High-res multi-view results

This table lists the benchmark results for the high-res multi-view scenario. The following metrics are evaluated:

Accuracy [%]: The fraction of the reconstruction which is closer to the ground truth than the evaluation threshold distance (*). Larger is better.
Completeness [%]: The fraction of the ground truth which is closer to the reconstruction than the evaluation threshold distance (*). Larger is better.
F₁ score [%]: The harmonic mean of accuracy and completeness, used to rank methods based on both metrics. Larger is better.
Time [s]: The runtime of the method. Smaller is better.

(*) For exact definitions, detailing how potentially incomplete ground truth is taken into account, see our paper.

The datasets are grouped into different categories, and result averages are computed for a category and method if results of the method are available for all datasets within the category. Note that the category "all" includes both the high-res multi-view and the low-res many-view scenarios.

Methods with suffix _ROB may participate in the Robust Vision Challenge.

Click a dataset result cell to show a visualization of the reconstruction. For training datasets, ground truth and accuracy / completeness visualizations are also available. The visualizations may not work with mobile browsers.

Method	all	high-res multi-view	indoor	outdoor	botani.	boulde.	bridge	door	exhibi.	lectur.	living.	lounge	observ.	old co.	statue	terrac.

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

DELS-MVS		82.32 5	82.50 5	81.79 12	86.80 48	56.89 29	92.77 2	86.30 94	77.83 1	77.88 38	92.13 49	60.24 7	94.78 19	78.97 53	89.61 8	93.69 8
Christian Sormann, Emanuele Santellani, Mattia Rossi, Andreas Kuhn, Friedrich Fraundorfer: DELS-MVS: Deep Epipolar Line Search for Multi-View Stereo. Winter Conference on Applications of Computer Vision (WACV), 2023
SED-MVS		81.92 8	81.75 9	82.44 7	89.48 17	56.89 29	92.48 3	88.94 35	57.50 248	84.61 4	94.09 4	58.81 13	96.37 6	82.28 32	87.60 18	94.06 3

OPU-MVS				81.71 13	92.05 3	55.97 48	92.48 3				94.01 6	67.21 2	95.10 15	89.82 3	92.55 3	94.06 3

DVP-MVS		81.30 10	81.00 13	82.20 8	89.40 20	57.45 19	92.34 5	89.99 21	57.71 242	81.91 15	93.64 15	55.17 31	96.44 2	81.68 36	87.13 21	92.72 28
Zhenlong Yuan, Jinguo Luo, Fei Shen, Zhaoxin Li, Cong Liu, Tianlu Mao, Zhaoqi Wang: DVP-MVS: Synergize Depth-Edge and Visibility Prior for Multi-View Stereo. AAAI2025
test_0728_SECOND				82.20 8	89.50 15	57.73 13	92.34 5	88.88 37					96.39 4	81.68 36	87.13 21	92.47 31

test0726					89.40 20	57.45 19	92.32 7	88.63 48	57.71 242	83.14 9	93.96 7	55.17 31

DPM-MVS		82.39 4	82.36 7	82.49 5	80.12 201	59.50 5	92.24 8	90.72 16	69.37 36	83.22 8	94.47 2	63.81 5	93.18 32	74.02 93	93.25 2	94.80 1

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

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

CNVR-MVS		81.76 9	81.90 8	81.33 18	90.04 10	57.70 14	91.71 11	88.87 39	70.31 27	77.64 41	93.87 8	52.58 48	93.91 26	84.17 19	87.92 16	92.39 33

PS-MVSNAJ		80.06 17	79.52 18	81.68 14	85.58 64	60.97 3	91.69 12	87.02 78	70.62 24	80.75 22	93.22 28	37.77 216	92.50 46	82.75 29	86.25 35	91.57 60

xiu_mvs_v2_base		79.86 18	79.31 19	81.53 15	85.03 76	60.73 4	91.65 13	86.86 81	70.30 28	80.77 21	93.07 33	37.63 221	92.28 52	82.73 30	85.71 39	91.57 60

CANet		80.90 11	81.17 12	80.09 37	87.62 41	54.21 96	91.60 14	86.47 90	73.13 9	79.89 27	93.10 29	49.88 72	92.98 33	84.09 21	84.75 50	93.08 19

lupinMVS		78.38 29	78.11 29	79.19 45	83.02 122	55.24 63	91.57 15	84.82 134	69.12 37	76.67 44	92.02 54	44.82 132	90.23 107	80.83 45	80.09 86	92.08 41

NCCC		79.57 20	79.23 20	80.59 24	89.50 15	56.99 26	91.38 16	88.17 57	67.71 52	73.81 65	92.75 38	46.88 95	93.28 30	78.79 56	84.07 55	91.50 64

test_yl		75.85 71	74.83 82	78.91 54	88.08 37	51.94 152	91.30 17	89.28 29	57.91 236	71.19 100	89.20 122	42.03 172	92.77 38	69.41 120	75.07 151	92.01 46

