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.

MSP-MVS		82.30 6	83.47 1	78.80 59	82.99 122	52.71 135	85.04 135	88.63 45	66.08 73	86.77 3	92.75 32	72.05 1	91.46 70	83.35 20	93.53 1	92.23 37
Zhenlong Yuan, Cong Liu, Fei Shen, Zhaoxin Li, Jingguo luo, Tianlu Mao and Zhaoqi Wang: MSP-MVS: Multi-granularity Segmentation Prior Guided Multi-View Stereo. AAAI2025
DVP-MVS++		82.44 3	82.38 6	82.62 4	91.77 4	57.49 17	84.98 138	88.88 34	58.00 221	83.60 6	93.39 18	67.21 2	96.39 4	81.64 31	91.98 4	93.98 5

OPU-MVS				81.71 13	92.05 3	55.97 48	92.48 3				94.01 5	67.21 2	95.10 15	89.82 3	92.55 3	94.06 3

PC_three_1452									66.58 61	87.27 2	93.70 10	66.82 4	94.95 17	89.74 4	91.98 4	93.98 5

DPM-MVS		82.39 4	82.36 7	82.49 5	80.12 198	59.50 5	92.24 8	90.72 15	69.37 33	83.22 8	94.47 2	63.81 5	93.18 32	74.02 84	93.25 2	94.80 1

WBMVS		73.93 96	73.39 89	75.55 144	87.82 39	55.21 65	89.37 37	87.29 70	67.27 53	63.70 174	80.30 249	60.32 6	86.47 233	61.58 170	62.85 254	84.97 217

DELS-MVS		82.32 5	82.50 5	81.79 12	86.80 47	56.89 29	92.77 2	86.30 90	77.83 1	77.88 33	92.13 41	60.24 7	94.78 19	78.97 44	89.61 8	93.69 8
Christian Sormann, Emanuele Santellani, Mattia Rossi, Andreas Kuhn, Friedrich Fraundorfer: DELS-MVS: Deep Epipolar Line Search for Multi-View Stereo. Winter Conference on Applications of Computer Vision (WACV), 2023
dcpmvs_2		79.33 21	78.94 21	80.49 25	89.75 12	56.54 36	84.83 145	83.68 158	67.85 45	69.36 107	90.24 89	60.20 8	92.10 58	84.14 16	80.40 82	92.82 25

baseline2		75.15 82	74.54 79	76.98 109	81.67 158	51.74 157	83.84 175	91.94 3	69.97 27	58.98 230	86.02 170	59.73 9	91.73 64	68.37 119	70.40 189	87.48 169

CSCG		80.41 15	79.72 16	82.49 5	89.12 25	57.67 15	89.29 41	91.54 5	59.19 197	71.82 82	90.05 97	59.72 10	96.04 10	78.37 50	88.40 14	93.75 7

GG-mvs-BLEND				77.77 86	86.68 48	50.61 176	68.67 347	88.45 51		68.73 114	87.45 151	59.15 11	90.67 92	54.83 233	87.67 17	92.03 45

SED-MVS		81.92 8	81.75 9	82.44 7	89.48 17	56.89 29	92.48 3	88.94 32	57.50 235	84.61 4	94.09 3	58.81 12	96.37 6	82.28 26	87.60 18	94.06 3

test_241102_ONE					89.48 17	56.89 29		88.94 32	57.53 233	84.61 4	93.29 22	58.81 12	96.45 1

gg-mvs-nofinetune		67.43 221	64.53 246	76.13 128	85.95 55	47.79 265	64.38 361	88.28 53	39.34 366	66.62 129	41.27 403	58.69 14	89.00 142	49.64 269	86.62 31	91.59 58

balanced_conf03		80.28 16	79.73 15	81.90 11	86.47 51	59.34 6	80.45 260	89.51 24	69.76 29	71.05 94	86.66 164	58.68 15	93.24 31	84.64 14	90.40 6	93.14 18

UBG		78.86 24	78.86 22	78.86 57	87.80 40	55.43 55	87.67 64	91.21 10	72.83 9	72.10 79	88.40 128	58.53 16	89.08 137	73.21 94	77.98 107	92.08 41

testing11		79.18 22	78.85 23	80.16 33	88.33 30	56.99 26	88.31 52	92.06 1	72.82 10	70.62 102	88.37 129	57.69 17	92.30 50	75.25 74	76.24 128	91.20 73

MVSMamba_PlusPlus		75.28 77	73.39 89	80.96 21	80.85 183	58.25 10	74.47 309	87.61 67	50.53 306	65.24 147	83.41 203	57.38 18	92.83 36	73.92 86	87.13 21	91.80 54

testing99		78.45 26	77.78 34	80.45 28	88.28 33	56.81 32	87.95 59	91.49 6	71.72 14	70.84 96	88.09 137	57.29 19	92.63 44	69.24 113	75.13 144	91.91 49

CostFormer		73.89 98	72.30 107	78.66 65	82.36 141	56.58 33	75.56 299	85.30 113	66.06 74	70.50 104	76.88 289	57.02 20	89.06 138	68.27 121	68.74 200	90.33 93

test_0728_THIRD									58.00 221	81.91 14	93.64 12	56.54 21	96.44 2	81.64 31	86.86 26	92.23 37

DPE-MVS		79.82 19	79.66 17	80.29 30	89.27 24	55.08 72	88.70 47	87.92 58	55.55 265	81.21 19	93.69 11	56.51 22	94.27 22	78.36 51	85.70 40	91.51 63
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
ETVMVS		75.80 72	75.44 64	76.89 112	86.23 54	50.38 185	85.55 118	91.42 7	71.30 20	68.80 113	87.94 143	56.42 23	89.24 132	56.54 222	74.75 151	91.07 77

DeepPCF-MVS	69.37 1	80.65 13	81.56 11	77.94 85	85.46 66	49.56 205	90.99 21	86.66 82	70.58 23	80.07 24	95.30 1	56.18 24	90.97 87	82.57 25	86.22 36	93.28 13

test_241102_TWO								88.76 41	57.50 235	83.60 6	94.09 3	56.14 25	96.37 6	82.28 26	87.43 20	92.55 30

testing91		78.30 32	77.54 37	80.61 23	88.16 35	57.12 25	87.94 60	91.07 14	71.43 17	70.75 97	88.04 141	55.82 26	92.65 42	69.61 109	75.00 148	92.05 44

patch_mono-2		80.84 12	81.59 10	78.62 66	90.34 9	53.77 104	88.08 54	88.36 52	76.17 2	79.40 27	91.09 64	55.43 27	90.09 110	85.01 12	80.40 82	91.99 48

testing222		77.70 40	77.22 42	79.14 48	86.95 45	54.89 78	87.18 79	91.96 2	72.29 12	71.17 93	88.70 122	55.19 28	91.24 76	65.18 148	76.32 127	91.29 71

DVP-MVS		81.30 10	81.00 13	82.20 8	89.40 20	57.45 19	92.34 5	89.99 20	57.71 229	81.91 14	93.64 12	55.17 29	96.44 2	81.68 29	87.13 21	92.72 28
Zhenlong Yuan, Jinguo Luo, Fei Shen, Zhaoxin Li, Cong Liu, Tianlu Mao, Zhaoqi Wang: DVP-MVS: Synergize Depth-Edge and Visibility Prior for Multi-View Stereo. AAAI2025
test0726					89.40 20	57.45 19	92.32 7	88.63 45	57.71 229	83.14 9	93.96 6	55.17 29

TSAR-MVS + MP.		78.31 31	78.26 26	78.48 70	81.33 172	56.31 42	81.59 240	86.41 87	69.61 31	81.72 16	88.16 136	55.09 31	88.04 183	74.12 83	86.31 34	91.09 76
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
BP-MVS1		76.09 62	75.55 61	77.71 88	79.49 205	52.27 146	84.70 148	90.49 17	64.44 95	69.86 106	90.31 88	55.05 32	91.35 72	70.07 107	75.58 137	89.53 117

baseline1		72.51 122	72.12 113	73.69 201	85.05 73	44.46 304	83.51 184	86.13 95	71.61 16	64.64 156	87.97 142	55.00 33	89.48 125	59.07 191	56.05 310	87.13 177

test_one_0601					89.39 22	57.29 22		88.09 55	57.21 241	82.06 13	93.39 18	54.94 34

MM		82.69 2	83.29 3	80.89 22	84.38 86	55.40 59	92.16 10	89.85 22	75.28 4	82.41 11	93.86 8	54.30 35	93.98 23	90.29 1	87.13 21	93.30 12

TSAR-MVS + GP.		77.82 38	77.59 36	78.49 69	85.25 71	50.27 192	90.02 26	90.57 16	56.58 254	74.26 53	91.60 59	54.26 36	92.16 55	75.87 66	79.91 90	93.05 20

EPP-MVSNet		71.14 145	70.07 149	74.33 179	79.18 213	46.52 280	83.81 176	86.49 85	56.32 258	57.95 249	84.90 185	54.23 37	89.14 136	58.14 204	69.65 195	87.33 173

MCST-MVS		83.01 1	83.30 2	82.15 10	92.84 2	57.58 16	93.77 1	91.10 11	75.95 3	77.10 37	93.09 27	54.15 38	95.57 12	85.80 10	85.87 38	93.31 11

alignmvs		78.08 35	77.98 30	78.39 74	83.53 103	53.22 122	89.77 32	85.45 106	66.11 71	76.59 41	91.99 48	54.07 39	89.05 139	77.34 60	77.00 116	92.89 23

GDP-MVS		75.27 78	74.38 80	77.95 84	79.04 216	52.86 133	85.22 126	86.19 93	62.43 138	70.66 100	90.40 86	53.51 40	91.60 66	69.25 112	72.68 167	89.39 120

WTY-MVS		77.47 43	77.52 38	77.30 97	88.33 30	46.25 287	88.46 50	90.32 18	71.40 18	72.32 77	91.72 54	53.44 41	92.37 49	66.28 133	75.42 138	93.28 13

IB-MVS	68.87 2	74.01 94	72.03 117	79.94 38	83.04 119	55.50 53	90.24 25	88.65 43	67.14 55	61.38 200	81.74 237	53.21 42	94.28 21	60.45 184	62.41 257	90.03 105
Christian Sormann, Mattia Rossi, Andreas Kuhn and Friedrich Fraundorfer: IB-MVS: An Iterative Algorithm for Deep Multi-View Stereo based on Binary Decisions. BMVC 2021
HPM-MVS++		80.50 14	80.71 14	79.88 39	87.34 43	55.20 67	89.93 29	87.55 68	66.04 76	79.46 26	93.00 30	53.10 43	91.76 63	80.40 37	89.56 9	92.68 29

miper_enhance_ethall		69.77 173	68.90 165	72.38 228	78.93 220	49.91 197	83.29 193	78.85 252	64.90 91	59.37 223	79.46 256	52.77 44	85.16 266	63.78 154	58.72 279	82.08 264

MVSTER		73.25 110	72.33 105	76.01 132	85.54 64	53.76 105	83.52 180	87.16 72	67.06 56	63.88 172	81.66 238	52.77 44	90.44 98	64.66 152	64.69 231	83.84 240

CNVR-MVS		81.76 9	81.90 8	81.33 18	90.04 10	57.70 14	91.71 11	88.87 36	70.31 25	77.64 36	93.87 7	52.58 46	93.91 26	84.17 15	87.92 16	92.39 33

FIs		70.00 168	70.24 147	69.30 283	77.93 240	38.55 353	83.99 170	87.72 64	66.86 59	57.66 256	84.17 190	52.28 47	85.31 261	52.72 253	68.80 199	84.02 231

tpm2		70.82 154	68.44 170	77.98 81	80.78 185	56.11 44	74.21 311	81.28 203	60.24 177	68.04 119	75.27 307	52.26 48	88.50 165	55.82 230	68.03 204	89.33 121

thisisatest0515		73.64 105	72.20 109	77.97 82	81.63 159	53.01 129	86.69 91	88.81 39	62.53 134	64.06 167	85.65 174	52.15 49	92.50 46	58.43 197	69.84 192	88.39 149

casdiffmvs_mvg		77.75 39	77.28 40	79.16 47	80.42 194	54.44 91	87.76 61	85.46 105	71.67 15	71.38 88	88.35 131	51.58 50	91.22 77	79.02 43	79.89 92	91.83 53
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
UniMVSNet_NR-MVSNet		68.82 191	68.29 173	70.40 269	75.71 276	42.59 329	84.23 162	86.78 78	66.31 67	58.51 240	82.45 222	51.57 51	84.64 274	53.11 244	55.96 311	83.96 237

PAPM		76.76 54	76.07 56	78.81 58	80.20 196	59.11 7	86.86 88	86.23 91	68.60 35	70.18 105	88.84 120	51.57 51	87.16 212	65.48 141	86.68 30	90.15 101

tttt0517		68.33 202	66.29 212	74.46 174	78.08 236	49.06 217	80.88 255	89.08 30	54.40 280	54.75 290	80.77 246	51.31 53	90.33 102	49.35 271	58.01 291	83.99 233

mvs_anonymous		72.29 126	70.74 132	76.94 111	82.85 129	54.72 82	78.43 284	81.54 197	63.77 109	61.69 197	79.32 258	51.11 54	85.31 261	62.15 166	75.79 133	90.79 84

