	90.05 206

fmvsm_s_conf0.1_n		85.61 56	85.93 49	84.68 126	82.95 281	63.48 203	94.03 68	89.46 233	81.69 33	89.86 25	96.74 20	61.85 113	97.75 49	94.74 9	82.01 158	92.81 155

xiu_mvs_v2_base		87.92 21	87.38 31	89.55 11	91.41 113	76.43 3	95.74 21	93.12 91	83.53 17	89.55 29	95.95 38	53.45 210	97.68 50	91.07 32	92.62 58	94.54 96

fmvsm_s_conf0.5_n_a		85.75 52	86.09 46	84.72 123	85.73 238	63.58 198	93.79 83	89.32 239	81.42 39	90.21 22	96.91 14	62.41 107	97.67 51	94.48 10	80.56 171	92.90 153

HFP-MVS		84.73 67	84.40 68	85.72 88	93.75 51	65.01 157	93.50 96	93.19 87	72.19 185	79.22 112	94.93 66	59.04 144	97.67 51	81.55 102	92.21 62	94.49 101

IB-MVS	77.80 4	82.18 112	80.46 131	87.35 39	89.14 160	70.28 31	95.59 26	95.17 17	78.85 76	70.19 214	85.82 231	70.66 35	97.67 51	72.19 174	66.52 277	94.09 113
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
APDe-MVS		87.54 25	87.84 24	86.65 58	96.07 23	66.30 126	94.84 45	93.78 59	69.35 245	88.39 33	96.34 28	67.74 48	97.66 54	90.62 36	93.44 49	96.01 39
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
3Dnovator+	73.60 7	82.10 116	80.60 128	86.60 59	90.89 122	66.80 114	95.20 34	93.44 78	74.05 140	67.42 253	92.49 128	49.46 242	97.65 55	70.80 184	91.68 72	95.33 59

SD-MVS		87.49 26	87.49 29	87.50 36	93.60 53	68.82 62	93.90 74	92.63 110	76.86 104	87.90 35	95.76 41	66.17 58	97.63 56	89.06 45	91.48 76	96.05 37
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
WTY-MVS		86.32 42	85.81 51	87.85 26	92.82 73	69.37 49	95.20 34	95.25 14	82.71 22	81.91 84	94.73 72	67.93 47	97.63 56	79.55 117	82.25 155	96.54 19

PAPR		85.15 61	84.47 66	87.18 42	96.02 25	68.29 73	91.85 160	93.00 96	76.59 111	79.03 114	95.00 63	61.59 116	97.61 58	78.16 131	89.00 100	95.63 48

test_fmvsmvis_n_1920		83.80 86	83.48 77	84.77 120	82.51 283	63.72 191	91.37 182	83.99 330	81.42 39	77.68 129	95.74 42	58.37 148	97.58 59	93.38 14	86.87 119	93.00 150

patch_mono-2		89.71 10	90.99 5	85.85 83	96.04 24	63.70 193	95.04 40	95.19 15	86.74 7	91.53 14	95.15 62	73.86 20	97.58 59	93.38 14	92.00 67	96.28 32

fmvsm_s_conf0.1_n_a		84.76 66	84.84 65	84.53 132	80.23 307	63.50 202	92.79 117	88.73 268	80.46 49	89.84 26	96.65 22	60.96 122	97.57 61	93.80 13	80.14 173	92.53 162

test12				87.09 45	94.60 36	68.86 60		92.91 98		82.67 81		65.44 66	97.55 62		93.69 46	94.84 83

region2R		84.36 72	84.03 71	85.36 99	93.54 55	64.31 176	93.43 99	92.95 97	72.16 188	78.86 119	94.84 70	56.97 165	97.53 63	81.38 106	92.11 65	94.24 105

PAPM_NR		82.97 101	81.84 109	86.37 69	94.10 44	66.76 115	87.66 273	92.84 100	69.96 238	74.07 168	93.57 106	63.10 101	97.50 64	70.66 187	90.58 88	94.85 80

ACMMPR		84.37 71	84.06 70	85.28 102	93.56 54	64.37 173	93.50 96	93.15 89	72.19 185	78.85 120	94.86 69	56.69 170	97.45 65	81.55 102	92.20 63	94.02 118

test_yl		84.28 74	83.16 87	87.64 30	94.52 37	69.24 51	95.78 18	95.09 19	69.19 248	81.09 91	92.88 120	57.00 163	97.44 66	81.11 109	81.76 160	96.23 33

DCV-MVSNet		84.28 74	83.16 87	87.64 30	94.52 37	69.24 51	95.78 18	95.09 19	69.19 248	81.09 91	92.88 120	57.00 163	97.44 66	81.11 109	81.76 160	96.23 33

XVS		83.87 84	83.47 78	85.05 108	93.22 61	63.78 187	92.92 114	92.66 107	73.99 141	78.18 124	94.31 89	55.25 184	97.41 68	79.16 121	91.58 74	93.95 120

X-MVStestdata		76.86 204	74.13 224	85.05 108	93.22 61	63.78 187	92.92 114	92.66 107	73.99 141	78.18 124	10.19 398	55.25 184	97.41 68	79.16 121	91.58 74	93.95 120

gm-plane-assit					88.42 176	67.04 108			78.62 81		91.83 140		97.37 70	76.57 139

CDPH-MVS		85.71 53	85.46 55	86.46 65	94.75 34	67.19 102	93.89 75	92.83 101	70.90 224	83.09 76	95.28 54	63.62 91	97.36 71	80.63 111	94.18 35	94.84 83

AdaColmap		78.94 169	77.00 185	84.76 121	96.34 17	65.86 136	92.66 126	87.97 292	62.18 307	70.56 207	92.37 132	43.53 286	97.35 72	64.50 247	82.86 150	91.05 195

EPNet		87.84 22	88.38 18	86.23 73	93.30 60	66.05 130	95.26 32	94.84 24	87.09 5	88.06 34	94.53 77	66.79 54	97.34 73	83.89 88	91.68 72	95.29 63
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
Anonymous20240529		76.84 207	74.15 223	84.88 114	91.02 118	64.95 159	93.84 80	91.09 174	53.57 349	73.00 175	87.42 211	35.91 328	97.32 74	69.14 202	72.41 238	92.36 165

PGM-MVS		83.25 96	82.70 97	84.92 112	92.81 75	64.07 182	90.44 213	92.20 124	71.28 216	77.23 136	94.43 80	55.17 188	97.31 75	79.33 120	91.38 78	93.37 136

ZD-MVS					96.63 9	65.50 146		93.50 75	70.74 229	85.26 59	95.19 61	64.92 73	97.29 76	87.51 55	93.01 54

Anonymous202405211		77.96 189	75.33 207	85.87 81	93.73 52	64.52 163	94.85 44	85.36 316	62.52 305	76.11 145	90.18 169	29.43 353	97.29 76	68.51 208	77.24 202	95.81 45

PVSNet_BlendedMVS		83.38 93	83.43 80	83.22 170	93.76 49	67.53 95	94.06 63	93.61 69	79.13 70	81.00 94	85.14 236	63.19 99	97.29 76	87.08 61	73.91 225	84.83 296

PVSNet_Blended		86.73 38	86.86 38	86.31 72	93.76 49	67.53 95	96.33 16	93.61 69	82.34 27	81.00 94	93.08 113	63.19 99	97.29 76	87.08 61	91.38 78	94.13 111

TEST9					94.18 41	67.28 100	94.16 58	93.51 73	71.75 202	85.52 54	95.33 51	68.01 45	97.27 80

train_agg		87.21 31	87.42 30	86.60 59	94.18 41	67.28 100	94.16 58	93.51 73	71.87 196	85.52 54	95.33 51	68.19 43	97.27 80	89.09 44	94.90 21	95.25 69

MSP-MVS		90.38 4	91.87 1	85.88 80	92.83 71	64.03 183	93.06 107	94.33 48	82.19 28	93.65 3	96.15 35	85.89 1	97.19 82	91.02 33	97.75 1	96.43 26
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
fmvsm_l_conf0.5_n_a		87.44 28	88.15 22	85.30 101	87.10 212	64.19 180	94.41 52	88.14 286	80.24 52	92.54 5	96.97 10	69.52 39	97.17 83	95.89 2	88.51 104	94.56 93

MP-MVS		85.02 62	84.97 62	85.17 107	92.60 81	64.27 178	93.24 102	92.27 119	73.13 160	79.63 107	94.43 80	61.90 111	97.17 83	85.00 77	92.56 59	94.06 116
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
MTAPA		83.91 83	83.38 84	85.50 93	91.89 99	65.16 153	81.75 317	92.23 120	75.32 124	80.53 98	95.21 60	56.06 178	97.16 85	84.86 80	92.55 60	94.18 107

fmvsm_l_conf0.5_n		87.49 26	88.19 21	85.39 97	86.95 215	64.37 173	94.30 54	88.45 277	80.51 48	92.70 4	96.86 15	69.98 37	97.15 86	95.83 3	88.08 108	94.65 90

h-mvs33		83.01 100	82.56 100	84.35 140	89.34 151	62.02 233	92.72 120	93.76 62	81.45 36	82.73 79	92.25 135	60.11 130	97.13 87	87.69 53	62.96 304	93.91 122

VDD-MVS		83.06 99	81.81 110	86.81 53	90.86 123	67.70 89	95.40 29	91.50 157	75.46 121	81.78 85	92.34 133	40.09 298	97.13 87	86.85 64	82.04 157	95.60 49

FA-MVS(test-final)		79.12 165	77.23 181	84.81 119	90.54 127	63.98 184	81.35 323	91.71 147	71.09 221	74.85 159	82.94 260	52.85 213	97.05 89	67.97 211	81.73 162	93.41 135

LFMVS		84.34 73	82.73 96	89.18 12	94.76 33	73.25 9	94.99 42	91.89 137	71.90 193	82.16 83	93.49 108	47.98 257	97.05 89	82.55 96	84.82 137	97.25 7

sss		82.71 106	82.38 103	83.73 156	89.25 155	59.58 278	92.24 139	94.89 23	77.96 87	79.86 104	92.38 131	56.70 169	97.05 89	77.26 136	80.86 168	94.55 94

1314		80.70 137	78.95 154	85.94 79	87.77 199	67.56 93	87.91 268	92.55 113	72.17 187	67.44 252	93.09 112	50.27 235	97.04 92	71.68 179	87.64 112	93.23 141

无先验							92.71 121	92.61 111	62.03 309				97.01 93	66.63 224		93.97 119

MP-MVS-pluss		85.24 60	85.13 59	85.56 92	91.42 111	65.59 142	91.54 172	92.51 114	74.56 132	80.62 97	95.64 44	59.15 143	97.00 94	86.94 63	93.80 41	94.07 115
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
VNet		86.20 44	85.65 54	87.84 27	93.92 46	69.99 33	95.73 23	95.94 7	78.43 82	86.00 49	93.07 114	58.22 150	97.00 94	85.22 74	84.33 142	96.52 20

