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.

MM		80.20 8	80.28 10	79.99 2	82.19 90	60.01 49	86.19 21	83.93 60	73.19 1	77.08 45	91.21 20	57.23 38	90.73 10	83.35 1	88.12 37	89.22 8

MGCNet		78.45 21	78.28 22	78.98 29	80.73 115	57.91 90	84.68 41	81.64 132	68.35 2	75.77 51	90.38 34	53.98 80	90.26 13	81.30 3	87.68 45	88.77 18

CANet		76.46 44	75.93 48	78.06 43	81.29 105	57.53 96	82.35 80	83.31 96	67.78 3	70.09 159	86.34 142	54.92 69	88.90 30	72.68 75	84.55 74	87.76 59

UA-Net		73.13 101	72.93 100	73.76 152	83.58 72	51.66 220	78.75 134	77.66 231	67.75 4	72.61 126	89.42 56	49.82 150	83.29 166	53.61 265	83.14 89	86.32 124

CNVR-MVS		79.84 12	79.97 12	79.45 11	87.90 2	62.17 17	84.37 45	85.03 42	66.96 5	77.58 39	90.06 45	59.47 25	89.13 27	78.67 17	89.73 16	87.03 89

TranMVSNet+NR-MVSNet		70.36 162	70.10 157	71.17 242	78.64 169	42.97 365	76.53 214	81.16 153	66.95 6	68.53 190	85.42 174	51.61 126	83.07 170	52.32 273	69.70 329	87.46 71

3Dnovator+	66.72 4	75.84 54	74.57 67	79.66 9	82.40 87	59.92 51	85.83 27	86.32 17	66.92 7	67.80 216	89.24 60	42.03 253	89.38 24	64.07 158	86.50 62	89.69 3

NCCC		78.58 19	78.31 21	79.39 12	87.51 12	62.61 13	85.20 36	84.42 51	66.73 8	74.67 75	89.38 58	55.30 64	89.18 26	74.19 63	87.34 49	86.38 115

SteuartSystems-ACMMP		79.48 14	79.31 14	79.98 3	83.01 81	62.18 16	87.60 9	85.83 25	66.69 9	78.03 36	90.98 21	54.26 75	90.06 14	78.42 23	89.02 26	87.69 61
Skip Steuart: Steuart Systems R&D Blog.
EPNet		73.09 102	72.16 113	75.90 80	75.95 264	56.28 115	83.05 67	72.39 332	66.53 10	65.27 268	87.00 114	50.40 143	85.47 119	62.48 184	86.32 64	85.94 136
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
UniMVSNet_NR-MVSNet		71.11 143	71.00 137	71.44 229	79.20 149	44.13 344	76.02 229	82.60 118	66.48 11	68.20 195	84.60 192	56.82 42	82.82 192	54.62 255	70.43 309	87.36 80

MSP-MVS		81.06 3	81.40 4	80.02 1	86.21 32	62.73 9	86.09 22	86.83 8	65.51 12	83.81 10	90.51 30	63.71 13	89.23 25	81.51 2	88.44 30	88.09 46
Zhenlong Yuan, Cong Liu, Fei Shen, Zhaoxin Li, Jingguo luo, Tianlu Mao and Zhaoqi Wang: MSP-MVS: Multi-granularity Segmentation Prior Guided Multi-View Stereo. AAAI2025
HPM-MVS++		79.88 11	80.14 11	79.10 21	88.17 1	64.80 1	86.59 16	83.70 79	65.37 13	78.78 29	90.64 24	58.63 30	87.24 60	79.00 14	90.37 14	85.26 176

NR-MVSNet		69.54 187	68.85 180	71.59 223	78.05 192	43.81 349	74.20 270	80.86 160	65.18 14	62.76 312	84.52 193	52.35 112	83.59 160	50.96 288	70.78 304	87.37 78

MTAPA		76.90 38	76.42 42	78.35 39	86.08 38	63.57 2	74.92 255	80.97 158	65.13 15	75.77 51	90.88 22	48.63 169	86.66 79	77.23 30	88.17 36	84.81 192

DVP-MVS++		81.67 1	82.40 1	79.47 10	87.24 14	59.15 68	88.18 1	87.15 3	65.04 16	84.26 5	91.86 6	67.01 1	90.84 3	79.48 7	91.38 2	88.42 31

test_0728_THIRD									65.04 16	83.82 8	92.00 3	64.69 11	90.75 8	79.48 7	90.63 10	88.09 46

EI-MVSNet-Vis-set		72.42 119	71.59 121	74.91 102	78.47 173	54.02 157	77.05 197	79.33 186	65.03 18	71.68 139	79.35 317	52.75 104	84.89 133	66.46 137	74.23 245	85.83 143

casdiffmvs_mvg		76.14 50	76.30 43	75.66 88	76.46 257	51.83 218	79.67 121	85.08 39	65.02 19	75.84 50	88.58 74	59.42 26	85.08 126	72.75 74	83.93 83	90.08 1
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_one_0601					87.58 9	59.30 62		86.84 7	65.01 20	83.80 11	91.86 6	64.03 12

ETV-MVS		74.46 72	73.84 82	76.33 75	79.27 147	55.24 141	79.22 128	85.00 44	64.97 21	72.65 125	79.46 314	53.65 92	87.87 49	67.45 125	82.91 96	85.89 139

NormalMVS		76.26 48	75.74 51	77.83 50	82.75 85	59.89 52	84.36 46	83.21 101	64.69 22	74.21 82	87.40 96	49.48 155	86.17 97	68.04 114	87.55 46	87.42 73

SymmetryMVS		75.28 59	74.60 66	77.30 59	83.85 70	59.89 52	84.36 46	75.51 281	64.69 22	74.21 82	87.40 96	49.48 155	86.17 97	68.04 114	83.88 84	85.85 141

WR-MVS		68.47 218	68.47 191	68.44 296	80.20 126	39.84 396	73.75 282	76.07 268	64.68 24	68.11 203	83.63 216	50.39 144	79.14 281	49.78 293	69.66 330	86.34 119

XVS		77.17 35	76.56 40	79.00 26	86.32 30	62.62 11	85.83 27	83.92 61	64.55 25	72.17 132	90.01 49	47.95 176	88.01 45	71.55 88	86.74 58	86.37 117

X-MVStestdata		70.21 165	67.28 225	79.00 26	86.32 30	62.62 11	85.83 27	83.92 61	64.55 25	72.17 132	6.49 508	47.95 176	88.01 45	71.55 88	86.74 58	86.37 117

HQP_MVS		74.31 73	73.73 84	76.06 78	81.41 102	56.31 113	84.22 51	84.01 58	64.52 27	69.27 178	86.10 150	45.26 218	87.21 64	68.16 110	80.58 126	84.65 196

plane_prior2							84.22 51		64.52 27

EI-MVSNet-UG-set		71.92 129	71.06 136	74.52 119	77.98 195	53.56 168	76.62 211	79.16 187	64.40 29	71.18 146	78.95 322	52.19 114	84.66 140	65.47 148	73.57 258	85.32 172

DU-MVS		70.01 170	69.53 164	71.44 229	78.05 192	44.13 344	75.01 251	81.51 135	64.37 30	68.20 195	84.52 193	49.12 166	82.82 192	54.62 255	70.43 309	87.37 78

DVP-MVS		80.84 4	81.64 3	78.42 38	87.75 7	59.07 73	87.85 5	85.03 42	64.26 31	83.82 8	92.00 3	64.82 8	90.75 8	78.66 18	90.61 11	85.45 164
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					87.75 7	59.07 73	87.86 4	86.83 8	64.26 31	84.19 7	91.92 5	64.82 8

test_241102_ONE					87.77 4	58.90 78		86.78 10	64.20 33	85.97 1	91.34 18	66.87 3	90.78 7

SED-MVS		81.56 2	82.30 2	79.32 13	87.77 4	58.90 78	87.82 7	86.78 10	64.18 34	85.97 1	91.84 8	66.87 3	90.83 5	78.63 20	90.87 5	88.23 39

test_241102_TWO								86.73 12	64.18 34	84.26 5	91.84 8	65.19 6	90.83 5	78.63 20	90.70 7	87.65 63

LFMVS		71.78 132	71.59 121	72.32 202	83.40 76	46.38 318	79.75 119	71.08 341	64.18 34	72.80 122	88.64 73	42.58 248	83.72 156	57.41 231	84.49 77	86.86 95

IS-MVSNet		71.57 136	71.00 137	73.27 177	78.86 159	45.63 329	80.22 109	78.69 201	64.14 37	66.46 243	87.36 99	49.30 160	85.60 112	50.26 292	83.71 88	88.59 27

plane_prior3						56.09 119			63.92 38	69.27 178

MP-MVS		78.35 23	78.26 24	78.64 35	86.54 26	63.47 4	86.02 24	83.55 85	63.89 39	73.60 96	90.60 25	54.85 70	86.72 77	77.20 31	88.06 39	85.74 150
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
DELS-MVS		74.76 65	74.46 68	75.65 89	77.84 199	52.25 207	75.59 237	84.17 55	63.76 40	73.15 109	82.79 231	59.58 24	86.80 75	67.24 126	86.04 66	87.89 51
Christian Sormann, Emanuele Santellani, Mattia Rossi, Andreas Kuhn, Friedrich Fraundorfer: DELS-MVS: Deep Epipolar Line Search for Multi-View Stereo. Winter Conference on Applications of Computer Vision (WACV), 2023
OPM-MVS		74.73 66	74.25 72	76.19 77	80.81 114	59.01 76	82.60 77	83.64 82	63.74 41	72.52 127	87.49 93	47.18 191	85.88 107	69.47 99	80.78 120	83.66 237
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
UniMVSNet (Re)		70.63 155	70.20 152	71.89 209	78.55 170	45.29 332	75.94 230	82.92 112	63.68 42	68.16 198	83.59 217	53.89 83	83.49 163	53.97 261	71.12 300	86.89 93

GST-MVS		78.14 25	77.85 27	78.99 28	86.05 39	61.82 22	85.84 26	85.21 36	63.56 43	74.29 81	90.03 47	52.56 106	88.53 34	74.79 59	88.34 32	86.63 107

testing3-2		62.06 330	62.36 309	61.17 391	79.29 144	30.31 472	64.09 414	63.49 413	63.50 44	62.84 309	82.22 253	32.35 388	69.02 397	40.01 394	73.43 263	84.17 213

EC-MVSNet		75.84 54	75.87 50	75.74 86	78.86 159	52.65 196	83.73 61	86.08 19	63.47 45	72.77 123	87.25 108	53.13 98	87.93 47	71.97 83	85.57 69	86.66 105

casdiffseed414692147		73.73 86	73.22 95	75.28 98	76.76 248	52.16 209	80.05 111	83.01 110	63.38 46	73.35 102	87.11 112	53.22 95	84.14 146	61.71 192	80.38 130	89.55 5

ZNCC-MVS		78.82 16	78.67 19	79.30 14	86.43 29	62.05 18	86.62 15	86.01 20	63.32 47	75.08 61	90.47 33	53.96 82	88.68 32	76.48 39	89.63 20	87.16 86

MED-MVS		80.40 6	80.84 6	79.07 25	85.30 50	59.25 64	86.84 11	85.86 23	63.31 48	83.65 12	91.48 12	64.70 10	89.91 16	77.02 34	89.43 22	88.06 49

TestfortrainingZip a		79.61 13	79.84 13	78.92 30	85.30 50	59.08 72	86.84 11	86.01 20	63.31 48	82.37 17	91.48 12	60.88 18	89.61 21	76.25 43	86.13 65	88.06 49

TestfortrainingZip				78.05 44	84.66 62	58.22 87	86.84 11	85.98 22	63.31 48	79.39 24	88.94 65	62.01 15	89.61 21		86.45 63	86.34 119

DPE-MVS		80.56 5	80.98 5	79.29 15	87.27 13	60.56 41	85.71 31	86.42 15	63.28 51	83.27 15	91.83 10	64.96 7	90.47 11	76.41 40	89.67 18	86.84 96
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
CS-MVS		76.25 49	75.98 47	77.06 61	80.15 129	55.63 131	84.51 44	83.90 63	63.24 52	73.30 103	87.27 103	55.06 66	86.30 94	71.78 85	84.58 73	89.25 7

DeepC-MVS	69.38 2	78.56 20	78.14 25	79.83 7	83.60 71	61.62 23	84.17 53	86.85 6	63.23 53	73.84 93	90.25 40	57.68 34	89.96 15	74.62 60	89.03 25	87.89 51
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
VDD-MVS		72.50 115	72.09 114	73.75 154	81.58 98	49.69 268	77.76 172	77.63 232	63.21 54	73.21 106	89.02 62	42.14 252	83.32 165	61.72 191	82.50 102	88.25 37

plane_prior						56.31 113	83.58 64		63.19 55						80.48 129

hybridcas		74.86 63	75.07 60	74.24 128	76.30 258	50.58 240	79.30 127	83.88 66	63.15 56	74.69 73	88.13 78	58.91 28	82.98 176	68.30 104	82.93 95	89.15 10

ME-MVS		80.04 10	80.36 9	79.08 24	86.63 23	59.25 64	85.62 32	86.73 12	63.10 57	82.27 18	90.57 27	61.90 16	89.88 18	77.02 34	89.43 22	88.10 44

ACMMP		76.02 52	75.33 56	78.07 42	85.20 53	61.91 20	85.49 35	84.44 50	63.04 58	69.80 169	89.74 55	45.43 214	87.16 66	72.01 81	82.87 98	85.14 178
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
PEN-MVS		66.60 263	66.45 243	67.04 317	77.11 236	36.56 431	77.03 198	80.42 168	62.95 59	62.51 320	84.03 205	46.69 199	79.07 284	44.22 356	63.08 396	85.51 159

APDe-MVS		80.16 9	80.59 7	78.86 33	86.64 21	60.02 48	88.12 3	86.42 15	62.94 60	82.40 16	92.12 2	59.64 23	89.76 19	78.70 15	88.32 34	86.79 98
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
mPP-MVS		76.54 43	75.93 48	78.34 40	86.47 27	63.50 3	85.74 30	82.28 122	62.90 61	71.77 137	90.26 39	46.61 200	86.55 85	71.71 86	85.66 68	84.97 187

ACMMP_NAP		78.77 18	78.78 17	78.74 34	85.44 46	61.04 31	83.84 60	85.16 37	62.88 62	78.10 34	91.26 19	52.51 107	88.39 35	79.34 9	90.52 13	86.78 99

DeepPCF-MVS	69.58 1	79.03 15	79.00 16	79.13 19	84.92 60	60.32 46	83.03 68	85.33 34	62.86 63	80.17 21	90.03 47	61.76 17	88.95 29	74.21 62	88.67 29	88.12 43

HFP-MVS		78.01 27	77.65 29	79.10 21	86.71 19	62.81 8	86.29 18	84.32 53	62.82 64	73.96 86	90.50 31	53.20 97	88.35 36	74.02 65	87.05 50	86.13 131

ACMMPR		77.71 29	77.23 32	79.16 17	86.75 18	62.93 7	86.29 18	84.24 54	62.82 64	73.55 98	90.56 29	49.80 151	88.24 38	74.02 65	87.03 51	86.32 124

region2R		77.67 31	77.18 33	79.15 18	86.76 17	62.95 6	86.29 18	84.16 56	62.81 66	73.30 103	90.58 26	49.90 148	88.21 39	73.78 67	87.03 51	86.29 128

casdiffmvs		74.80 64	74.89 64	74.53 118	75.59 272	50.37 249	78.17 156	85.06 41	62.80 67	74.40 78	87.86 87	57.88 32	83.61 159	69.46 100	82.79 100	89.59 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
baseline		74.61 69	74.70 65	74.34 123	75.70 267	49.99 259	77.54 177	84.63 48	62.73 68	73.98 85	87.79 90	57.67 35	83.82 155	69.49 98	82.74 101	89.20 9

HPM-MVS		77.28 33	76.85 34	78.54 36	85.00 55	60.81 38	82.91 71	85.08 39	62.57 69	73.09 114	89.97 50	50.90 139	87.48 58	75.30 53	86.85 56	87.33 81
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
DTE-MVSNet		65.58 277	65.34 269	66.31 332	76.06 263	34.79 444	76.43 216	79.38 185	62.55 70	61.66 333	83.83 210	45.60 208	79.15 280	41.64 386	60.88 418	85.00 184