HY-MVS	67.03 5	73.90 97	73.14 95	76.18 127	84.70 79	47.36 270	75.56 299	86.36 89	66.27 68	70.66 100	83.91 193	51.05 55	89.31 130	67.10 127	72.61 168	91.88 51

thisisatest0530		70.47 161	68.56 167	76.20 125	79.78 202	51.52 163	83.49 186	88.58 49	57.62 232	58.60 239	82.79 211	51.03 56	91.48 69	52.84 248	62.36 259	85.59 210

sasdasda		78.17 33	77.86 32	79.12 50	84.30 87	54.22 94	87.71 62	84.57 139	67.70 49	77.70 34	92.11 44	50.90 57	89.95 113	78.18 54	77.54 111	93.20 15

miper_ehance_all_eth		68.70 197	67.58 187	72.08 235	76.91 257	49.48 211	82.47 216	78.45 265	62.68 132	58.28 248	77.88 271	50.90 57	85.01 269	61.91 167	58.72 279	81.75 269

canonicalmvs		78.17 33	77.86 32	79.12 50	84.30 87	54.22 94	87.71 62	84.57 139	67.70 49	77.70 34	92.11 44	50.90 57	89.95 113	78.18 54	77.54 111	93.20 15

casdiffmvs		77.36 44	76.85 46	78.88 56	80.40 195	54.66 87	87.06 82	85.88 98	72.11 13	71.57 85	88.63 127	50.89 60	90.35 101	76.00 65	79.11 98	91.63 57
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
MVS_0304		82.10 7	82.64 4	80.47 27	86.63 49	54.69 84	92.20 9	86.66 82	74.48 5	82.63 10	93.80 9	50.83 61	93.70 28	90.11 2	86.44 33	93.01 21

baseline		76.86 52	76.24 54	78.71 62	80.47 193	54.20 98	83.90 173	84.88 129	71.38 19	71.51 86	89.15 115	50.51 62	90.55 97	75.71 67	78.65 101	91.39 66

MVS_Test		75.85 68	74.93 73	78.62 66	84.08 92	55.20 67	83.99 170	85.17 120	68.07 41	73.38 61	82.76 212	50.44 63	89.00 142	65.90 137	80.61 78	91.64 56

FC-MVSNet-test		67.49 219	67.91 178	66.21 315	76.06 269	33.06 374	80.82 256	87.18 71	64.44 95	54.81 288	82.87 209	50.40 64	82.60 292	48.05 281	66.55 217	82.98 256

nrg030		72.27 128	71.56 120	74.42 176	75.93 273	50.60 177	86.97 84	83.21 169	62.75 130	67.15 125	84.38 187	50.07 65	86.66 227	71.19 100	62.37 258	85.99 199

fmvsm_l_conf0.5_n		75.95 65	76.16 55	75.31 154	76.01 272	48.44 241	84.98 138	71.08 344	63.50 117	81.70 17	93.52 15	50.00 66	87.18 211	87.80 5	76.87 119	90.32 94

cl22		68.85 189	67.69 185	72.35 229	78.07 237	49.98 196	82.45 217	78.48 264	62.50 136	58.46 244	77.95 269	49.99 67	85.17 265	62.55 161	58.72 279	81.90 267

fmvsm_l_conf0.5_n_a		75.88 67	76.07 56	75.31 154	76.08 268	48.34 244	85.24 125	70.62 347	63.13 125	81.45 18	93.62 14	49.98 68	87.40 207	87.76 6	76.77 120	90.20 99

tpmrst		71.04 150	69.77 152	74.86 169	83.19 114	55.86 50	75.64 298	78.73 258	67.88 44	64.99 153	73.73 319	49.96 69	79.56 325	65.92 136	67.85 207	89.14 128

CANet		80.90 11	81.17 12	80.09 37	87.62 41	54.21 96	91.60 14	86.47 86	73.13 8	79.89 25	93.10 25	49.88 70	92.98 33	84.09 17	84.75 50	93.08 19

ET-MVSNet_ETH3D		75.23 80	74.08 84	78.67 64	84.52 83	55.59 51	88.92 44	89.21 28	68.06 42	53.13 305	90.22 91	49.71 71	87.62 201	72.12 97	70.82 184	92.82 25

c3_l		67.97 207	66.66 205	71.91 246	76.20 267	49.31 214	82.13 223	78.00 272	61.99 143	57.64 257	76.94 286	49.41 72	84.93 270	60.62 179	57.01 301	81.49 273

Vis-MVSNet (Re-imp)		65.52 252	65.63 229	65.17 323	77.49 246	30.54 381	75.49 302	77.73 276	59.34 192	52.26 312	86.69 163	49.38 73	80.53 312	37.07 328	75.28 140	84.42 225

EPNet		78.36 30	78.49 25	77.97 82	85.49 65	52.04 149	89.36 39	84.07 151	73.22 7	77.03 38	91.72 54	49.32 74	90.17 109	73.46 90	82.77 60	91.69 55
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
testing3		59.97 289	60.19 279	59.32 352	77.60 243	30.01 387	81.75 233	81.79 193	53.54 284	50.34 323	79.94 251	48.99 75	76.91 345	17.19 402	50.59 342	71.03 375

tpm		68.36 200	67.48 192	70.97 261	79.93 201	51.34 167	76.58 295	78.75 257	67.73 47	63.54 179	74.86 309	48.33 76	72.36 369	53.93 240	63.71 239	89.21 125

APDe-MVS		78.44 27	78.20 27	79.19 45	88.56 26	54.55 89	89.76 33	87.77 62	55.91 260	78.56 30	92.49 37	48.20 77	92.65 42	79.49 39	83.04 59	90.39 91
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
MG-MVS		78.42 28	76.99 45	82.73 2	93.17 1	64.46 1	89.93 29	88.51 50	64.83 92	73.52 59	88.09 137	48.07 78	92.19 54	62.24 164	84.53 52	91.53 62

DeepC-MVS	67.15 4	76.90 51	76.27 53	78.80 59	80.70 187	55.02 73	86.39 94	86.71 80	66.96 58	67.91 120	89.97 99	48.03 79	91.41 71	75.60 69	84.14 54	89.96 107
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
MGCFI-Net		74.07 93	74.64 78	72.34 230	82.90 126	43.33 321	80.04 269	79.96 227	65.61 79	74.93 45	91.85 51	48.01 80	80.86 305	71.41 99	77.10 114	92.84 24

test_prior2							89.04 43		61.88 146	73.55 58	91.46 63	48.01 80		74.73 77	85.46 42

myMVS_eth3d		63.52 263	63.56 254	63.40 332	81.73 153	34.28 366	80.97 252	81.02 206	60.93 166	55.06 285	82.64 217	48.00 82	80.81 306	23.42 387	58.32 283	75.10 349

SF-MVS		77.64 41	77.42 39	78.32 76	83.75 100	52.47 140	86.63 92	87.80 59	58.78 209	74.63 48	92.38 38	47.75 83	91.35 72	78.18 54	86.85 27	91.15 75

test2506		72.91 114	72.43 104	74.32 180	80.12 198	44.18 311	83.19 196	84.77 133	64.02 103	65.97 138	87.43 152	47.67 84	88.72 154	59.08 190	79.66 94	90.08 103

1112_ss		70.05 166	69.37 158	72.10 234	80.77 186	42.78 327	85.12 133	76.75 293	59.69 184	61.19 202	92.12 42	47.48 85	83.84 280	53.04 246	68.21 202	89.66 112

Effi-MVS+		75.24 79	73.61 88	80.16 33	81.92 148	57.42 21	85.21 127	76.71 296	60.68 172	73.32 62	89.34 110	47.30 86	91.63 65	68.28 120	79.72 93	91.42 65

UniMVSNet (Re)		67.71 213	66.80 201	70.45 267	74.44 291	42.93 325	82.42 218	84.90 128	63.69 112	59.63 217	80.99 243	47.18 87	85.23 264	51.17 261	56.75 302	83.19 251

test12				79.24 44	86.89 46	56.08 45		85.16 121		72.27 78		47.15 88	91.10 82		85.93 37	90.54 89

PVSNet_Blended_VisFu		73.40 108	72.44 103	76.30 120	81.32 173	54.70 83	85.81 105	78.82 254	63.70 111	64.53 160	85.38 178	47.11 89	87.38 208	67.75 123	77.55 110	86.81 186

test_fmvsm_n_1920		75.56 74	75.54 62	75.61 141	74.60 290	49.51 210	81.82 231	74.08 318	66.52 64	80.40 22	93.46 17	46.95 90	89.72 120	86.69 7	75.30 139	87.61 167

NCCC		79.57 20	79.23 20	80.59 24	89.50 15	56.99 26	91.38 16	88.17 54	67.71 48	73.81 56	92.75 32	46.88 91	93.28 30	78.79 47	84.07 55	91.50 64

9.14			78.19 28		85.67 61		88.32 51	88.84 38	59.89 180	74.58 50	92.62 35	46.80 92	92.66 41	81.40 35	85.62 41

VNet		77.99 37	77.92 31	78.19 78	87.43 42	50.12 193	90.93 22	91.41 8	67.48 52	75.12 43	90.15 95	46.77 93	91.00 84	73.52 89	78.46 103	93.44 9

PVSNet_BlendedMVS		73.42 107	73.30 91	73.76 198	85.91 56	51.83 155	86.18 99	84.24 148	65.40 84	69.09 111	80.86 245	46.70 94	88.13 179	75.43 70	65.92 224	81.33 281

PVSNet_Blended		76.53 56	76.54 49	76.50 118	85.91 56	51.83 155	88.89 45	84.24 148	67.82 46	69.09 111	89.33 112	46.70 94	88.13 179	75.43 70	81.48 73	89.55 115

SMA-MVS		79.10 23	78.76 24	80.12 35	84.42 84	55.87 49	87.58 69	86.76 79	61.48 154	80.26 23	93.10 25	46.53 96	92.41 48	79.97 38	88.77 11	92.08 41
Yufeng Yin; Xiaoyan Liu; Zichao Zhang: SMA-MVS: Segmentation-Guided Multi-Scale Anchor Deformation Patch Multi-View Stereo. IEEE Transactions on Circuits and Systems for Video Technology
test_fmvsmconf_n		74.41 88	74.05 85	75.49 148	74.16 296	48.38 242	82.66 207	72.57 331	67.05 57	75.11 44	92.88 31	46.35 97	87.81 188	83.93 18	71.71 175	90.28 95

tpm cat1		66.28 245	62.78 255	76.77 117	81.40 170	57.14 24	70.03 340	77.19 285	53.00 289	58.76 238	70.73 349	46.17 98	86.73 225	43.27 308	64.46 233	86.44 191

cl____		67.43 221	65.93 222	71.95 243	76.33 262	48.02 257	82.58 209	79.12 249	61.30 157	56.72 271	76.92 287	46.12 99	86.44 235	57.98 206	56.31 305	81.38 280

DIV-MVS_self_test		67.43 221	65.93 222	71.94 244	76.33 262	48.01 258	82.57 210	79.11 250	61.31 156	56.73 270	76.92 287	46.09 100	86.43 236	57.98 206	56.31 305	81.39 279

IS-MVSNet		68.80 193	67.55 189	72.54 223	78.50 231	43.43 318	81.03 250	79.35 245	59.12 202	57.27 266	86.71 162	46.05 101	87.70 196	44.32 304	75.60 136	86.49 190

diffmvs		75.11 83	74.65 77	76.46 119	78.52 230	53.35 117	83.28 194	79.94 228	70.51 24	71.64 84	88.72 121	46.02 102	86.08 248	77.52 58	75.75 135	89.96 107
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
EI-MVSNet		69.70 177	68.70 166	72.68 220	75.00 284	48.90 225	79.54 273	87.16 72	61.05 162	63.88 172	83.74 196	45.87 103	90.44 98	57.42 217	64.68 232	78.70 309

IterMVS-LS		66.63 240	65.36 237	70.42 268	75.10 282	48.90 225	81.45 246	76.69 297	61.05 162	55.71 281	77.10 284	45.86 104	83.65 284	57.44 216	57.88 295	78.70 309
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
EIA-MVS		75.92 66	75.18 69	78.13 79	85.14 72	51.60 160	87.17 80	85.32 112	64.69 93	68.56 115	90.53 80	45.79 105	91.58 67	67.21 126	82.18 66	91.20 73

MVS		76.91 49	75.48 63	81.23 19	84.56 82	55.21 65	80.23 266	91.64 4	58.65 211	65.37 146	91.48 62	45.72 106	95.05 16	72.11 98	89.52 10	93.44 9

PAPM_NR		71.80 136	69.98 150	77.26 100	81.54 165	53.34 118	78.60 283	85.25 117	53.46 285	60.53 208	88.66 123	45.69 107	89.24 132	56.49 223	79.62 96	89.19 126

CS-MVS		76.77 53	76.70 48	76.99 108	83.55 102	48.75 230	88.60 48	85.18 119	66.38 66	72.47 75	91.62 58	45.53 108	90.99 86	74.48 79	82.51 62	91.23 72

DeepC-MVS_fast	67.50 3	78.00 36	77.63 35	79.13 49	88.52 27	55.12 69	89.95 28	85.98 97	68.31 36	71.33 89	92.75 32	45.52 109	90.37 100	71.15 101	85.14 46	91.91 49
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
fmvsm_s_conf0.5_n		74.48 86	74.12 83	75.56 143	76.96 256	47.85 263	85.32 123	69.80 354	64.16 101	78.74 28	93.48 16	45.51 110	89.29 131	86.48 8	66.62 215	89.55 115

fmvsm_s_conf0.5_n_a		73.68 104	73.15 93	75.29 157	75.45 279	48.05 256	83.88 174	68.84 359	63.43 119	78.60 29	93.37 20	45.32 111	88.92 149	85.39 11	64.04 235	88.89 133