APD-MVS		85.93 49	85.99 48	85.76 87	95.98 26	65.21 151	93.59 92	92.58 112	66.54 272	86.17 47	95.88 39	63.83 86	97.00 94	86.39 67	92.94 55	95.06 73
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
mPP-MVS		82.96 102	82.44 102	84.52 133	92.83 71	62.92 216	92.76 118	91.85 141	71.52 212	75.61 152	94.24 91	53.48 209	96.99 97	78.97 124	90.73 85	93.64 131

test_fmvsmconf_n		86.58 39	87.17 32	84.82 116	85.28 244	62.55 223	94.26 56	89.78 221	83.81 16	87.78 36	96.33 29	65.33 67	96.98 98	94.40 11	87.55 113	94.95 78

CANet_DTU		84.09 80	83.52 74	85.81 84	90.30 132	66.82 112	91.87 158	89.01 256	85.27 9	86.09 48	93.74 101	47.71 261	96.98 98	77.90 133	89.78 95	93.65 130

PVSNet_Blended_VisFu		83.97 82	83.50 76	85.39 97	90.02 137	66.59 120	93.77 84	91.73 145	77.43 100	77.08 139	89.81 176	63.77 88	96.97 100	79.67 116	88.21 106	92.60 159

ACMMP		81.49 124	80.67 125	83.93 151	91.71 103	62.90 217	92.13 143	92.22 123	71.79 200	71.68 198	93.49 108	50.32 233	96.96 101	78.47 129	84.22 146	91.93 178
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_8					94.19 40	67.19 102	94.15 61	93.42 79	71.87 196	85.38 57	95.35 50	68.19 43	96.95 102

HY-MVS	76.49 5	84.28 74	83.36 85	87.02 48	92.22 87	67.74 88	84.65 294	94.50 37	79.15 69	82.23 82	87.93 203	66.88 53	96.94 103	80.53 112	82.20 156	96.39 28

MG-MVS		87.11 32	86.27 41	89.62 7	97.79 1	76.27 4	94.96 43	94.49 38	78.74 80	83.87 72	92.94 117	64.34 80	96.94 103	75.19 147	94.09 36	95.66 47

test_fmvsmconf0.1_n		85.71 53	86.08 47	84.62 130	80.83 297	62.33 227	93.84 80	88.81 264	83.50 18	87.00 42	96.01 37	63.36 96	96.93 105	94.04 12	87.29 116	94.61 92

canonicalmvs		86.85 35	86.25 43	88.66 18	91.80 101	71.92 14	93.54 94	91.71 147	80.26 51	87.55 37	95.25 58	63.59 93	96.93 105	88.18 49	84.34 141	97.11 8

alignmvs		87.28 30	86.97 35	88.24 24	91.30 114	71.14 21	95.61 25	93.56 71	79.30 65	87.07 41	95.25 58	68.43 41	96.93 105	87.87 51	84.33 142	96.65 14

test_prior				86.42 67	94.71 35	67.35 99		93.10 92					96.84 108			95.05 74

test_fmvsmconf0.01_n		83.70 90	83.52 74	84.25 144	75.26 349	61.72 241	92.17 141	87.24 299	82.36 26	84.91 61	95.41 48	55.60 182	96.83 109	92.85 17	85.87 131	94.21 106

MSLP-MVS++		86.27 43	85.91 50	87.35 39	92.01 93	68.97 59	95.04 40	92.70 104	79.04 74	81.50 87	96.50 25	58.98 145	96.78 110	83.49 90	93.93 39	96.29 30

agg_prior					94.16 43	66.97 110		93.31 82		84.49 65			96.75 111

FE-MVS		75.97 221	73.02 237	84.82 116	89.78 141	65.56 143	77.44 348	91.07 177	64.55 285	72.66 180	79.85 307	46.05 275	96.69 112	54.97 294	80.82 169	92.21 174

原ACMM1				84.42 136	93.21 63	64.27 178		93.40 81	65.39 280	79.51 108	92.50 126	58.11 152	96.69 112	65.27 243	93.96 38	92.32 167

ab-mvs		80.18 147	78.31 161	85.80 85	88.44 175	65.49 147	83.00 311	92.67 106	71.82 199	77.36 134	85.01 237	54.50 193	96.59 114	76.35 141	75.63 212	95.32 61

PCF-MVS	73.15 9	79.29 162	77.63 172	84.29 142	86.06 230	65.96 134	87.03 280	91.10 173	69.86 240	69.79 221	90.64 157	57.54 157	96.59 114	64.37 248	82.29 153	90.32 202
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
新几何1				84.73 122	92.32 84	64.28 177		91.46 159	59.56 327	79.77 105	92.90 118	56.95 166	96.57 116	63.40 253	92.91 56	93.34 137

VDDNet		80.50 140	78.26 162	87.21 41	86.19 228	69.79 40	94.48 50	91.31 163	60.42 320	79.34 110	90.91 155	38.48 307	96.56 117	82.16 97	81.05 166	95.27 66

dcpmvs_2		87.37 29	87.55 28	86.85 50	95.04 32	68.20 78	90.36 217	90.66 188	79.37 64	81.20 89	93.67 103	74.73 15	96.55 118	90.88 34	92.00 67	95.82 44

thisisatest0515		83.41 92	82.49 101	86.16 74	89.46 150	68.26 75	93.54 94	94.70 30	74.31 136	75.75 147	90.92 154	72.62 28	96.52 119	69.64 194	81.50 163	93.71 128

cascas		78.18 185	75.77 200	85.41 96	87.14 211	69.11 53	92.96 112	91.15 171	66.71 271	70.47 208	86.07 228	37.49 318	96.48 120	70.15 190	79.80 176	90.65 198

EIA-MVS		84.84 65	84.88 63	84.69 125	91.30 114	62.36 226	93.85 77	92.04 129	79.45 61	79.33 111	94.28 90	62.42 106	96.35 121	80.05 114	91.25 81	95.38 56

casdiffmvs_mvg		85.66 55	85.18 58	87.09 45	88.22 185	69.35 50	93.74 86	91.89 137	81.47 35	80.10 101	91.45 146	64.80 75	96.35 121	87.23 60	87.69 111	95.58 50
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
baseline2		83.68 91	83.42 82	84.48 135	87.37 206	66.00 132	90.06 226	95.93 8	79.71 59	69.08 226	90.39 164	77.92 6	96.28 123	78.91 125	81.38 164	91.16 193

HPM-MVS		83.25 96	82.95 91	84.17 146	92.25 86	62.88 218	90.91 198	91.86 139	70.30 234	77.12 137	93.96 98	56.75 168	96.28 123	82.04 99	91.34 80	93.34 137
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
CP-MVS		83.71 89	83.40 83	84.65 127	93.14 66	63.84 185	94.59 49	92.28 118	71.03 222	77.41 133	94.92 67	55.21 187	96.19 125	81.32 107	90.70 86	93.91 122

UGNet		79.87 154	78.68 156	83.45 166	89.96 138	61.51 244	92.13 143	90.79 183	76.83 106	78.85 120	86.33 225	38.16 310	96.17 126	67.93 213	87.17 117	92.67 157
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
APD-MVS_3200maxsize		81.64 123	81.32 114	82.59 183	92.36 83	58.74 290	91.39 179	91.01 181	63.35 295	79.72 106	94.62 76	51.82 220	96.14 127	79.71 115	87.93 109	92.89 154

BH-RMVSNet		79.46 161	77.65 171	84.89 113	91.68 104	65.66 139	93.55 93	88.09 288	72.93 165	73.37 173	91.12 153	46.20 273	96.12 128	56.28 290	85.61 134	92.91 152

SDMVSNet		80.26 145	78.88 155	84.40 137	89.25 155	67.63 92	85.35 290	93.02 93	76.77 108	70.84 205	87.12 215	47.95 258	96.09 129	85.04 76	74.55 216	89.48 216

testdata2													96.09 129	61.26 269

MVS_Test		84.16 79	83.20 86	87.05 47	91.56 107	69.82 39	89.99 231	92.05 128	77.77 91	82.84 77	86.57 221	63.93 85	96.09 129	74.91 152	89.18 99	95.25 69

baseline		85.01 63	84.44 67	86.71 56	88.33 180	68.73 63	90.24 222	91.82 143	81.05 44	81.18 90	92.50 126	63.69 89	96.08 132	84.45 83	86.71 125	95.32 61

casdiffmvs		85.37 58	84.87 64	86.84 51	88.25 183	69.07 55	93.04 109	91.76 144	81.27 41	80.84 96	92.07 137	64.23 81	96.06 133	84.98 78	87.43 115	95.39 55
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
thisisatest0530		81.15 128	80.07 133	84.39 138	88.26 182	65.63 141	91.40 177	94.62 34	71.27 217	70.93 204	89.18 181	72.47 29	96.04 134	65.62 238	76.89 204	91.49 182

TSAR-MVS + MP.		88.11 18	88.64 16	86.54 63	91.73 102	68.04 81	90.36 217	93.55 72	82.89 19	91.29 15	92.89 119	72.27 30	96.03 135	87.99 50	94.77 25	95.54 52
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
MSDG		69.54 284	65.73 294	80.96 228	85.11 249	63.71 192	84.19 296	83.28 336	56.95 338	54.50 335	84.03 249	31.50 345	96.03 135	42.87 344	69.13 259	83.14 315

Effi-MVS+		83.82 85	82.76 95	86.99 49	89.56 147	69.40 46	91.35 184	86.12 310	72.59 172	83.22 75	92.81 123	59.60 137	96.01 137	81.76 101	87.80 110	95.56 51

UA-Net		80.02 151	79.65 141	81.11 222	89.33 153	57.72 300	86.33 287	89.00 259	77.44 99	81.01 93	89.15 182	59.33 141	95.90 138	61.01 270	84.28 144	89.73 212

SR-MVS		82.81 103	82.58 99	83.50 164	93.35 58	61.16 250	92.23 140	91.28 166	64.48 286	81.27 88	95.28 54	53.71 205	95.86 139	82.87 93	88.77 102	93.49 134

lupinMVS		87.74 23	87.77 25	87.63 34	89.24 158	71.18 19	96.57 11	92.90 99	82.70 23	87.13 39	95.27 56	64.99 70	95.80 140	89.34 41	91.80 70	95.93 40

MS-PatchMatch		77.90 192	76.50 190	82.12 199	85.99 231	69.95 36	91.75 167	92.70 104	73.97 143	62.58 298	84.44 246	41.11 295	95.78 141	63.76 252	92.17 64	80.62 342

CLD-MVS		82.73 104	82.35 104	83.86 152	87.90 193	67.65 91	95.45 28	92.18 126	85.06 10	72.58 183	92.27 134	52.46 217	95.78 141	84.18 84	79.06 182	88.16 235
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
CS-MVS-test		86.14 46	87.01 34	83.52 161	92.63 80	59.36 283	95.49 27	91.92 134	80.09 53	85.46 56	95.53 47	61.82 115	95.77 143	86.77 65	93.37 50	95.41 54