SMA-MVS		80.28 7	80.39 8	79.95 4	86.60 24	61.95 19	86.33 17	85.75 27	62.49 71	82.20 19	92.28 1	56.53 43	89.70 20	79.85 6	91.48 1	88.19 41
Yufeng Yin; Xiaoyan Liu; Zichao Zhang: SMA-MVS: Segmentation-Guided Multi-Scale Anchor Deformation Patch Multi-View Stereo. IEEE Transactions on Circuits and Systems for Video Technology
CP-MVSNet		66.49 266	66.41 247	66.72 320	77.67 206	36.33 434	76.83 208	79.52 182	62.45 72	62.54 318	83.47 223	46.32 202	78.37 302	45.47 348	63.43 392	85.45 164

CP-MVS		77.12 36	76.68 36	78.43 37	86.05 39	63.18 5	87.55 10	83.45 88	62.44 73	72.68 124	90.50 31	48.18 174	87.34 59	73.59 69	85.71 67	84.76 195

PS-CasMVS		66.42 267	66.32 251	66.70 322	77.60 214	36.30 436	76.94 202	79.61 180	62.36 74	62.43 323	83.66 215	45.69 206	78.37 302	45.35 350	63.26 394	85.42 167

E5new		74.10 77	74.09 74	74.15 134	77.14 228	50.74 233	78.24 148	83.86 70	62.34 75	73.95 87	87.27 103	55.97 58	82.95 179	68.16 110	79.86 137	88.77 18

E6new		74.10 77	74.09 74	74.15 134	77.14 228	50.74 233	78.24 148	83.85 72	62.34 75	73.95 87	87.27 103	55.98 56	82.95 179	68.17 108	79.85 139	88.77 18

E6		74.10 77	74.09 74	74.15 134	77.14 228	50.74 233	78.24 148	83.85 72	62.34 75	73.95 87	87.27 103	55.98 56	82.95 179	68.17 108	79.85 139	88.77 18

E5		74.10 77	74.09 74	74.15 134	77.14 228	50.74 233	78.24 148	83.86 70	62.34 75	73.95 87	87.27 103	55.97 58	82.95 179	68.16 110	79.86 137	88.77 18

3Dnovator	64.47 5	72.49 116	71.39 127	75.79 83	77.70 204	58.99 77	80.66 104	83.15 106	62.24 79	65.46 264	86.59 132	42.38 251	85.52 115	59.59 211	84.72 72	82.85 260

E4		73.91 83	73.83 83	74.15 134	77.13 232	50.47 246	77.15 194	83.79 75	62.21 80	73.61 95	87.19 110	56.08 54	83.03 171	67.91 116	79.35 151	88.94 13

MP-MVS-pluss		78.35 23	78.46 20	78.03 45	84.96 56	59.52 58	82.93 70	85.39 33	62.15 81	76.41 49	91.51 11	52.47 109	86.78 76	80.66 4	89.64 19	87.80 57
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
HQP-NCC					80.66 116		82.31 82		62.10 82	67.85 210

ACMP_Plane					80.66 116		82.31 82		62.10 82	67.85 210

HQP-MVS		73.45 91	72.80 103	75.40 93	80.66 116	54.94 144	82.31 82	83.90 63	62.10 82	67.85 210	85.54 172	45.46 212	86.93 72	67.04 130	80.35 131	84.32 206

SPE-MVS-test		75.62 57	75.31 57	76.56 72	80.63 119	55.13 142	83.88 59	85.22 35	62.05 85	71.49 144	86.03 153	53.83 84	86.36 92	67.74 118	86.91 55	88.19 41

VPNet		67.52 242	68.11 204	65.74 346	79.18 151	36.80 429	72.17 315	72.83 328	62.04 86	67.79 217	85.83 162	48.88 168	76.60 348	51.30 284	72.97 272	83.81 227

WR-MVS_H		67.02 254	66.92 235	67.33 315	77.95 196	37.75 418	77.57 175	82.11 125	62.03 87	62.65 315	82.48 246	50.57 142	79.46 270	42.91 374	64.01 383	84.79 193

DeepC-MVS_fast	68.24 3	77.25 34	76.63 37	79.12 20	86.15 35	60.86 36	84.71 40	84.85 46	61.98 88	73.06 115	88.88 67	53.72 88	89.06 28	68.27 105	88.04 40	87.42 73
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
SF-MVS		78.82 16	79.22 15	77.60 52	82.88 83	57.83 91	84.99 37	88.13 2	61.86 89	79.16 26	90.75 23	57.96 31	87.09 69	77.08 33	90.18 15	87.87 53

PGM-MVS		76.77 41	76.06 46	78.88 32	86.14 36	62.73 9	82.55 78	83.74 76	61.71 90	72.45 130	90.34 37	48.48 172	88.13 42	72.32 78	86.85 56	85.78 144

fmvsm_s_conf0.5_n_8		74.30 74	74.39 69	74.01 142	75.33 279	52.89 189	78.24 148	77.32 241	61.65 91	78.13 33	88.90 66	52.82 103	81.54 220	78.46 22	78.67 175	87.60 66

E2		73.72 87	73.60 87	74.06 139	77.16 226	50.40 247	76.97 199	83.74 76	61.64 92	73.36 100	86.75 123	56.14 50	82.99 173	67.50 123	79.18 161	88.80 15

E3		73.72 87	73.60 87	74.06 139	77.16 226	50.40 247	76.97 199	83.74 76	61.64 92	73.36 100	86.76 120	56.13 51	82.99 173	67.50 123	79.18 161	88.80 15

Effi-MVS+		73.31 96	72.54 108	75.62 90	77.87 197	53.64 165	79.62 123	79.61 180	61.63 94	72.02 135	82.61 236	56.44 45	85.97 105	63.99 161	79.07 164	87.25 83

MG-MVS		73.96 82	73.89 81	74.16 132	85.65 43	49.69 268	81.59 93	81.29 146	61.45 95	71.05 147	88.11 79	51.77 123	87.73 53	61.05 198	83.09 90	85.05 183

fmvsm_s_conf0.5_n_9		75.16 60	75.22 59	75.01 101	78.34 180	55.37 139	77.30 187	73.95 313	61.40 96	79.46 23	90.14 41	57.07 39	81.15 230	80.00 5	79.31 153	88.51 30

LPG-MVS_test		72.74 109	71.74 120	75.76 84	80.22 124	57.51 97	82.55 78	83.40 90	61.32 97	66.67 240	87.33 101	39.15 297	86.59 80	67.70 119	77.30 203	83.19 250

LGP-MVS_train				75.76 84	80.22 124	57.51 97		83.40 90	61.32 97	66.67 240	87.33 101	39.15 297	86.59 80	67.70 119	77.30 203	83.19 250

CLD-MVS		73.33 95	72.68 105	75.29 97	78.82 161	53.33 177	78.23 153	84.79 47	61.30 99	70.41 156	81.04 280	52.41 110	87.12 67	64.61 157	82.49 103	85.41 168
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
RRT-MVS		71.46 139	70.70 143	73.74 155	77.76 202	49.30 276	76.60 212	80.45 167	61.25 100	68.17 197	84.78 182	44.64 226	84.90 132	64.79 153	77.88 191	87.03 89

viewcassd2359sk11		73.56 89	73.41 92	74.00 143	77.13 232	50.35 250	76.86 206	83.69 80	61.23 101	73.14 110	86.38 141	56.09 53	82.96 177	67.15 127	79.01 166	88.70 24

fmvsm_s_conf0.5_n_3		73.55 90	74.39 69	71.03 247	74.09 317	51.86 217	77.77 171	75.60 277	61.18 102	78.67 30	88.98 63	55.88 61	77.73 317	78.69 16	78.68 174	83.50 242

MVS_111021_HR		74.02 81	73.46 90	75.69 87	83.01 81	60.63 40	77.29 188	78.40 219	61.18 102	70.58 153	85.97 156	54.18 77	84.00 152	67.52 122	82.98 94	82.45 272

BridgeMVS		76.58 42	76.55 41	76.68 67	81.73 96	52.90 187	80.94 99	85.70 29	61.12 104	74.90 67	87.17 111	56.46 44	88.14 41	72.87 73	88.03 41	89.00 11

FIs		70.82 152	71.43 125	68.98 288	78.33 181	38.14 414	76.96 201	83.59 84	61.02 105	67.33 224	86.73 124	55.07 65	81.64 216	54.61 257	79.22 157	87.14 87

MED-MVS test				79.09 23	85.30 50	59.25 64	86.84 11	85.86 23	60.95 106	83.65 12	90.57 27		89.91 16	77.02 34	89.43 22	88.10 44

E3new		73.41 93	73.22 95	73.95 146	77.06 237	50.31 251	76.78 209	83.66 81	60.90 107	72.93 118	86.02 154	55.99 55	82.95 179	66.89 135	78.77 171	88.61 26

FOURS1					86.12 37	60.82 37	88.18 1	83.61 83	60.87 108	81.50 20

FC-MVSNet-test		69.80 177	70.58 146	67.46 311	77.61 213	34.73 447	76.05 227	83.19 105	60.84 109	65.88 258	86.46 138	54.52 74	80.76 245	52.52 272	78.12 187	86.91 92

v8		70.33 163	69.28 170	73.49 169	73.15 330	50.22 253	78.62 139	80.78 161	60.79 110	66.45 244	82.11 260	49.35 159	84.98 129	63.58 171	68.71 345	85.28 174

CSCG		76.92 37	76.75 35	77.41 56	83.96 69	59.60 56	82.95 69	86.50 14	60.78 111	75.27 56	84.83 180	60.76 19	86.56 82	67.86 117	87.87 44	86.06 133

Vis-MVSNet		72.18 123	71.37 128	74.61 113	81.29 105	55.41 137	80.90 100	78.28 222	60.73 112	69.23 181	88.09 80	44.36 230	82.65 196	57.68 228	81.75 113	85.77 147
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
KinetiMVS		71.26 142	70.16 154	74.57 116	74.59 300	52.77 194	75.91 231	81.20 150	60.72 113	69.10 184	85.71 167	41.67 264	83.53 161	63.91 164	78.62 177	87.42 73

BP-MVS1		73.41 93	72.25 112	76.88 62	76.68 250	53.70 163	79.15 129	81.07 154	60.66 114	71.81 136	87.39 98	40.93 277	87.24 60	71.23 90	81.29 117	89.71 2

APD-MVS		78.02 26	78.04 26	77.98 46	86.44 28	60.81 38	85.52 33	84.36 52	60.61 115	79.05 27	90.30 38	55.54 63	88.32 37	73.48 70	87.03 51	84.83 191
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
ACMP	63.53 6	72.30 121	71.20 133	75.59 92	80.28 122	57.54 95	82.74 74	82.84 116	60.58 116	65.24 272	86.18 147	39.25 295	86.03 103	66.95 134	76.79 211	83.22 248
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
lecture		77.75 28	77.84 28	77.50 54	82.75 85	57.62 94	85.92 25	86.20 18	60.53 117	78.99 28	91.45 14	51.51 128	87.78 52	75.65 49	87.55 46	87.10 88

testdata1							72.65 303		60.50 118

UGNet		68.81 208	67.39 220	73.06 181	78.33 181	54.47 150	79.77 118	75.40 284	60.45 119	63.22 301	84.40 197	32.71 377	80.91 241	51.71 282	80.56 128	83.81 227
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
viewmacassd2359aftdt		73.15 100	73.16 97	73.11 180	75.15 285	49.31 275	77.53 179	83.21 101	60.42 120	73.20 107	87.34 100	53.82 85	81.05 235	67.02 132	80.79 119	88.96 12

h-mvs33		72.71 110	71.49 124	76.40 73	81.99 93	59.58 57	76.92 203	76.74 256	60.40 121	74.81 69	85.95 157	45.54 210	85.76 110	70.41 95	70.61 307	83.86 226

hse-mvs2		71.04 144	69.86 158	74.60 114	79.58 138	57.12 107	73.96 274	75.25 287	60.40 121	74.81 69	81.95 262	45.54 210	82.90 185	70.41 95	66.83 362	83.77 231

EPP-MVSNet		72.16 126	71.31 130	74.71 107	78.68 165	49.70 266	82.10 86	81.65 131	60.40 121	65.94 254	85.84 161	51.74 124	86.37 91	55.93 241	79.55 147	88.07 48

UniMVSNet_ETH3D		67.60 241	67.07 234	69.18 285	77.39 219	42.29 371	74.18 271	75.59 278	60.37 124	66.77 236	86.06 152	37.64 316	78.93 294	52.16 275	73.49 260	86.32 124

test_prior2							81.75 89		60.37 124	75.01 62	89.06 61	56.22 48		72.19 79	88.96 27

SD-MVS		77.70 30	77.62 30	77.93 47	84.47 64	61.88 21	84.55 43	83.87 67	60.37 124	79.89 22	89.38 58	54.97 68	85.58 114	76.12 45	84.94 71	86.33 122
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
VNet		69.68 181	70.19 153	68.16 301	79.73 135	41.63 380	70.53 343	77.38 238	60.37 124	70.69 150	86.63 129	51.08 135	77.09 332	53.61 265	81.69 115	85.75 149

sasdasda		74.67 67	74.98 62	73.71 157	78.94 157	50.56 243	80.23 107	83.87 67	60.30 128	77.15 42	86.56 134	59.65 21	82.00 210	66.01 142	82.12 104	88.58 28

canonicalmvs		74.67 67	74.98 62	73.71 157	78.94 157	50.56 243	80.23 107	83.87 67	60.30 128	77.15 42	86.56 134	59.65 21	82.00 210	66.01 142	82.12 104	88.58 28

v7n		69.01 204	67.36 222	73.98 144	72.51 344	52.65 196	78.54 143	81.30 145	60.26 130	62.67 314	81.62 269	43.61 236	84.49 141	57.01 232	68.70 346	84.79 193

reproduce-ours		76.90 38	76.58 38	77.87 48	83.99 67	60.46 43	84.75 38	83.34 93	60.22 131	77.85 37	91.42 16	50.67 140	87.69 54	72.46 76	84.53 75	85.46 162

our_new_method		76.90 38	76.58 38	77.87 48	83.99 67	60.46 43	84.75 38	83.34 93	60.22 131	77.85 37	91.42 16	50.67 140	87.69 54	72.46 76	84.53 75	85.46 162

HPM-MVS_fast		74.30 74	73.46 90	76.80 64	84.45 65	59.04 75	83.65 63	81.05 155	60.15 133	70.43 154	89.84 52	41.09 276	85.59 113	67.61 121	82.90 97	85.77 147

VPA-MVSNet		69.02 203	69.47 166	67.69 307	77.42 218	41.00 387	74.04 272	79.68 178	60.06 134	69.26 180	84.81 181	51.06 136	77.58 322	54.44 258	74.43 243	84.48 203

v10		70.21 165	69.02 175	73.81 149	73.51 324	50.92 229	78.74 135	81.39 138	60.05 135	66.39 245	81.83 265	47.58 183	85.41 122	62.80 181	68.86 344	85.09 182

viewdifsd2359ckpt07		71.90 130	71.97 116	71.69 219	74.81 292	48.08 300	75.30 242	80.49 166	60.00 136	71.63 140	86.33 143	56.34 47	79.25 274	65.40 149	77.41 199	87.76 59

SR-MVS		76.13 51	75.70 52	77.40 58	85.87 41	61.20 29	85.52 33	82.19 123	59.99 137	75.10 60	90.35 36	47.66 181	86.52 86	71.64 87	82.99 92	84.47 204

SSC-MVS3.2		60.57 347	61.39 321	58.12 415	74.29 310	32.63 462	59.52 439	65.53 393	59.90 138	62.45 321	79.75 307	41.96 254	63.90 429	39.47 398	69.65 332	77.84 365

9.14			78.75 18		83.10 78		84.15 54	88.26 1	59.90 138	78.57 31	90.36 35	57.51 37	86.86 74	77.39 29	89.52 21

v2v482		70.50 158	69.45 167	73.66 160	72.62 340	50.03 258	77.58 174	80.51 165	59.90 138	69.52 171	82.14 258	47.53 184	84.88 135	65.07 152	70.17 317	86.09 132

Baseline_NR-MVSNet		67.05 253	67.56 212	65.50 350	75.65 268	37.70 420	75.42 240	74.65 300	59.90 138	68.14 199	83.15 229	49.12 166	77.20 330	52.23 274	69.78 326	81.60 285

API-MVS		72.17 124	71.41 126	74.45 121	81.95 94	57.22 100	84.03 56	80.38 169	59.89 142	68.40 192	82.33 249	49.64 153	87.83 51	51.87 279	84.16 82	78.30 356

Effi-MVS+-dtu		69.64 183	67.53 215	75.95 79	76.10 262	62.29 15	80.20 110	76.06 269	59.83 143	65.26 271	77.09 357	41.56 267	84.02 151	60.60 202	71.09 303	81.53 288

reproduce_model		76.43 45	76.08 45	77.49 55	83.47 75	60.09 47	84.60 42	82.90 113	59.65 144	77.31 40	91.43 15	49.62 154	87.24 60	71.99 82	83.75 87	85.14 178