Test_1112_low_res		67.18 228	66.23 214	70.02 277	78.75 223	41.02 343	83.43 187	73.69 323	57.29 238	58.45 245	82.39 224	45.30 112	80.88 304	50.50 263	66.26 223	88.16 152

ETV-MVS		77.17 46	76.74 47	78.48 70	81.80 151	54.55 89	86.13 100	85.33 111	68.20 38	73.10 64	90.52 81	45.23 113	90.66 93	79.37 40	80.95 74	90.22 97

SPE-MVS-test		77.20 45	77.25 41	77.05 103	84.60 81	49.04 220	89.42 36	85.83 100	65.90 77	72.85 68	91.98 50	45.10 114	91.27 74	75.02 76	84.56 51	90.84 82

NR-MVSNet		67.25 226	65.99 220	71.04 260	73.27 305	43.91 312	85.32 123	84.75 134	66.05 75	53.65 303	82.11 232	45.05 115	85.97 252	47.55 283	56.18 308	83.24 249

UWE-MVS		72.17 129	72.15 111	72.21 232	82.26 142	44.29 308	86.83 89	89.58 23	65.58 80	65.82 141	85.06 181	45.02 116	84.35 276	54.07 238	75.18 141	87.99 159

train_agg		76.91 49	76.40 51	78.45 72	85.68 59	55.42 56	87.59 67	84.00 152	57.84 226	72.99 65	90.98 67	44.99 117	88.58 160	78.19 52	85.32 44	91.34 70

test_8					85.72 58	55.31 61	87.60 66	83.88 155	57.84 226	72.84 69	90.99 66	44.99 117	88.34 171

segment_acmp												44.97 119

test_fmvsmconf0.1_n		73.69 103	73.15 93	75.34 152	70.71 334	48.26 247	82.15 221	71.83 336	66.75 60	74.47 52	92.59 36	44.89 120	87.78 193	83.59 19	71.35 179	89.97 106

TEST9					85.68 59	55.42 56	87.59 67	84.00 152	57.72 228	72.99 65	90.98 67	44.87 121	88.58 160

eth_miper_zixun_eth		66.98 235	65.28 238	72.06 236	75.61 277	50.40 183	81.00 251	76.97 292	62.00 142	56.99 268	76.97 285	44.84 122	85.58 256	58.75 194	54.42 324	80.21 297

MVSFormer		73.53 106	72.19 110	77.57 91	83.02 120	55.24 63	81.63 237	81.44 199	50.28 307	76.67 39	90.91 72	44.82 123	86.11 243	60.83 176	80.09 86	91.36 68

lupinMVS		78.38 29	78.11 29	79.19 45	83.02 120	55.24 63	91.57 15	84.82 130	69.12 34	76.67 39	92.02 46	44.82 123	90.23 107	80.83 36	80.09 86	92.08 41

WR-MVS		67.58 216	66.76 202	70.04 276	75.92 274	45.06 302	86.23 98	85.28 115	64.31 98	58.50 242	81.00 242	44.80 125	82.00 297	49.21 273	55.57 316	83.06 254

fmvsm_s_conf0.1_n		73.80 99	73.26 92	75.43 149	73.28 304	47.80 264	84.57 155	69.43 356	63.34 120	78.40 31	93.29 22	44.73 126	89.22 134	85.99 9	66.28 222	89.26 122

ZD-MVS					89.55 14	53.46 110		84.38 142	57.02 243	73.97 55	91.03 65	44.57 127	91.17 79	75.41 73	81.78 71

Fast-Effi-MVS+		72.73 117	71.15 129	77.48 93	82.75 132	54.76 79	86.77 90	80.64 214	63.05 126	65.93 139	84.01 191	44.42 128	89.03 140	56.45 226	76.36 126	88.64 140

fmvsm_s_conf0.1_n_a		72.82 116	72.05 115	75.12 163	70.95 333	47.97 259	82.72 206	68.43 361	62.52 135	78.17 32	93.08 28	44.21 129	88.86 150	84.82 13	63.54 241	88.54 144

PCF-MVS	61.03 10	70.10 164	68.40 171	75.22 162	77.15 254	51.99 150	79.30 278	82.12 185	56.47 256	61.88 196	86.48 168	43.98 130	87.24 210	55.37 231	72.79 166	86.43 192
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
CDS-MVSNet		70.48 160	69.43 156	73.64 202	77.56 245	48.83 227	83.51 184	77.45 281	63.27 122	62.33 190	85.54 177	43.85 131	83.29 290	57.38 218	74.00 154	88.79 137
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
EI-MVSNet-Vis-set		73.19 111	72.60 100	74.99 167	82.56 138	49.80 201	82.55 212	89.00 31	66.17 70	65.89 140	88.98 116	43.83 132	92.29 51	65.38 147	69.01 198	82.87 258

APD-MVS		76.15 61	75.68 58	77.54 92	88.52 27	53.44 113	87.26 78	85.03 125	53.79 282	74.91 46	91.68 56	43.80 133	90.31 103	74.36 80	81.82 69	88.87 134
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
MVS_111021_HR		76.39 58	75.38 66	79.42 42	85.33 69	56.47 38	88.15 53	84.97 126	65.15 90	66.06 137	89.88 100	43.79 134	92.16 55	75.03 75	80.03 89	89.64 113

thres100view900		66.87 237	65.42 236	71.24 255	83.29 111	43.15 323	81.67 236	87.78 60	59.04 203	55.92 280	82.18 231	43.73 135	87.80 190	28.80 365	66.36 219	82.78 260

thres600view7		66.46 243	65.12 240	70.47 266	83.41 105	43.80 314	82.15 221	87.78 60	59.37 191	56.02 279	82.21 230	43.73 135	86.90 221	26.51 377	64.94 228	80.71 291

v148		68.24 205	66.35 210	73.88 193	71.76 322	51.47 164	84.23 162	81.90 192	63.69 112	58.94 231	76.44 294	43.72 137	87.78 193	60.63 178	55.86 313	82.39 262

SD-MVS		76.18 60	74.85 74	80.18 32	85.39 67	56.90 28	85.75 109	82.45 182	56.79 249	74.48 51	91.81 52	43.72 137	90.75 91	74.61 78	78.65 101	92.91 22
Zhenlong Yuan, Jiakai Cao, Zhaoxin Li, Hao Jiang and Zhaoqi Wang: SD-MVS: Segmentation-driven Deformation Multi-View Stereo with Spherical Refinement and EM optimization. AAAI2024
XXY-MVS		70.18 162	69.28 162	72.89 217	77.64 242	42.88 326	85.06 134	87.50 69	62.58 133	62.66 188	82.34 229	43.64 139	89.83 116	58.42 199	63.70 240	85.96 201

tfpn200view9		67.57 217	66.13 216	71.89 247	84.05 93	45.07 299	83.40 189	87.71 65	60.79 169	57.79 253	82.76 212	43.53 140	87.80 190	28.80 365	66.36 219	82.78 260

thres400		67.40 224	66.13 216	71.19 257	84.05 93	45.07 299	83.40 189	87.71 65	60.79 169	57.79 253	82.76 212	43.53 140	87.80 190	28.80 365	66.36 219	80.71 291

PAPR		75.20 81	74.13 82	78.41 73	88.31 32	55.10 71	84.31 160	85.66 102	63.76 110	67.55 122	90.73 77	43.48 142	89.40 127	66.36 132	77.03 115	90.73 85

kuosan		50.20 347	50.09 337	50.52 371	73.09 307	29.09 393	65.25 356	74.89 312	48.27 322	41.34 365	60.85 382	43.45 143	67.48 379	18.59 400	25.07 402	55.01 396

MP-MVS		74.99 84	74.33 81	76.95 110	82.89 127	53.05 128	85.63 114	83.50 163	57.86 225	67.25 124	90.24 89	43.38 144	88.85 153	76.03 64	82.23 65	88.96 131
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
EI-MVSNet-UG-set		72.37 123	71.73 118	74.29 181	81.60 161	49.29 215	81.85 229	88.64 44	65.29 89	65.05 150	88.29 134	43.18 145	91.83 62	63.74 155	67.97 205	81.75 269

thres200		68.71 195	67.27 196	73.02 212	84.73 78	46.76 277	85.03 136	87.73 63	62.34 139	59.87 212	83.45 202	43.15 146	88.32 173	31.25 358	67.91 206	83.98 235

PHI-MVS		77.49 42	77.00 44	78.95 53	85.33 69	50.69 175	88.57 49	88.59 48	58.14 218	73.60 57	93.31 21	43.14 147	93.79 27	73.81 87	88.53 13	92.37 34

ab-mvs		70.65 157	69.11 163	75.29 157	80.87 182	46.23 288	73.48 316	85.24 118	59.99 179	66.65 128	80.94 244	43.13 148	88.69 155	63.58 156	68.07 203	90.95 80

CDPH-MVS		76.05 64	75.19 68	78.62 66	86.51 50	54.98 75	87.32 73	84.59 138	58.62 212	70.75 97	90.85 74	43.10 149	90.63 95	70.50 104	84.51 53	90.24 96

reproduce_monomvs		69.71 174	68.52 168	73.29 210	86.43 52	48.21 249	83.91 172	86.17 94	68.02 43	54.91 287	77.46 277	42.96 150	88.86 150	68.44 118	48.38 347	82.80 259

v8		67.25 226	64.99 242	74.04 187	72.89 311	53.31 120	82.37 219	80.11 224	61.54 152	54.29 296	76.02 303	42.89 151	88.41 167	58.43 197	56.36 303	80.39 295

EC-MVSNet		75.30 76	75.20 67	75.62 140	80.98 176	49.00 221	87.43 70	84.68 136	63.49 118	70.97 95	90.15 95	42.86 152	91.14 81	74.33 81	81.90 68	86.71 187

h-mvs33		73.95 95	72.89 98	77.15 102	80.17 197	50.37 186	84.68 150	83.33 164	68.08 39	71.97 80	88.65 126	42.50 153	91.15 80	78.82 45	57.78 297	89.91 109

hse-mvs2		71.44 143	70.68 133	73.73 200	76.34 261	47.44 269	79.45 276	79.47 240	68.08 39	71.97 80	86.01 172	42.50 153	86.93 220	78.82 45	53.46 334	86.83 185

SteuartSystems-ACMMP		77.08 47	76.33 52	79.34 43	80.98 176	55.31 61	89.76 33	86.91 76	62.94 128	71.65 83	91.56 60	42.33 155	92.56 45	77.14 61	83.69 57	90.15 101
Skip Steuart: Steuart Systems R&D Blog.
HyFIR lowres test		69.94 171	67.58 187	77.04 104	77.11 255	57.29 22	81.49 245	79.11 250	58.27 216	58.86 235	80.41 248	42.33 155	86.96 218	61.91 167	68.68 201	86.87 180

ZNCC-MVS		75.82 71	75.02 71	78.23 77	83.88 98	53.80 103	86.91 87	86.05 96	59.71 183	67.85 121	90.55 79	42.23 157	91.02 83	72.66 96	85.29 45	89.87 110

FMVSNet3		68.84 190	67.40 193	73.19 211	85.05 73	48.53 236	85.71 113	85.36 109	60.90 168	57.58 258	79.15 261	42.16 158	86.77 223	47.25 286	63.40 242	84.27 227

VPA-MVSNet		71.12 146	70.66 134	72.49 225	78.75 223	44.43 306	87.64 65	90.02 19	63.97 106	65.02 151	81.58 240	42.14 159	87.42 206	63.42 157	63.38 245	85.63 209

jason		77.01 48	76.45 50	78.69 63	79.69 203	54.74 80	90.56 24	83.99 154	68.26 37	74.10 54	90.91 72	42.14 159	89.99 112	79.30 41	79.12 97	91.36 68
jason: jason.
CLD-MVS		75.60 73	75.39 65	76.24 122	80.69 188	52.40 141	90.69 23	86.20 92	74.40 6	65.01 152	88.93 117	42.05 161	90.58 96	76.57 63	73.96 155	85.73 205
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
test_yl		75.85 68	74.83 75	78.91 54	88.08 37	51.94 151	91.30 17	89.28 26	57.91 223	71.19 91	89.20 113	42.03 162	92.77 38	69.41 110	75.07 146	92.01 46

DCV-MVSNet		75.85 68	74.83 75	78.91 54	88.08 37	51.94 151	91.30 17	89.28 26	57.91 223	71.19 91	89.20 113	42.03 162	92.77 38	69.41 110	75.07 146	92.01 46

TAMVS		69.51 181	68.16 176	73.56 205	76.30 264	48.71 232	82.57 210	77.17 286	62.10 141	61.32 201	84.23 189	41.90 164	83.46 287	54.80 235	73.09 163	88.50 146

TransMVSNet (Re)		62.82 271	60.76 273	69.02 285	73.98 298	41.61 337	86.36 95	79.30 248	56.90 244	52.53 308	76.44 294	41.85 165	87.60 202	38.83 321	40.61 374	77.86 322