HPM-MVS_fast		80.25 146	79.55 145	82.33 189	91.55 108	59.95 273	91.32 186	89.16 247	65.23 283	74.71 161	93.07 114	47.81 260	95.74 144	74.87 154	88.23 105	91.31 190

xiu_mvs_v1_base_debu		82.16 113	81.12 116	85.26 104	86.42 223	68.72 64	92.59 130	90.44 195	73.12 161	84.20 67	94.36 82	38.04 312	95.73 145	84.12 85	86.81 120	91.33 186

xiu_mvs_v1_base		82.16 113	81.12 116	85.26 104	86.42 223	68.72 64	92.59 130	90.44 195	73.12 161	84.20 67	94.36 82	38.04 312	95.73 145	84.12 85	86.81 120	91.33 186

xiu_mvs_v1_base_debi		82.16 113	81.12 116	85.26 104	86.42 223	68.72 64	92.59 130	90.44 195	73.12 161	84.20 67	94.36 82	38.04 312	95.73 145	84.12 85	86.81 120	91.33 186

DP-MVS		69.90 281	66.48 288	80.14 243	95.36 28	62.93 214	89.56 237	76.11 353	50.27 359	57.69 326	85.23 235	39.68 299	95.73 145	33.35 370	71.05 247	81.78 332

114514_t		79.17 164	77.67 170	83.68 158	95.32 29	65.53 145	92.85 116	91.60 153	63.49 293	67.92 244	90.63 159	46.65 266	95.72 149	67.01 222	83.54 147	89.79 210

TR-MVS		78.77 175	77.37 180	82.95 174	90.49 128	60.88 254	93.67 88	90.07 211	70.08 237	74.51 162	91.37 150	45.69 276	95.70 150	60.12 276	80.32 172	92.29 168

ETV-MVS		86.01 48	86.11 45	85.70 89	90.21 134	67.02 109	93.43 99	91.92 134	81.21 42	84.13 70	94.07 96	60.93 123	95.63 151	89.28 42	89.81 93	94.46 102

tttt0517		79.50 159	78.53 159	82.41 188	87.22 209	61.43 246	89.75 236	94.76 27	69.29 246	67.91 245	88.06 202	72.92 25	95.63 151	62.91 259	73.90 226	90.16 204

SR-MVS-dyc-post		81.06 132	80.70 124	82.15 197	92.02 91	58.56 292	90.90 199	90.45 192	62.76 302	78.89 115	94.46 78	51.26 228	95.61 153	78.77 127	86.77 123	92.28 169

thres200		79.66 156	78.33 160	83.66 160	92.54 82	65.82 138	93.06 107	96.31 3	74.90 130	73.30 174	88.66 185	59.67 136	95.61 153	47.84 323	78.67 186	89.56 215

HQP4-MVS										74.18 164			95.61 153			88.63 225

BH-w/o		80.49 141	79.30 150	84.05 149	90.83 124	64.36 175	93.60 91	89.42 236	74.35 135	69.09 225	90.15 171	55.23 186	95.61 153	64.61 246	86.43 129	92.17 175

HQP-MVS		81.14 129	80.64 126	82.64 181	87.54 201	63.66 196	94.06 63	91.70 149	79.80 56	74.18 164	90.30 166	51.63 224	95.61 153	77.63 134	78.90 183	88.63 225

HQP_MVS		80.34 144	79.75 140	82.12 199	86.94 216	62.42 224	93.13 105	91.31 163	78.81 78	72.53 184	89.14 183	50.66 231	95.55 158	76.74 137	78.53 188	88.39 232

plane_prior5								91.31 163					95.55 158	76.74 137	78.53 188	88.39 232

jason		86.40 40	86.17 44	87.11 44	86.16 229	70.54 28	95.71 24	92.19 125	82.00 30	84.58 64	94.34 87	61.86 112	95.53 160	87.76 52	90.89 84	95.27 66
jason: jason.
CS-MVS		85.80 51	86.65 40	83.27 169	92.00 94	58.92 288	95.31 31	91.86 139	79.97 54	84.82 62	95.40 49	62.26 108	95.51 161	86.11 69	92.08 66	95.37 57

EC-MVSNet		84.53 70	85.04 61	83.01 173	89.34 151	61.37 247	94.42 51	91.09 174	77.91 89	83.24 74	94.20 92	58.37 148	95.40 162	85.35 73	91.41 77	92.27 172

BH-untuned		78.68 176	77.08 182	83.48 165	89.84 140	63.74 189	92.70 122	88.59 274	71.57 210	66.83 262	88.65 186	51.75 222	95.39 163	59.03 281	84.77 138	91.32 189

MVS_111021_LR		82.02 117	81.52 112	83.51 163	88.42 176	62.88 218	89.77 235	88.93 260	76.78 107	75.55 153	93.10 111	50.31 234	95.38 164	83.82 89	87.02 118	92.26 173

thres100view900		78.37 182	77.01 184	82.46 184	91.89 99	63.21 207	91.19 193	96.33 1	72.28 183	70.45 210	87.89 204	60.31 127	95.32 165	45.16 334	77.58 195	88.83 220

tfpn200view9		78.79 174	77.43 175	82.88 175	92.21 88	64.49 164	92.05 149	96.28 4	73.48 155	71.75 196	88.26 195	60.07 132	95.32 165	45.16 334	77.58 195	88.83 220

thres400		78.68 176	77.43 175	82.43 185	92.21 88	64.49 164	92.05 149	96.28 4	73.48 155	71.75 196	88.26 195	60.07 132	95.32 165	45.16 334	77.58 195	87.48 241

RPMNet		70.42 276	65.68 295	84.63 129	83.15 276	67.96 83	70.25 362	90.45 192	46.83 368	69.97 218	65.10 367	56.48 174	95.30 168	35.79 365	73.13 229	90.64 199

ECVR-MVS		81.29 127	80.38 132	84.01 150	88.39 178	61.96 235	92.56 133	86.79 303	77.66 94	76.63 141	91.42 147	46.34 270	95.24 169	74.36 156	89.23 97	94.85 80

OPM-MVS		79.00 167	78.09 164	81.73 207	83.52 273	63.83 186	91.64 171	90.30 202	76.36 114	71.97 193	89.93 175	46.30 272	95.17 170	75.10 148	77.70 193	86.19 268
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
test2506		83.29 94	82.92 92	84.37 139	88.39 178	63.18 209	92.01 151	91.35 162	77.66 94	78.49 123	91.42 147	64.58 78	95.09 171	73.19 159	89.23 97	94.85 80

PAPM		85.89 50	85.46 55	87.18 42	88.20 186	72.42 13	92.41 135	92.77 102	82.11 29	80.34 99	93.07 114	68.27 42	95.02 172	78.39 130	93.59 47	94.09 113

sd_testset		77.08 202	75.37 205	82.20 195	89.25 155	62.11 232	82.06 315	89.09 252	76.77 108	70.84 205	87.12 215	41.43 294	95.01 173	67.23 220	74.55 216	89.48 216

PMMVS		81.98 118	82.04 106	81.78 206	89.76 143	56.17 315	91.13 194	90.69 185	77.96 87	80.09 102	93.57 106	46.33 271	94.99 174	81.41 105	87.46 114	94.17 108

CostFormer		82.33 110	81.15 115	85.86 82	89.01 163	68.46 69	82.39 314	93.01 94	75.59 119	80.25 100	81.57 279	72.03 32	94.96 175	79.06 123	77.48 198	94.16 109

EPP-MVSNet		81.79 120	81.52 112	82.61 182	88.77 169	60.21 270	93.02 111	93.66 68	68.52 257	72.90 178	90.39 164	72.19 31	94.96 175	74.93 151	79.29 181	92.67 157

ACMH	63.93 17	68.62 291	64.81 301	80.03 247	85.22 245	63.25 206	87.72 271	84.66 322	60.83 318	51.57 347	79.43 312	27.29 358	94.96 175	41.76 347	64.84 290	81.88 330
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
thres600view7		78.00 187	76.66 189	82.03 204	91.93 96	63.69 194	91.30 187	96.33 1	72.43 178	70.46 209	87.89 204	60.31 127	94.92 178	42.64 346	76.64 205	87.48 241

baseline1		81.84 119	81.03 120	84.28 143	91.60 105	66.62 118	91.08 195	91.66 151	81.87 31	74.86 158	91.67 144	69.98 37	94.92 178	71.76 177	64.75 292	91.29 191

XXY-MVS		77.94 190	76.44 191	82.43 185	82.60 282	64.44 168	92.01 151	91.83 142	73.59 154	70.00 217	85.82 231	54.43 197	94.76 180	69.63 195	68.02 267	88.10 236

Vis-MVSNet		80.92 135	79.98 137	83.74 154	88.48 173	61.80 237	93.44 98	88.26 285	73.96 144	77.73 128	91.76 141	49.94 238	94.76 180	65.84 235	90.37 90	94.65 90
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
nrg030		80.93 134	79.86 138	84.13 147	83.69 270	68.83 61	93.23 103	91.20 167	75.55 120	75.06 157	88.22 198	63.04 102	94.74 182	81.88 100	66.88 274	88.82 223

GA-MVS		78.33 184	76.23 194	84.65 127	83.65 271	66.30 126	91.44 173	90.14 209	76.01 116	70.32 212	84.02 250	42.50 290	94.72 183	70.98 182	77.00 203	92.94 151

EI-MVSNet		78.97 168	78.22 163	81.25 217	85.33 242	62.73 221	89.53 240	93.21 84	72.39 180	72.14 191	90.13 172	60.99 120	94.72 183	67.73 215	72.49 236	86.29 264

MVSTER		82.47 108	82.05 105	83.74 154	92.68 78	69.01 57	91.90 157	93.21 84	79.83 55	72.14 191	85.71 233	74.72 16	94.72 183	75.72 143	72.49 236	87.50 240

test1111		80.84 136	80.02 134	83.33 167	87.87 194	60.76 258	92.62 127	86.86 302	77.86 90	75.73 148	91.39 149	46.35 269	94.70 186	72.79 165	88.68 103	94.52 98

test_vis1_n_1920		81.66 122	82.01 107	80.64 233	82.24 286	55.09 323	94.76 46	86.87 301	81.67 34	84.40 66	94.63 75	38.17 309	94.67 187	91.98 26	83.34 148	92.16 176

iter_conf_final		81.74 121	80.93 121	84.18 145	92.66 79	69.10 54	92.94 113	82.80 339	79.01 75	74.85 159	88.40 190	61.83 114	94.61 188	79.36 118	76.52 207	88.83 220

iter_conf05		83.27 95	82.70 97	84.98 111	93.32 59	71.84 15	94.16 58	81.76 341	82.74 21	73.83 171	88.40 190	72.77 27	94.61 188	82.10 98	75.21 214	88.48 229

tt0805		73.07 252	70.73 264	80.07 245	78.37 332	57.05 310	87.78 270	92.18 126	61.23 316	67.04 258	86.49 222	31.35 347	94.58 190	65.06 244	67.12 272	88.57 227

hse-mvs2		81.12 131	81.11 119	81.16 220	86.52 222	57.48 305	89.40 243	91.16 169	81.45 36	82.73 79	90.49 162	60.11 130	94.58 190	87.69 53	60.41 331	91.41 185

AUN-MVS		78.37 182	77.43 175	81.17 219	86.60 221	57.45 306	89.46 242	91.16 169	74.11 139	74.40 163	90.49 162	55.52 183	94.57 192	74.73 155	60.43 330	91.48 183