MVSMamba_PlusPlus		75.75 56	75.44 54	76.67 68	80.84 113	53.06 184	78.62 139	85.13 38	59.65 144	71.53 143	87.47 94	56.92 40	88.17 40	72.18 80	86.63 61	88.80 15

CANet_DTU		68.18 226	67.71 211	69.59 276	74.83 291	46.24 320	78.66 138	76.85 250	59.60 146	63.45 299	82.09 261	35.25 342	77.41 325	59.88 208	78.76 172	85.14 178

EI-MVSNet		69.27 197	68.44 193	71.73 216	74.47 303	49.39 273	75.20 246	78.45 215	59.60 146	69.16 182	76.51 370	51.29 131	82.50 201	59.86 210	71.45 297	83.30 245

IterMVS-LS		69.22 199	68.48 189	71.43 231	74.44 305	49.40 272	76.23 221	77.55 233	59.60 146	65.85 259	81.59 272	51.28 132	81.58 219	59.87 209	69.90 324	83.30 245
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
MGCFI-Net		72.45 117	73.34 94	69.81 273	77.77 201	43.21 358	75.84 234	81.18 151	59.59 149	75.45 54	86.64 127	57.74 33	77.94 309	63.92 162	81.90 109	88.30 35

VDDNet		71.81 131	71.33 129	73.26 178	82.80 84	47.60 309	78.74 135	75.27 286	59.59 149	72.94 117	89.40 57	41.51 269	83.91 153	58.75 223	82.99 92	88.26 36

viewmanbaseed2359cas		72.92 106	72.89 101	73.00 182	75.16 283	49.25 278	77.25 191	83.11 109	59.52 151	72.93 118	86.63 129	54.11 78	80.98 236	66.63 136	80.67 123	88.76 23

alignmvs		73.86 84	73.99 78	73.45 171	78.20 184	50.50 245	78.57 141	82.43 120	59.40 152	76.57 47	86.71 126	56.42 46	81.23 229	65.84 145	81.79 110	88.62 25

MVS_Test		72.45 117	72.46 109	72.42 200	74.88 288	48.50 293	76.28 219	83.14 107	59.40 152	72.46 128	84.68 185	55.66 62	81.12 231	65.98 144	79.66 144	87.63 64

TSAR-MVS + MP.		78.44 22	78.28 22	78.90 31	84.96 56	61.41 26	84.03 56	83.82 74	59.34 154	79.37 25	89.76 54	59.84 20	87.62 57	76.69 37	86.74 58	87.68 62
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
MSLP-MVS++		73.77 85	73.47 89	74.66 110	83.02 80	59.29 63	82.30 85	81.88 127	59.34 154	71.59 141	86.83 118	45.94 205	83.65 158	65.09 151	85.22 70	81.06 305

PAPM_NR		72.63 113	71.80 118	75.13 99	81.72 97	53.42 175	79.91 116	83.28 99	59.14 156	66.31 247	85.90 159	51.86 120	86.06 101	57.45 230	80.62 124	85.91 138

testing91		64.46 294	63.80 285	66.47 329	78.43 175	40.06 394	67.63 376	69.59 358	59.06 157	63.18 303	78.05 335	34.05 355	76.99 337	48.30 309	75.87 225	82.37 274

myMVS_eth3d28		60.66 346	61.04 329	59.51 399	77.32 221	31.58 467	63.11 419	63.87 409	59.00 158	60.90 342	78.26 332	32.69 379	66.15 419	36.10 424	78.13 186	80.81 310

save fliter					86.17 34	61.30 28	83.98 58	79.66 179	59.00 158

v148		68.24 224	67.19 232	71.40 232	70.43 384	47.77 306	75.76 235	77.03 246	58.91 160	67.36 223	80.10 300	48.60 171	81.89 212	60.01 206	66.52 365	84.53 201

TransMVSNet (Re)		64.72 288	64.33 278	65.87 345	75.22 280	38.56 409	74.66 261	75.08 295	58.90 161	61.79 329	82.63 235	51.18 133	78.07 307	43.63 367	55.87 443	80.99 307

Anonymous202405211		66.84 258	65.99 257	69.40 280	80.19 127	42.21 373	71.11 333	71.31 340	58.80 162	67.90 207	86.39 140	29.83 405	79.65 264	49.60 299	78.78 170	86.33 122

test2506		65.33 282	64.61 276	67.50 308	79.46 142	34.19 452	74.43 267	51.92 463	58.72 163	66.75 237	88.05 82	25.99 443	80.92 240	51.94 278	84.25 79	87.39 76

ECVR-MVS		67.72 239	67.51 216	68.35 297	79.46 142	36.29 437	74.79 258	66.93 381	58.72 163	67.19 228	88.05 82	36.10 334	81.38 224	52.07 276	84.25 79	87.39 76

test1111		67.21 246	67.14 233	67.42 312	79.24 148	34.76 446	73.89 279	65.65 391	58.71 165	66.96 233	87.95 86	36.09 335	80.53 248	52.03 277	83.79 85	86.97 91

LCM-MVSNet-Re		61.88 336	61.35 322	63.46 371	74.58 301	31.48 468	61.42 429	58.14 442	58.71 165	53.02 435	79.55 312	43.07 242	76.80 341	45.69 340	77.96 189	82.11 280

fmvsm_s_conf0.5_n_11		73.16 99	73.35 93	72.58 191	75.48 274	52.41 206	78.84 133	76.85 250	58.64 167	73.58 97	87.25 108	54.09 79	79.47 269	76.19 44	79.27 154	85.86 140

testing99		64.05 300	63.29 298	66.34 331	78.17 188	39.76 398	67.33 381	68.00 372	58.60 168	63.03 306	78.10 334	32.57 384	76.94 339	48.22 310	75.58 229	82.34 275

v1144		70.42 160	69.31 169	73.76 152	73.22 328	50.64 238	77.83 168	81.43 137	58.58 169	69.40 175	81.16 277	47.53 184	85.29 124	64.01 160	70.64 305	85.34 171

TSAR-MVS + GP.		74.90 62	74.15 73	77.17 60	82.00 92	58.77 81	81.80 88	78.57 208	58.58 169	74.32 80	84.51 195	55.94 60	87.22 63	67.11 128	84.48 78	85.52 158

BH-RMVSNet		68.81 208	67.42 219	72.97 183	80.11 130	52.53 200	74.26 269	76.29 264	58.48 171	68.38 193	84.20 200	42.59 247	83.83 154	46.53 330	75.91 224	82.56 266

APD-MVS_3200maxsize		74.96 61	74.39 69	76.67 68	82.20 89	58.24 86	83.67 62	83.29 97	58.41 172	73.71 94	90.14 41	45.62 207	85.99 104	69.64 97	82.85 99	85.78 144

OMC-MVS		71.40 141	70.60 144	73.78 150	76.60 253	53.15 181	79.74 120	79.78 176	58.37 173	68.75 186	86.45 139	45.43 214	80.60 246	62.58 182	77.73 192	87.58 68

nrg030		72.96 105	73.01 99	72.84 186	75.41 277	50.24 252	80.02 112	82.89 115	58.36 174	74.44 77	86.73 124	58.90 29	80.83 242	65.84 145	74.46 241	87.44 72

K. test v3		60.47 350	57.11 368	70.56 258	73.74 321	48.22 296	75.10 250	62.55 421	58.27 175	53.62 428	76.31 374	27.81 426	81.59 218	47.42 316	39.18 479	81.88 283

FA-MVS(test-final)		69.82 175	68.48 189	73.84 148	78.44 174	50.04 257	75.58 239	78.99 193	58.16 176	67.59 220	82.14 258	42.66 246	85.63 111	56.60 234	76.19 218	85.84 142

MVS_111021_LR		69.50 190	68.78 183	71.65 221	78.38 176	59.33 61	74.82 257	70.11 352	58.08 177	67.83 215	84.68 185	41.96 254	76.34 353	65.62 147	77.54 195	79.30 344

SR-MVS-dyc-post		74.57 70	73.90 80	76.58 71	83.49 73	59.87 54	84.29 48	81.36 140	58.07 178	73.14 110	90.07 43	44.74 224	85.84 108	68.20 106	81.76 111	84.03 216

RE-MVS-def			73.71 85		83.49 73	59.87 54	84.29 48	81.36 140	58.07 178	73.14 110	90.07 43	43.06 243		68.20 106	81.76 111	84.03 216

SDMVSNet		68.03 229	68.10 205	67.84 303	77.13 232	48.72 289	65.32 399	79.10 188	58.02 180	65.08 275	82.55 242	47.83 178	73.40 367	63.92 162	73.92 249	81.41 290

sd_testset		64.46 294	64.45 277	64.51 362	77.13 232	42.25 372	62.67 422	72.11 335	58.02 180	65.08 275	82.55 242	41.22 275	69.88 393	47.32 320	73.92 249	81.41 290

GeoE		71.01 146	70.15 155	73.60 165	79.57 139	52.17 208	78.93 132	78.12 224	58.02 180	67.76 219	83.87 209	52.36 111	82.72 194	56.90 233	75.79 226	85.92 137

viewdifsd2359ckpt09		73.42 92	72.45 110	76.30 76	77.25 224	53.27 178	80.36 106	82.48 119	57.96 183	72.24 131	85.73 166	53.22 95	86.27 95	63.79 168	79.06 165	89.36 6

ZD-MVS					86.64 21	60.38 45		82.70 117	57.95 184	78.10 34	90.06 45	56.12 52	88.84 31	74.05 64	87.00 54

EIA-MVS		71.78 132	70.60 144	75.30 96	79.85 133	53.54 169	77.27 190	83.26 100	57.92 185	66.49 242	79.39 315	52.07 117	86.69 78	60.05 205	79.14 163	85.66 154

test_yl		69.69 179	69.13 172	71.36 235	78.37 178	45.74 325	74.71 259	80.20 171	57.91 186	70.01 164	83.83 210	42.44 249	82.87 188	54.97 251	79.72 142	85.48 160

DCV-MVSNet		69.69 179	69.13 172	71.36 235	78.37 178	45.74 325	74.71 259	80.20 171	57.91 186	70.01 164	83.83 210	42.44 249	82.87 188	54.97 251	79.72 142	85.48 160

MonoMVSNet		64.15 299	63.31 297	66.69 323	70.51 382	44.12 346	74.47 265	74.21 308	57.81 188	63.03 306	76.62 366	38.33 309	77.31 328	54.22 259	60.59 424	78.64 353

dcpmvs_2		74.55 71	75.23 58	72.48 196	82.34 88	53.34 176	77.87 165	81.46 136	57.80 189	75.49 53	86.81 119	62.22 14	77.75 316	71.09 91	82.02 107	86.34 119

diffmvs_AUTHOR		71.02 145	70.87 139	71.45 228	69.89 395	48.97 284	73.16 296	78.33 221	57.79 190	72.11 134	85.26 177	51.84 121	77.89 312	71.00 92	78.47 182	87.49 70

viewdifsd2359ckpt11		69.13 200	68.38 196	71.38 233	71.57 362	48.61 290	73.22 294	73.18 323	57.65 191	70.67 151	84.73 183	50.03 146	79.80 261	63.25 174	71.10 301	85.74 150

viewmsd2359difaftdt		69.13 200	68.38 196	71.38 233	71.57 362	48.61 290	73.22 294	73.18 323	57.65 191	70.67 151	84.73 183	50.03 146	79.80 261	63.25 174	71.10 301	85.74 150

fmvsm_s_conf0.5_n_6		72.59 114	72.87 102	71.73 216	75.14 286	51.96 215	76.28 219	77.12 244	57.63 193	73.85 92	86.91 116	51.54 127	77.87 313	77.18 32	80.18 135	85.37 170

Fast-Effi-MVS+-dtu		67.37 244	65.33 270	73.48 170	72.94 335	57.78 93	77.47 180	76.88 249	57.60 194	61.97 326	76.85 361	39.31 293	80.49 251	54.72 254	70.28 315	82.17 279

v1192		69.97 172	68.68 185	73.85 147	73.19 329	50.94 227	77.68 173	81.36 140	57.51 195	68.95 185	80.85 287	45.28 217	85.33 123	62.97 180	70.37 311	85.27 175

ACMH+	57.40 11	66.12 271	64.06 280	72.30 203	77.79 200	52.83 192	80.39 105	78.03 225	57.30 196	57.47 384	82.55 242	27.68 428	84.17 145	45.54 343	69.78 326	79.90 333

diffmvs		70.69 154	70.43 147	71.46 226	69.45 402	48.95 285	72.93 299	78.46 214	57.27 197	71.69 138	83.97 208	51.48 129	77.92 311	70.70 94	77.95 190	87.53 69
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
BH-untuned		68.27 222	67.29 224	71.21 239	79.74 134	53.22 179	76.06 226	77.46 236	57.19 198	66.10 251	81.61 270	45.37 216	83.50 162	45.42 349	76.68 213	76.91 381

fmvsm_s_conf0.5_n_10		74.11 76	73.98 79	74.48 120	74.61 299	52.86 191	78.10 160	77.06 245	57.14 199	78.24 32	88.79 71	52.83 102	82.26 206	77.79 28	81.30 116	88.32 34

viewdifsd2359ckpt13		72.40 120	71.79 119	74.22 130	75.63 269	51.77 219	78.67 137	83.13 108	57.08 200	71.59 141	85.36 176	53.10 99	82.64 197	63.07 178	78.51 179	88.24 38

thres100view900		63.28 309	62.41 308	65.89 343	77.31 222	38.66 408	72.65 303	69.11 365	57.07 201	62.45 321	81.03 281	37.01 328	79.17 277	31.84 445	73.25 267	79.83 336

fmvsm_s_conf0.5_n_7		69.54 187	69.67 162	69.15 287	73.47 326	51.41 222	70.35 347	73.34 319	57.05 202	68.41 191	85.83 162	49.86 149	72.84 370	71.86 84	76.83 210	83.19 250

DP-MVS Recon		72.15 127	70.73 142	76.40 73	86.57 25	57.99 89	81.15 98	82.96 111	57.03 203	66.78 235	85.56 169	44.50 228	88.11 43	51.77 281	80.23 134	83.10 255

thres600view7		63.30 308	62.27 310	66.41 330	77.18 225	38.87 406	72.35 311	69.11 365	56.98 204	62.37 324	80.96 283	37.01 328	79.00 292	31.43 452	73.05 271	81.36 293

V42		68.65 212	67.35 223	72.56 193	68.93 412	50.18 254	72.90 301	79.47 183	56.92 205	69.45 174	80.26 296	46.29 203	82.99 173	64.07 158	67.82 353	84.53 201

MCST-MVS		77.48 32	77.45 31	77.54 53	86.67 20	58.36 85	83.22 66	86.93 5	56.91 206	74.91 66	88.19 76	59.15 27	87.68 56	73.67 68	87.45 48	86.57 108

balanced_ft_v1		72.98 104	72.55 107	74.27 126	79.52 141	50.64 238	77.78 170	83.29 97	56.76 207	67.88 209	85.95 157	49.42 158	85.29 124	68.64 103	83.76 86	86.87 94

GA-MVS		65.53 278	63.70 287	71.02 248	70.87 377	48.10 299	70.48 344	74.40 302	56.69 208	64.70 284	76.77 362	33.66 363	81.10 232	55.42 250	70.32 314	83.87 225

v144192		69.71 178	68.51 188	73.33 176	73.10 331	50.13 255	77.54 177	80.64 162	56.65 209	68.57 189	80.55 290	46.87 198	84.96 131	62.98 179	69.66 330	84.89 190

fmvsm_l_conf0.5_n_3		73.23 98	73.13 98	73.55 167	74.40 306	55.13 142	78.97 131	74.96 296	56.64 210	74.76 72	88.75 72	55.02 67	78.77 298	76.33 41	78.31 185	86.74 100

tfpn200view9		63.18 311	62.18 312	66.21 335	76.85 246	39.62 400	71.96 319	69.44 361	56.63 211	62.61 316	79.83 303	37.18 322	79.17 277	31.84 445	73.25 267	79.83 336

thres400		63.31 307	62.18 312	66.72 320	76.85 246	39.62 400	71.96 319	69.44 361	56.63 211	62.61 316	79.83 303	37.18 322	79.17 277	31.84 445	73.25 267	81.36 293