VPNet		72.07 130	71.42 124	74.04 187	78.64 228	47.17 274	89.91 31	87.97 57	72.56 11	64.66 155	85.04 182	41.83 166	88.33 172	61.17 174	60.97 264	86.62 188

v2v482		69.55 180	67.64 186	75.26 161	72.32 318	53.83 102	84.93 142	81.94 188	65.37 86	60.80 205	79.25 259	41.62 167	88.98 145	63.03 159	59.51 272	82.98 256

API-MVS		74.17 92	72.07 114	80.49 25	90.02 11	58.55 9	87.30 75	84.27 145	57.51 234	65.77 143	87.77 146	41.61 168	95.97 11	51.71 256	82.63 61	86.94 178

GeoE		69.96 170	67.88 180	76.22 123	81.11 175	51.71 158	84.15 164	76.74 295	59.83 181	60.91 203	84.38 187	41.56 169	88.10 181	51.67 257	70.57 187	88.84 135

CHOSEN 1792x2688		76.24 59	74.03 86	82.88 1	83.09 117	62.84 2	85.73 111	85.39 108	69.79 28	64.87 154	83.49 201	41.52 170	93.69 29	70.55 103	81.82 69	92.12 40

LFMVS		78.52 25	77.14 43	82.67 3	89.58 13	58.90 8	91.27 19	88.05 56	63.22 123	74.63 48	90.83 75	41.38 171	94.40 20	75.42 72	79.90 91	94.72 2

MAR-MVS		76.76 54	75.60 60	80.21 31	90.87 7	54.68 85	89.14 42	89.11 29	62.95 127	70.54 103	92.33 39	41.05 172	94.95 17	57.90 210	86.55 32	91.00 79
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
dongtai		43.51 357	44.07 358	41.82 382	63.75 375	21.90 406	63.80 362	72.05 335	39.59 365	33.35 393	54.54 393	41.04 173	57.30 394	10.75 411	17.77 411	46.26 405

test_fmvsmvis_n_1920		71.29 144	70.38 141	74.00 189	71.04 332	48.79 229	79.19 279	64.62 370	62.75 130	66.73 126	91.99 48	40.94 174	88.35 170	83.00 21	73.18 160	84.85 221

GST-MVS		74.87 85	73.90 87	77.77 86	83.30 110	53.45 112	85.75 109	85.29 114	59.22 196	66.50 133	89.85 101	40.94 174	90.76 90	70.94 102	83.35 58	89.10 129

DU-MVS		66.84 238	65.74 227	70.16 272	73.27 305	42.59 329	81.50 243	82.92 176	63.53 116	58.51 240	82.11 232	40.75 176	84.64 274	53.11 244	55.96 311	83.24 249

Baseline_NR-MVSNet		65.49 253	64.27 249	69.13 284	74.37 294	41.65 336	83.39 191	78.85 252	59.56 186	59.62 218	76.88 289	40.75 176	87.44 205	49.99 265	55.05 318	78.28 318

miper_lstm_enhance		63.91 259	62.30 258	68.75 291	75.06 283	46.78 276	69.02 344	81.14 204	59.68 185	52.76 307	72.39 336	40.71 178	77.99 336	56.81 221	53.09 335	81.48 275

HFP-MVS		74.37 89	73.13 97	78.10 80	84.30 87	53.68 106	85.58 115	84.36 143	56.82 247	65.78 142	90.56 78	40.70 179	90.90 88	69.18 114	80.88 75	89.71 111

RRT-MVS		73.29 109	71.37 125	79.07 52	84.63 80	54.16 99	78.16 285	86.64 84	61.67 149	60.17 210	82.35 228	40.63 180	92.26 53	70.19 106	77.87 108	90.81 83

CL-MVSNet_self_test		62.98 269	61.14 270	68.50 297	65.86 362	42.96 324	84.37 157	82.98 174	60.98 164	53.95 299	72.70 332	40.43 181	83.71 283	41.10 315	47.93 350	78.83 308

ACMMP_NAP		76.43 57	75.66 59	78.73 61	81.92 148	54.67 86	84.06 168	85.35 110	61.10 161	72.99 65	91.50 61	40.25 182	91.00 84	76.84 62	86.98 25	90.51 90

v1144		68.81 192	66.82 200	74.80 170	72.34 317	53.46 110	84.68 150	81.77 195	64.25 99	60.28 209	77.91 270	40.23 183	88.95 146	60.37 185	59.52 271	81.97 265

WR-MVS_H		58.91 301	58.04 293	61.54 344	69.07 346	33.83 371	76.91 292	81.99 187	51.40 302	48.17 332	74.67 310	40.23 183	74.15 357	31.78 355	48.10 348	76.64 335

原ACMM1				76.13 128	84.89 77	54.59 88		85.26 116	51.98 296	66.70 127	87.07 158	40.15 185	89.70 121	51.23 260	85.06 48	84.10 229

MVP-Stereo		70.97 151	70.44 137	72.59 222	76.03 271	51.36 166	85.02 137	86.99 75	60.31 176	56.53 275	78.92 263	40.11 186	90.00 111	60.00 188	90.01 7	76.41 338
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
v10		66.61 241	64.20 250	73.83 196	72.59 314	53.37 116	81.88 228	79.91 230	61.11 160	54.09 298	75.60 305	40.06 187	88.26 177	56.47 224	56.10 309	79.86 301

test_fmvsmconf0.01_n		71.97 132	70.95 131	75.04 164	66.21 359	47.87 262	80.35 263	70.08 351	65.85 78	72.69 70	91.68 56	39.99 188	87.67 197	82.03 28	69.66 194	89.58 114

MP-MVS-pluss		75.54 75	75.03 70	77.04 104	81.37 171	52.65 137	84.34 159	84.46 141	61.16 158	69.14 110	91.76 53	39.98 189	88.99 144	78.19 52	84.89 49	89.48 119
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
TranMVSNet+NR-MVSNet		66.94 236	65.61 230	70.93 262	73.45 301	43.38 319	83.02 202	84.25 146	65.31 88	58.33 247	81.90 236	39.92 190	85.52 257	49.43 270	54.89 320	83.89 239

Patchmatch-test		53.33 335	48.17 345	68.81 289	73.31 302	42.38 333	42.98 400	58.23 380	32.53 384	38.79 377	70.77 347	39.66 191	73.51 363	25.18 380	52.06 339	90.55 87

Test By Simon												39.38 192

v144192		67.86 209	65.76 226	74.16 184	71.68 323	53.09 126	84.14 165	80.83 212	62.85 129	59.21 228	77.28 281	39.30 193	88.00 184	58.67 195	57.88 295	81.40 278

BH-w/o		70.02 167	68.51 169	74.56 172	82.77 131	50.39 184	86.60 93	78.14 270	59.77 182	59.65 216	85.57 176	39.27 194	87.30 209	49.86 267	74.94 149	85.99 199

dmvs_testset		57.65 311	58.21 292	55.97 363	74.62 289	9.82 424	63.75 363	63.34 374	67.23 54	48.89 330	83.68 200	39.12 195	76.14 350	23.43 386	59.80 270	81.96 266

CR-MVSNet		62.47 276	59.04 288	72.77 218	73.97 299	56.57 34	60.52 376	71.72 338	60.04 178	57.49 261	65.86 365	38.94 196	80.31 314	42.86 311	59.93 268	81.42 276

Patchmtry		56.56 317	52.95 324	67.42 303	72.53 315	50.59 178	59.05 380	71.72 338	37.86 372	46.92 343	65.86 365	38.94 196	80.06 318	36.94 330	46.72 360	71.60 371

sam_mvs1												38.86 198				88.13 155

UA-Net		67.32 225	66.23 214	70.59 265	78.85 221	41.23 342	73.60 314	75.45 308	61.54 152	66.61 130	84.53 186	38.73 199	86.57 232	42.48 314	74.24 153	83.98 235

cdsmvs_eth3d_5k		18.33 387	24.44 379	0.00 408	0.00 430	0.00 432	0.00 419	89.40 25	0.00 424	0.00 427	92.02 46	38.55 200	0.00 425	0.00 426	0.00 423	0.00 423

patchmatchnet-post											59.74 385	38.41 201	79.91 321

CHOSEN 280x420		57.53 313	56.38 305	60.97 348	74.01 297	48.10 254	46.30 396	54.31 386	48.18 324	50.88 321	77.43 279	38.37 202	59.16 392	54.83 233	63.14 250	75.66 342

V42		67.66 214	65.60 231	73.86 194	70.69 336	53.63 107	81.50 243	78.61 261	63.85 108	59.49 222	77.49 276	37.98 203	87.65 198	62.33 162	58.43 282	80.29 296

tpmvs		62.45 277	59.42 284	71.53 252	83.93 95	54.32 92	70.03 340	77.61 278	51.91 297	53.48 304	68.29 359	37.91 204	86.66 227	33.36 348	58.27 285	73.62 360

PatchmatchNet		67.07 233	63.63 253	77.40 95	83.10 115	58.03 11	72.11 331	77.77 275	58.85 207	59.37 223	70.83 346	37.84 205	84.93 270	42.96 310	69.83 193	89.26 122
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
pcd_1.5k_mvsjas		3.15 394	4.20 397	0.00 408	0.00 430	0.00 432	0.00 419	0.00 430	0.00 424	0.00 427	0.00 426	37.77 206	0.00 425	0.00 426	0.00 423	0.00 423

PS-MVSNAJss		68.78 194	67.17 197	73.62 204	73.01 308	48.33 246	84.95 141	84.81 131	59.30 195	58.91 234	79.84 254	37.77 206	88.86 150	62.83 160	63.12 251	83.67 243

PS-MVSNAJ		80.06 17	79.52 18	81.68 14	85.58 63	60.97 3	91.69 12	87.02 74	70.62 22	80.75 21	93.22 24	37.77 206	92.50 46	82.75 23	86.25 35	91.57 60

pm-mvs1		64.12 258	62.56 256	68.78 290	71.68 323	38.87 351	82.89 204	81.57 196	55.54 266	53.89 300	77.82 272	37.73 209	86.74 224	48.46 279	53.49 332	80.72 290

RPMNet		59.29 293	54.25 317	74.42 176	73.97 299	56.57 34	60.52 376	76.98 289	35.72 378	57.49 261	58.87 388	37.73 209	85.26 263	27.01 376	59.93 268	81.42 276

SDMVSNet		71.89 133	70.62 135	75.70 139	81.70 155	51.61 159	73.89 312	88.72 42	66.58 61	61.64 198	82.38 225	37.63 211	89.48 125	77.44 59	65.60 225	86.01 197

xiu_mvs_v2_base		79.86 18	79.31 19	81.53 15	85.03 75	60.73 4	91.65 13	86.86 77	70.30 26	80.77 20	93.07 29	37.63 211	92.28 52	82.73 24	85.71 39	91.57 60

Patchmatch-RL test		58.72 303	54.32 316	71.92 245	63.91 374	44.25 309	61.73 372	55.19 384	57.38 237	49.31 328	54.24 394	37.60 213	80.89 303	62.19 165	47.28 355	90.63 86

HPM-MVS		72.60 119	71.50 121	75.89 134	82.02 144	51.42 165	80.70 258	83.05 172	56.12 259	64.03 168	89.53 106	37.55 214	88.37 168	70.48 105	80.04 88	87.88 160
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
test_post											16.22 418	37.52 215	84.72 272

PatchT		56.60 316	52.97 323	67.48 302	72.94 310	46.16 289	57.30 384	73.78 322	38.77 368	54.37 294	57.26 391	37.52 215	78.06 333	32.02 353	52.79 336	78.23 320

v1192		67.96 208	65.74 227	74.63 171	71.79 321	53.43 115	84.06 168	80.99 210	63.19 124	59.56 219	77.46 277	37.50 217	88.65 156	58.20 203	58.93 278	81.79 268

HQP2-MVS												37.35 218

HQP-MVS		72.34 124	71.44 123	75.03 165	79.02 217	51.56 161	88.00 55	83.68 158	65.45 81	64.48 161	85.13 179	37.35 218	88.62 157	66.70 128	73.12 161	84.91 219

region2R		73.75 101	72.55 101	77.33 96	83.90 97	52.98 130	85.54 119	84.09 150	56.83 246	65.10 149	90.45 82	37.34 220	90.24 106	68.89 116	80.83 77	88.77 138

TESTMET0.1,1		72.86 115	72.33 105	74.46 174	81.98 145	50.77 173	85.13 130	85.47 104	66.09 72	67.30 123	83.69 198	37.27 221	83.57 285	65.06 150	78.97 100	89.05 130

mvsmamba		69.38 182	67.52 191	74.95 168	82.86 128	52.22 147	67.36 352	76.75 293	61.14 159	49.43 326	82.04 234	37.26 222	84.14 277	73.93 85	76.91 117	88.50 146

ACMMPR		73.76 100	72.61 99	77.24 101	83.92 96	52.96 131	85.58 115	84.29 144	56.82 247	65.12 148	90.45 82	37.24 223	90.18 108	69.18 114	80.84 76	88.58 142

MonoMVSNet		66.80 239	64.41 247	73.96 190	76.21 266	48.07 255	76.56 296	78.26 268	64.34 97	54.32 295	74.02 316	37.21 224	86.36 238	64.85 151	53.96 327	87.45 171

sss		70.49 159	70.13 148	71.58 251	81.59 162	39.02 350	80.78 257	84.71 135	59.34 192	66.61 130	88.09 137	37.17 225	85.52 257	61.82 169	71.02 182	90.20 99

reproduce-ours		71.77 138	70.43 138	75.78 136	81.96 146	49.54 208	82.54 213	81.01 208	48.77 319	69.21 108	90.96 69	37.13 226	89.40 127	66.28 133	76.01 129	88.39 149

our_new_method		71.77 138	70.43 138	75.78 136	81.96 146	49.54 208	82.54 213	81.01 208	48.77 319	69.21 108	90.96 69	37.13 226	89.40 127	66.28 133	76.01 129	88.39 149