DCV-MVSNet		75.85 71	74.83 82	78.91 54	88.08 37	51.94 152	91.30 17	89.28 29	57.91 236	71.19 100	89.20 122	42.03 172	92.77 38	69.41 120	75.07 151	92.01 46

LFMVS		78.52 25	77.14 44	82.67 3	89.58 13	58.90 8	91.27 19	88.05 60	63.22 136	74.63 56	90.83 84	41.38 181	94.40 20	75.42 81	79.90 91	94.72 2

VDD-MVS		76.08 66	74.97 78	79.44 41	84.27 91	53.33 119	91.13 20	85.88 102	65.33 97	72.37 85	89.34 119	32.52 294	92.76 40	77.90 66	75.96 136	92.22 39

DeepPCF-MVS	69.37 1	80.65 13	81.56 11	77.94 85	85.46 67	49.56 206	90.99 21	86.66 86	70.58 25	80.07 26	95.30 1	56.18 26	90.97 87	82.57 31	86.22 36	93.28 13

VNet		77.99 37	77.92 32	78.19 78	87.43 43	50.12 194	90.93 22	91.41 8	67.48 56	75.12 51	90.15 104	46.77 98	91.00 84	73.52 98	78.46 104	93.44 9

CLD-MVS		75.60 77	75.39 70	76.24 123	80.69 191	52.40 142	90.69 23	86.20 96	74.40 6	65.01 162	88.93 126	42.05 171	90.58 96	76.57 72	73.96 161	85.73 216
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
jason		77.01 49	76.45 53	78.69 63	79.69 206	54.74 80	90.56 24	83.99 158	68.26 40	74.10 62	90.91 81	42.14 169	89.99 112	79.30 50	79.12 98	91.36 68
jason: jason.
IB-MVS	68.87 2	74.01 101	72.03 126	79.94 38	83.04 121	55.50 53	90.24 25	88.65 46	67.14 60	61.38 211	81.74 249	53.21 44	94.28 21	60.45 194	62.41 269	90.03 111
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
VDDNet		74.37 96	72.13 121	81.09 20	79.58 207	56.52 37	90.02 26	86.70 85	52.61 305	71.23 99	87.20 165	31.75 304	93.96 25	74.30 91	75.77 139	92.79 27

TSAR-MVS + GP.		77.82 38	77.59 37	78.49 69	85.25 72	50.27 193	90.02 26	90.57 17	56.58 267	74.26 61	91.60 68	54.26 38	92.16 55	75.87 75	79.91 90	93.05 20

DeepC-MVS_fast	67.50 3	78.00 36	77.63 36	79.13 49	88.52 27	55.12 69	89.95 28	85.98 101	68.31 39	71.33 98	92.75 38	45.52 117	90.37 100	71.15 110	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
HPM-MVS++		80.50 14	80.71 14	79.88 39	87.34 44	55.20 67	89.93 29	87.55 72	66.04 86	79.46 29	93.00 35	53.10 45	91.76 63	80.40 46	89.56 9	92.68 29

MG-MVS		78.42 28	76.99 46	82.73 2	93.17 1	64.46 1	89.93 29	88.51 53	64.83 102	73.52 68	88.09 147	48.07 80	92.19 54	62.24 174	84.53 52	91.53 62

VPNet		72.07 139	71.42 134	74.04 193	78.64 232	47.17 280	89.91 31	87.97 61	72.56 12	64.66 165	85.04 192	41.83 176	88.33 173	61.17 184	60.97 276	86.62 197

alignmvs		78.08 35	77.98 30	78.39 74	83.53 104	53.22 122	89.77 32	85.45 110	66.11 81	76.59 46	91.99 56	54.07 41	89.05 140	77.34 69	77.00 118	92.89 23

APDe-MVS		78.44 27	78.20 27	79.19 45	88.56 26	54.55 89	89.76 33	87.77 66	55.91 273	78.56 34	92.49 44	48.20 79	92.65 42	79.49 48	83.04 59	90.39 96
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
SteuartSystems-ACMMP		77.08 48	76.33 55	79.34 43	80.98 179	55.31 61	89.76 33	86.91 80	62.94 141	71.65 92	91.56 69	42.33 165	92.56 45	77.14 70	83.69 57	90.15 107
Skip Steuart: Steuart Systems R&D Blog.
Anonymous202405211		70.11 174	67.88 192	76.79 117	87.20 45	47.24 279	89.49 35	77.38 288	54.88 287	66.14 145	86.84 170	20.93 373	91.54 68	56.45 236	71.62 184	91.59 58

SPE-MVS-test		77.20 46	77.25 42	77.05 104	84.60 82	49.04 221	89.42 36	85.83 104	65.90 87	72.85 77	91.98 58	45.10 123	91.27 74	75.02 85	84.56 51	90.84 84