GBi-Net		67.21 246	66.55 241	69.19 282	77.63 208	43.33 355	77.31 184	77.83 228	56.62 213	65.04 277	82.70 232	41.85 259	80.33 253	47.18 322	72.76 275	83.92 222

test1		67.21 246	66.55 241	69.19 282	77.63 208	43.33 355	77.31 184	77.83 228	56.62 213	65.04 277	82.70 232	41.85 259	80.33 253	47.18 322	72.76 275	83.92 222

FMVSNet2		66.93 256	66.31 252	68.79 291	77.63 208	42.98 364	76.11 224	77.47 234	56.62 213	65.22 274	82.17 256	41.85 259	80.18 259	47.05 328	72.72 278	83.20 249

fmvsm_l_conf0.5_n_9		73.27 97	73.66 86	72.09 205	73.82 318	52.72 195	77.45 181	74.28 306	56.61 216	77.10 44	88.16 77	56.17 49	77.09 332	78.27 24	81.13 118	86.48 112

DPM-MVS		75.47 58	75.00 61	76.88 62	81.38 104	59.16 67	79.94 114	85.71 28	56.59 217	72.46 128	86.76 120	56.89 41	87.86 50	66.36 138	88.91 28	83.64 239

v1921920		69.47 191	68.17 202	73.36 175	73.06 332	50.10 256	77.39 182	80.56 163	56.58 218	68.59 187	80.37 292	44.72 225	84.98 129	62.47 185	69.82 325	85.00 184

FMVSNet1		66.70 261	65.87 258	69.19 282	77.49 216	43.33 355	77.31 184	77.83 228	56.45 219	64.60 286	82.70 232	38.08 314	80.33 253	46.08 336	72.31 284	83.92 222

v1240		69.24 198	67.91 207	73.25 179	73.02 334	49.82 260	77.21 192	80.54 164	56.43 220	68.34 194	80.51 291	43.33 239	84.99 127	62.03 189	69.77 328	84.95 188

fmvsm_s_conf0.5_n_4		72.04 128	71.85 117	72.58 191	73.74 321	52.49 202	76.69 210	72.42 331	56.42 221	75.32 55	87.04 113	52.13 116	78.01 308	79.29 12	73.65 255	87.26 82

testing222		62.29 327	61.31 323	65.25 357	77.87 197	38.53 410	68.34 370	66.31 387	56.37 222	63.15 305	77.58 351	28.47 417	76.18 356	37.04 413	76.65 214	81.05 306

CDPH-MVS		76.31 46	75.67 53	78.22 41	85.35 49	59.14 70	81.31 96	84.02 57	56.32 223	74.05 84	88.98 63	53.34 94	87.92 48	69.23 101	88.42 31	87.59 67

Vis-MVSNet (Re-imp)		63.69 304	63.88 283	63.14 375	74.75 294	31.04 470	71.16 331	63.64 412	56.32 223	59.80 354	84.99 178	44.51 227	75.46 358	39.12 400	80.62 124	82.92 257

AdaColmap		69.99 171	68.66 186	73.97 145	84.94 58	57.83 91	82.63 76	78.71 200	56.28 225	64.34 287	84.14 202	41.57 266	87.06 70	46.45 331	78.88 167	77.02 377

PS-MVSNAJss		72.24 122	71.21 132	75.31 95	78.50 171	55.93 123	81.63 90	82.12 124	56.24 226	70.02 163	85.68 168	47.05 193	84.34 144	65.27 150	74.41 244	85.67 153

c3_l		68.33 221	67.56 212	70.62 257	70.87 377	46.21 321	74.47 265	78.80 198	56.22 227	66.19 248	78.53 330	51.88 119	81.40 223	62.08 186	69.04 340	84.25 209

Fast-Effi-MVS+		70.28 164	69.12 174	73.73 156	78.50 171	51.50 221	75.01 251	79.46 184	56.16 228	68.59 187	79.55 312	53.97 81	84.05 148	53.34 267	77.53 196	85.65 155

PHI-MVS		75.87 53	75.36 55	77.41 56	80.62 120	55.91 124	84.28 50	85.78 26	56.08 229	73.41 99	86.58 133	50.94 138	88.54 33	70.79 93	89.71 17	87.79 58

baseline1		63.81 303	63.87 284	63.62 370	76.29 259	36.36 432	71.78 322	67.29 377	56.05 230	64.23 292	82.95 230	47.11 192	74.41 363	47.30 321	61.85 412	80.10 330

train_agg		76.27 47	76.15 44	76.64 70	85.58 44	61.59 24	81.62 91	81.26 147	55.86 231	74.93 64	88.81 68	53.70 89	84.68 138	75.24 55	88.33 33	83.65 238

test_8					85.40 47	60.96 34	81.54 94	81.18 151	55.86 231	74.81 69	88.80 70	53.70 89	84.45 142

FMVSNet3		66.32 270	65.61 263	68.46 295	76.48 256	42.34 370	74.98 253	77.15 243	55.83 233	65.04 277	81.16 277	39.91 284	80.14 260	47.18 322	72.76 275	82.90 259

PAPR		71.72 135	70.82 140	74.41 122	81.20 109	51.17 223	79.55 125	83.33 95	55.81 234	66.93 234	84.61 189	50.95 137	86.06 101	55.79 244	79.20 158	86.00 134

eth_miper_zixun_eth		67.63 240	66.28 253	71.67 220	71.60 361	48.33 295	73.68 283	77.88 226	55.80 235	65.91 255	78.62 328	47.35 190	82.88 187	59.45 212	66.25 366	83.81 227

ACMH	55.70 15	65.20 284	63.57 289	70.07 266	78.07 191	52.01 214	79.48 126	79.69 177	55.75 236	56.59 393	80.98 282	27.12 433	80.94 238	42.90 375	71.58 295	77.25 375
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
IB-MVS	56.42 12	65.40 281	62.73 305	73.40 174	74.89 287	52.78 193	73.09 298	75.13 291	55.69 237	58.48 372	73.73 403	32.86 372	86.32 93	50.63 289	70.11 318	81.10 303
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
CL-MVSNet_self_test		61.53 339	60.94 331	63.30 373	68.95 410	36.93 428	67.60 377	72.80 329	55.67 238	59.95 351	76.63 365	45.01 223	72.22 377	39.74 397	62.09 411	80.74 312

TEST9					85.58 44	61.59 24	81.62 91	81.26 147	55.65 239	74.93 64	88.81 68	53.70 89	84.68 138

thres200		62.20 328	61.16 328	65.34 355	75.38 278	39.99 395	69.60 358	69.29 363	55.64 240	61.87 328	76.99 358	37.07 327	78.96 293	31.28 453	73.28 266	77.06 376

guyue		68.10 228	67.23 231	70.71 256	73.67 323	49.27 277	73.65 284	76.04 270	55.62 241	67.84 214	82.26 252	41.24 274	78.91 296	61.01 199	73.72 253	83.94 220

pm-mvs1		65.24 283	64.97 274	66.04 340	72.38 348	39.40 403	72.62 305	75.63 276	55.53 242	62.35 325	83.18 228	47.45 186	76.47 351	49.06 303	66.54 364	82.24 276

testing11		62.81 315	61.90 315	65.54 348	78.38 176	40.76 389	67.59 378	66.78 383	55.48 243	60.13 346	77.11 356	31.67 391	76.79 342	45.53 344	74.45 242	79.06 347

ACMM	61.98 7	70.80 153	69.73 160	74.02 141	80.59 121	58.59 83	82.68 75	82.02 126	55.46 244	67.18 229	84.39 198	38.51 306	83.17 169	60.65 201	76.10 222	80.30 325
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
AstraMVS		67.86 235	66.83 236	70.93 249	73.50 325	49.34 274	73.28 292	74.01 311	55.45 245	68.10 204	83.28 224	38.93 300	79.14 281	63.22 176	71.74 292	84.30 208

Anonymous20240529		69.91 173	69.02 175	72.56 193	80.19 127	47.65 307	77.56 176	80.99 157	55.45 245	69.88 167	86.76 120	39.24 296	82.18 208	54.04 260	77.10 207	87.85 54

tt0805		67.77 238	67.24 229	69.34 281	74.87 289	40.08 393	77.36 183	81.37 139	55.31 247	66.33 246	84.65 187	37.35 320	82.55 200	55.65 247	72.28 285	85.39 169

GDP-MVS		72.64 112	71.28 131	76.70 65	77.72 203	54.22 155	79.57 124	84.45 49	55.30 248	71.38 145	86.97 115	39.94 283	87.00 71	67.02 132	79.20 158	88.89 14

CPTT-MVS		72.78 108	72.08 115	74.87 104	84.88 61	61.41 26	84.15 54	77.86 227	55.27 249	67.51 222	88.08 81	41.93 256	81.85 213	69.04 102	80.01 136	81.35 295

XVG-OURS		68.76 211	67.37 221	72.90 185	74.32 309	57.22 100	70.09 351	78.81 197	55.24 250	67.79 217	85.81 165	36.54 332	78.28 304	62.04 188	75.74 227	83.19 250

hybrid		69.38 194	68.93 179	70.75 253	67.86 426	48.20 297	72.49 309	76.90 248	55.23 251	70.42 155	84.34 199	49.76 152	77.62 321	67.11 128	76.20 217	86.42 114

tfpnnormal		62.47 320	61.63 318	64.99 359	74.81 292	39.01 405	71.22 329	73.72 315	55.22 252	60.21 345	80.09 301	41.26 273	76.98 338	30.02 459	68.09 351	78.97 350

cl____		67.18 249	66.26 254	69.94 268	70.20 388	45.74 325	73.30 289	76.83 252	55.10 253	65.27 268	79.57 311	47.39 188	80.53 248	59.41 214	69.22 338	83.53 241

DIV-MVS_self_test		67.18 249	66.26 254	69.94 268	70.20 388	45.74 325	73.29 291	76.83 252	55.10 253	65.27 268	79.58 310	47.38 189	80.53 248	59.43 213	69.22 338	83.54 240

PC_three_1452									55.09 255	84.46 4	89.84 52	66.68 5	89.41 23	74.24 61	91.38 2	88.42 31

EPNet_dtu		61.90 335	61.97 314	61.68 384	72.89 336	39.78 397	75.85 233	65.62 392	55.09 255	54.56 418	79.36 316	37.59 317	67.02 412	39.80 396	76.95 208	78.25 357
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
PVSNet_Blended_VisFu		71.45 140	70.39 148	74.65 111	82.01 91	58.82 80	79.93 115	80.35 170	55.09 255	65.82 260	82.16 257	49.17 163	82.64 197	60.34 203	78.62 177	82.50 271

cl22		67.47 243	66.45 243	70.54 259	69.85 397	46.49 317	73.85 280	77.35 239	55.07 258	65.51 263	77.92 339	47.64 182	81.10 232	61.58 195	69.32 334	84.01 218

miper_ehance_all_eth		68.03 229	67.24 229	70.40 261	70.54 381	46.21 321	73.98 273	78.68 202	55.07 258	66.05 252	77.80 345	52.16 115	81.31 226	61.53 197	69.32 334	83.67 235

fmvsm_s_conf0.5_n_2		69.82 175	69.27 171	71.46 226	72.00 355	51.08 224	73.30 289	67.79 373	55.06 260	75.24 57	87.51 92	44.02 233	77.00 336	75.67 48	72.86 273	86.31 127

Elysia		70.19 167	68.29 198	75.88 81	74.15 313	54.33 153	78.26 145	83.21 101	55.04 261	67.28 225	83.59 217	30.16 400	86.11 99	63.67 169	79.26 155	87.20 84

StellarMVS		70.19 167	68.29 198	75.88 81	74.15 313	54.33 153	78.26 145	83.21 101	55.04 261	67.28 225	83.59 217	30.16 400	86.11 99	63.67 169	79.26 155	87.20 84

PS-MVSNAJ		70.51 157	69.70 161	72.93 184	81.52 99	55.79 127	74.92 255	79.00 192	55.04 261	69.88 167	78.66 325	47.05 193	82.19 207	61.61 193	79.58 145	80.83 309

fmvsm_s_conf0.1_n_2		69.64 183	69.01 177	71.52 224	71.66 360	51.04 225	73.39 288	67.14 379	55.02 264	75.11 59	87.64 91	42.94 245	77.01 335	75.55 50	72.63 279	86.52 111

mmtdpeth		60.40 351	59.12 351	64.27 365	69.59 399	48.99 282	70.67 341	70.06 353	54.96 265	62.78 310	73.26 408	27.00 435	67.66 405	58.44 226	45.29 471	76.16 387

xiu_mvs_v2_base		70.52 156	69.75 159	72.84 186	81.21 108	55.63 131	75.11 248	78.92 194	54.92 266	69.96 166	79.68 309	47.00 197	82.09 209	61.60 194	79.37 148	80.81 310

MAR-MVS		71.51 137	70.15 155	75.60 91	81.84 95	59.39 60	81.38 95	82.90 113	54.90 267	68.08 205	78.70 323	47.73 179	85.51 116	51.68 283	84.17 81	81.88 283
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
reproduce_monomvs		62.56 318	61.20 327	66.62 327	70.62 380	44.30 343	70.13 350	73.13 326	54.78 268	61.13 339	76.37 373	25.63 446	75.63 357	58.75 223	60.29 425	79.93 332

XVG-OURS-SEG-HR		68.81 208	67.47 218	72.82 188	74.40 306	56.87 110	70.59 342	79.04 191	54.77 269	66.99 232	86.01 155	39.57 289	78.21 305	62.54 183	73.33 265	83.37 244

testing3		56.54 384	55.92 384	58.41 410	77.52 215	27.93 480	69.72 354	56.36 451	54.75 270	58.63 370	77.80 345	20.88 462	71.75 380	25.31 476	62.25 409	75.53 394

FE-MVSNET2		62.01 332	60.88 332	65.42 352	68.74 414	38.43 412	72.92 300	77.39 237	54.74 271	55.40 406	76.71 363	35.46 340	76.72 345	44.25 355	62.31 408	81.10 303

Anonymous20231211		69.28 196	68.47 191	71.73 216	80.28 122	47.18 313	79.98 113	82.37 121	54.61 272	67.24 227	84.01 206	39.43 290	82.41 204	55.45 249	72.83 274	85.62 156

SixPastTwentyTwo		61.65 338	58.80 356	70.20 264	75.80 265	47.22 312	75.59 237	69.68 356	54.61 272	54.11 422	79.26 318	27.07 434	82.96 177	43.27 369	49.79 464	80.41 319

test_0402		63.25 310	61.01 330	69.96 267	80.00 131	54.37 152	76.86 206	72.02 336	54.58 274	58.71 366	80.79 289	35.00 345	84.36 143	26.41 474	64.71 377	71.15 446

tttt0517		67.83 236	65.66 262	74.33 124	76.69 249	50.82 231	77.86 166	73.99 312	54.54 275	64.64 285	82.53 245	35.06 344	85.50 117	55.71 245	69.91 323	86.67 104

BH-w/o		66.85 257	65.83 259	69.90 271	79.29 144	52.46 203	74.66 261	76.65 257	54.51 276	64.85 282	78.12 333	45.59 209	82.95 179	43.26 370	75.54 230	74.27 412

AUN-MVS		68.45 220	66.41 247	74.57 116	79.53 140	57.08 108	73.93 277	75.23 288	54.44 277	66.69 238	81.85 264	37.10 326	82.89 186	62.07 187	66.84 361	83.75 232

LTVRE_ROB	55.42 16	63.15 312	61.23 326	68.92 289	76.57 254	47.80 304	59.92 438	76.39 261	54.35 278	58.67 368	82.46 247	29.44 409	81.49 221	42.12 379	71.14 299	77.46 369
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
test_fmvsmconf_n		73.01 103	72.59 106	74.27 126	71.28 372	55.88 125	78.21 155	75.56 279	54.31 279	74.86 68	87.80 89	54.72 71	80.23 257	78.07 26	78.48 180	86.70 101

test_fmvsmconf0.01_n		72.17 124	71.50 123	74.16 132	67.96 424	55.58 134	78.06 161	74.67 299	54.19 280	74.54 76	88.23 75	50.35 145	80.24 256	78.07 26	77.46 198	86.65 106

test_fmvsmconf0.1_n		72.81 107	72.33 111	74.24 128	69.89 395	55.81 126	78.22 154	75.40 284	54.17 281	75.00 63	88.03 85	53.82 85	80.23 257	78.08 25	78.34 184	86.69 102

ETVMVS		59.51 361	58.81 354	61.58 386	77.46 217	34.87 443	64.94 405	59.35 437	54.06 282	61.08 340	76.67 364	29.54 406	71.87 379	32.16 441	74.07 247	78.01 364

ab-mvs		66.65 262	66.42 246	67.37 313	76.17 261	41.73 377	70.41 346	76.14 267	53.99 283	65.98 253	83.51 221	49.48 155	76.24 354	48.60 306	73.46 262	84.14 214

fmvsm_s_conf0.5_n_5		72.69 111	72.80 103	72.37 201	74.11 316	53.21 180	78.12 157	73.31 320	53.98 284	76.81 46	88.05 82	53.38 93	77.37 327	76.64 38	80.78 120	86.53 110