EPNet_dtu		66.25 246	66.71 203	64.87 325	78.66 227	34.12 369	82.80 205	75.51 306	61.75 147	64.47 164	86.90 159	37.06 228	72.46 368	43.65 307	69.63 196	88.02 158
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
mamv4		42.60 359	44.05 359	38.26 387	59.21 386	38.00 356	44.14 399	39.03 403	25.03 397	40.61 371	68.39 358	37.01 229	24.28 421	46.62 291	36.43 380	52.50 399

v1921920		67.45 220	65.23 239	74.10 186	71.51 326	52.90 132	83.75 178	80.44 218	62.48 137	59.12 229	77.13 282	36.98 230	87.90 186	57.53 215	58.14 289	81.49 273

旧先验1					81.57 164	47.48 267		71.83 336			88.66 123	36.94 231			78.34 105	88.67 139

test-LLR		69.65 178	69.01 164	71.60 249	78.67 225	48.17 250	85.13 130	79.72 233	59.18 199	63.13 181	82.58 219	36.91 232	80.24 315	60.56 180	75.17 142	86.39 193

test0.0.03 1		62.54 273	62.44 257	62.86 337	72.28 320	29.51 390	82.93 203	78.78 255	59.18 199	53.07 306	82.41 223	36.91 232	77.39 342	37.45 324	58.96 277	81.66 271

MDTV_nov1_ep13_2view						43.62 315	71.13 336		54.95 273	59.29 227		36.76 234		46.33 294		87.32 174

KD-MVS_2432*1600		59.04 299	56.44 303	66.86 309	79.07 214	45.87 291	72.13 329	80.42 219	55.03 271	48.15 333	71.01 344	36.73 235	78.05 334	35.21 339	30.18 396	76.67 332

miper_refine_blended		59.04 299	56.44 303	66.86 309	79.07 214	45.87 291	72.13 329	80.42 219	55.03 271	48.15 333	71.01 344	36.73 235	78.05 334	35.21 339	30.18 396	76.67 332

GBi-Net		67.09 231	65.47 233	71.96 240	82.71 133	46.36 282	83.52 180	83.31 165	58.55 213	57.58 258	76.23 298	36.72 237	86.20 239	47.25 286	63.40 242	83.32 246

test1		67.09 231	65.47 233	71.96 240	82.71 133	46.36 282	83.52 180	83.31 165	58.55 213	57.58 258	76.23 298	36.72 237	86.20 239	47.25 286	63.40 242	83.32 246

FMVSNet2		67.57 217	65.79 225	72.90 215	82.71 133	47.97 259	85.15 129	84.93 127	58.55 213	56.71 272	78.26 268	36.72 237	86.67 226	46.15 295	62.94 253	84.07 230

AUN-MVS		68.20 206	66.35 210	73.76 198	76.37 260	47.45 268	79.52 275	79.52 238	60.98 164	62.34 189	86.02 170	36.59 240	86.94 219	62.32 163	53.47 333	86.89 179

reproduce_model		71.07 148	69.67 154	75.28 159	81.51 168	48.82 228	81.73 234	80.57 217	47.81 325	68.26 117	90.78 76	36.49 241	88.60 159	65.12 149	74.76 150	88.42 148

BH-untuned		68.28 203	66.40 209	73.91 192	81.62 160	50.01 195	85.56 117	77.39 282	57.63 231	57.47 263	83.69 198	36.36 242	87.08 214	44.81 300	73.08 164	84.65 222

EPMVS		68.45 199	65.44 235	77.47 94	84.91 76	56.17 43	71.89 333	81.91 191	61.72 148	60.85 204	72.49 333	36.21 243	87.06 215	47.32 285	71.62 176	89.17 127

MSLP-MVS++		74.21 91	72.25 108	80.11 36	81.45 169	56.47 38	86.32 96	79.65 236	58.19 217	66.36 134	92.29 40	36.11 244	90.66 93	67.39 124	82.49 63	93.18 17

FA-MVS(test-final)		69.00 188	66.60 207	76.19 126	83.48 104	47.96 261	74.73 306	82.07 186	57.27 239	62.18 192	78.47 267	36.09 245	92.89 34	53.76 242	71.32 180	87.73 164

MTAPA		72.73 117	71.22 127	77.27 99	81.54 165	53.57 108	67.06 354	81.31 201	59.41 190	68.39 116	90.96 69	36.07 246	89.01 141	73.80 88	82.45 64	89.23 124

HQP_MVS		70.96 152	69.91 151	74.12 185	77.95 238	49.57 203	85.76 107	82.59 179	63.60 114	62.15 193	83.28 206	36.04 247	88.30 174	65.46 142	72.34 170	84.49 223

plane_prior6					78.42 233	49.39 213						36.04 247

sam_mvs												35.99 249

PGM-MVS		72.60 119	71.20 128	76.80 115	82.95 123	52.82 134	83.07 200	82.14 184	56.51 255	63.18 180	89.81 102	35.68 250	89.76 119	67.30 125	80.19 85	87.83 161

XVS		72.92 113	71.62 119	76.81 113	83.41 105	52.48 138	84.88 143	83.20 170	58.03 219	63.91 170	89.63 105	35.50 251	89.78 117	65.50 139	80.50 80	88.16 152

X-MVStestdata		65.85 251	62.20 259	76.81 113	83.41 105	52.48 138	84.88 143	83.20 170	58.03 219	63.91 170	4.82 422	35.50 251	89.78 117	65.50 139	80.50 80	88.16 152

v1240		66.99 234	64.68 244	73.93 191	71.38 329	52.66 136	83.39 191	79.98 226	61.97 144	58.44 246	77.11 283	35.25 253	87.81 188	56.46 225	58.15 287	81.33 281

test1111		71.06 149	70.42 140	72.97 214	79.48 206	41.49 339	84.82 146	82.74 178	64.20 100	62.98 183	87.43 152	35.20 254	87.92 185	58.54 196	78.42 104	89.49 118

dp		64.41 255	61.58 263	72.90 215	82.40 139	54.09 100	72.53 323	76.59 299	60.39 175	55.68 282	70.39 350	35.18 255	76.90 347	39.34 320	61.71 261	87.73 164

Syy-MVS		61.51 282	61.35 267	62.00 340	81.73 153	30.09 385	80.97 252	81.02 206	60.93 166	55.06 285	82.64 217	35.09 256	80.81 306	16.40 404	58.32 283	75.10 349

ECVR-MVS		71.81 135	71.00 130	74.26 182	80.12 198	43.49 316	84.69 149	82.16 183	64.02 103	64.64 156	87.43 152	35.04 257	89.21 135	61.24 173	79.66 94	90.08 103

CP-MVS		72.59 121	71.46 122	76.00 133	82.93 125	52.32 144	86.93 86	82.48 181	55.15 269	63.65 175	90.44 85	35.03 258	88.53 164	68.69 117	77.83 109	87.15 176

CP-MVSNet		58.54 307	57.57 296	61.46 345	68.50 350	33.96 370	76.90 293	78.60 262	51.67 301	47.83 336	76.60 293	34.99 259	72.79 366	35.45 336	47.58 352	77.64 326

dmvs_re		67.61 215	66.00 219	72.42 227	81.86 150	43.45 317	64.67 360	80.00 225	69.56 32	60.07 211	85.00 183	34.71 260	87.63 199	51.48 258	66.68 213	86.17 196

MDTV_nov1_ep13			61.56 264		81.68 157	55.12 69	72.41 325	78.18 269	59.19 197	58.85 236	69.29 355	34.69 261	86.16 242	36.76 332	62.96 252

WB-MVSnew		69.36 183	68.24 174	72.72 219	79.26 211	49.40 212	85.72 112	88.85 37	61.33 155	64.59 159	82.38 225	34.57 262	87.53 204	46.82 290	70.63 185	81.22 285

3Dnovator	64.70 6	74.46 87	72.48 102	80.41 29	82.84 130	55.40 59	83.08 199	88.61 47	67.61 51	59.85 213	88.66 123	34.57 262	93.97 24	58.42 199	88.70 12	91.85 52

Vis-MVSNet		70.61 158	69.34 159	74.42 176	80.95 181	48.49 238	86.03 103	77.51 280	58.74 210	65.55 145	87.78 145	34.37 264	85.95 253	52.53 254	80.61 78	88.80 136
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
test_post1							70.84 337				14.72 421	34.33 265	83.86 279	48.80 275

OPM-MVS		70.75 156	69.58 155	74.26 182	75.55 278	51.34 167	86.05 102	83.29 168	61.94 145	62.95 184	85.77 173	34.15 266	88.44 166	65.44 145	71.07 181	82.99 255
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
DP-MVS Recon		71.99 131	70.31 143	77.01 106	90.65 8	53.44 113	89.37 37	82.97 175	56.33 257	63.56 178	89.47 107	34.02 267	92.15 57	54.05 239	72.41 169	85.43 212

PEN-MVS		58.35 308	57.15 298	61.94 341	67.55 357	34.39 365	77.01 291	78.35 267	51.87 298	47.72 337	76.73 291	33.91 268	73.75 361	34.03 346	47.17 356	77.68 324

QAPM		71.88 134	69.33 160	79.52 40	82.20 143	54.30 93	86.30 97	88.77 40	56.61 253	59.72 215	87.48 150	33.90 269	95.36 13	47.48 284	81.49 72	88.90 132

新几何1				73.30 209	83.10 115	53.48 109		71.43 342	45.55 341	66.14 135	87.17 156	33.88 270	80.54 311	48.50 278	80.33 84	85.88 204

1314		71.11 147	69.41 157	76.22 123	79.32 209	50.49 180	80.23 266	85.14 123	59.44 189	58.93 232	88.89 119	33.83 271	89.60 124	61.49 171	77.42 113	88.57 143

SR-MVS		70.92 153	69.73 153	74.50 173	83.38 109	50.48 181	84.27 161	79.35 245	48.96 317	66.57 132	90.45 82	33.65 272	87.11 213	66.42 130	74.56 152	85.91 202

mPP-MVS		71.79 137	70.38 141	76.04 131	82.65 136	52.06 148	84.45 156	81.78 194	55.59 264	62.05 195	89.68 104	33.48 273	88.28 176	65.45 144	78.24 106	87.77 163

OMC-MVS		65.97 250	65.06 241	68.71 292	72.97 309	42.58 331	78.61 282	75.35 309	54.72 275	59.31 225	86.25 169	33.30 274	77.88 338	57.99 205	67.05 211	85.66 207

BH-RMVSNet		70.08 165	68.01 177	76.27 121	84.21 91	51.22 171	87.29 76	79.33 247	58.96 206	63.63 176	86.77 161	33.29 275	90.30 105	44.63 302	73.96 155	87.30 175

JIA-IIPM		52.33 340	47.77 348	66.03 316	71.20 330	46.92 275	40.00 405	76.48 300	37.10 373	46.73 344	37.02 405	32.96 276	77.88 338	35.97 334	52.45 338	73.29 363

PS-CasMVS		58.12 309	57.03 300	61.37 346	68.24 354	33.80 372	76.73 294	78.01 271	51.20 303	47.54 340	76.20 301	32.85 277	72.76 367	35.17 341	47.37 354	77.55 327

DTE-MVSNet		57.03 314	55.73 309	60.95 349	65.94 361	32.57 377	75.71 297	77.09 288	51.16 304	46.65 346	76.34 296	32.84 278	73.22 365	30.94 359	44.87 365	77.06 329

pmmvs4		63.34 266	61.07 271	70.16 272	70.14 338	50.53 179	79.97 270	71.41 343	55.08 270	54.12 297	78.58 265	32.79 279	82.09 296	50.33 264	57.22 300	77.86 322

TR-MVS		69.71 174	67.85 183	75.27 160	82.94 124	48.48 239	87.40 72	80.86 211	57.15 242	64.61 158	87.08 157	32.67 280	89.64 123	46.38 293	71.55 178	87.68 166

VDD-MVS		76.08 63	74.97 72	79.44 41	84.27 90	53.33 119	91.13 20	85.88 98	65.33 87	72.37 76	89.34 110	32.52 281	92.76 40	77.90 57	75.96 131	92.22 39

3Dnovator+	62.71 7	72.29 126	70.50 136	77.65 90	83.40 108	51.29 169	87.32 73	86.40 88	59.01 204	58.49 243	88.32 133	32.40 282	91.27 74	57.04 219	82.15 67	90.38 92

tfpnnormal		61.47 283	59.09 287	68.62 294	76.29 265	41.69 335	81.14 249	85.16 121	54.48 278	51.32 316	73.63 323	32.32 283	86.89 222	21.78 391	55.71 315	77.29 328

MS-PatchMatch		72.34 124	71.26 126	75.61 141	82.38 140	55.55 52	88.00 55	89.95 21	65.38 85	56.51 276	80.74 247	32.28 284	92.89 34	57.95 208	88.10 15	78.39 316

v7n		62.50 275	59.27 286	72.20 233	67.25 358	49.83 200	77.87 288	80.12 223	52.50 293	48.80 331	73.07 327	32.10 285	87.90 186	46.83 289	54.92 319	78.86 307