PLC	68.80 14	75.23 232	73.68 231	79.86 253	92.93 70	58.68 291	90.64 210	88.30 281	60.90 317	64.43 281	90.53 160	42.38 291	94.57 192	56.52 288	76.54 206	86.33 263
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
GG-mvs-BLEND				86.53 64	91.91 98	69.67 45	75.02 356	94.75 28		78.67 122	90.85 156	77.91 7	94.56 194	72.25 171	93.74 43	95.36 58

OMC-MVS		78.67 178	77.91 169	80.95 229	85.76 237	57.40 307	88.49 259	88.67 271	73.85 146	72.43 188	92.10 136	49.29 245	94.55 195	72.73 166	77.89 191	90.91 196

Fast-Effi-MVS+		81.14 129	80.01 135	84.51 134	90.24 133	65.86 136	94.12 62	89.15 248	73.81 148	75.37 155	88.26 195	57.26 158	94.53 196	66.97 223	84.92 136	93.15 143

diffmvs		84.28 74	83.83 72	85.61 91	87.40 205	68.02 82	90.88 201	89.24 242	80.54 47	81.64 86	92.52 125	59.83 134	94.52 197	87.32 58	85.11 135	94.29 103
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
HyFIR lowres test		81.03 133	79.56 143	85.43 95	87.81 197	68.11 80	90.18 223	90.01 216	70.65 230	72.95 177	86.06 229	63.61 92	94.50 198	75.01 150	79.75 177	93.67 129

v2v482		77.42 197	75.65 203	82.73 178	80.38 303	67.13 105	91.85 160	90.23 206	75.09 127	69.37 222	83.39 257	53.79 204	94.44 199	71.77 176	65.00 289	86.63 260

v1144		76.73 210	74.88 210	82.27 191	80.23 307	66.60 119	91.68 169	90.21 208	73.69 151	69.06 227	81.89 272	52.73 215	94.40 200	69.21 201	65.23 286	85.80 279

dmvs_re		76.93 203	75.36 206	81.61 210	87.78 198	60.71 261	80.00 336	87.99 290	79.42 62	69.02 228	89.47 179	46.77 264	94.32 201	63.38 254	74.45 219	89.81 209

TAPA-MVS	70.22 12	74.94 236	73.53 232	79.17 266	90.40 130	52.07 335	89.19 248	89.61 230	62.69 304	70.07 215	92.67 124	48.89 251	94.32 201	38.26 360	79.97 174	91.12 194
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
LPG-MVS_test		75.82 224	74.58 215	79.56 261	84.31 262	59.37 281	90.44 213	89.73 226	69.49 243	64.86 272	88.42 188	38.65 304	94.30 203	72.56 168	72.76 233	85.01 294

LGP-MVS_train				79.56 261	84.31 262	59.37 281		89.73 226	69.49 243	64.86 272	88.42 188	38.65 304	94.30 203	72.56 168	72.76 233	85.01 294

v1192		75.98 220	73.92 227	82.15 197	79.73 311	66.24 128	91.22 190	89.75 223	72.67 171	68.49 238	81.42 282	49.86 239	94.27 205	67.08 221	65.02 288	85.95 276

tpmvs		72.88 257	69.76 273	82.22 194	90.98 119	67.05 107	78.22 345	88.30 281	63.10 300	64.35 282	74.98 341	55.09 189	94.27 205	43.25 340	69.57 253	85.34 290

tpm2		79.80 155	77.95 168	85.34 100	88.28 181	68.26 75	81.56 320	91.42 160	70.11 236	77.59 132	80.50 297	67.40 50	94.26 207	67.34 218	77.35 199	93.51 133

mvsmamba		76.85 206	75.71 202	80.25 241	83.07 278	59.16 285	91.44 173	80.64 346	76.84 105	67.95 243	86.33 225	46.17 274	94.24 208	76.06 142	72.92 232	87.36 245

PVSNet_0	68.08 15	71.81 266	68.32 283	82.27 191	84.68 253	62.31 229	88.68 256	90.31 201	75.84 117	57.93 325	80.65 296	37.85 315	94.19 209	69.94 192	29.05 388	90.31 203

MVP-Stereo		77.12 201	76.23 194	79.79 255	81.72 291	66.34 125	89.29 244	90.88 182	70.56 232	62.01 301	82.88 261	49.34 243	94.13 210	65.55 240	93.80 41	78.88 356
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
ACMM	69.62 13	74.34 240	72.73 243	79.17 266	84.25 264	57.87 298	90.36 217	89.93 217	63.17 299	65.64 267	86.04 230	37.79 316	94.10 211	65.89 234	71.52 243	85.55 285
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
V42		76.46 212	74.55 216	82.19 196	79.14 321	67.82 86	90.26 221	89.42 236	73.75 149	68.63 236	81.89 272	51.31 227	94.09 212	71.69 178	64.84 290	84.66 297

TESTMET0.1,1		82.41 109	81.98 108	83.72 157	88.08 187	63.74 189	92.70 122	93.77 61	79.30 65	77.61 131	87.57 209	58.19 151	94.08 213	73.91 158	86.68 126	93.33 139

Anonymous20231211		73.08 251	70.39 267	81.13 221	90.62 126	63.33 205	91.40 177	90.06 213	51.84 354	64.46 280	80.67 295	36.49 326	94.07 214	63.83 251	64.17 297	85.98 275

v8		75.35 230	73.26 235	81.61 210	80.67 300	66.82 112	89.54 239	89.27 241	71.65 204	63.30 290	80.30 301	54.99 190	94.06 215	67.33 219	62.33 311	83.94 302

EG-PatchMatch MVS		68.55 292	65.41 298	77.96 280	78.69 328	62.93 214	89.86 233	89.17 246	60.55 319	50.27 352	77.73 322	22.60 367	94.06 215	47.18 326	72.65 235	76.88 364

PVSNet	73.49 8	80.05 150	78.63 157	84.31 141	90.92 121	64.97 158	92.47 134	91.05 179	79.18 68	72.43 188	90.51 161	37.05 324	94.06 215	68.06 210	86.00 130	93.90 124

GeoE		78.90 170	77.43 175	83.29 168	88.95 164	62.02 233	92.31 136	86.23 308	70.24 235	71.34 202	89.27 180	54.43 197	94.04 218	63.31 255	80.81 170	93.81 127

v10		74.77 237	72.54 247	81.46 213	80.33 305	66.71 116	89.15 249	89.08 253	70.94 223	63.08 293	79.86 306	52.52 216	94.04 218	65.70 237	62.17 312	83.64 304

v144192		76.05 218	74.03 225	82.12 199	79.50 315	66.55 121	91.39 179	89.71 229	72.30 182	68.17 240	81.33 284	51.75 222	94.03 220	67.94 212	64.19 296	85.77 280

tpm cat1		75.30 231	72.21 250	84.58 131	88.52 171	67.77 87	78.16 346	88.02 289	61.88 312	68.45 239	76.37 334	60.65 124	94.03 220	53.77 300	74.11 222	91.93 178

gg-mvs-nofinetune		77.18 200	74.31 220	85.80 85	91.42 111	68.36 71	71.78 359	94.72 29	49.61 360	77.12 137	45.92 383	77.41 8	93.98 222	67.62 216	93.16 53	95.05 74

PS-MVSNAJss		77.26 199	76.31 193	80.13 244	80.64 301	59.16 285	90.63 212	91.06 178	72.80 169	68.58 237	84.57 244	53.55 206	93.96 223	72.97 161	71.96 240	87.27 249

OpenMVS_ROB	61.12 18	66.39 307	62.92 315	76.80 297	76.51 344	57.77 299	89.22 246	83.41 334	55.48 345	53.86 339	77.84 321	26.28 361	93.95 224	34.90 367	68.76 261	78.68 358

MDTV_nov1_ep13			72.61 245		89.06 161	68.48 68	80.33 330	90.11 210	71.84 198	71.81 195	75.92 338	53.01 212	93.92 225	48.04 320	73.38 227

v1921920		75.63 228	73.49 233	82.06 203	79.38 316	66.35 124	91.07 197	89.48 232	71.98 190	67.99 241	81.22 287	49.16 248	93.90 226	66.56 225	64.56 295	85.92 278

v1240		75.21 233	72.98 238	81.88 205	79.20 318	66.00 132	90.75 206	89.11 251	71.63 208	67.41 254	81.22 287	47.36 262	93.87 227	65.46 241	64.72 293	85.77 280

ACMP	71.68 10	75.58 229	74.23 222	79.62 259	84.97 251	59.64 276	90.80 204	89.07 254	70.39 233	62.95 294	87.30 213	38.28 308	93.87 227	72.89 162	71.45 244	85.36 289
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
v148		76.19 213	74.47 218	81.36 215	80.05 309	64.44 168	91.75 167	90.23 206	73.68 152	67.13 257	80.84 292	55.92 180	93.86 229	68.95 204	61.73 319	85.76 282

LS3D		69.17 286	66.40 290	77.50 284	91.92 97	56.12 316	85.12 291	80.37 347	46.96 366	56.50 330	87.51 210	37.25 319	93.71 230	32.52 376	79.40 178	82.68 323

EPMVS		78.49 181	75.98 197	86.02 76	91.21 116	69.68 44	80.23 332	91.20 167	75.25 125	72.48 186	78.11 319	54.65 192	93.69 231	57.66 287	83.04 149	94.69 86

IS-MVSNet		80.14 148	79.41 147	82.33 189	87.91 192	60.08 272	91.97 155	88.27 283	72.90 168	71.44 201	91.73 143	61.44 117	93.66 232	62.47 263	86.53 127	93.24 140

v7n		71.31 271	68.65 278	79.28 264	76.40 345	60.77 257	86.71 285	89.45 234	64.17 288	58.77 319	78.24 317	44.59 283	93.54 233	57.76 285	61.75 318	83.52 307

VPA-MVSNet		79.03 166	78.00 166	82.11 202	85.95 232	64.48 166	93.22 104	94.66 32	75.05 128	74.04 169	84.95 238	52.17 219	93.52 234	74.90 153	67.04 273	88.32 234

tfpnnormal		70.10 278	67.36 286	78.32 275	83.45 274	60.97 253	88.85 253	92.77 102	64.85 284	60.83 306	78.53 315	43.52 287	93.48 235	31.73 377	61.70 320	80.52 343

旧先验2							92.00 154		59.37 328	87.54 38			93.47 236	75.39 146

1112_ss		80.56 139	79.83 139	82.77 177	88.65 170	60.78 256	92.29 137	88.36 279	72.58 173	72.46 187	94.95 64	65.09 69	93.42 237	66.38 229	77.71 192	94.10 112

testdata				81.34 216	89.02 162	57.72 300		89.84 220	58.65 331	85.32 58	94.09 94	57.03 161	93.28 238	69.34 199	90.56 89	93.03 148