IU-MVS					87.77 4	59.15 68		85.53 32	53.93 285	84.64 3				79.07 13	90.87 5	88.37 33

SSM_0407		70.41 161	68.96 178	74.75 106	78.65 166	53.46 171	77.28 189	80.00 174	53.88 286	68.14 199	84.61 189	43.21 240	86.26 96	58.80 221	76.11 219	84.54 198

SSM_0404		70.84 149	69.41 168	75.12 100	79.20 149	53.86 159	77.89 164	80.00 174	53.88 286	69.40 175	84.61 189	43.21 240	86.56 82	58.80 221	77.68 194	84.95 188

XVG-ACMP-BASELINE		64.36 296	62.23 311	70.74 254	72.35 349	52.45 204	70.80 340	78.45 215	53.84 288	59.87 352	81.10 279	16.24 471	79.32 273	55.64 248	71.76 291	80.47 316

mamba_0408		67.78 237	65.42 266	74.85 105	78.65 166	53.46 171	50.83 472	79.09 189	53.75 289	68.14 199	83.83 210	41.79 262	86.56 82	56.58 235	76.11 219	84.54 198

SSM_04072		64.98 287	65.42 266	63.68 369	78.65 166	53.46 171	50.83 472	79.09 189	53.75 289	68.14 199	83.83 210	41.79 262	53.03 475	56.58 235	76.11 219	84.54 198

VortexMVS		66.41 268	65.50 265	69.16 286	73.75 319	48.14 298	73.41 287	78.28 222	53.73 291	64.98 281	78.33 331	40.62 279	79.07 284	58.88 220	67.50 356	80.26 326

FE-MVS		65.91 273	63.33 296	73.63 163	77.36 220	51.95 216	72.62 305	75.81 273	53.70 292	65.31 266	78.96 321	28.81 415	86.39 90	43.93 361	73.48 261	82.55 267

thisisatest0530		67.92 233	65.78 260	74.33 124	76.29 259	51.03 226	76.89 204	74.25 307	53.67 293	65.59 262	81.76 267	35.15 343	85.50 117	55.94 240	72.47 280	86.47 113

PVSNet_BlendedMVS		68.56 217	67.72 209	71.07 246	77.03 243	50.57 241	74.50 264	81.52 133	53.66 294	64.22 293	79.72 308	49.13 164	82.87 188	55.82 242	73.92 249	79.77 339

patch_mono-2		69.85 174	71.09 135	66.16 336	79.11 154	54.80 148	71.97 318	74.31 304	53.50 295	70.90 149	84.17 201	57.63 36	63.31 431	66.17 139	82.02 107	80.38 320

EG-PatchMatch MVS		64.71 289	62.87 302	70.22 262	77.68 205	53.48 170	77.99 162	78.82 196	53.37 296	56.03 400	77.41 353	24.75 451	84.04 149	46.37 332	73.42 264	73.14 418

SD_0403		63.07 313	63.49 293	61.82 383	75.16 283	31.14 469	71.89 321	73.47 317	53.34 297	58.22 375	81.81 266	45.17 220	73.86 366	37.43 409	74.87 239	80.45 317

usedtu_dtu_shiyan1		64.34 297	63.57 289	66.66 324	72.44 346	40.74 390	69.60 358	76.80 254	53.21 298	61.73 331	77.92 339	41.92 257	77.68 319	46.23 333	72.25 286	81.57 286

FE-MVSNET3		64.34 297	63.57 289	66.66 324	72.44 346	40.74 390	69.60 358	76.80 254	53.21 298	61.73 331	77.92 339	41.92 257	77.68 319	46.23 333	72.25 286	81.57 286

DP-MVS		65.68 275	63.66 288	71.75 215	84.93 59	56.87 110	80.74 103	73.16 325	53.06 300	59.09 363	82.35 248	36.79 331	85.94 106	32.82 439	69.96 322	72.45 427

TR-MVS		66.59 265	65.07 273	71.17 242	79.18 151	49.63 270	73.48 285	75.20 290	52.95 301	67.90 207	80.33 295	39.81 287	83.68 157	43.20 371	73.56 259	80.20 327

ET-MVSNet_ETH3D		67.96 232	65.72 261	74.68 109	76.67 251	55.62 133	75.11 248	74.74 297	52.91 302	60.03 349	80.12 299	33.68 362	82.64 197	61.86 190	76.34 215	85.78 144

QAPM		70.05 169	68.81 182	73.78 150	76.54 255	53.43 174	83.23 65	83.48 86	52.89 303	65.90 256	86.29 144	41.55 268	86.49 88	51.01 286	78.40 183	81.42 289

LuminaMVS		68.24 224	66.82 237	72.51 195	73.46 327	53.60 167	76.23 221	78.88 195	52.78 304	68.08 205	80.13 298	32.70 378	81.41 222	63.16 177	75.97 223	82.53 268

icg_test_0407_2		66.41 268	66.75 238	65.37 354	77.06 237	49.73 262	63.79 415	78.60 204	52.70 305	66.19 248	82.58 237	45.17 220	63.65 430	59.20 216	75.46 232	82.74 262

IMVS_0407		68.90 206	67.93 206	71.82 212	77.06 237	49.73 262	74.40 268	78.60 204	52.70 305	66.19 248	82.58 237	45.17 220	83.00 172	59.20 216	75.46 232	82.74 262

IMVS_0404		64.63 291	64.22 279	65.88 344	77.06 237	49.73 262	64.40 408	78.60 204	52.70 305	53.16 433	82.58 237	34.82 347	65.16 424	59.20 216	75.46 232	82.74 262

IMVS_0403		69.09 202	68.14 203	71.95 207	77.06 237	49.73 262	74.51 263	78.60 204	52.70 305	66.69 238	82.58 237	46.43 201	83.38 164	59.20 216	75.46 232	82.74 262

OpenMVS	61.03 9	68.85 207	67.56 212	72.70 190	74.26 311	53.99 158	81.21 97	81.34 144	52.70 305	62.75 313	85.55 171	38.86 301	84.14 146	48.41 308	83.01 91	79.97 331

pmmvs6		63.69 304	62.82 304	66.27 334	70.63 379	39.27 404	73.13 297	75.47 283	52.69 310	59.75 356	82.30 250	39.71 288	77.03 334	47.40 317	64.35 382	82.53 268

IterMVS		62.79 316	61.27 324	67.35 314	69.37 403	52.04 213	71.17 330	68.24 371	52.63 311	59.82 353	76.91 360	37.32 321	72.36 373	52.80 271	63.19 395	77.66 367
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
mvs_tets		68.18 226	66.36 249	73.63 163	75.61 271	55.35 140	80.77 102	78.56 209	52.48 312	64.27 290	84.10 204	27.45 430	81.84 214	63.45 173	70.56 308	83.69 234

jajsoiax		68.25 223	66.45 243	73.66 160	75.62 270	55.49 136	80.82 101	78.51 211	52.33 313	64.33 288	84.11 203	28.28 421	81.81 215	63.48 172	70.62 306	83.67 235

TAMVS		66.78 260	65.27 271	71.33 238	79.16 153	53.67 164	73.84 281	69.59 358	52.32 314	65.28 267	81.72 268	44.49 229	77.40 326	42.32 378	78.66 176	82.92 257

CDS-MVSNet		66.80 259	65.37 268	71.10 245	78.98 156	53.13 183	73.27 293	71.07 342	52.15 315	64.72 283	80.23 297	43.56 237	77.10 331	45.48 347	78.88 167	83.05 256
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
gbinet_0.2-2-1-0.02		62.43 323	60.41 339	68.49 294	68.91 413	43.71 350	71.73 323	75.89 272	52.10 316	58.33 373	69.67 442	36.86 330	80.59 247	47.18 322	63.05 397	81.16 301

mvsmamba		68.47 218	66.56 240	74.21 131	79.60 137	52.95 185	74.94 254	75.48 282	52.09 317	60.10 347	83.27 225	36.54 332	84.70 137	59.32 215	77.69 193	84.99 186

viewmambaseed2359dif		68.91 205	68.18 201	71.11 244	70.21 387	48.05 303	72.28 313	75.90 271	51.96 318	70.93 148	84.47 196	51.37 130	78.59 300	61.55 196	74.97 237	86.68 103

usedtu_blend_shiyan5		62.63 317	60.77 335	68.20 299	68.53 417	44.64 338	73.47 286	77.00 247	51.91 319	57.10 387	69.95 435	38.83 302	79.61 267	47.44 314	62.67 399	80.37 321

PVSNet_Blended		68.59 213	67.72 209	71.19 240	77.03 243	50.57 241	72.51 308	81.52 133	51.91 319	64.22 293	77.77 348	49.13 164	82.87 188	55.82 242	79.58 145	80.14 329

mvs_anonymous		68.03 229	67.51 216	69.59 276	72.08 353	44.57 341	71.99 317	75.23 288	51.67 321	67.06 231	82.57 241	54.68 72	77.94 309	56.56 237	75.71 228	86.26 129

blend_shiyan4		61.38 342	59.10 352	68.20 299	68.94 411	44.64 338	70.81 339	76.52 258	51.63 322	57.56 383	69.94 438	28.30 420	79.61 267	47.44 314	60.78 420	80.36 324

xiu_mvs_v1_base_debu		68.58 214	67.28 225	72.48 196	78.19 185	57.19 102	75.28 243	75.09 292	51.61 323	70.04 160	81.41 274	32.79 373	79.02 289	63.81 165	77.31 200	81.22 298

xiu_mvs_v1_base		68.58 214	67.28 225	72.48 196	78.19 185	57.19 102	75.28 243	75.09 292	51.61 323	70.04 160	81.41 274	32.79 373	79.02 289	63.81 165	77.31 200	81.22 298

xiu_mvs_v1_base_debi		68.58 214	67.28 225	72.48 196	78.19 185	57.19 102	75.28 243	75.09 292	51.61 323	70.04 160	81.41 274	32.79 373	79.02 289	63.81 165	77.31 200	81.22 298

MVSTER		67.16 251	65.58 264	71.88 210	70.37 386	49.70 266	70.25 349	78.45 215	51.52 326	69.16 182	80.37 292	38.45 307	82.50 201	60.19 204	71.46 296	83.44 243

blended_shiyan6		62.46 321	60.71 336	67.71 305	69.14 409	43.42 354	70.82 338	76.52 258	51.50 327	57.64 381	71.37 422	39.38 291	79.08 283	47.36 319	62.67 399	80.65 313

blended_shiyan8		62.46 321	60.71 336	67.71 305	69.15 408	43.43 353	70.83 337	76.52 258	51.49 328	57.67 380	71.36 423	39.38 291	79.07 284	47.37 318	62.67 399	80.62 314

CNLPA		65.43 279	64.02 281	69.68 274	78.73 164	58.07 88	77.82 169	70.71 348	51.49 328	61.57 335	83.58 220	38.23 312	70.82 385	43.90 362	70.10 319	80.16 328

原ACMM1				74.69 108	85.39 48	59.40 59		83.42 89	51.47 330	70.27 158	86.61 131	48.61 170	86.51 87	53.85 263	87.96 42	78.16 358

miper_enhance_ethall		67.11 252	66.09 256	70.17 265	69.21 406	45.98 323	72.85 302	78.41 218	51.38 331	65.65 261	75.98 380	51.17 134	81.25 227	60.82 200	69.32 334	83.29 247

MSDG		61.81 337	59.23 349	69.55 279	72.64 339	52.63 198	70.45 345	75.81 273	51.38 331	53.70 425	76.11 375	29.52 407	81.08 234	37.70 407	65.79 370	74.93 403

test20.03		53.87 406	54.02 403	53.41 441	61.47 463	28.11 479	61.30 430	59.21 438	51.34 333	52.09 438	77.43 352	33.29 367	58.55 452	29.76 460	60.27 426	73.58 417

wanda-best-256-512		62.00 333	60.17 342	67.49 309	68.53 417	43.07 362	69.65 355	76.38 262	51.26 334	57.10 387	69.95 435	38.83 302	79.04 287	47.14 326	62.67 399	80.37 321

FE-blended-shiyan7		62.00 333	60.17 342	67.49 309	68.53 417	43.07 362	69.65 355	76.38 262	51.26 334	57.10 387	69.95 435	38.83 302	79.04 287	47.14 326	62.67 399	80.37 321

MVSFormer		71.50 138	70.38 149	74.88 103	78.76 162	57.15 105	82.79 72	78.48 212	51.26 334	69.49 172	83.22 226	43.99 234	83.24 167	66.06 140	79.37 148	84.23 210

test_djsdf		69.45 192	67.74 208	74.58 115	74.57 302	54.92 146	82.79 72	78.48 212	51.26 334	65.41 265	83.49 222	38.37 308	83.24 167	66.06 140	69.25 337	85.56 157

dmvs_testset		50.16 425	51.90 414	44.94 462	66.49 437	11.78 502	61.01 435	51.50 464	51.17 338	50.30 450	67.44 453	39.28 294	60.29 442	22.38 480	57.49 436	62.76 467

PAPM		67.92 233	66.69 239	71.63 222	78.09 190	49.02 281	77.09 196	81.24 149	51.04 339	60.91 341	83.98 207	47.71 180	84.99 127	40.81 388	79.32 152	80.90 308

Syy-MVS		56.00 391	56.23 382	55.32 428	74.69 296	26.44 486	65.52 394	57.49 446	50.97 340	56.52 394	72.18 412	39.89 285	68.09 401	24.20 477	64.59 380	71.44 442

myMVS_eth3d		54.86 402	54.61 395	55.61 427	74.69 296	27.31 483	65.52 394	57.49 446	50.97 340	56.52 394	72.18 412	21.87 460	68.09 401	27.70 468	64.59 380	71.44 442

miper_lstm_enhance		62.03 331	60.88 332	65.49 351	66.71 435	46.25 319	56.29 456	75.70 275	50.68 342	61.27 337	75.48 387	40.21 282	68.03 403	56.31 239	65.25 373	82.18 277

gg-mvs-nofinetune		57.86 376	56.43 379	62.18 381	72.62 340	35.35 442	66.57 384	56.33 452	50.65 343	57.64 381	57.10 478	30.65 394	76.36 352	37.38 410	78.88 167	74.82 405

TAPA-MVS	59.36 10	66.60 263	65.20 272	70.81 251	76.63 252	48.75 287	76.52 215	80.04 173	50.64 344	65.24 272	84.93 179	39.15 297	78.54 301	36.77 415	76.88 209	85.14 178
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
dmvs_re		56.77 383	56.83 373	56.61 422	69.23 405	41.02 384	58.37 444	64.18 405	50.59 345	57.45 385	71.42 420	35.54 339	58.94 450	37.23 411	67.45 357	69.87 455

MVP-Stereo		65.41 280	63.80 285	70.22 262	77.62 212	55.53 135	76.30 218	78.53 210	50.59 345	56.47 396	78.65 326	39.84 286	82.68 195	44.10 360	72.12 289	72.44 428
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
PCF-MVS	61.88 8	70.95 148	69.49 165	75.35 94	77.63 208	55.71 128	76.04 228	81.81 129	50.30 347	69.66 170	85.40 175	52.51 107	84.89 133	51.82 280	80.24 133	85.45 164
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
mvs5depth		55.64 394	53.81 405	61.11 392	59.39 473	40.98 388	65.89 389	68.28 370	50.21 348	58.11 377	75.42 388	17.03 467	67.63 407	43.79 364	46.21 468	74.73 407

baseline2		63.42 306	61.26 325	69.89 272	72.55 342	47.62 308	71.54 324	68.38 369	50.11 349	54.82 414	75.55 385	43.06 243	80.96 237	48.13 311	67.16 360	81.11 302

test-LLR		58.15 374	58.13 364	58.22 412	68.57 415	44.80 335	65.46 396	57.92 443	50.08 350	55.44 404	69.82 439	32.62 381	57.44 457	49.66 297	73.62 256	72.41 429

test0.0.03 1		53.32 412	53.59 408	52.50 447	62.81 457	29.45 474	59.51 440	54.11 459	50.08 350	54.40 420	74.31 397	32.62 381	55.92 466	30.50 456	63.95 385	72.15 434

fmvsm_s_conf0.5_n		69.58 185	68.84 181	71.79 214	72.31 351	52.90 187	77.90 163	62.43 424	49.97 352	72.85 121	85.90 159	52.21 113	76.49 349	75.75 47	70.26 316	85.97 135