IterMVS		63.77 262	61.67 262	70.08 274	72.68 313	51.24 170	80.44 261	75.51 306	60.51 174	51.41 315	73.70 322	32.08 286	78.91 326	54.30 237	54.35 325	80.08 299
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
IterMVS-SCA-FT		59.12 296	58.81 290	60.08 350	70.68 337	45.07 299	80.42 262	74.25 316	43.54 356	50.02 324	73.73 319	31.97 287	56.74 396	51.06 262	53.60 331	78.42 315

SCA		63.84 260	60.01 281	75.32 153	78.58 229	57.92 12	61.61 373	77.53 279	56.71 250	57.75 255	70.77 347	31.97 287	79.91 321	48.80 275	56.36 303	88.13 155

ACMMP		70.81 155	69.29 161	75.39 151	81.52 167	51.92 153	83.43 187	83.03 173	56.67 252	58.80 237	88.91 118	31.92 289	88.58 160	65.89 138	73.39 159	85.67 206
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
APD-MVS_3200maxsize		69.62 179	68.23 175	73.80 197	81.58 163	48.22 248	81.91 227	79.50 239	48.21 323	64.24 166	89.75 103	31.91 290	87.55 203	63.08 158	73.85 157	85.64 208

VDDNet		74.37 89	72.13 112	81.09 20	79.58 204	56.52 37	90.02 26	86.70 81	52.61 292	71.23 90	87.20 155	31.75 291	93.96 25	74.30 82	75.77 134	92.79 27

pmmvs5		62.80 272	61.18 269	67.66 301	69.53 342	42.37 334	82.65 208	75.19 310	54.30 281	52.03 313	78.51 266	31.64 292	80.67 308	48.60 277	58.15 287	79.95 300

LCM-MVSNet-Re		58.82 302	56.54 301	65.68 317	79.31 210	29.09 393	61.39 375	45.79 393	60.73 171	37.65 380	72.47 334	31.42 293	81.08 302	49.66 268	70.41 188	86.87 180

testdata				67.08 307	77.59 244	45.46 296		69.20 357	44.47 349	71.50 87	88.34 132	31.21 294	70.76 374	52.20 255	75.88 132	85.03 215

SR-MVS-dyc-post		68.27 204	66.87 199	72.48 226	80.96 178	48.14 252	81.54 241	76.98 289	46.42 336	62.75 186	89.42 108	31.17 295	86.09 247	60.52 182	72.06 173	83.19 251

GA-MVS		69.04 186	66.70 204	76.06 130	75.11 281	52.36 142	83.12 198	80.23 222	63.32 121	60.65 207	79.22 260	30.98 296	88.37 168	61.25 172	66.41 218	87.46 170

OpenMVS	61.00 11	69.99 169	67.55 189	77.30 97	78.37 234	54.07 101	84.36 158	85.76 101	57.22 240	56.71 272	87.67 148	30.79 297	92.83 36	43.04 309	84.06 56	85.01 216

Effi-MVS+-dtu		66.24 247	64.96 243	70.08 274	75.17 280	49.64 202	82.01 224	74.48 315	62.15 140	57.83 251	76.08 302	30.59 298	83.79 281	65.40 146	60.93 265	76.81 331

sd_testset		67.79 212	65.95 221	73.32 207	81.70 155	46.33 285	68.99 345	80.30 221	66.58 61	61.64 198	82.38 225	30.45 299	87.63 199	55.86 228	65.60 225	86.01 197

test222					79.36 207	50.97 172	77.99 287	67.84 362	42.54 360	62.84 185	86.53 166	30.26 300			76.91 117	85.23 213

MVS_111021_LR		69.07 185	67.91 178	72.54 223	77.27 249	49.56 205	79.77 271	73.96 321	59.33 194	60.73 206	87.82 144	30.19 301	81.53 298	69.94 108	72.19 172	86.53 189

114514_t		69.87 172	67.88 180	75.85 135	88.38 29	52.35 143	86.94 85	83.68 158	53.70 283	55.68 282	85.60 175	30.07 302	91.20 78	55.84 229	71.02 182	83.99 233

CPTT-MVS		67.15 229	65.84 224	71.07 259	80.96 178	50.32 189	81.94 226	74.10 317	46.18 339	57.91 250	87.64 149	29.57 303	81.31 300	64.10 153	70.18 191	81.56 272

CANet_DTU		73.71 102	73.14 95	75.40 150	82.61 137	50.05 194	84.67 152	79.36 244	69.72 30	75.39 42	90.03 98	29.41 304	85.93 254	67.99 122	79.11 98	90.22 97

AdaColmap		67.86 209	65.48 232	75.00 166	88.15 36	54.99 74	86.10 101	76.63 298	49.30 314	57.80 252	86.65 165	29.39 305	88.94 148	45.10 299	70.21 190	81.06 286

RE-MVS-def			66.66 205		80.96 178	48.14 252	81.54 241	76.98 289	46.42 336	62.75 186	89.42 108	29.28 306		60.52 182	72.06 173	83.19 251

CVMVSNet		60.85 286	60.44 276	62.07 338	75.00 284	32.73 376	79.54 273	73.49 326	36.98 374	56.28 278	83.74 196	29.28 306	69.53 377	46.48 292	63.23 247	83.94 238

PMMVS		72.98 112	72.05 115	75.78 136	83.57 101	48.60 233	84.08 166	82.85 177	61.62 150	68.24 118	90.33 87	28.35 308	87.78 193	72.71 95	76.69 121	90.95 80

our_test_3		59.11 297	55.08 313	71.18 258	71.42 327	53.29 121	81.96 225	74.52 314	48.32 321	42.08 360	69.28 356	28.14 309	82.15 294	34.35 345	45.68 364	78.11 321

Fast-Effi-MVS+-dtu		66.53 242	64.10 251	73.84 195	72.41 316	52.30 145	84.73 147	75.66 305	59.51 187	56.34 277	79.11 262	28.11 310	85.85 255	57.74 214	63.29 246	83.35 245

Anonymous20231211		66.08 249	63.67 252	73.31 208	83.07 118	48.75 230	86.01 104	84.67 137	45.27 343	56.54 274	76.67 292	28.06 311	88.95 146	52.78 250	59.95 267	82.23 263

Anonymous20240529		69.71 174	67.28 195	77.00 107	83.78 99	50.36 187	88.87 46	85.10 124	47.22 329	64.03 168	83.37 204	27.93 312	92.10 58	57.78 213	67.44 209	88.53 145

HPM-MVS_fast		67.86 209	66.28 213	72.61 221	80.67 189	48.34 244	81.18 248	75.95 304	50.81 305	59.55 220	88.05 140	27.86 313	85.98 250	58.83 193	73.58 158	83.51 244

FMVSNet1		64.57 254	62.11 260	71.96 240	77.32 248	46.36 282	83.52 180	83.31 165	52.43 294	54.42 293	76.23 298	27.80 314	86.20 239	42.59 313	61.34 263	83.32 246

CNLPA		60.59 287	58.44 291	67.05 308	79.21 212	47.26 272	79.75 272	64.34 372	42.46 361	51.90 314	83.94 192	27.79 315	75.41 354	37.12 326	59.49 273	78.47 313

TAPA-MVS	56.12 14	61.82 281	60.18 280	66.71 311	78.48 232	37.97 357	75.19 304	76.41 301	46.82 332	57.04 267	86.52 167	27.67 316	77.03 344	26.50 378	67.02 212	85.14 214
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
pmmvs6		59.64 291	57.15 298	67.09 306	66.01 360	36.86 361	80.50 259	78.64 259	45.05 345	49.05 329	73.94 317	27.28 317	86.10 245	43.96 306	49.94 344	78.31 317

test-mter		68.36 200	67.29 194	71.60 249	78.67 225	48.17 250	85.13 130	79.72 233	53.38 286	63.13 181	82.58 219	27.23 318	80.24 315	60.56 180	75.17 142	86.39 193

D2MVS		63.49 264	61.39 266	69.77 278	69.29 344	48.93 224	78.89 281	77.71 277	60.64 173	49.70 325	72.10 341	27.08 319	83.48 286	54.48 236	62.65 255	76.90 330

XVG-OURS-SEG-HR		62.02 279	59.54 283	69.46 281	65.30 365	45.88 290	65.06 358	73.57 325	46.45 335	57.42 264	83.35 205	26.95 320	78.09 332	53.77 241	64.03 236	84.42 225

test_djsdf		63.84 260	61.56 264	70.70 264	68.78 347	44.69 303	81.63 237	81.44 199	50.28 307	52.27 311	76.26 297	26.72 321	86.11 243	60.83 176	55.84 314	81.29 284

Anonymous20231206		59.08 298	57.59 295	63.55 330	68.77 348	32.14 379	80.26 265	79.78 232	50.00 311	49.39 327	72.39 336	26.64 322	78.36 329	33.12 351	57.94 292	80.14 298

ppachtmachnet_test		58.56 305	54.34 315	71.24 255	71.42 327	54.74 80	81.84 230	72.27 333	49.02 316	45.86 350	68.99 357	26.27 323	83.30 289	30.12 360	43.23 369	75.69 341

test20.03		55.22 325	54.07 318	58.68 355	63.14 378	25.00 399	77.69 289	74.78 313	52.64 291	43.43 355	72.39 336	26.21 324	74.76 356	29.31 363	47.05 358	76.28 339

FE-MVS		64.15 257	60.43 277	75.30 156	80.85 183	49.86 199	68.28 349	78.37 266	50.26 310	59.31 225	73.79 318	26.19 325	91.92 61	40.19 317	66.67 214	84.12 228

FMVSNet5		58.61 304	56.45 302	65.10 324	77.20 253	39.74 347	74.77 305	77.12 287	50.27 309	43.28 357	67.71 360	26.15 326	76.90 347	36.78 331	54.78 321	78.65 311

ACMP	61.11 9	66.24 247	64.33 248	72.00 239	74.89 286	49.12 216	83.18 197	79.83 231	55.41 267	52.29 310	82.68 216	25.83 327	86.10 245	60.89 175	63.94 238	80.78 289
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
MIMVSNet		63.12 268	60.29 278	71.61 248	75.92 274	46.65 278	65.15 357	81.94 188	59.14 201	54.65 291	69.47 353	25.74 328	80.63 309	41.03 316	69.56 197	87.55 168

LPG-MVS_test		66.44 244	64.58 245	72.02 237	74.42 292	48.60 233	83.07 200	80.64 214	54.69 276	53.75 301	83.83 194	25.73 329	86.98 216	60.33 186	64.71 229	80.48 293

LGP-MVS_train				72.02 237	74.42 292	48.60 233		80.64 214	54.69 276	53.75 301	83.83 194	25.73 329	86.98 216	60.33 186	64.71 229	80.48 293

test_vis1_n_1920		68.59 198	68.31 172	69.44 282	69.16 345	41.51 338	84.63 153	68.58 360	58.80 208	73.26 63	88.37 129	25.30 331	80.60 310	79.10 42	67.55 208	86.23 195

ACMM	58.35 12	64.35 256	62.01 261	71.38 253	74.21 295	48.51 237	82.25 220	79.66 235	47.61 327	54.54 292	80.11 250	25.26 332	86.00 249	51.26 259	63.16 249	79.64 302
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
XVG-OURS		61.88 280	59.34 285	69.49 280	65.37 364	46.27 286	64.80 359	73.49 326	47.04 331	57.41 265	82.85 210	25.15 333	78.18 330	53.00 247	64.98 227	84.01 232

PVSNet_0	57.04 13	61.19 284	57.24 297	73.02 212	77.45 247	50.31 190	79.43 277	77.36 284	63.96 107	47.51 341	72.45 335	25.03 334	83.78 282	52.76 252	19.22 410	84.96 218

WB-MVS		37.41 367	36.37 367	40.54 385	54.23 394	10.43 423	65.29 355	43.75 396	34.86 383	27.81 402	54.63 392	24.94 335	63.21 382	6.81 418	15.00 413	47.98 404

UniMVSNet_ETH3D		62.51 274	60.49 275	68.57 296	68.30 353	40.88 345	73.89 312	79.93 229	51.81 300	54.77 289	79.61 255	24.80 336	81.10 301	49.93 266	61.35 262	83.73 241

DP-MVS		59.24 294	56.12 306	68.63 293	88.24 34	50.35 188	82.51 215	64.43 371	41.10 363	46.70 345	78.77 264	24.75 337	88.57 163	22.26 389	56.29 307	66.96 381

test_cas_vis1_n_1920		67.10 230	66.60 207	68.59 295	65.17 367	43.23 322	83.23 195	69.84 353	55.34 268	70.67 99	87.71 147	24.70 338	76.66 349	78.57 49	64.20 234	85.89 203

tt0805		63.39 265	61.31 268	69.64 279	69.36 343	38.87 351	78.00 286	85.48 103	48.82 318	55.66 284	81.66 238	24.38 339	86.37 237	49.04 274	59.36 275	83.68 242

cascas		69.01 187	66.13 216	77.66 89	79.36 207	55.41 58	86.99 83	83.75 157	56.69 251	58.92 233	81.35 241	24.31 340	92.10 58	53.23 243	70.61 186	85.46 211