LTVRE_ROB	59.60 19	66.27 308	63.54 311	74.45 312	84.00 267	51.55 337	67.08 372	83.53 332	58.78 330	54.94 334	80.31 300	34.54 333	93.23 239	40.64 353	68.03 266	78.58 359
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
VPNet		78.82 172	77.53 174	82.70 179	84.52 257	66.44 122	93.93 72	92.23 120	80.46 49	72.60 182	88.38 192	49.18 246	93.13 240	72.47 170	63.97 301	88.55 228

Test_1112_low_res		79.56 158	78.60 158	82.43 185	88.24 184	60.39 267	92.09 146	87.99 290	72.10 189	71.84 194	87.42 211	64.62 77	93.04 241	65.80 236	77.30 200	93.85 126

PatchMatch-RL		72.06 265	69.98 268	78.28 276	89.51 149	55.70 319	83.49 301	83.39 335	61.24 315	63.72 286	82.76 262	34.77 332	93.03 242	53.37 302	77.59 194	86.12 272

Fast-Effi-MVS+-dtu		75.04 234	73.37 234	80.07 245	80.86 296	59.52 279	91.20 192	85.38 315	71.90 193	65.20 270	84.84 240	41.46 293	92.97 243	66.50 228	72.96 231	87.73 238

cl____		76.07 215	74.67 211	80.28 239	85.15 246	61.76 239	90.12 224	88.73 268	71.16 218	65.43 268	81.57 279	61.15 118	92.95 244	66.54 226	62.17 312	86.13 271

pm-mvs1		72.89 256	71.09 260	78.26 277	79.10 322	57.62 303	90.80 204	89.30 240	67.66 263	62.91 295	81.78 274	49.11 249	92.95 244	60.29 275	58.89 336	84.22 300

TAMVS		80.37 143	79.45 146	83.13 172	85.14 247	63.37 204	91.23 189	90.76 184	74.81 131	72.65 181	88.49 187	60.63 125	92.95 244	69.41 198	81.95 159	93.08 146

ACMH+	65.35 16	67.65 300	64.55 304	76.96 295	84.59 256	57.10 309	88.08 263	80.79 344	58.59 332	53.00 341	81.09 291	26.63 360	92.95 244	46.51 328	61.69 321	80.82 339

DIV-MVS_self_test		76.07 215	74.67 211	80.28 239	85.14 247	61.75 240	90.12 224	88.73 268	71.16 218	65.42 269	81.60 278	61.15 118	92.94 248	66.54 226	62.16 314	86.14 269

cl22		77.94 190	76.78 187	81.42 214	87.57 200	64.93 160	90.67 208	88.86 263	72.45 177	67.63 251	82.68 264	64.07 82	92.91 249	71.79 175	65.30 283	86.44 262

CDS-MVSNet		81.43 125	80.74 123	83.52 161	86.26 227	64.45 167	92.09 146	90.65 189	75.83 118	73.95 170	89.81 176	63.97 84	92.91 249	71.27 180	82.82 151	93.20 142
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
miper_enhance_ethall		78.86 171	77.97 167	81.54 212	88.00 191	65.17 152	91.41 175	89.15 248	75.19 126	68.79 233	83.98 251	67.17 51	92.82 251	72.73 166	65.30 283	86.62 261

eth_miper_zixun_eth		75.96 222	74.40 219	80.66 232	84.66 254	63.02 211	89.28 245	88.27 283	71.88 195	65.73 266	81.65 276	59.45 138	92.81 252	68.13 209	60.53 328	86.14 269

CPTT-MVS		79.59 157	79.16 152	80.89 231	91.54 109	59.80 275	92.10 145	88.54 276	60.42 320	72.96 176	93.28 110	48.27 253	92.80 253	78.89 126	86.50 128	90.06 205

PatchmatchNet		77.46 196	74.63 213	85.96 78	89.55 148	70.35 30	79.97 337	89.55 231	72.23 184	70.94 203	76.91 330	57.03 161	92.79 254	54.27 297	81.17 165	94.74 85
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
jajsoiax		73.05 253	71.51 258	77.67 282	77.46 340	54.83 324	88.81 254	90.04 214	69.13 250	62.85 296	83.51 255	31.16 348	92.75 255	70.83 183	69.80 250	85.43 288

mvs_tets		72.71 260	71.11 259	77.52 283	77.41 341	54.52 326	88.45 260	89.76 222	68.76 255	62.70 297	83.26 258	29.49 352	92.71 256	70.51 189	69.62 252	85.34 290

tpmrst		80.57 138	79.14 153	84.84 115	90.10 136	68.28 74	81.70 318	89.72 228	77.63 96	75.96 146	79.54 311	64.94 72	92.71 256	75.43 145	77.28 201	93.55 132

D2MVS		73.80 247	72.02 252	79.15 268	79.15 320	62.97 212	88.58 258	90.07 211	72.94 164	59.22 314	78.30 316	42.31 292	92.70 258	65.59 239	72.00 239	81.79 331

test_post											23.01 393	56.49 173	92.67 259

MVSFormer		83.75 88	82.88 93	86.37 69	89.24 158	71.18 19	89.07 250	90.69 185	65.80 277	87.13 39	94.34 87	64.99 70	92.67 259	72.83 163	91.80 70	95.27 66

test_djsdf		73.76 249	72.56 246	77.39 287	77.00 343	53.93 328	89.07 250	90.69 185	65.80 277	63.92 283	82.03 271	43.14 289	92.67 259	72.83 163	68.53 263	85.57 284

RRT_MVS		74.44 239	72.97 239	78.84 271	82.36 285	57.66 302	89.83 234	88.79 267	70.61 231	64.58 276	84.89 239	39.24 300	92.65 262	70.11 191	66.34 278	86.21 267

miper_ehance_all_eth		77.60 194	76.44 191	81.09 226	85.70 239	64.41 171	90.65 209	88.64 273	72.31 181	67.37 256	82.52 265	64.77 76	92.64 263	70.67 186	65.30 283	86.24 266

c3_l		76.83 208	75.47 204	80.93 230	85.02 250	64.18 181	90.39 216	88.11 287	71.66 203	66.65 264	81.64 277	63.58 94	92.56 264	69.31 200	62.86 305	86.04 273

dp		75.01 235	72.09 251	83.76 153	89.28 154	66.22 129	79.96 338	89.75 223	71.16 218	67.80 249	77.19 327	51.81 221	92.54 265	50.39 308	71.44 245	92.51 163

Effi-MVS+-dtu		76.14 214	75.28 208	78.72 272	83.22 275	55.17 322	89.87 232	87.78 293	75.42 122	67.98 242	81.43 281	45.08 281	92.52 266	75.08 149	71.63 241	88.48 229

F-COLMAP		70.66 273	68.44 281	77.32 288	86.37 226	55.91 317	88.00 266	86.32 305	56.94 339	57.28 328	88.07 201	33.58 337	92.49 267	51.02 306	68.37 264	83.55 305

USDC		67.43 304	64.51 305	76.19 300	77.94 337	55.29 321	78.38 343	85.00 319	73.17 159	48.36 359	80.37 299	21.23 369	92.48 268	52.15 304	64.02 300	80.81 340

pmmvs6		67.57 301	64.76 302	76.00 302	72.82 359	53.37 330	88.71 255	86.78 304	53.19 350	57.58 327	78.03 320	35.33 331	92.41 269	55.56 292	54.88 348	82.21 328

test-LLR		80.10 149	79.56 143	81.72 208	86.93 218	61.17 248	92.70 122	91.54 154	71.51 213	75.62 150	86.94 217	53.83 202	92.38 270	72.21 172	84.76 139	91.60 180

test-mter		79.96 152	79.38 149	81.72 208	86.93 218	61.17 248	92.70 122	91.54 154	73.85 146	75.62 150	86.94 217	49.84 240	92.38 270	72.21 172	84.76 139	91.60 180

UniMVSNet (Re)		77.58 195	76.78 187	79.98 248	84.11 265	60.80 255	91.76 165	93.17 88	76.56 112	69.93 220	84.78 241	63.32 98	92.36 272	64.89 245	62.51 310	86.78 256

ET-MVSNet_ETH3D		84.01 81	83.15 89	86.58 61	90.78 125	70.89 24	94.74 47	94.62 34	81.44 38	58.19 320	93.64 104	73.64 23	92.35 273	82.66 94	78.66 187	96.50 24

mvs_anonymous		81.36 126	79.99 136	85.46 94	90.39 131	68.40 70	86.88 284	90.61 190	74.41 133	70.31 213	84.67 242	63.79 87	92.32 274	73.13 160	85.70 132	95.67 46

IterMVS-LS		76.49 211	75.18 209	80.43 236	84.49 258	62.74 220	90.64 210	88.80 265	72.40 179	65.16 271	81.72 275	60.98 121	92.27 275	67.74 214	64.65 294	86.29 264
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
FMVSNet3		77.73 193	76.04 196	82.80 176	91.20 117	68.99 58	91.87 158	91.99 131	73.35 157	67.04 258	83.19 259	56.62 171	92.14 276	59.80 278	69.34 254	87.28 248

UniMVSNet_NR-MVSNet		78.15 186	77.55 173	79.98 248	84.46 259	60.26 268	92.25 138	93.20 86	77.50 98	68.88 231	86.61 220	66.10 59	92.13 277	66.38 229	62.55 308	87.54 239

DU-MVS		76.86 204	75.84 199	79.91 251	82.96 279	60.26 268	91.26 188	91.54 154	76.46 113	68.88 231	86.35 223	56.16 175	92.13 277	66.38 229	62.55 308	87.35 246

tpm		78.58 179	77.03 183	83.22 170	85.94 234	64.56 162	83.21 308	91.14 172	78.31 83	73.67 172	79.68 309	64.01 83	92.09 279	66.07 233	71.26 246	93.03 148

Baseline_NR-MVSNet		73.99 245	72.83 240	77.48 285	80.78 298	59.29 284	91.79 162	84.55 323	68.85 252	68.99 229	80.70 293	56.16 175	92.04 280	62.67 261	60.98 325	81.11 336

FMVSNet2		76.07 215	74.01 226	82.26 193	88.85 165	67.66 90	91.33 185	91.61 152	70.84 225	65.98 265	82.25 268	48.03 254	92.00 281	58.46 283	68.73 262	87.10 251

TransMVSNet (Re)		70.07 279	67.66 285	77.31 289	80.62 302	59.13 287	91.78 164	84.94 320	65.97 276	60.08 310	80.44 298	50.78 230	91.87 282	48.84 316	45.46 366	80.94 338

UniMVSNet_ETH3D		72.74 259	70.53 266	79.36 263	78.62 330	56.64 313	85.01 292	89.20 244	63.77 291	64.84 274	84.44 246	34.05 335	91.86 283	63.94 250	70.89 248	89.57 214

NR-MVSNet		76.05 218	74.59 214	80.44 235	82.96 279	62.18 231	90.83 203	91.73 145	77.12 102	60.96 305	86.35 223	59.28 142	91.80 284	60.74 271	61.34 323	87.35 246

FIs		79.47 160	79.41 147	79.67 257	85.95 232	59.40 280	91.68 169	93.94 56	78.06 86	68.96 230	88.28 193	66.61 56	91.77 285	66.20 232	74.99 215	87.82 237