COLMAP_ROB	52.97 17	61.27 344	58.81 354	68.64 292	74.63 298	52.51 201	78.42 144	73.30 321	49.92 353	50.96 442	81.51 273	23.06 454	79.40 271	31.63 449	65.85 368	74.01 415
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_a		69.54 187	68.74 184	71.93 208	72.47 345	53.82 161	78.25 147	62.26 426	49.78 354	73.12 113	86.21 146	52.66 105	76.79 342	75.02 56	68.88 342	85.18 177

WBMVS		60.54 348	60.61 338	60.34 396	78.00 194	35.95 439	64.55 407	64.89 397	49.63 355	63.39 300	78.70 323	33.85 360	67.65 406	42.10 380	70.35 313	77.43 370

tpmvs		58.47 367	56.95 371	63.03 377	70.20 388	41.21 383	67.90 375	67.23 378	49.62 356	54.73 416	70.84 426	34.14 354	76.24 354	36.64 419	61.29 416	71.64 438

fmvsm_s_conf0.1_n		69.41 193	68.60 187	71.83 211	71.07 374	52.88 190	77.85 167	62.44 423	49.58 357	72.97 116	86.22 145	51.68 125	76.48 350	75.53 51	70.10 319	86.14 130

UBG		59.62 360	59.53 347	59.89 397	78.12 189	35.92 440	64.11 413	60.81 434	49.45 358	61.34 336	75.55 385	33.05 368	67.39 410	38.68 402	74.62 240	76.35 386

thisisatest0515		65.83 274	63.50 292	72.82 188	73.75 319	49.50 271	71.32 327	73.12 327	49.39 359	63.82 295	76.50 372	34.95 346	84.84 136	53.20 269	75.49 231	84.13 215

fmvsm_s_conf0.1_n_a		69.32 195	68.44 193	71.96 206	70.91 376	53.78 162	78.12 157	62.30 425	49.35 360	73.20 107	86.55 136	51.99 118	76.79 342	74.83 58	68.68 347	85.32 172

HY-MVS	56.14 13	64.55 293	63.89 282	66.55 328	74.73 295	41.02 384	69.96 352	74.43 301	49.29 361	61.66 333	80.92 284	47.43 187	76.68 347	44.91 353	71.69 293	81.94 281

MIMVSNet1		55.17 399	54.31 400	57.77 418	70.03 392	32.01 465	65.68 392	64.81 398	49.19 362	46.75 461	76.00 377	25.53 447	64.04 427	28.65 464	62.13 410	77.26 374

SCA		60.49 349	58.38 360	66.80 319	74.14 315	48.06 301	63.35 418	63.23 416	49.13 363	59.33 362	72.10 414	37.45 318	74.27 364	44.17 357	62.57 405	78.05 360

test_fmvsmvis_n_1920		70.84 149	70.38 149	72.22 204	71.16 373	55.39 138	75.86 232	72.21 334	49.03 364	73.28 105	86.17 148	51.83 122	77.29 329	75.80 46	78.05 188	83.98 219

testgi		51.90 417	52.37 412	50.51 454	60.39 471	23.55 493	58.42 443	58.15 441	49.03 364	51.83 439	79.21 319	22.39 455	55.59 467	29.24 463	62.64 404	72.40 431

sc_t1		59.76 356	57.84 366	65.54 348	74.87 289	42.95 366	69.61 357	64.16 407	48.90 366	58.68 367	77.12 355	28.19 423	72.35 374	43.75 366	55.28 445	81.31 296

MIMVSNet		57.35 378	57.07 369	58.22 412	74.21 312	37.18 423	62.46 423	60.88 433	48.88 367	55.29 408	75.99 379	31.68 390	62.04 436	31.87 444	72.35 282	75.43 396

gm-plane-assit					71.40 369	41.72 379			48.85 368		73.31 406		82.48 203	48.90 304

fmvsm_l_conf0.5_n		70.99 147	70.82 140	71.48 225	71.45 365	54.40 151	77.18 193	70.46 350	48.67 369	75.17 58	86.86 117	53.77 87	76.86 340	76.33 41	77.51 197	83.17 254

0.4-1-1-0.1		59.29 362	56.70 376	67.07 316	69.35 404	43.16 359	66.59 383	70.87 346	48.59 370	55.11 410	62.25 470	28.22 422	78.92 295	45.49 346	63.79 386	79.14 345

UWE-MVS		60.18 352	59.78 345	61.39 389	77.67 206	33.92 455	69.04 366	63.82 410	48.56 371	64.27 290	77.64 350	27.20 432	70.40 390	33.56 436	76.24 216	79.83 336

cascas		65.98 272	63.42 294	73.64 162	77.26 223	52.58 199	72.26 314	77.21 242	48.56 371	61.21 338	74.60 395	32.57 384	85.82 109	50.38 291	76.75 212	82.52 270

PLC	56.13 14	65.09 285	63.21 299	70.72 255	81.04 111	54.87 147	78.57 141	77.47 234	48.51 373	55.71 401	81.89 263	33.71 361	79.71 263	41.66 384	70.37 311	77.58 368
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
LS3D		64.71 289	62.50 307	71.34 237	79.72 136	55.71 128	79.82 117	74.72 298	48.50 374	56.62 392	84.62 188	33.59 364	82.34 205	29.65 461	75.23 236	75.97 388

anonymousdsp		67.00 255	64.82 275	73.57 166	70.09 391	56.13 118	76.35 217	77.35 239	48.43 375	64.99 280	80.84 288	33.01 370	80.34 252	64.66 155	67.64 355	84.23 210

无先验							79.66 122	74.30 305	48.40 376				80.78 244	53.62 264		79.03 349

FE-MVSNET		55.16 400	53.75 406	59.41 400	65.29 445	33.20 459	67.21 382	66.21 388	48.39 377	49.56 452	73.53 405	29.03 411	72.51 372	30.38 457	54.10 451	72.52 425

114514_t		70.83 151	69.56 163	74.64 112	86.21 32	54.63 149	82.34 81	81.81 129	48.22 378	63.01 308	85.83 162	40.92 278	87.10 68	57.91 227	79.79 141	82.18 277

tpm		57.34 379	58.16 362	54.86 431	71.80 359	34.77 445	67.47 380	56.04 455	48.20 379	60.10 347	76.92 359	37.17 324	53.41 474	40.76 389	65.01 374	76.40 385

test_fmvsm_n_1920		71.73 134	71.14 134	73.50 168	72.52 343	56.53 112	75.60 236	76.16 265	48.11 380	77.22 41	85.56 169	53.10 99	77.43 324	74.86 57	77.14 205	86.55 109

MDA-MVSNet-bldmvs		53.87 406	50.81 419	63.05 376	66.25 439	48.58 292	56.93 454	63.82 410	48.09 381	41.22 474	70.48 431	30.34 397	68.00 404	34.24 431	45.92 470	72.57 424

XXY-MVS		60.68 345	61.67 317	57.70 419	70.43 384	38.45 411	64.19 411	66.47 384	48.05 382	63.22 301	80.86 286	49.28 161	60.47 440	45.25 351	67.28 359	74.19 413

F-COLMAP		63.05 314	60.87 334	69.58 278	76.99 245	53.63 166	78.12 157	76.16 265	47.97 383	52.41 437	81.61 270	27.87 425	78.11 306	40.07 391	66.66 363	77.00 378

tt0320-xc		58.33 370	56.41 380	64.08 366	75.79 266	41.34 381	68.30 371	62.72 420	47.90 384	56.29 397	74.16 400	28.53 416	71.04 384	41.50 387	52.50 456	79.88 334

fmvsm_l_conf0.5_n_a		70.50 158	70.27 151	71.18 241	71.30 371	54.09 156	76.89 204	69.87 354	47.90 384	74.37 79	86.49 137	53.07 101	76.69 346	75.41 52	77.11 206	82.76 261

0.3-1-1-0.015		58.40 368	55.56 387	66.91 318	68.08 423	43.09 361	65.25 402	70.96 345	47.89 386	53.10 434	59.82 473	26.48 438	78.79 297	45.07 352	63.43 392	78.84 352

Patchmatch-RL test		58.16 373	55.49 389	66.15 337	67.92 425	48.89 286	60.66 436	51.07 467	47.86 387	59.36 359	62.71 469	34.02 357	72.27 376	56.41 238	59.40 428	77.30 372

D2MVS		62.30 326	60.29 341	68.34 298	66.46 438	48.42 294	65.70 391	73.42 318	47.71 388	58.16 376	75.02 391	30.51 395	77.71 318	53.96 262	71.68 294	78.90 351

0.4-1-1-0.2		58.31 371	55.53 388	66.64 326	67.46 429	42.78 368	64.38 409	70.97 344	47.65 389	53.38 432	59.02 474	28.39 419	78.72 299	44.86 354	63.63 388	78.42 355

ANet_high		41.38 444	37.47 451	53.11 443	39.73 499	24.45 491	56.94 453	69.69 355	47.65 389	26.04 491	52.32 481	12.44 479	62.38 435	21.80 481	10.61 500	72.49 426

CostFormer		64.04 301	62.51 306	68.61 293	71.88 357	45.77 324	71.30 328	70.60 349	47.55 391	64.31 289	76.61 368	41.63 265	79.62 266	49.74 295	69.00 341	80.42 318

PatchmatchNet		59.84 355	58.24 361	64.65 361	73.05 333	46.70 316	69.42 362	62.18 427	47.55 391	58.88 365	71.96 416	34.49 351	69.16 395	42.99 373	63.60 389	78.07 359
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
KD-MVS_self_test		55.22 398	53.89 404	59.21 404	57.80 477	27.47 482	57.75 450	74.32 303	47.38 393	50.90 443	70.00 434	28.45 418	70.30 391	40.44 390	57.92 434	79.87 335

ITE_SJBPF				62.09 382	66.16 440	44.55 342		64.32 403	47.36 394	55.31 407	80.34 294	19.27 463	62.68 434	36.29 423	62.39 407	79.04 348

KD-MVS_2432*1600		53.45 408	51.50 417	59.30 401	62.82 455	37.14 424	55.33 457	71.79 338	47.34 395	55.09 411	70.52 429	21.91 458	70.45 388	35.72 426	42.97 474	70.31 451

miper_refine_blended		53.45 408	51.50 417	59.30 401	62.82 455	37.14 424	55.33 457	71.79 338	47.34 395	55.09 411	70.52 429	21.91 458	70.45 388	35.72 426	42.97 474	70.31 451

OurMVSNet-221017-0		61.37 343	58.63 358	69.61 275	72.05 354	48.06 301	73.93 277	72.51 330	47.23 397	54.74 415	80.92 284	21.49 461	81.24 228	48.57 307	56.22 442	79.53 341

tpmrst		58.24 372	58.70 357	56.84 421	66.97 432	34.32 450	69.57 361	61.14 432	47.17 398	58.58 371	71.60 419	41.28 272	60.41 441	49.20 301	62.84 398	75.78 391

tt0320		58.59 366	56.81 374	63.92 368	75.46 275	41.32 382	68.63 368	64.06 408	47.05 399	56.19 398	74.19 398	30.34 397	71.36 381	39.92 395	55.45 444	79.09 346

PVSNet	50.76 19	58.40 368	57.39 367	61.42 387	75.53 273	44.04 347	61.43 428	63.45 414	47.04 400	56.91 390	73.61 404	27.00 435	64.76 425	39.12 400	72.40 281	75.47 395

WB-MVSnew		59.66 358	59.69 346	59.56 398	75.19 282	35.78 441	69.34 363	64.28 404	46.88 401	61.76 330	75.79 381	40.61 280	65.20 423	32.16 441	71.21 298	77.70 366

UWE-MVS-28		52.25 416	52.35 413	51.93 451	66.99 431	22.79 494	63.48 417	48.31 475	46.78 402	52.73 436	76.11 375	27.78 427	57.82 456	20.58 483	68.41 349	75.17 397

FMVSNet5		55.86 392	54.93 392	58.66 409	71.05 375	36.35 433	64.18 412	62.48 422	46.76 403	50.66 447	74.73 394	25.80 444	64.04 427	33.11 437	65.57 371	75.59 393

jason		69.65 182	68.39 195	73.43 173	78.27 183	56.88 109	77.12 195	73.71 316	46.53 404	69.34 177	83.22 226	43.37 238	79.18 276	64.77 154	79.20 158	84.23 210
jason: jason.
MS-PatchMatch		62.42 324	61.46 320	65.31 356	75.21 281	52.10 210	72.05 316	74.05 310	46.41 405	57.42 386	74.36 396	34.35 353	77.57 323	45.62 342	73.67 254	66.26 464

1112_ss		64.00 302	63.36 295	65.93 342	79.28 146	42.58 369	71.35 326	72.36 333	46.41 405	60.55 344	77.89 343	46.27 204	73.28 368	46.18 335	69.97 321	81.92 282

lupinMVS		69.57 186	68.28 200	73.44 172	78.76 162	57.15 105	76.57 213	73.29 322	46.19 407	69.49 172	82.18 254	43.99 234	79.23 275	64.66 155	79.37 148	83.93 221

testdata				64.66 360	81.52 99	52.93 186		65.29 395	46.09 408	73.88 91	87.46 95	38.08 314	66.26 418	53.31 268	78.48 180	74.78 406

UnsupCasMVSNet_eth		53.16 414	52.47 411	55.23 429	59.45 472	33.39 458	59.43 441	69.13 364	45.98 409	50.35 449	72.32 411	29.30 410	58.26 454	42.02 382	44.30 472	74.05 414

AllTest		57.08 381	54.65 394	64.39 363	71.44 366	49.03 279	69.92 353	67.30 375	45.97 410	47.16 458	79.77 305	17.47 465	67.56 408	33.65 433	59.16 429	76.57 383

TestCases				64.39 363	71.44 366	49.03 279		67.30 375	45.97 410	47.16 458	79.77 305	17.47 465	67.56 408	33.65 433	59.16 429	76.57 383

WTY-MVS		59.75 357	60.39 340	57.85 417	72.32 350	37.83 417	61.05 434	64.18 405	45.95 412	61.91 327	79.11 320	47.01 196	60.88 439	42.50 377	69.49 333	74.83 404

IterMVS-SCA-FT		62.49 319	61.52 319	65.40 353	71.99 356	50.80 232	71.15 332	69.63 357	45.71 413	60.61 343	77.93 338	37.45 318	65.99 420	55.67 246	63.50 391	79.42 342

WB-MVS		43.26 438	43.41 438	42.83 466	63.32 454	10.32 504	58.17 446	45.20 482	45.42 414	40.44 477	67.26 456	34.01 358	58.98 449	11.96 494	24.88 489	59.20 470

旧先验2							76.08 225		45.32 415	76.55 48			65.56 422	58.75 223

OpenMVS_ROB	52.78 18	60.03 353	58.14 363	65.69 347	70.47 383	44.82 334	75.33 241	70.86 347	45.04 416	56.06 399	76.00 377	26.89 437	79.65 264	35.36 428	67.29 358	72.60 423

TinyColmap		54.14 403	51.72 415	61.40 388	66.84 434	41.97 374	66.52 385	68.51 368	44.81 417	42.69 473	75.77 382	11.66 481	72.94 369	31.96 443	56.77 440	69.27 459

MDTV_nov1_ep13			57.00 370		72.73 338	38.26 413	65.02 404	64.73 400	44.74 418	55.46 403	72.48 410	32.61 383	70.47 387	37.47 408	67.75 354

新几何1				70.76 252	85.66 42	61.13 30		66.43 385	44.68 419	70.29 157	86.64 127	41.29 271	75.23 359	49.72 296	81.75 113	75.93 389

Patchmtry		57.16 380	56.47 378	59.23 403	69.17 407	34.58 448	62.98 420	63.15 417	44.53 420	56.83 391	74.84 392	35.83 337	68.71 398	40.03 392	60.91 417	74.39 411

ppachtmachnet_test		58.06 375	55.38 390	66.10 339	69.51 400	48.99 282	68.01 374	66.13 389	44.50 421	54.05 423	70.74 427	32.09 389	72.34 375	36.68 418	56.71 441	76.99 380

PatchT		53.17 413	53.44 409	52.33 448	68.29 422	25.34 490	58.21 445	54.41 458	44.46 422	54.56 418	69.05 446	33.32 366	60.94 438	36.93 414	61.76 414	70.73 449