CMPMVS	40.41 21	55.34 324	52.64 327	63.46 331	60.88 384	43.84 313	61.58 374	71.06 345	30.43 390	36.33 382	74.63 311	24.14 341	75.44 353	48.05 281	66.62 215	71.12 374
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
UGNet		68.71 195	67.11 198	73.50 206	80.55 192	47.61 266	84.08 166	78.51 263	59.45 188	65.68 144	82.73 215	23.78 342	85.08 268	52.80 249	76.40 122	87.80 162
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
YYNet1		53.82 332	49.96 338	65.41 321	70.09 340	48.95 222	72.30 326	71.66 340	44.25 352	31.89 395	63.07 375	23.73 343	73.95 359	33.26 349	39.40 376	73.34 362

MDA-MVSNet_test_wron		53.82 332	49.95 339	65.43 320	70.13 339	49.05 218	72.30 326	71.65 341	44.23 353	31.85 396	63.13 374	23.68 344	74.01 358	33.25 350	39.35 377	73.23 364

PLC	52.38 18	60.89 285	58.97 289	66.68 313	81.77 152	45.70 294	78.96 280	74.04 320	43.66 355	47.63 338	83.19 208	23.52 345	77.78 341	37.47 323	60.46 266	76.55 337
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
SSC-MVS		35.20 369	34.30 371	37.90 388	52.58 396	8.65 426	61.86 371	41.64 400	31.81 388	25.54 405	52.94 398	23.39 346	59.28 391	6.10 419	12.86 414	45.78 407

ADS-MVSNet2		55.21 326	51.44 331	66.51 314	80.60 190	49.56 205	55.03 388	65.44 367	44.72 347	51.00 318	61.19 380	22.83 347	75.41 354	28.54 368	53.63 329	74.57 354

ADS-MVSNet		56.17 320	51.95 330	68.84 287	80.60 190	53.07 127	55.03 388	70.02 352	44.72 347	51.00 318	61.19 380	22.83 347	78.88 327	28.54 368	53.63 329	74.57 354

test_0402		56.45 318	53.03 322	66.69 312	76.78 258	50.31 190	81.76 232	69.61 355	42.79 359	43.88 352	72.13 339	22.82 349	86.46 234	16.57 403	50.94 341	63.31 390

UnsupCasMVSNet_eth		57.56 312	55.15 311	64.79 326	64.57 372	33.12 373	73.17 319	83.87 156	58.98 205	41.75 363	70.03 351	22.54 350	79.92 319	46.12 296	35.31 383	81.32 283

xiu_mvs_v1_base_debu		71.60 140	70.29 144	75.55 144	77.26 250	53.15 123	85.34 120	79.37 241	55.83 261	72.54 71	90.19 92	22.38 351	86.66 227	73.28 91	76.39 123	86.85 182

xiu_mvs_v1_base		71.60 140	70.29 144	75.55 144	77.26 250	53.15 123	85.34 120	79.37 241	55.83 261	72.54 71	90.19 92	22.38 351	86.66 227	73.28 91	76.39 123	86.85 182

xiu_mvs_v1_base_debi		71.60 140	70.29 144	75.55 144	77.26 250	53.15 123	85.34 120	79.37 241	55.83 261	72.54 71	90.19 92	22.38 351	86.66 227	73.28 91	76.39 123	86.85 182

LS3D		56.40 319	53.82 319	64.12 327	81.12 174	45.69 295	73.42 317	66.14 366	35.30 382	43.24 358	79.88 252	22.18 354	79.62 324	19.10 398	64.00 237	67.05 380

PVSNet	62.49 8	69.27 184	67.81 184	73.64 202	84.41 85	51.85 154	84.63 153	77.80 274	66.42 65	59.80 214	84.95 184	22.14 355	80.44 313	55.03 232	75.11 145	88.62 141

MDA-MVSNet-bldmvs		51.56 342	47.75 349	63.00 334	71.60 325	47.32 271	69.70 343	72.12 334	43.81 354	27.65 403	63.38 373	21.97 356	75.96 351	27.30 375	32.19 391	65.70 386

pmmvs-eth3d		55.97 322	52.78 326	65.54 319	61.02 383	46.44 281	75.36 303	67.72 363	49.61 313	43.65 354	67.58 361	21.63 357	77.04 343	44.11 305	44.33 366	73.15 365

anonymousdsp		60.46 288	57.65 294	68.88 286	63.63 376	45.09 298	72.93 320	78.63 260	46.52 334	51.12 317	72.80 331	21.46 358	83.07 291	57.79 212	53.97 326	78.47 313

MVS-HIRNet		49.01 349	44.71 353	61.92 342	76.06 269	46.61 279	63.23 366	54.90 385	24.77 398	33.56 390	36.60 407	21.28 359	75.88 352	29.49 362	62.54 256	63.26 391

Anonymous202405211		70.11 163	67.88 180	76.79 116	87.20 44	47.24 273	89.49 35	77.38 283	54.88 274	66.14 135	86.84 160	20.93 360	91.54 68	56.45 226	71.62 176	91.59 58

UnsupCasMVSNet_bld		53.86 331	50.53 335	63.84 328	63.52 377	34.75 364	71.38 334	81.92 190	46.53 333	38.95 376	57.93 389	20.55 361	80.20 317	39.91 319	34.09 390	76.57 336

EU-MVSNet		52.63 337	50.72 334	58.37 356	62.69 380	28.13 396	72.60 322	75.97 303	30.94 389	40.76 370	72.11 340	20.16 362	70.80 373	35.11 342	46.11 362	76.19 340

N_pmnet		41.25 360	39.77 363	45.66 378	68.50 350	0.82 430	72.51 324	0.38 429	35.61 379	35.26 386	61.51 379	20.07 363	67.74 378	23.51 385	40.63 373	68.42 379

MSDG		59.44 292	55.14 312	72.32 231	74.69 287	50.71 174	74.39 310	73.58 324	44.44 350	43.40 356	77.52 275	19.45 364	90.87 89	31.31 357	57.49 299	75.38 344

K. test v3		54.04 330	49.42 342	67.92 300	68.55 349	42.57 332	75.51 301	63.07 375	52.07 295	39.21 374	64.59 371	19.34 365	82.21 293	37.11 327	25.31 401	78.97 306

lessismore_v0				67.98 299	64.76 371	41.25 341		45.75 394		36.03 384	65.63 368	19.29 366	84.11 278	35.67 335	21.24 407	78.59 312

KD-MVS_self_test		49.24 348	46.85 351	56.44 361	54.32 393	22.87 402	57.39 383	73.36 330	44.36 351	37.98 379	59.30 387	18.97 367	71.17 372	33.48 347	42.44 370	75.26 346

OpenMVS_ROB	53.19 17	59.20 295	56.00 307	68.83 288	71.13 331	44.30 307	83.64 179	75.02 311	46.42 336	46.48 347	73.03 328	18.69 368	88.14 178	27.74 373	61.80 260	74.05 357

mvsany_test1		43.38 358	42.57 361	45.82 377	50.96 401	26.10 398	55.80 386	27.74 417	27.15 394	47.41 342	74.39 313	18.67 369	44.95 408	44.66 301	36.31 381	66.40 383

LTVRE_ROB	45.45 19	52.73 336	49.74 340	61.69 343	69.78 341	34.99 363	44.52 397	67.60 364	43.11 358	43.79 353	74.03 315	18.54 370	81.45 299	28.39 370	57.94 292	68.62 378
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
SixPastTwentyTwo		54.37 327	50.10 336	67.21 305	70.70 335	41.46 340	74.73 306	64.69 369	47.56 328	39.12 375	69.49 352	18.49 371	84.69 273	31.87 354	34.20 389	75.48 343

new-patchmatchnet		48.21 350	46.55 352	53.18 367	57.73 389	18.19 416	70.24 338	71.02 346	45.70 340	33.70 389	60.23 383	18.00 372	69.86 376	27.97 372	34.35 387	71.49 373

F-COLMAP		55.96 323	53.65 321	62.87 336	72.76 312	42.77 328	74.70 308	70.37 349	40.03 364	41.11 368	79.36 257	17.77 373	73.70 362	32.80 352	53.96 327	72.15 367

jajsoiax		63.21 267	60.84 272	70.32 270	68.33 352	44.45 305	81.23 247	81.05 205	53.37 287	50.96 320	77.81 273	17.49 374	85.49 259	59.31 189	58.05 290	81.02 287

RPSCF		45.77 355	44.13 357	50.68 369	57.67 390	29.66 389	54.92 390	45.25 395	26.69 395	45.92 349	75.92 304	17.43 375	45.70 407	27.44 374	45.95 363	76.67 332

mmtdpeth		57.93 310	54.78 314	67.39 304	72.32 318	43.38 319	72.72 321	68.93 358	54.45 279	56.85 269	62.43 376	17.02 376	83.46 287	57.95 208	30.31 395	75.31 345

PatchMatch-RL		56.66 315	53.75 320	65.37 322	77.91 241	45.28 297	69.78 342	60.38 378	41.35 362	47.57 339	73.73 319	16.83 377	76.91 345	36.99 329	59.21 276	73.92 358

mvs_tets		62.96 270	60.55 274	70.19 271	68.22 355	44.24 310	80.90 254	80.74 213	52.99 290	50.82 322	77.56 274	16.74 378	85.44 260	59.04 192	57.94 292	80.89 288

ACMH+	54.58 15	58.55 306	55.24 310	68.50 297	74.68 288	45.80 293	80.27 264	70.21 350	47.15 330	42.77 359	75.48 306	16.73 379	85.98 250	35.10 343	54.78 321	73.72 359

ACMH	53.70 16	59.78 290	55.94 308	71.28 254	76.59 259	48.35 243	80.15 268	76.11 302	49.74 312	41.91 362	73.45 326	16.50 380	90.31 103	31.42 356	57.63 298	75.17 347
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
MIMVSNet1		50.35 346	47.81 347	57.96 357	61.53 382	27.80 397	67.40 351	74.06 319	43.25 357	33.31 394	65.38 370	16.03 381	71.34 371	21.80 390	47.55 353	74.75 351

DSMNet-mixed		38.35 364	35.36 369	47.33 376	48.11 407	14.91 420	37.87 406	36.60 408	19.18 403	34.37 387	59.56 386	15.53 382	53.01 400	20.14 396	46.89 359	74.07 356

EG-PatchMatch MVS		62.40 278	59.59 282	70.81 263	73.29 303	49.05 218	85.81 105	84.78 132	51.85 299	44.19 351	73.48 325	15.52 383	89.85 115	40.16 318	67.24 210	73.54 361

testgi		54.25 329	52.57 328	59.29 353	62.76 379	21.65 408	72.21 328	70.47 348	53.25 288	41.94 361	77.33 280	14.28 384	77.95 337	29.18 364	51.72 340	78.28 318

COLMAP_ROB	43.60 20	50.90 345	48.05 346	59.47 351	67.81 356	40.57 346	71.25 335	62.72 377	36.49 377	36.19 383	73.51 324	13.48 385	73.92 360	20.71 393	50.26 343	63.92 389
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
OurMVSNet-221017-0		52.39 339	48.73 343	63.35 333	65.21 366	38.42 354	68.54 348	64.95 368	38.19 369	39.57 373	71.43 343	13.23 386	79.92 319	37.16 325	40.32 375	71.72 370

MVStest1		38.35 364	34.53 370	49.82 373	51.43 399	30.41 382	50.39 392	55.25 383	17.56 406	26.45 404	65.85 367	11.72 387	57.00 395	14.79 405	17.31 412	62.05 392

test_fmvs1		53.60 334	52.54 329	56.78 359	58.07 387	30.26 383	68.95 346	42.19 399	32.46 385	63.59 177	82.56 221	11.55 388	60.81 386	58.25 202	55.27 317	79.28 303

tmp_tt		9.44 389	10.68 392	5.73 405	2.49 428	4.21 429	10.48 418	18.04 424	0.34 422	12.59 414	20.49 416	11.39 389	7.03 424	13.84 408	6.46 421	5.95 419

ITE_SJBPF				51.84 368	58.03 388	31.94 380		53.57 389	36.67 375	41.32 366	75.23 308	11.17 390	51.57 401	25.81 379	48.04 349	72.02 369

Anonymous20240521		51.65 341	48.42 344	61.34 347	56.43 392	39.65 349	73.57 315	73.47 329	36.64 376	36.59 381	63.98 372	10.75 391	72.25 370	35.35 337	49.01 345	72.11 368

mvs5depth		50.97 344	46.98 350	62.95 335	56.63 391	34.23 368	62.73 370	67.35 365	45.03 346	48.00 335	65.41 369	10.40 392	79.88 323	36.00 333	31.27 394	74.73 352

AllTest		47.32 352	44.66 354	55.32 365	65.08 368	37.50 359	62.96 368	54.25 387	35.45 380	33.42 391	72.82 329	9.98 393	59.33 389	24.13 383	43.84 367	69.13 376

TestCases				55.32 365	65.08 368	37.50 359		54.25 387	35.45 380	33.42 391	72.82 329	9.98 393	59.33 389	24.13 383	43.84 367	69.13 376

USDC		54.36 328	51.23 332	63.76 329	64.29 373	37.71 358	62.84 369	73.48 328	56.85 245	35.47 385	71.94 342	9.23 395	78.43 328	38.43 322	48.57 346	75.13 348