XVG-OURS		74.25 242	72.46 248	79.63 258	78.45 331	57.59 304	80.33 330	87.39 295	63.86 290	68.76 234	89.62 178	40.50 297	91.72 286	69.00 203	74.25 221	89.58 213

test_0402		64.54 317	61.09 323	74.92 309	84.10 266	60.75 259	87.95 267	79.71 349	52.03 352	52.41 343	77.20 326	32.21 343	91.64 287	23.14 383	61.03 324	72.36 372

test_cas_vis1_n_1920		80.45 142	80.61 127	79.97 250	78.25 333	57.01 311	94.04 67	88.33 280	79.06 73	82.81 78	93.70 102	38.65 304	91.63 288	90.82 35	79.81 175	91.27 192

XVG-OURS-SEG-HR		74.70 238	73.08 236	79.57 260	78.25 333	57.33 308	80.49 328	87.32 296	63.22 297	68.76 234	90.12 174	44.89 282	91.59 289	70.55 188	74.09 223	89.79 210

TranMVSNet+NR-MVSNet		75.86 223	74.52 217	79.89 252	82.44 284	60.64 264	91.37 182	91.37 161	76.63 110	67.65 250	86.21 227	52.37 218	91.55 290	61.84 266	60.81 326	87.48 241

GBi-Net		75.65 226	73.83 228	81.10 223	88.85 165	65.11 154	90.01 228	90.32 198	70.84 225	67.04 258	80.25 302	48.03 254	91.54 291	59.80 278	69.34 254	86.64 257

test1		75.65 226	73.83 228	81.10 223	88.85 165	65.11 154	90.01 228	90.32 198	70.84 225	67.04 258	80.25 302	48.03 254	91.54 291	59.80 278	69.34 254	86.64 257

FMVSNet1		72.71 260	69.91 271	81.10 223	83.60 272	65.11 154	90.01 228	90.32 198	63.92 289	63.56 287	80.25 302	36.35 327	91.54 291	54.46 296	66.75 275	86.64 257

pmmvs4		73.92 246	71.81 255	80.25 241	79.17 319	65.24 150	87.43 276	87.26 298	67.64 265	63.46 288	83.91 252	48.96 250	91.53 294	62.94 258	65.49 282	83.96 301

test_post1							78.95 339				20.70 396	53.05 211	91.50 295	60.43 273

anonymousdsp		71.14 272	69.37 276	76.45 298	72.95 357	54.71 325	84.19 296	88.88 261	61.92 311	62.15 300	79.77 308	38.14 311	91.44 296	68.90 205	67.45 271	83.21 313

XVG-ACMP-BASELINE		68.04 297	65.53 297	75.56 303	74.06 354	52.37 333	78.43 342	85.88 312	62.03 309	58.91 318	81.21 289	20.38 372	91.15 297	60.69 272	68.18 265	83.16 314

CNLPA		74.31 241	72.30 249	80.32 237	91.49 110	61.66 242	90.85 202	80.72 345	56.67 341	63.85 285	90.64 157	46.75 265	90.84 298	53.79 299	75.99 211	88.47 231

ppachtmachnet_test		67.72 299	63.70 310	79.77 256	78.92 323	66.04 131	88.68 256	82.90 338	60.11 324	55.45 332	75.96 337	39.19 301	90.55 299	39.53 355	52.55 354	82.71 321

pmmvs5		73.35 250	71.52 257	78.86 270	78.64 329	60.61 265	91.08 195	86.90 300	67.69 262	63.32 289	83.64 253	44.33 284	90.53 300	62.04 265	66.02 280	85.46 287

SixPastTwentyTwo		64.92 315	61.78 322	74.34 314	78.74 327	49.76 346	83.42 304	79.51 350	62.86 301	50.27 352	77.35 323	30.92 350	90.49 301	45.89 332	47.06 363	82.78 317

COLMAP_ROB	57.96 20	62.98 325	59.65 327	72.98 323	81.44 293	53.00 332	83.75 299	75.53 358	48.34 364	48.81 358	81.40 283	24.14 363	90.30 302	32.95 372	60.52 329	75.65 367
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
patchmatchnet-post											67.62 363	57.62 156	90.25 303

SCA		75.82 224	72.76 241	85.01 110	86.63 220	70.08 32	81.06 325	89.19 245	71.60 209	70.01 216	77.09 328	45.53 277	90.25 303	60.43 273	73.27 228	94.68 87

JIA-IIPM		66.06 309	62.45 318	76.88 296	81.42 294	54.45 327	57.49 384	88.67 271	49.36 361	63.86 284	46.86 382	56.06 178	90.25 303	49.53 313	68.83 260	85.95 276

WR-MVS		76.76 209	75.74 201	79.82 254	84.60 255	62.27 230	92.60 128	92.51 114	76.06 115	67.87 248	85.34 234	56.76 167	90.24 306	62.20 264	63.69 303	86.94 254

FC-MVSNet-test		77.99 188	78.08 165	77.70 281	84.89 252	55.51 320	90.27 220	93.75 65	76.87 103	66.80 263	87.59 208	65.71 64	90.23 307	62.89 260	73.94 224	87.37 244

EPNet_dtu		78.80 173	79.26 151	77.43 286	88.06 188	49.71 347	91.96 156	91.95 133	77.67 93	76.56 143	91.28 151	58.51 147	90.20 308	56.37 289	80.95 167	92.39 164
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
CMPMVS	48.56 21	66.77 306	64.41 307	73.84 317	70.65 365	50.31 344	77.79 347	85.73 314	45.54 370	44.76 369	82.14 270	35.40 330	90.14 309	63.18 257	74.54 218	81.07 337
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
Vis-MVSNet (Re-imp)		79.24 163	79.57 142	78.24 278	88.46 174	52.29 334	90.41 215	89.12 250	74.24 137	69.13 224	91.91 139	65.77 63	90.09 310	59.00 282	88.09 107	92.33 166

lessismore_v0				73.72 318	72.93 358	47.83 356		61.72 383		45.86 365	73.76 344	28.63 356	89.81 311	47.75 325	31.37 385	83.53 306

MVS-HIRNet		60.25 332	55.55 339	74.35 313	84.37 261	56.57 314	71.64 360	74.11 361	34.44 381	45.54 367	42.24 388	31.11 349	89.81 311	40.36 354	76.10 210	76.67 365

our_test_3		68.29 295	64.69 303	79.11 269	78.92 323	64.85 161	88.40 261	85.06 318	60.32 322	52.68 342	76.12 336	40.81 296	89.80 313	44.25 339	55.65 344	82.67 324

CR-MVSNet		73.79 248	70.82 263	82.70 179	83.15 276	67.96 83	70.25 362	84.00 328	73.67 153	69.97 218	72.41 348	57.82 154	89.48 314	52.99 303	73.13 229	90.64 199

Patchmtry		67.53 302	63.93 309	78.34 274	82.12 288	64.38 172	68.72 366	84.00 328	48.23 365	59.24 313	72.41 348	57.82 154	89.27 315	46.10 331	56.68 343	81.36 333

ADS-MVSNet		68.54 293	64.38 308	81.03 227	88.06 188	66.90 111	68.01 369	84.02 327	57.57 333	64.48 278	69.87 358	38.68 302	89.21 316	40.87 351	67.89 268	86.97 252

Patchmatch-RL test		68.17 296	64.49 306	79.19 265	71.22 361	53.93 328	70.07 364	71.54 370	69.22 247	56.79 329	62.89 370	56.58 172	88.61 317	69.53 197	52.61 353	95.03 76

UnsupCasMVSNet_bld		61.60 328	57.71 332	73.29 321	68.73 370	51.64 336	78.61 341	89.05 255	57.20 337	46.11 362	61.96 373	28.70 355	88.60 318	50.08 311	38.90 377	79.63 350

OurMVSNet-221017-0		64.68 316	62.17 320	72.21 330	76.08 348	47.35 358	80.67 327	81.02 343	56.19 342	51.60 346	79.66 310	27.05 359	88.56 319	53.60 301	53.63 351	80.71 341

PatchT		69.11 287	65.37 299	80.32 237	82.07 289	63.68 195	67.96 371	87.62 294	50.86 357	69.37 222	65.18 366	57.09 160	88.53 320	41.59 349	66.60 276	88.74 224

bld_raw_dy_0_64		71.59 269	69.71 274	77.22 291	77.82 339	58.12 296	87.71 272	73.66 362	68.01 260	61.90 303	84.29 248	33.68 336	88.43 321	69.91 193	70.43 249	85.11 293

TinyColmap		60.32 331	56.42 338	72.00 334	78.78 326	53.18 331	78.36 344	75.64 356	52.30 351	41.59 376	75.82 339	14.76 381	88.35 322	35.84 363	54.71 349	74.46 368

LCM-MVSNet-Re		72.93 255	71.84 254	76.18 301	88.49 172	48.02 354	80.07 335	70.17 371	73.96 144	52.25 344	80.09 305	49.98 237	88.24 323	67.35 217	84.23 145	92.28 169

ambc				69.61 340	61.38 381	41.35 375	49.07 389	85.86 313		50.18 354	66.40 364	10.16 386	88.14 324	45.73 333	44.20 367	79.32 353

Patchmatch-test		65.86 310	60.94 324	80.62 234	83.75 269	58.83 289	58.91 383	75.26 359	44.50 373	50.95 351	77.09 328	58.81 146	87.90 325	35.13 366	64.03 299	95.12 72

test_fmvs1_n		72.69 262	71.92 253	74.99 308	71.15 362	47.08 361	87.34 278	75.67 355	63.48 294	78.08 126	91.17 152	20.16 373	87.87 326	84.65 81	75.57 213	90.01 207

MIMVSNet		71.64 267	68.44 281	81.23 218	81.97 290	64.44 168	73.05 358	88.80 265	69.67 242	64.59 275	74.79 342	32.79 339	87.82 327	53.99 298	76.35 208	91.42 184

K. test v3		63.09 324	59.61 328	73.53 319	76.26 346	49.38 351	83.27 305	77.15 352	64.35 287	47.77 361	72.32 350	28.73 354	87.79 328	49.93 312	36.69 379	83.41 310

test_fmvs1		74.07 243	73.69 230	75.22 305	78.91 325	47.34 359	89.06 252	74.69 360	63.68 292	79.41 109	91.59 145	24.36 362	87.77 329	85.22 74	76.26 209	90.55 201

CL-MVSNet_self_test		69.92 280	68.09 284	75.41 304	73.25 356	55.90 318	90.05 227	89.90 218	69.96 238	61.96 302	76.54 331	51.05 229	87.64 330	49.51 314	50.59 358	82.70 322

KD-MVS_2432*1600		69.03 288	66.37 291	77.01 293	85.56 240	61.06 251	81.44 321	90.25 204	67.27 267	58.00 323	76.53 332	54.49 194	87.63 331	48.04 320	35.77 380	82.34 326

miper_refine_blended		69.03 288	66.37 291	77.01 293	85.56 240	61.06 251	81.44 321	90.25 204	67.27 267	58.00 323	76.53 332	54.49 194	87.63 331	48.04 320	35.77 380	82.34 326

miper_lstm_enhance		73.05 253	71.73 256	77.03 292	83.80 268	58.32 294	81.76 316	88.88 261	69.80 241	61.01 304	78.23 318	57.19 159	87.51 333	65.34 242	59.53 333	85.27 292