EPMVS		53.96 404	53.69 407	54.79 432	66.12 441	31.96 466	62.34 425	49.05 471	44.42 423	55.54 402	71.33 424	30.22 399	56.70 460	41.65 385	62.54 406	75.71 392

pmmvs4		61.48 341	59.39 348	67.76 304	71.57 362	53.86 159	71.42 325	65.34 394	44.20 424	59.46 358	77.92 339	35.90 336	74.71 361	43.87 363	64.87 376	74.71 408

dp		51.89 418	51.60 416	52.77 445	68.44 421	32.45 464	62.36 424	54.57 457	44.16 425	49.31 453	67.91 448	28.87 414	56.61 462	33.89 432	54.89 447	69.24 460

PatchMatch-RL		56.25 389	54.55 396	61.32 390	77.06 237	56.07 120	65.57 393	54.10 460	44.13 426	53.49 431	71.27 425	25.20 448	66.78 413	36.52 421	63.66 387	61.12 468

our_test_3		56.49 385	54.42 397	62.68 379	69.51 400	45.48 330	66.08 388	61.49 430	44.11 427	50.73 446	69.60 443	33.05 368	68.15 400	38.38 404	56.86 438	74.40 410

USDC		56.35 388	54.24 401	62.69 378	64.74 447	40.31 392	65.05 403	73.83 314	43.93 428	47.58 456	77.71 349	15.36 474	75.05 360	38.19 406	61.81 413	72.70 422

PM-MVS		52.33 415	50.19 424	58.75 408	62.10 460	45.14 333	65.75 390	40.38 489	43.60 429	53.52 429	72.65 409	9.16 489	65.87 421	50.41 290	54.18 450	65.24 466

pmmvs-eth3d		58.81 365	56.31 381	66.30 333	67.61 427	52.42 205	72.30 312	64.76 399	43.55 430	54.94 413	74.19 398	28.95 412	72.60 371	43.31 368	57.21 437	73.88 416

SSC-MVS		41.96 443	41.99 442	41.90 467	62.46 459	9.28 506	57.41 452	44.32 485	43.38 431	38.30 483	66.45 459	32.67 380	58.42 453	10.98 495	21.91 492	57.99 474

new-patchmatchnet		47.56 432	47.73 432	47.06 457	58.81 475	9.37 505	48.78 476	59.21 438	43.28 432	44.22 469	68.66 447	25.67 445	57.20 459	31.57 451	49.35 465	74.62 409

Test_1112_low_res		62.32 325	61.77 316	64.00 367	79.08 155	39.53 402	68.17 372	70.17 351	43.25 433	59.03 364	79.90 302	44.08 231	71.24 383	43.79 364	68.42 348	81.25 297

RPMNet		61.53 339	58.42 359	70.86 250	69.96 393	52.07 211	65.31 400	81.36 140	43.20 434	59.36 359	70.15 433	35.37 341	85.47 119	36.42 422	64.65 378	75.06 399

tpm2		62.07 329	60.10 344	67.99 302	72.79 337	43.86 348	71.05 335	66.85 382	43.14 435	62.77 311	75.39 389	38.32 310	80.80 243	41.69 383	68.88 342	79.32 343

usedtu_dtu_shiyan2		53.34 411	50.78 420	61.00 394	61.86 462	39.63 399	68.47 369	64.58 401	42.94 436	45.22 465	67.61 452	19.25 464	66.71 414	28.08 466	59.05 431	76.66 382

JIA-IIPM		51.56 419	47.68 433	63.21 374	64.61 448	50.73 237	47.71 478	58.77 440	42.90 437	48.46 455	51.72 482	24.97 449	70.24 392	36.06 425	53.89 452	68.64 461

1314		64.61 292	63.21 299	68.80 290	71.87 358	47.46 310	73.95 275	78.39 220	42.88 438	59.97 350	76.60 369	38.11 313	79.39 272	54.84 253	72.32 283	79.55 340

HyFIR lowres test		65.67 276	63.01 301	73.67 159	79.97 132	55.65 130	69.07 365	75.52 280	42.68 439	63.53 298	77.95 337	40.43 281	81.64 216	46.01 337	71.91 290	83.73 233

CR-MVSNet		59.91 354	57.90 365	65.96 341	69.96 393	52.07 211	65.31 400	63.15 417	42.48 440	59.36 359	74.84 392	35.83 337	70.75 386	45.50 345	64.65 378	75.06 399

test222					83.14 77	58.68 82	72.57 307	63.45 414	41.78 441	67.56 221	86.12 149	37.13 325			78.73 173	74.98 402

TDRefinement		53.44 410	50.72 421	61.60 385	64.31 450	46.96 314	70.89 336	65.27 396	41.78 441	44.61 468	77.98 336	11.52 483	66.36 417	28.57 465	51.59 458	71.49 441

sss		56.17 390	56.57 377	54.96 430	66.93 433	36.32 435	57.94 447	61.69 429	41.67 443	58.64 369	75.32 390	38.72 305	56.25 464	42.04 381	66.19 367	72.31 432

PVSNet_0	43.31 20	47.46 433	45.64 436	52.92 444	67.60 428	44.65 337	54.06 462	54.64 456	41.59 444	46.15 463	58.75 475	30.99 393	58.66 451	32.18 440	24.81 490	55.46 478

MVS		67.37 244	66.33 250	70.51 260	75.46 275	50.94 227	73.95 275	81.85 128	41.57 445	62.54 318	78.57 329	47.98 175	85.47 119	52.97 270	82.05 106	75.14 398

Anonymous20240521		55.30 396	54.41 398	57.96 416	60.92 470	41.73 377	71.09 334	71.06 343	41.18 446	48.65 454	73.31 406	16.93 468	59.25 447	42.54 376	64.01 383	72.90 420

Anonymous20231206		55.10 401	55.30 391	54.48 433	69.81 398	33.94 454	62.91 421	62.13 428	41.08 447	55.18 409	75.65 383	32.75 376	56.59 463	30.32 458	67.86 352	72.91 419

MDA-MVSNet_test_wron		50.71 424	48.95 426	56.00 426	61.17 465	41.84 375	51.90 468	56.45 449	40.96 448	44.79 467	67.84 449	30.04 403	55.07 471	36.71 417	50.69 461	71.11 447

YYNet1		50.73 423	48.96 425	56.03 425	61.10 466	41.78 376	51.94 467	56.44 450	40.94 449	44.84 466	67.80 450	30.08 402	55.08 470	36.77 415	50.71 460	71.22 444

dongtai		34.52 453	34.94 453	33.26 476	61.06 467	16.00 501	52.79 466	23.78 502	40.71 450	39.33 481	48.65 490	16.91 469	48.34 483	12.18 493	19.05 494	35.44 493

CHOSEN 1792x2688		65.08 286	62.84 303	71.82 212	81.49 101	56.26 116	66.32 387	74.20 309	40.53 451	63.16 304	78.65 326	41.30 270	77.80 315	45.80 339	74.09 246	81.40 292

pmmvs5		56.47 386	55.68 386	58.86 407	61.41 464	36.71 430	66.37 386	62.75 419	40.38 452	53.70 425	76.62 366	34.56 349	67.05 411	40.02 393	65.27 372	72.83 421

test_vis1_n_1920		58.86 364	59.06 353	58.25 411	63.76 451	43.14 360	67.49 379	66.36 386	40.22 453	65.89 257	71.95 417	31.04 392	59.75 445	59.94 207	64.90 375	71.85 436

MDTV_nov1_ep13_2view						25.89 488	61.22 431		40.10 454	51.10 441		32.97 371		38.49 403		78.61 354

tpm cat1		59.25 363	56.95 371	66.15 337	72.19 352	46.96 314	68.09 373	65.76 390	40.03 455	57.81 379	70.56 428	38.32 310	74.51 362	38.26 405	61.50 415	77.00 378

test-mter		56.42 387	55.82 385	58.22 412	68.57 415	44.80 335	65.46 396	57.92 443	39.94 456	55.44 404	69.82 439	21.92 457	57.44 457	49.66 297	73.62 256	72.41 429

UnsupCasMVSNet_bld		50.07 426	48.87 427	53.66 438	60.97 469	33.67 456	57.62 451	64.56 402	39.47 457	47.38 457	64.02 467	27.47 429	59.32 446	34.69 430	43.68 473	67.98 463

TESTMET0.1,1		55.28 397	54.90 393	56.42 423	66.56 436	43.67 351	65.46 396	56.27 453	39.18 458	53.83 424	67.44 453	24.21 452	55.46 468	48.04 312	73.11 270	70.13 453

ADS-MVSNet2		51.33 421	48.76 428	59.07 406	66.02 442	44.60 340	50.90 470	59.76 436	36.90 459	50.74 444	66.18 461	26.38 439	63.11 432	27.17 470	54.76 448	69.50 457

ADS-MVSNet		48.48 430	47.77 431	50.63 453	66.02 442	29.92 473	50.90 470	50.87 469	36.90 459	50.74 444	66.18 461	26.38 439	52.47 477	27.17 470	54.76 448	69.50 457

RPSCF		55.80 393	54.22 402	60.53 395	65.13 446	42.91 367	64.30 410	57.62 445	36.84 461	58.05 378	82.28 251	28.01 424	56.24 465	37.14 412	58.61 432	82.44 273

test_cas_vis1_n_1920		56.91 382	56.71 375	57.51 420	59.13 474	45.40 331	63.58 416	61.29 431	36.24 462	67.14 230	71.85 418	29.89 404	56.69 461	57.65 229	63.58 390	70.46 450

Patchmatch-test		49.08 428	48.28 430	51.50 452	64.40 449	30.85 471	45.68 482	48.46 474	35.60 463	46.10 464	72.10 414	34.47 352	46.37 486	27.08 472	60.65 422	77.27 373

CHOSEN 280x420		47.83 431	46.36 435	52.24 450	67.37 430	49.78 261	38.91 490	43.11 487	35.00 464	43.27 472	63.30 468	28.95 412	49.19 482	36.53 420	60.80 419	57.76 475

N_pmnet		39.35 448	40.28 445	36.54 473	63.76 451	1.62 519	49.37 475	0.76 519	34.62 465	43.61 471	66.38 460	26.25 441	42.57 490	26.02 475	51.77 457	65.44 465

kuosan		29.62 460	30.82 459	26.02 481	52.99 480	16.22 500	51.09 469	22.71 503	33.91 466	33.99 485	40.85 492	15.89 472	33.11 498	7.59 504	18.37 495	28.72 495

PMMVS		53.96 404	53.26 410	56.04 424	62.60 458	50.92 229	61.17 432	56.09 454	32.81 467	53.51 430	66.84 458	34.04 356	59.93 444	44.14 359	68.18 350	57.27 476

CMPMVS	42.80 21	57.81 377	55.97 383	63.32 372	60.98 468	47.38 311	64.66 406	69.50 360	32.06 468	46.83 460	77.80 345	29.50 408	71.36 381	48.68 305	73.75 252	71.21 445
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
ttmdpeth		45.56 434	42.95 439	53.39 442	52.33 484	29.15 475	57.77 448	48.20 476	31.81 469	49.86 451	77.21 354	8.69 490	59.16 448	27.31 469	33.40 486	71.84 437

CVMVSNet		59.63 359	59.14 350	61.08 393	74.47 303	38.84 407	75.20 246	68.74 367	31.15 470	58.24 374	76.51 370	32.39 386	68.58 399	49.77 294	65.84 369	75.81 390

FPMVS		42.18 442	41.11 444	45.39 459	58.03 476	41.01 386	49.50 474	53.81 461	30.07 471	33.71 486	64.03 465	11.69 480	52.08 480	14.01 489	55.11 446	43.09 487

EU-MVSNet		55.61 395	54.41 398	59.19 405	65.41 444	33.42 457	72.44 310	71.91 337	28.81 472	51.27 440	73.87 402	24.76 450	69.08 396	43.04 372	58.20 433	75.06 399

test_vis1_n		49.89 427	48.69 429	53.50 440	53.97 478	37.38 422	61.53 427	47.33 479	28.54 473	59.62 357	67.10 457	13.52 476	52.27 478	49.07 302	57.52 435	70.84 448

test_fmvs1_n		51.37 420	50.35 423	54.42 435	52.85 481	37.71 419	61.16 433	51.93 462	28.15 474	63.81 296	69.73 441	13.72 475	53.95 472	51.16 285	60.65 422	71.59 439

LF4IMVS		42.95 439	42.26 441	45.04 460	48.30 489	32.50 463	54.80 459	48.49 473	28.03 475	40.51 476	70.16 432	9.24 488	43.89 489	31.63 449	49.18 466	58.72 472

test_fmvs1		51.32 422	50.48 422	53.81 437	53.57 479	37.51 421	60.63 437	51.16 465	28.02 476	63.62 297	69.23 445	16.41 470	53.93 473	51.01 286	60.70 421	69.99 454

MVS-HIRNet		45.52 435	44.48 437	48.65 456	68.49 420	34.05 453	59.41 442	44.50 484	27.03 477	37.96 484	50.47 486	26.16 442	64.10 426	26.74 473	59.52 427	47.82 485

PMVS	28.69 22	36.22 451	33.29 456	45.02 461	36.82 501	35.98 438	54.68 460	48.74 472	26.31 478	21.02 494	51.61 483	2.88 502	60.10 443	9.99 499	47.58 467	38.99 492
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
pmmvs3		44.92 436	41.95 443	53.86 436	52.58 483	43.55 352	62.11 426	46.90 481	26.05 479	40.63 475	60.19 472	11.08 486	57.91 455	31.83 448	46.15 469	60.11 469

test_fmvs2		48.69 429	47.49 434	52.29 449	48.63 488	33.06 461	57.76 449	48.05 477	25.71 480	59.76 355	69.60 443	11.57 482	52.23 479	49.45 300	56.86 438	71.58 440

PMMVS2		27.40 461	25.91 464	31.87 478	39.46 500	6.57 508	31.17 493	28.52 498	23.96 481	20.45 495	48.94 489	4.20 498	37.94 494	16.51 486	19.97 493	51.09 480

MVStest1		42.65 440	39.29 447	52.71 446	47.26 491	34.58 448	54.41 461	50.84 470	23.35 482	39.31 482	74.08 401	12.57 478	55.09 469	23.32 478	28.47 488	68.47 462

Gipuma		34.77 452	31.91 457	43.33 464	62.05 461	37.87 415	20.39 495	67.03 380	23.23 483	18.41 496	25.84 500	4.24 496	62.73 433	14.71 488	51.32 459	29.38 494
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
test_vis1_rt		41.35 445	39.45 446	47.03 458	46.65 492	37.86 416	47.76 477	38.65 490	23.10 484	44.21 470	51.22 484	11.20 485	44.08 488	39.27 399	53.02 454	59.14 471

new_pmnet		34.13 454	34.29 455	33.64 475	52.63 482	18.23 499	44.43 485	33.90 495	22.81 485	30.89 488	53.18 480	10.48 487	35.72 497	20.77 482	39.51 478	46.98 486

mvsany_test1		39.38 447	38.16 450	43.02 465	49.05 486	34.28 451	44.16 486	25.94 500	22.74 486	46.57 462	62.21 471	23.85 453	41.16 493	33.01 438	35.91 482	53.63 479

LCM-MVSNet		40.30 446	35.88 452	53.57 439	42.24 494	29.15 475	45.21 484	60.53 435	22.23 487	28.02 489	50.98 485	3.72 499	61.78 437	31.22 454	38.76 480	69.78 456

test_fmvs3		44.30 437	42.55 440	49.55 455	42.83 493	27.15 485	53.03 464	44.93 483	22.03 488	53.69 427	64.94 464	4.21 497	49.63 481	47.47 313	49.82 463	71.88 435

APD_test1		37.39 450	34.94 453	44.72 463	48.88 487	33.19 460	52.95 465	44.00 486	19.49 489	27.28 490	58.59 476	3.18 501	52.84 476	18.92 484	41.17 477	48.14 484

mvsany_test3		32.62 455	30.57 460	38.77 471	36.16 502	24.20 492	38.10 491	20.63 504	19.14 490	40.36 478	57.43 477	5.06 494	36.63 496	29.59 462	28.66 487	55.49 477

E-PMN		23.77 462	22.73 466	26.90 479	42.02 495	20.67 496	42.66 487	35.70 493	17.43 491	10.28 504	25.05 501	6.42 492	42.39 491	10.28 498	14.71 497	17.63 499

EMVS		22.97 463	21.84 467	26.36 480	40.20 498	19.53 498	41.95 488	34.64 494	17.09 492	9.73 505	22.83 503	7.29 491	42.22 492	9.18 501	13.66 498	17.32 500

test_vis3_rt		32.09 456	30.20 461	37.76 472	35.36 503	27.48 481	40.60 489	28.29 499	16.69 493	32.52 487	40.53 493	1.96 503	37.40 495	33.64 435	42.21 476	48.39 482

test_f		31.86 457	31.05 458	34.28 474	32.33 505	21.86 495	32.34 492	30.46 497	16.02 494	39.78 480	55.45 479	4.80 495	32.36 499	30.61 455	37.66 481	48.64 481