XVG-ACMP-BASELINE		56.03 321	52.85 325	65.58 318	61.91 381	40.95 344	63.36 364	72.43 332	45.20 344	46.02 348	74.09 314	9.20 396	78.12 331	45.13 298	58.27 285	77.66 325

test_fmvs1_n		52.55 338	51.19 333	56.65 360	51.90 398	30.14 384	67.66 350	42.84 398	32.27 386	62.30 191	82.02 235	9.12 397	60.84 385	57.82 211	54.75 323	78.99 305

test_vis1_n		51.19 343	49.66 341	55.76 364	51.26 400	29.85 388	67.20 353	38.86 404	32.12 387	59.50 221	79.86 253	8.78 398	58.23 393	56.95 220	52.46 337	79.19 304

pmmvs3		45.53 356	41.55 362	57.44 358	48.97 405	39.68 348	70.06 339	57.66 381	28.32 393	34.06 388	57.29 390	8.50 399	66.85 380	34.86 344	34.26 388	65.80 385

EGC-MVSNET		33.75 371	30.42 375	43.75 381	64.94 370	36.21 362	60.47 378	40.70 402	0.02 423	0.10 424	53.79 395	7.39 400	60.26 387	11.09 410	35.23 385	34.79 409

test_fmvs2		45.89 354	44.32 356	50.62 370	45.85 409	24.70 400	58.87 382	37.84 407	25.22 396	52.46 309	74.56 312	7.07 401	54.69 397	49.28 272	47.70 351	72.48 366

ANet_high		34.39 370	29.59 376	48.78 374	30.34 419	22.28 404	55.53 387	63.79 373	38.11 370	15.47 411	36.56 408	6.94 402	59.98 388	13.93 407	5.64 422	64.08 388

FPMVS		35.40 368	33.67 372	40.57 384	46.34 408	28.74 395	41.05 402	57.05 382	20.37 402	22.27 407	53.38 396	6.87 403	44.94 409	8.62 412	47.11 357	48.01 403

test_vis1_rt		40.29 363	38.64 364	45.25 379	48.91 406	30.09 385	59.44 379	27.07 418	24.52 399	38.48 378	51.67 399	6.71 404	49.44 402	44.33 303	46.59 361	56.23 394

new_pmnet		33.56 372	31.89 374	38.59 386	49.01 404	20.42 409	51.01 391	37.92 406	20.58 400	23.45 406	46.79 401	6.66 405	49.28 404	20.00 397	31.57 393	46.09 406

TinyColmap		48.15 351	44.49 355	59.13 354	65.73 363	38.04 355	63.34 365	62.86 376	38.78 367	29.48 398	67.23 363	6.46 406	73.30 364	24.59 382	41.90 372	66.04 384

ambc				62.06 339	53.98 395	29.38 391	35.08 408	79.65 236		41.37 364	59.96 384	6.27 407	82.15 294	35.34 338	38.22 378	74.65 353

TDRefinement		40.91 361	38.37 365	48.55 375	50.45 402	33.03 375	58.98 381	50.97 390	28.50 391	29.89 397	67.39 362	6.21 408	54.51 398	17.67 401	35.25 384	58.11 393

ttmdpeth		40.58 362	37.50 366	49.85 372	49.40 403	22.71 403	56.65 385	46.78 391	28.35 392	40.29 372	69.42 354	5.35 409	61.86 384	20.16 395	21.06 408	64.96 387

PM-MVS		46.92 353	43.76 360	56.41 362	52.18 397	32.26 378	63.21 367	38.18 405	37.99 371	40.78 369	66.20 364	5.09 410	65.42 381	48.19 280	41.99 371	71.54 372

LF4IMVS		33.04 373	32.55 373	34.52 391	40.96 410	22.03 405	44.45 398	35.62 409	20.42 401	28.12 401	62.35 377	5.03 411	31.88 420	21.61 392	34.42 386	49.63 402

EMVS		18.42 386	17.66 390	20.71 402	34.13 416	12.64 422	46.94 395	29.94 415	10.46 416	5.58 422	14.93 420	4.23 412	38.83 412	5.24 422	7.51 419	10.67 418

E-PMN		19.16 385	18.40 389	21.44 401	36.19 414	13.63 421	47.59 394	30.89 413	10.73 414	5.91 421	16.59 417	3.66 413	39.77 411	5.95 420	8.14 417	10.92 417

test_method		24.09 382	21.07 386	33.16 394	27.67 423	8.35 428	26.63 414	35.11 411	3.40 420	14.35 412	36.98 406	3.46 414	35.31 415	19.08 399	22.95 404	55.81 395

mvsany_test3		28.00 375	25.98 377	34.05 392	28.97 420	15.31 418	34.54 409	18.17 423	16.24 407	29.30 399	53.37 397	2.79 415	33.38 419	30.01 361	20.41 409	53.45 398

test_f		27.12 377	24.85 378	33.93 393	26.17 425	15.25 419	30.24 413	22.38 422	12.53 412	28.23 400	49.43 400	2.59 416	34.34 418	25.12 381	26.99 399	52.20 400

test_fmvs3		37.95 366	35.75 368	44.55 380	35.50 415	18.92 412	48.32 393	34.00 412	18.36 405	41.31 367	61.58 378	2.29 417	48.06 406	42.72 312	37.71 379	66.66 382

PMMVS2		26.71 378	22.98 383	37.87 389	36.89 413	8.51 427	42.51 401	29.32 416	19.09 404	13.01 413	37.54 404	2.23 418	53.11 399	14.54 406	11.71 415	51.99 401

Gipuma		27.47 376	24.26 381	37.12 390	60.55 385	29.17 392	11.68 417	60.00 379	14.18 409	10.52 418	15.12 419	2.20 419	63.01 383	8.39 413	35.65 382	19.18 415
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
LCM-MVSNet		28.07 374	23.85 382	40.71 383	27.46 424	18.93 411	30.82 412	46.19 392	12.76 411	16.40 409	34.70 410	1.90 420	48.69 405	20.25 394	24.22 403	54.51 397

DeepMVS_CX				13.10 403	21.34 427	8.99 425		10.02 427	10.59 415	7.53 420	30.55 413	1.82 421	14.55 422	6.83 417	7.52 418	15.75 416

APD_test1		26.46 379	24.41 380	32.62 396	37.58 412	21.74 407	40.50 404	30.39 414	11.45 413	16.33 410	43.76 402	1.63 422	41.62 410	11.24 409	26.82 400	34.51 410

PMVS	19.57 22	25.07 380	22.43 385	32.99 395	23.12 426	22.98 401	40.98 403	35.19 410	15.99 408	11.95 417	35.87 409	1.47 423	49.29 403	5.41 421	31.90 392	26.70 414
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
test_vis3_rt		24.79 381	22.95 384	30.31 397	28.59 421	18.92 412	37.43 407	17.27 425	12.90 410	21.28 408	29.92 414	1.02 424	36.35 413	28.28 371	29.82 398	35.65 408

MVE	16.60 23	17.34 388	13.39 391	29.16 398	28.43 422	19.72 410	13.73 416	23.63 421	7.23 419	7.96 419	21.41 415	0.80 425	36.08 414	6.97 416	10.39 416	31.69 411
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
testf1		21.11 383	19.08 387	27.18 399	30.56 417	18.28 414	33.43 410	24.48 419	8.02 417	12.02 415	33.50 411	0.75 426	35.09 416	7.68 414	21.32 405	28.17 412

APD_test2		21.11 383	19.08 387	27.18 399	30.56 417	18.28 414	33.43 410	24.48 419	8.02 417	12.02 415	33.50 411	0.75 426	35.09 416	7.68 414	21.32 405	28.17 412

wuyk23d		9.11 390	8.77 394	10.15 404	40.18 411	16.76 417	20.28 415	1.01 428	2.58 421	2.66 423	0.98 423	0.23 428	12.49 423	4.08 423	6.90 420	1.19 420

mmdepth		0.00 395	0.00 398	0.00 408	0.00 430	0.00 432	0.00 419	0.00 430	0.00 424	0.00 427	0.00 426	0.00 429	0.00 425	0.00 426	0.00 423	0.00 423

monomultidepth		0.00 395	0.00 398	0.00 408	0.00 430	0.00 432	0.00 419	0.00 430	0.00 424	0.00 427	0.00 426	0.00 429	0.00 425	0.00 426	0.00 423	0.00 423

test_blank		0.00 395	0.00 398	0.00 408	0.00 430	0.00 432	0.00 419	0.00 430	0.00 424	0.00 427	0.00 426	0.00 429	0.00 425	0.00 426	0.00 423	0.00 423

uanet_test		0.00 395	0.00 398	0.00 408	0.00 430	0.00 432	0.00 419	0.00 430	0.00 424	0.00 427	0.00 426	0.00 429	0.00 425	0.00 426	0.00 423	0.00 423

DCPMVS		0.00 395	0.00 398	0.00 408	0.00 430	0.00 432	0.00 419	0.00 430	0.00 424	0.00 427	0.00 426	0.00 429	0.00 425	0.00 426	0.00 423	0.00 423

sosnet-low-res		0.00 395	0.00 398	0.00 408	0.00 430	0.00 432	0.00 419	0.00 430	0.00 424	0.00 427	0.00 426	0.00 429	0.00 425	0.00 426	0.00 423	0.00 423

sosnet		0.00 395	0.00 398	0.00 408	0.00 430	0.00 432	0.00 419	0.00 430	0.00 424	0.00 427	0.00 426	0.00 429	0.00 425	0.00 426	0.00 423	0.00 423

uncertanet		0.00 395	0.00 398	0.00 408	0.00 430	0.00 432	0.00 419	0.00 430	0.00 424	0.00 427	0.00 426	0.00 429	0.00 425	0.00 426	0.00 423	0.00 423

Regformer		0.00 395	0.00 398	0.00 408	0.00 430	0.00 432	0.00 419	0.00 430	0.00 424	0.00 427	0.00 426	0.00 429	0.00 425	0.00 426	0.00 423	0.00 423

testmvs		6.14 392	8.18 395	0.01 406	0.01 429	0.00 432	73.40 318	0.00 430	0.00 424	0.02 425	0.15 424	0.00 429	0.00 425	0.02 424	0.00 423	0.02 421

test123		6.01 393	8.01 396	0.01 406	0.00 430	0.01 431	71.93 332	0.00 430	0.00 424	0.02 425	0.11 425	0.00 429	0.00 425	0.02 424	0.00 423	0.02 421

ab-mvs-re		7.68 391	10.24 393	0.00 408	0.00 430	0.00 432	0.00 419	0.00 430	0.00 424	0.00 427	92.12 42	0.00 429	0.00 425	0.00 426	0.00 423	0.00 423

uanet		0.00 395	0.00 398	0.00 408	0.00 430	0.00 432	0.00 419	0.00 430	0.00 424	0.00 427	0.00 426	0.00 429	0.00 425	0.00 426	0.00 423	0.00 423

WAC-MVS						34.28 366								22.56 388

FOURS1					83.24 112	49.90 198	84.98 138	78.76 256	47.71 326	73.42 60

MSC_two_6792asdad				81.53 15	91.77 4	56.03 46		91.10 11					96.22 8	81.46 33	86.80 28	92.34 35

No_MVS				81.53 15	91.77 4	56.03 46		91.10 11					96.22 8	81.46 33	86.80 28	92.34 35

eth-test2					0.00 430

eth-test					0.00 430

IU-MVS					89.48 17	57.49 17		91.38 9	66.22 69	88.26 1				82.83 22	87.60 18	92.44 32

save fliter					85.35 68	56.34 41	89.31 40	81.46 198	61.55 151

test_0728_SECOND				82.20 8	89.50 15	57.73 13	92.34 5	88.88 34					96.39 4	81.68 29	87.13 21	92.47 31

GSMVS																88.13 155

test_part2					89.33 23	55.48 54				82.27 12

MTGPA								81.31 201

MTMP							87.27 77	15.34 426

gm-plane-assit					83.24 112	54.21 96			70.91 21		88.23 135		95.25 14	66.37 131

test9_res														78.72 48	85.44 43	91.39 66

agg_prior2														75.65 68	85.11 47	91.01 78

agg_prior					85.64 62	54.92 76		83.61 162		72.53 74			88.10 181

test_prior4						56.39 40	87.15 81

test_prior				78.39 74	86.35 53	54.91 77		85.45 106					89.70 121			90.55 87

旧先验2							81.73 234		45.53 342	74.66 47			70.48 375	58.31 201

新几何2							81.61 239

无先验							85.19 128	78.00 272	49.08 315				85.13 267	52.78 250		87.45 171

原ACMM2							83.77 177

testdata2													77.81 340	45.64 297

testdata1							77.55 290		64.14 102

plane_prior7					77.95 238	48.46 240

plane_prior5								82.59 179					88.30 174	65.46 142	72.34 170	84.49 223

plane_prior4											83.28 206

plane_prior3						48.95 222			64.01 105	62.15 193

plane_prior2							85.76 107		63.60 114

plane_prior1					78.31 235

plane_prior						49.57 203	87.43 70		64.57 94						72.84 165

n2								0.00 430

nn								0.00 430

door-mid								41.31 401

test11								84.25 146

door								43.27 397

HQP5-MVS						51.56 161

HQP-NCC					79.02 217		88.00 55		65.45 81	64.48 161

ACMP_Plane					79.02 217		88.00 55		65.45 81	64.48 161

BP-MVS														66.70 128

HQP4-MVS										64.47 164			88.61 158			84.91 219

HQP3-MVS								83.68 158							73.12 161

NP-MVS					78.76 222	50.43 182					85.12 180

ACMMP++_ref															63.20 248

ACMMP++															59.38 274

High-resolution multi-view benchmark