UnsupCasMVSNet_eth		65.79 311	63.10 313	73.88 316	70.71 364	50.29 345	81.09 324	89.88 219	72.58 173	49.25 357	74.77 343	32.57 341	87.43 334	55.96 291	41.04 373	83.90 303

Anonymous20231206		67.53 302	65.78 293	72.79 325	74.95 350	47.59 357	88.23 262	87.32 296	61.75 314	58.07 322	77.29 325	37.79 316	87.29 335	42.91 342	63.71 302	83.48 308

pmmvs-eth3d		65.53 314	62.32 319	75.19 306	69.39 369	59.59 277	82.80 312	83.43 333	62.52 305	51.30 349	72.49 346	32.86 338	87.16 336	55.32 293	50.73 357	78.83 357

IterMVS		72.65 263	70.83 261	78.09 279	82.17 287	62.96 213	87.64 274	86.28 306	71.56 211	60.44 307	78.85 314	45.42 279	86.66 337	63.30 256	61.83 316	84.65 298
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
AllTest		61.66 327	58.06 331	72.46 327	79.57 312	51.42 339	80.17 333	68.61 374	51.25 355	45.88 363	81.23 285	19.86 374	86.58 338	38.98 357	57.01 341	79.39 351

TestCases				72.46 327	79.57 312	51.42 339		68.61 374	51.25 355	45.88 363	81.23 285	19.86 374	86.58 338	38.98 357	57.01 341	79.39 351

MDA-MVSNet-bldmvs		61.54 329	57.70 333	73.05 322	79.53 314	57.00 312	83.08 309	81.23 342	57.57 333	34.91 381	72.45 347	32.79 339	86.26 340	35.81 364	41.95 371	75.89 366

test_vis1_n		71.63 268	70.73 264	74.31 315	69.63 368	47.29 360	86.91 282	72.11 366	63.21 298	75.18 156	90.17 170	20.40 371	85.76 341	84.59 82	74.42 220	89.87 208

Syy-MVS		69.65 283	69.52 275	70.03 339	87.87 194	43.21 372	88.07 264	89.01 256	72.91 166	63.11 291	88.10 199	45.28 280	85.54 342	22.07 385	69.23 257	81.32 334

myMVS_eth3d		72.58 264	72.74 242	72.10 332	87.87 194	49.45 349	88.07 264	89.01 256	72.91 166	63.11 291	88.10 199	63.63 90	85.54 342	32.73 374	69.23 257	81.32 334

Anonymous20240521		62.09 326	59.08 329	71.10 336	67.19 372	48.72 353	83.91 298	85.23 317	50.38 358	47.84 360	71.22 357	20.74 370	85.51 344	46.47 329	58.75 337	79.06 354

FMVSNet5		68.04 297	65.66 296	75.18 307	84.43 260	57.89 297	83.54 300	86.26 307	61.83 313	53.64 340	73.30 345	37.15 322	85.08 345	48.99 315	61.77 317	82.56 325

test0.0.03 1		72.76 258	72.71 244	72.88 324	80.25 306	47.99 355	91.22 190	89.45 234	71.51 213	62.51 299	87.66 207	53.83 202	85.06 346	50.16 310	67.84 270	85.58 283

testgi		64.48 318	62.87 316	69.31 342	71.24 360	40.62 377	85.49 289	79.92 348	65.36 281	54.18 337	83.49 256	23.74 365	84.55 347	41.60 348	60.79 327	82.77 318

testing3		70.38 277	70.83 261	69.03 343	85.82 236	43.93 371	90.72 207	90.56 191	68.06 259	60.24 308	86.82 219	64.83 74	84.12 348	26.33 381	64.10 298	79.04 355

ADS-MVSNet2		66.90 305	63.44 312	77.26 290	88.06 188	60.70 262	68.01 369	75.56 357	57.57 333	64.48 278	69.87 358	38.68 302	84.10 349	40.87 351	67.89 268	86.97 252

CVMVSNet		74.04 244	74.27 221	73.33 320	85.33 242	43.94 370	89.53 240	88.39 278	54.33 348	70.37 211	90.13 172	49.17 247	84.05 350	61.83 267	79.36 179	91.99 177

ITE_SJBPF				70.43 338	74.44 352	47.06 362		77.32 351	60.16 323	54.04 338	83.53 254	23.30 366	84.01 351	43.07 341	61.58 322	80.21 348

CHOSEN 280x420		77.35 198	76.95 186	78.55 273	87.07 213	62.68 222	69.71 365	82.95 337	68.80 253	71.48 200	87.27 214	66.03 60	84.00 352	76.47 140	82.81 152	88.95 219

DTE-MVSNet		68.46 294	67.33 287	71.87 335	77.94 337	49.00 352	86.16 288	88.58 275	66.36 274	58.19 320	82.21 269	46.36 268	83.87 353	44.97 337	55.17 346	82.73 319

IterMVS-SCA-FT		71.55 270	69.97 269	76.32 299	81.48 292	60.67 263	87.64 274	85.99 311	66.17 275	59.50 312	78.88 313	45.53 277	83.65 354	62.58 262	61.93 315	84.63 299

PEN-MVS		69.46 285	68.56 279	72.17 331	79.27 317	49.71 347	86.90 283	89.24 242	67.24 270	59.08 316	82.51 266	47.23 263	83.54 355	48.42 318	57.12 339	83.25 312

WR-MVS_H		70.59 274	69.94 270	72.53 326	81.03 295	51.43 338	87.35 277	92.03 130	67.38 266	60.23 309	80.70 293	55.84 181	83.45 356	46.33 330	58.58 338	82.72 320

YYNet1		63.76 323	60.14 326	74.62 311	78.06 336	60.19 271	83.46 303	83.99 330	56.18 343	39.25 377	71.56 355	37.18 321	83.34 357	42.90 343	48.70 361	80.32 345

PM-MVS		59.40 334	56.59 336	67.84 346	63.63 376	41.86 373	76.76 349	63.22 381	59.01 329	51.07 350	72.27 351	11.72 384	83.25 358	61.34 268	50.28 359	78.39 360

MDA-MVSNet_test_wron		63.78 322	60.16 325	74.64 310	78.15 335	60.41 266	83.49 301	84.03 326	56.17 344	39.17 378	71.59 354	37.22 320	83.24 359	42.87 344	48.73 360	80.26 346

KD-MVS_self_test		60.87 330	58.60 330	67.68 348	66.13 374	39.93 379	75.63 355	84.70 321	57.32 336	49.57 355	68.45 361	29.55 351	82.87 360	48.09 319	47.94 362	80.25 347

N_pmnet		50.55 342	49.11 345	54.88 363	77.17 342	4.02 406	84.36 295	2.00 404	48.59 362	45.86 365	68.82 360	32.22 342	82.80 361	31.58 378	51.38 356	77.81 362

test20.03		63.83 321	62.65 317	67.38 350	70.58 366	39.94 378	86.57 286	84.17 325	63.29 296	51.86 345	77.30 324	37.09 323	82.47 362	38.87 359	54.13 350	79.73 349

TDRefinement		55.28 340	51.58 343	66.39 352	59.53 383	46.15 364	76.23 352	72.80 364	44.60 372	42.49 374	76.28 335	15.29 379	82.39 363	33.20 371	43.75 368	70.62 374

CP-MVSNet		70.50 275	69.91 271	72.26 329	80.71 299	51.00 341	87.23 279	90.30 202	67.84 261	59.64 311	82.69 263	50.23 236	82.30 364	51.28 305	59.28 334	83.46 309

PS-CasMVS		69.86 282	69.13 277	72.07 333	80.35 304	50.57 343	87.02 281	89.75 223	67.27 267	59.19 315	82.28 267	46.58 267	82.24 365	50.69 307	59.02 335	83.39 311

RPSCF		64.24 319	61.98 321	71.01 337	76.10 347	45.00 367	75.83 354	75.94 354	46.94 367	58.96 317	84.59 243	31.40 346	82.00 366	47.76 324	60.33 332	86.04 273

new-patchmatchnet		59.30 335	56.48 337	67.79 347	65.86 375	44.19 368	82.47 313	81.77 340	59.94 325	43.65 373	66.20 365	27.67 357	81.68 367	39.34 356	41.40 372	77.50 363

MIMVSNet1		60.16 333	57.33 334	68.67 344	69.71 367	44.13 369	78.92 340	84.21 324	55.05 346	44.63 370	71.85 352	23.91 364	81.54 368	32.63 375	55.03 347	80.35 344

test_fmvs2		65.78 312	64.84 300	68.60 345	66.54 373	41.71 374	83.27 305	69.81 372	54.38 347	67.91 245	84.54 245	15.35 378	81.22 369	75.65 144	66.16 279	82.88 316

dmvs_testset		65.55 313	66.45 289	62.86 355	79.87 310	22.35 398	76.55 350	71.74 368	77.42 101	55.85 331	87.77 206	51.39 226	80.69 370	31.51 380	65.92 281	85.55 285

test_vis1_rt		59.09 336	57.31 335	64.43 353	68.44 371	46.02 365	83.05 310	48.63 393	51.96 353	49.57 355	63.86 369	16.30 376	80.20 371	71.21 181	62.79 306	67.07 378

EU-MVSNet		64.01 320	63.01 314	67.02 351	74.40 353	38.86 382	83.27 305	86.19 309	45.11 371	54.27 336	81.15 290	36.91 325	80.01 372	48.79 317	57.02 340	82.19 329

pmmvs3		55.51 339	51.50 344	67.53 349	57.90 384	50.93 342	80.37 329	73.66 362	40.63 379	44.15 372	64.75 368	16.30 376	78.97 373	44.77 338	40.98 375	72.69 370

mvsany_test1		68.77 290	68.56 279	69.39 341	73.57 355	45.88 366	80.93 326	60.88 384	59.65 326	71.56 199	90.26 168	43.22 288	75.05 374	74.26 157	62.70 307	87.25 250

DSMNet-mixed		56.78 338	54.44 341	63.79 354	63.21 377	29.44 393	64.43 375	64.10 380	42.12 378	51.32 348	71.60 353	31.76 344	75.04 375	36.23 362	65.20 287	86.87 255

EGC-MVSNET		42.35 349	38.09 352	55.11 362	74.57 351	46.62 363	71.63 361	55.77 385	0.04 399	0.24 400	62.70 371	14.24 382	74.91 376	17.59 388	46.06 365	43.80 385

test_fmvs3		56.82 337	54.86 340	62.69 356	53.59 386	35.47 384	75.87 353	65.64 379	43.91 374	55.10 333	71.43 356	6.91 392	74.40 377	68.64 207	52.63 352	78.20 361

WB-MVS		46.23 346	44.94 348	50.11 367	62.13 380	21.23 400	76.48 351	55.49 386	45.89 369	35.78 379	61.44 375	35.54 329	72.83 378	9.96 394	21.75 389	56.27 382

new_pmnet		49.31 343	46.44 346	57.93 358	62.84 378	40.74 376	68.47 368	62.96 382	36.48 380	35.09 380	57.81 377	14.97 380	72.18 379	32.86 373	46.44 364	60.88 380