DSMNet-mixed		39.30 449	38.72 448	41.03 468	51.22 485	19.66 497	45.53 483	31.35 496	15.83 495	39.80 479	67.42 455	22.19 456	45.13 487	22.43 479	52.69 455	58.31 473

testf1		31.46 458	28.89 462	39.16 469	41.99 496	28.78 477	46.45 480	37.56 491	14.28 496	21.10 492	48.96 487	1.48 505	47.11 484	13.63 490	34.56 483	41.60 488

APD_test2		31.46 458	28.89 462	39.16 469	41.99 496	28.78 477	46.45 480	37.56 491	14.28 496	21.10 492	48.96 487	1.48 505	47.11 484	13.63 490	34.56 483	41.60 488

MVE	17.77 23	21.41 464	17.77 469	32.34 477	34.34 504	25.44 489	16.11 496	24.11 501	11.19 498	13.22 498	31.92 496	1.58 504	30.95 500	10.47 497	17.03 496	40.62 491
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
DeepMVS_CX				12.03 485	17.97 506	10.91 503		10.60 507	7.46 499	11.07 502	28.36 499	3.28 500	11.29 504	8.01 502	9.74 502	13.89 502

RoMa-SfM		11.96 468	11.39 471	13.68 484	10.24 510	6.80 507	15.83 497	1.33 513	6.34 500	13.06 499	41.41 491	0.16 509	12.72 503	10.58 496	3.56 506	21.52 496

DKM		10.33 469	10.10 473	11.02 486	10.54 509	5.43 509	14.18 498	1.03 515	4.97 501	11.74 501	36.09 495	0.11 512	9.09 506	9.38 500	2.85 507	18.53 498

wuyk23d		13.32 467	12.52 470	15.71 483	47.54 490	26.27 487	31.06 494	1.98 510	4.93 502	5.18 509	1.94 520	0.45 507	18.54 502	6.81 505	12.83 499	2.33 507

PDCNetPlus		9.23 472	8.89 475	10.23 488	13.70 507	3.70 512	12.27 500	1.51 512	3.98 503	6.73 507	29.50 498	0.24 508	8.07 508	7.83 503	4.30 505	18.93 497

LoFTR		9.45 470	9.00 474	10.79 487	10.22 511	4.31 511	11.11 502	4.11 508	2.40 504	10.53 503	30.89 497	0.13 510	10.75 505	3.12 506	8.52 503	17.31 501

test_method		19.68 465	18.10 468	24.41 482	13.68 508	3.11 514	12.06 501	42.37 488	2.00 505	11.97 500	36.38 494	5.77 493	29.35 501	15.06 487	23.65 491	40.76 490

MatchFormer		7.03 473	6.96 477	7.26 489	7.64 512	3.36 513	10.21 503	3.04 509	1.31 506	9.02 506	22.94 502	0.08 518	8.15 507	1.46 508	6.91 504	10.26 504

ELoFTR		4.04 478	3.55 482	5.50 491	2.33 520	1.25 520	3.58 505	1.18 514	0.90 507	4.23 510	16.28 504	0.03 524	5.46 511	1.95 507	1.42 514	9.81 505

GLUNet-SfM		4.33 477	3.64 481	6.41 490	3.38 516	1.65 517	3.23 507	1.54 511	0.66 508	6.36 508	15.13 505	0.08 518	5.54 509	0.94 509	1.44 513	12.05 503

tmp_tt		9.43 471	11.14 472	4.30 492	2.38 519	4.40 510	13.62 499	16.08 506	0.39 509	15.89 497	13.06 506	15.80 473	5.54 509	12.63 492	10.46 501	2.95 506

ALIKED-LG		2.35 480	2.54 483	1.78 493	5.54 513	1.79 516	3.81 504	0.96 516	0.33 510	1.86 511	7.18 507	0.13 510	1.60 512	0.20 517	2.81 508	1.94 508

ALIKED-MNN		2.09 481	2.23 484	1.67 494	5.15 514	1.82 515	3.53 506	0.77 517	0.25 511	1.45 513	6.03 509	0.09 516	1.52 513	0.17 518	2.64 509	1.66 509

ALIKED-NN		1.96 482	2.12 485	1.48 495	4.72 515	1.65 517	3.19 508	0.77 517	0.23 512	1.43 514	5.87 510	0.10 514	1.37 514	0.16 519	2.61 510	1.42 515

SP-DiffGlue		0.98 484	1.05 487	0.75 500	0.81 537	0.40 527	1.24 513	0.37 521	0.19 513	1.26 516	3.80 512	0.11 512	0.34 521	0.51 510	1.18 515	1.52 513

SP-LightGlue		0.94 485	0.99 488	0.78 496	2.60 517	0.38 528	1.71 509	0.34 522	0.17 514	0.50 518	2.14 516	0.09 516	0.38 518	0.26 513	1.13 516	1.59 510

SP-SuperGlue		0.93 486	0.98 489	0.77 497	2.54 518	0.38 528	1.70 510	0.34 522	0.17 514	0.52 517	2.13 517	0.10 514	0.36 520	0.26 513	1.10 517	1.57 512

XFeat-MNN		1.07 483	1.17 486	0.77 497	0.52 538	0.31 535	1.15 514	0.41 520	0.15 516	1.62 512	4.35 511	0.07 522	0.77 515	0.38 511	1.88 511	1.22 516

SP-NN		0.85 489	0.90 492	0.73 501	2.22 522	0.33 534	1.63 512	0.31 525	0.14 517	0.47 520	1.97 519	0.08 518	0.38 518	0.25 515	1.01 519	1.47 514

SP-MNN		0.89 487	0.93 491	0.77 497	2.32 521	0.34 532	1.68 511	0.33 524	0.13 518	0.49 519	2.07 518	0.08 518	0.39 517	0.25 515	1.07 518	1.58 511

XFeat-NN		0.87 488	0.97 490	0.59 502	0.48 539	0.24 538	0.94 515	0.29 526	0.12 519	1.41 515	3.45 515	0.06 523	0.56 516	0.29 512	1.65 512	0.95 517

SIFT-NN-UMatch		0.48 495	0.52 498	0.36 508	1.27 532	0.36 530	0.75 519	0.12 530	0.10 520	0.25 526	1.29 523	0.02 525	0.26 526	0.04 520	0.85 524	0.44 522

SIFT-NN		0.60 490	0.65 493	0.45 503	1.90 523	0.55 521	0.90 516	0.16 527	0.10 520	0.34 521	1.43 521	0.02 525	0.28 522	0.04 520	0.95 520	0.50 518

SIFT-MNN		0.56 491	0.61 494	0.43 504	1.75 524	0.50 522	0.82 517	0.16 527	0.10 520	0.30 522	1.38 522	0.02 525	0.28 522	0.04 520	0.92 522	0.50 518

SIFT-UM-Cal		0.41 500	0.46 502	0.28 513	1.35 530	0.29 536	0.57 525	0.08 537	0.09 523	0.20 530	1.10 530	0.02 525	0.23 531	0.03 528	0.68 529	0.30 530

SIFT-NCM-Cal		0.51 493	0.55 496	0.38 506	1.66 525	0.45 524	0.75 519	0.12 530	0.09 523	0.21 529	1.18 528	0.02 525	0.27 524	0.03 528	0.89 523	0.43 524

SIFT-CM-Cal		0.42 499	0.46 502	0.31 512	1.40 529	0.35 531	0.56 526	0.09 536	0.09 523	0.20 530	1.09 531	0.02 525	0.23 531	0.03 528	0.66 530	0.34 528

SIFT-NN-NCMNet		0.53 492	0.58 495	0.40 505	1.60 526	0.49 523	0.80 518	0.15 529	0.09 523	0.28 524	1.29 523	0.02 525	0.27 524	0.04 520	0.94 521	0.44 522

SIFT-NN-CMatch		0.49 494	0.53 497	0.38 506	1.35 530	0.41 526	0.70 521	0.12 530	0.09 523	0.30 522	1.28 525	0.02 525	0.26 526	0.04 520	0.83 525	0.47 520

SIFT-NN-PointCN		0.44 498	0.47 501	0.33 510	1.17 533	0.29 536	0.64 523	0.11 533	0.09 523	0.25 526	1.14 529	0.02 525	0.25 528	0.03 528	0.78 526	0.46 521

SIFT-UMatch		0.45 497	0.50 500	0.32 511	1.46 528	0.34 532	0.66 522	0.10 535	0.09 523	0.22 528	1.19 527	0.02 525	0.25 528	0.04 520	0.73 528	0.36 527

SIFT-ConvMatch		0.48 495	0.52 498	0.35 509	1.51 527	0.42 525	0.64 523	0.11 533	0.09 523	0.26 525	1.24 526	0.02 525	0.25 528	0.04 520	0.76 527	0.38 525

SIFT-PCN-Cal		0.36 501	0.39 504	0.26 514	1.16 534	0.21 539	0.46 528	0.07 539	0.08 531	0.17 533	0.92 532	0.01 536	0.20 534	0.03 528	0.59 532	0.37 526

SIFT-NCMNet		0.30 503	0.33 506	0.19 516	1.04 536	0.18 541	0.39 529	0.05 540	0.08 531	0.14 535	0.77 534	0.01 536	0.16 535	0.02 535	0.49 533	0.22 531

SIFT-PointCN		0.36 501	0.39 504	0.25 515	1.14 535	0.21 539	0.50 527	0.08 537	0.08 531	0.17 533	0.89 533	0.01 536	0.21 533	0.03 528	0.60 531	0.34 528

EGC-MVSNET		42.47 441	38.48 449	54.46 434	74.33 308	48.73 288	70.33 348	51.10 466	0.03 534	0.18 532	67.78 451	13.28 477	66.49 416	18.91 485	50.36 462	48.15 483

testmvs		4.52 476	6.03 479	0.01 518	0.01 540	0.00 543	53.86 463	0.00 541	0.01 535	0.04 536	0.27 535	0.00 540	0.00 536	0.04 520	0.00 534	0.03 533

test123		4.73 475	6.30 478	0.02 517	0.01 540	0.01 542	56.36 455	0.00 541	0.01 535	0.04 536	0.21 536	0.01 536	0.00 536	0.03 528	0.00 534	0.04 532

mmdepth		0.00 504	0.00 507	0.00 519	0.00 542	0.00 543	0.00 530	0.00 541	0.00 537	0.00 538	0.00 537	0.00 540	0.00 536	0.00 536	0.00 534	0.00 534

monomultidepth		0.00 504	0.00 507	0.00 519	0.00 542	0.00 543	0.00 530	0.00 541	0.00 537	0.00 538	0.00 537	0.00 540	0.00 536	0.00 536	0.00 534	0.00 534

test_blank		0.00 504	0.00 507	0.00 519	0.00 542	0.00 543	0.00 530	0.00 541	0.00 537	0.00 538	0.00 537	0.00 540	0.00 536	0.00 536	0.00 534	0.00 534

uanet_test		0.00 504	0.00 507	0.00 519	0.00 542	0.00 543	0.00 530	0.00 541	0.00 537	0.00 538	0.00 537	0.00 540	0.00 536	0.00 536	0.00 534	0.00 534

DCPMVS		0.00 504	0.00 507	0.00 519	0.00 542	0.00 543	0.00 530	0.00 541	0.00 537	0.00 538	0.00 537	0.00 540	0.00 536	0.00 536	0.00 534	0.00 534

cdsmvs_eth3d_5k		17.50 466	23.34 465	0.00 519	0.00 542	0.00 543	0.00 530	78.63 203	0.00 537	0.00 538	82.18 254	49.25 162	0.00 536	0.00 536	0.00 534	0.00 534

pcd_1.5k_mvsjas		3.92 479	5.23 480	0.00 519	0.00 542	0.00 543	0.00 530	0.00 541	0.00 537	0.00 538	0.00 537	47.05 193	0.00 536	0.00 536	0.00 534	0.00 534

sosnet-low-res		0.00 504	0.00 507	0.00 519	0.00 542	0.00 543	0.00 530	0.00 541	0.00 537	0.00 538	0.00 537	0.00 540	0.00 536	0.00 536	0.00 534	0.00 534

sosnet		0.00 504	0.00 507	0.00 519	0.00 542	0.00 543	0.00 530	0.00 541	0.00 537	0.00 538	0.00 537	0.00 540	0.00 536	0.00 536	0.00 534	0.00 534

uncertanet		0.00 504	0.00 507	0.00 519	0.00 542	0.00 543	0.00 530	0.00 541	0.00 537	0.00 538	0.00 537	0.00 540	0.00 536	0.00 536	0.00 534	0.00 534

Regformer		0.00 504	0.00 507	0.00 519	0.00 542	0.00 543	0.00 530	0.00 541	0.00 537	0.00 538	0.00 537	0.00 540	0.00 536	0.00 536	0.00 534	0.00 534

ab-mvs-re		6.49 474	8.65 476	0.00 519	0.00 542	0.00 543	0.00 530	0.00 541	0.00 537	0.00 538	77.89 343	0.00 540	0.00 536	0.00 536	0.00 534	0.00 534

uanet		0.00 504	0.00 507	0.00 519	0.00 542	0.00 543	0.00 530	0.00 541	0.00 537	0.00 538	0.00 537	0.00 540	0.00 536	0.00 536	0.00 534	0.00 534

WAC-MVS						27.31 483								27.77 467

MSC_two_6792asdad				79.95 4	87.24 14	61.04 31		85.62 30					90.96 1	79.31 10	90.65 8	87.85 54

No_MVS				79.95 4	87.24 14	61.04 31		85.62 30					90.96 1	79.31 10	90.65 8	87.85 54

eth-test2					0.00 542

eth-test					0.00 542

OPU-MVS				79.83 7	87.54 11	60.93 35	87.82 7				89.89 51	67.01 1	90.33 12	73.16 71	91.15 4	88.23 39

test_0728_SECOND				79.19 16	87.82 3	59.11 71	87.85 5	87.15 3					90.84 3	78.66 18	90.61 11	87.62 65

GSMVS																78.05 360

test_part2					87.58 9	60.47 42				83.42 14

sam_mvs1												34.74 348				78.05 360

sam_mvs												33.43 365

ambc				65.13 358	63.72 453	37.07 426	47.66 479	78.78 199		54.37 421	71.42 420	11.24 484	80.94 238	45.64 341	53.85 453	77.38 371

MTGPA								80.97 158

test_post1							68.67 367				3.64 513	32.39 386	69.49 394	44.17 357

test_post											3.55 514	33.90 359	66.52 415

patchmatchnet-post											64.03 465	34.50 350	74.27 364

GG-mvs-BLEND				62.34 380	71.36 370	37.04 427	69.20 364	57.33 448		54.73 416	65.48 463	30.37 396	77.82 314	34.82 429	74.93 238	72.17 433

MTMP							86.03 23	17.08 505

test9_res														75.28 54	88.31 35	83.81 227

agg_prior2														73.09 72	87.93 43	84.33 205

agg_prior					85.04 54	59.96 50		81.04 156		74.68 74			84.04 149

test_prior4						62.51 14	82.08 87

test_prior				76.69 66	84.20 66	57.27 99		84.88 45					86.43 89			86.38 115

新几何2							76.12 223

旧先验1					83.04 79	53.15 181		67.52 374			87.85 88	44.08 231			80.76 122	78.03 363

原ACMM2							79.02 130

testdata2													72.18 378	46.95 329

segment_acmp												54.23 76

test12				77.76 51	84.52 63	58.41 84		83.36 92		72.93 118		54.61 73	88.05 44		88.12 37	86.81 97

plane_prior7					81.41 102	55.96 122

plane_prior6					81.20 109	56.24 117						45.26 218

plane_prior5								84.01 58					87.21 64	68.16 110	80.58 126	84.65 196

plane_prior4											86.10 150

plane_prior1					81.27 107

n2								0.00 541

nn								0.00 541

door-mid								47.19 480

lessismore_v0				69.91 270	71.42 368	47.80 304		50.90 468		50.39 448	75.56 384	27.43 431	81.33 225	45.91 338	34.10 485	80.59 315

test11								83.47 87

door								47.60 478

HQP5-MVS						54.94 144

BP-MVS														67.04 130

HQP4-MVS										67.85 210			86.93 72			84.32 206

HQP3-MVS								83.90 63							80.35 131

HQP2-MVS												45.46 212

NP-MVS					80.98 112	56.05 121					85.54 172

ACMMP++_ref															74.07 247

ACMMP++															72.16 288

Test By Simon												48.33 173

High-resolution multi-view benchmark