Gipuma		34.91 356	31.44 359	45.30 372	70.99 363	39.64 381	19.85 394	72.56 365	20.10 390	16.16 394	21.47 395	5.08 395	71.16 380	13.07 392	43.70 369	25.08 392
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
SSC-MVS		44.51 348	43.35 350	47.99 371	61.01 382	18.90 402	74.12 357	54.36 387	43.42 376	34.10 382	60.02 376	34.42 334	70.39 381	9.14 396	19.57 390	54.68 383

test_vis3_rt		40.46 352	37.79 353	48.47 370	44.49 394	33.35 387	66.56 373	32.84 401	32.39 383	29.65 383	39.13 391	3.91 399	68.65 382	50.17 309	40.99 374	43.40 386

LF4IMVS		54.01 341	52.12 342	59.69 357	62.41 379	39.91 380	68.59 367	68.28 376	42.96 377	44.55 371	75.18 340	14.09 383	68.39 383	41.36 350	51.68 355	70.78 373

PMVS	26.43 22	31.84 359	28.16 362	42.89 373	25.87 402	27.58 394	50.92 388	49.78 391	21.37 389	14.17 395	40.81 390	2.01 402	66.62 384	9.61 395	38.88 378	34.49 391
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
APD_test1		40.50 351	37.31 354	50.09 368	51.88 387	35.27 385	59.45 382	52.59 389	21.64 388	26.12 386	57.80 378	4.56 396	66.56 385	22.64 384	39.09 376	48.43 384

LCM-MVSNet		40.54 350	35.79 355	54.76 364	36.92 399	30.81 390	51.41 387	69.02 373	22.07 387	24.63 387	45.37 384	4.56 396	65.81 386	33.67 369	34.50 383	67.67 376

test_f		46.58 345	43.45 349	55.96 360	45.18 393	32.05 388	61.18 378	49.49 392	33.39 382	42.05 375	62.48 372	7.00 391	65.56 387	47.08 327	43.21 370	70.27 375

PMMVS2		37.93 355	33.61 358	50.92 366	46.31 391	24.76 396	60.55 381	50.05 390	28.94 386	20.93 388	47.59 381	4.41 398	65.13 388	25.14 382	18.55 392	62.87 379

FPMVS		45.64 347	43.10 351	53.23 365	51.42 389	36.46 383	64.97 374	71.91 367	29.13 385	27.53 385	61.55 374	9.83 387	65.01 389	16.00 391	55.58 345	58.22 381

ANet_high		40.27 353	35.20 356	55.47 361	34.74 400	34.47 386	63.84 376	71.56 369	48.42 363	18.80 390	41.08 389	9.52 388	64.45 390	20.18 386	8.66 397	67.49 377

mvsany_test3		48.86 344	46.35 347	56.41 359	46.00 392	31.67 389	62.26 377	47.25 394	43.71 375	45.54 367	68.15 362	10.84 385	64.44 391	57.95 284	35.44 382	73.13 369

testf1		32.77 357	29.47 360	42.67 374	41.89 396	30.81 390	52.07 385	43.45 395	15.45 391	18.52 391	44.82 385	2.12 400	58.38 392	16.05 389	30.87 386	38.83 387

APD_test2		32.77 357	29.47 360	42.67 374	41.89 396	30.81 390	52.07 385	43.45 395	15.45 391	18.52 391	44.82 385	2.12 400	58.38 392	16.05 389	30.87 386	38.83 387

test_method		38.59 354	35.16 357	48.89 369	54.33 385	21.35 399	45.32 390	53.71 388	7.41 396	28.74 384	51.62 380	8.70 389	52.87 394	33.73 368	32.89 384	72.47 371

MVE	24.84 23	24.35 361	19.77 367	38.09 376	34.56 401	26.92 395	26.57 392	38.87 399	11.73 395	11.37 396	27.44 392	1.37 403	50.42 395	11.41 393	14.60 393	36.93 389
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
E-PMN		24.61 360	24.00 364	26.45 378	43.74 395	18.44 403	60.86 379	39.66 397	15.11 393	9.53 397	22.10 394	6.52 393	46.94 396	8.31 397	10.14 394	13.98 394

EMVS		23.76 362	23.20 366	25.46 379	41.52 398	16.90 404	60.56 380	38.79 400	14.62 394	8.99 398	20.24 397	7.35 390	45.82 397	7.25 398	9.46 395	13.64 395

DeepMVS_CX				34.71 377	51.45 388	24.73 397		28.48 403	31.46 384	17.49 393	52.75 379	5.80 394	42.60 398	18.18 387	19.42 391	36.81 390

tmp_tt		22.26 363	23.75 365	17.80 380	5.23 403	12.06 405	35.26 391	39.48 398	2.82 398	18.94 389	44.20 387	22.23 368	24.64 399	36.30 361	9.31 396	16.69 393

wuyk23d		11.30 365	10.95 368	12.33 381	48.05 390	19.89 401	25.89 393	1.92 405	3.58 397	3.12 399	1.37 399	0.64 404	15.77 400	6.23 399	7.77 398	1.35 396

testmvs		7.23 367	9.62 370	0.06 383	0.04 404	0.02 408	84.98 293	0.02 406	0.03 400	0.18 401	1.21 400	0.01 406	0.02 401	0.14 400	0.01 399	0.13 398

test123		6.92 368	9.21 371	0.08 382	0.03 405	0.05 407	81.65 319	0.01 407	0.02 401	0.14 402	0.85 401	0.03 405	0.02 401	0.12 401	0.00 400	0.16 397

test_blank		0.00 370	0.00 373	0.00 384	0.00 406	0.00 409	0.00 395	0.00 408	0.00 402	0.00 403	0.00 402	0.00 407	0.00 403	0.00 402	0.00 400	0.00 399

uanet_test		0.00 370	0.00 373	0.00 384	0.00 406	0.00 409	0.00 395	0.00 408	0.00 402	0.00 403	0.00 402	0.00 407	0.00 403	0.00 402	0.00 400	0.00 399

DCPMVS		0.00 370	0.00 373	0.00 384	0.00 406	0.00 409	0.00 395	0.00 408	0.00 402	0.00 403	0.00 402	0.00 407	0.00 403	0.00 402	0.00 400	0.00 399

cdsmvs_eth3d_5k		19.86 364	26.47 363	0.00 384	0.00 406	0.00 409	0.00 395	93.45 77	0.00 402	0.00 403	95.27 56	49.56 241	0.00 403	0.00 402	0.00 400	0.00 399

pcd_1.5k_mvsjas		4.46 369	5.95 372	0.00 384	0.00 406	0.00 409	0.00 395	0.00 408	0.00 402	0.00 403	0.00 402	53.55 206	0.00 403	0.00 402	0.00 400	0.00 399

sosnet-low-res		0.00 370	0.00 373	0.00 384	0.00 406	0.00 409	0.00 395	0.00 408	0.00 402	0.00 403	0.00 402	0.00 407	0.00 403	0.00 402	0.00 400	0.00 399

sosnet		0.00 370	0.00 373	0.00 384	0.00 406	0.00 409	0.00 395	0.00 408	0.00 402	0.00 403	0.00 402	0.00 407	0.00 403	0.00 402	0.00 400	0.00 399

uncertanet		0.00 370	0.00 373	0.00 384	0.00 406	0.00 409	0.00 395	0.00 408	0.00 402	0.00 403	0.00 402	0.00 407	0.00 403	0.00 402	0.00 400	0.00 399

Regformer		0.00 370	0.00 373	0.00 384	0.00 406	0.00 409	0.00 395	0.00 408	0.00 402	0.00 403	0.00 402	0.00 407	0.00 403	0.00 402	0.00 400	0.00 399

ab-mvs-re		7.91 366	10.55 369	0.00 384	0.00 406	0.00 409	0.00 395	0.00 408	0.00 402	0.00 403	94.95 64	0.00 407	0.00 403	0.00 402	0.00 400	0.00 399

uanet		0.00 370	0.00 373	0.00 384	0.00 406	0.00 409	0.00 395	0.00 408	0.00 402	0.00 403	0.00 402	0.00 407	0.00 403	0.00 402	0.00 400	0.00 399

WAC-MVS						49.45 349								31.56 379

FOURS1					93.95 45	61.77 238	93.96 70	91.92 134	62.14 308	86.57 44

test_one_0601					96.32 18	69.74 42		94.18 51	71.42 215	90.67 18	96.85 16	74.45 18

eth-test2					0.00 406

eth-test					0.00 406

RE-MVS-def			80.48 130		92.02 91	58.56 292	90.90 199	90.45 192	62.76 302	78.89 115	94.46 78	49.30 244		78.77 127	86.77 123	92.28 169

IU-MVS					96.46 11	69.91 37		95.18 16	80.75 46	95.28 1				92.34 21	95.36 13	96.47 25

save fliter					93.84 48	67.89 85	95.05 39	92.66 107	78.19 84

test0726					96.40 15	69.99 33	96.76 7	94.33 48	71.92 191	91.89 10	97.11 6	73.77 21

GSMVS																94.68 87

test_part2					96.29 19	68.16 79				90.78 16

sam_mvs1												57.85 153				94.68 87

sam_mvs												54.91 191

MTGPA								92.23 120

MTMP							93.77 84	32.52 402

test9_res														89.41 39	94.96 18	95.29 63

agg_prior2														86.41 66	94.75 29	95.33 59

test_prior4						67.18 104	93.92 73

test_prior2							95.10 38		75.40 123	85.25 60	95.61 45	67.94 46		87.47 56	94.77 25

新几何2							91.41 175

旧先验1					91.94 95	60.74 260		91.50 157			94.36 82	65.23 68			91.84 69	94.55 94

原ACMM2							92.01 151

test222					89.77 142	61.60 243	89.55 238	89.42 236	56.83 340	77.28 135	92.43 130	52.76 214			91.14 83	93.09 145

segment_acmp												65.94 61

testdata1							89.21 247		77.55 97

plane_prior7					86.94 216	61.51 244

plane_prior6					87.23 208	62.32 228						50.66 231

plane_prior4											89.14 183

plane_prior3						61.95 236			79.09 71	72.53 184

plane_prior2							93.13 105		78.81 78

plane_prior1					87.15 210

plane_prior						62.42 224	93.85 77		79.38 63						78.80 185

n2								0.00 408

nn								0.00 408

door-mid								66.01 378

test11								93.01 94

door								66.57 377

HQP5-MVS						63.66 196

HQP-NCC					87.54 201		94.06 63		79.80 56	74.18 164

ACMP_Plane					87.54 201		94.06 63		79.80 56	74.18 164

BP-MVS														77.63 134

HQP3-MVS								91.70 149							78.90 183

HQP2-MVS												51.63 224

NP-MVS					87.41 204	63.04 210					90.30 166

MDTV_nov1_ep13_2view						59.90 274	80.13 334		67.65 264	72.79 179		54.33 199		59.83 277		92.58 160

ACMMP++_ref															71.63 241

ACMMP++															69.72 251

Test By Simon												54.21 200

High-resolution multi-view benchmark