WBMVS		73.93 103	73.39 97	75.55 147	87.82 39	55.21 65	89.37 37	87.29 74	67.27 57	63.70 184	80.30 261	60.32 6	86.47 238	61.58 180	62.85 266	84.97 228

DP-MVS Recon		71.99 141	70.31 154	77.01 107	90.65 8	53.44 113	89.37 37	82.97 179	56.33 270	63.56 188	89.47 116	34.02 280	92.15 57	54.05 250	72.41 176	85.43 223

EPNet		78.36 30	78.49 25	77.97 82	85.49 66	52.04 150	89.36 39	84.07 155	73.22 8	77.03 43	91.72 63	49.32 76	90.17 109	73.46 99	82.77 60	91.69 55
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
save fliter					85.35 69	56.34 41	89.31 40	81.46 202	61.55 164

CSCG		80.41 15	79.72 16	82.49 5	89.12 25	57.67 15	89.29 41	91.54 5	59.19 210	71.82 91	90.05 106	59.72 10	96.04 10	78.37 59	88.40 14	93.75 7

MAR-MVS		76.76 55	75.60 64	80.21 31	90.87 7	54.68 85	89.14 42	89.11 32	62.95 140	70.54 112	92.33 47	41.05 182	94.95 17	57.90 220	86.55 32	91.00 80
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
test_prior2							89.04 43		61.88 159	73.55 67	91.46 72	48.01 82		74.73 86	85.46 42

ET-MVSNet_ETH3D		75.23 84	74.08 91	78.67 64	84.52 84	55.59 51	88.92 44	89.21 31	68.06 46	53.13 318	90.22 100	49.71 73	87.62 204	72.12 106	70.82 192	92.82 25

PVSNet_Blended		76.53 57	76.54 52	76.50 119	85.91 57	51.83 156	88.89 45	84.24 152	67.82 50	69.09 120	89.33 121	46.70 99	88.13 181	75.43 79	81.48 73	89.55 121

Anonymous20240529		69.71 185	67.28 207	77.00 108	83.78 100	50.36 188	88.87 46	85.10 128	47.22 342	64.03 178	83.37 216	27.93 325	92.10 58	57.78 223	67.44 218	88.53 152

DPE-MVS		79.82 19	79.66 17	80.29 30	89.27 24	55.08 72	88.70 47	87.92 62	55.55 278	81.21 20	93.69 14	56.51 24	94.27 22	78.36 60	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
CS-MVS		76.77 54	76.70 50	76.99 109	83.55 103	48.75 231	88.60 48	85.18 123	66.38 74	72.47 84	91.62 67	45.53 116	90.99 86	74.48 88	82.51 62	91.23 72

PHI-MVS		77.49 43	77.00 45	78.95 53	85.33 70	50.69 176	88.57 49	88.59 51	58.14 231	73.60 66	93.31 25	43.14 157	93.79 27	73.81 96	88.53 13	92.37 34

WTY-MVS		77.47 44	77.52 39	77.30 97	88.33 30	46.25 295	88.46 50	90.32 19	71.40 20	72.32 86	91.72 63	53.44 43	92.37 49	66.28 143	75.42 143	93.28 13

9.14			78.19 28		85.67 62		88.32 51	88.84 41	59.89 193	74.58 58	92.62 41	46.80 96	92.66 41	81.40 43	85.62 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 11	70.62 111	88.37 138	57.69 19	92.30 50	75.25 83	76.24 132	91.20 73

MVS_111021_HR		76.39 60	75.38 71	79.42 42	85.33 70	56.47 38	88.15 53	84.97 130	65.15 100	66.06 147	89.88 109	43.79 143	92.16 55	75.03 84	80.03 89	89.64 119

patch_mono-2		80.84 12	81.59 10	78.62 66	90.34 9	53.77 104	88.08 54	88.36 55	76.17 2	79.40 31	91.09 73	55.43 29	90.09 110	85.01 14	80.40 82	91.99 48

MS-PatchMatch		72.34 132	71.26 136	75.61 143	82.38 142	55.55 52	88.00 55	89.95 22	65.38 95	56.51 289	80.74 259	32.28 297	92.89 34	57.95 218	88.10 15	78.39 329

HQP-NCC					79.02 220		88.00 55		65.45 91	64.48 171

ACMP_Plane					79.02 220		88.00 55		65.45 91	64.48 171

HQP-MVS		72.34 132	71.44 133	75.03 168	79.02 220	51.56 162	88.00 55	83.68 162	65.45 91	64.48 171	85.13 189	37.35 228	88.62 158	66.70 138	73.12 168	84.91 230

testing99		78.45 26	77.78 35	80.45 28	88.28 33	56.81 32	87.95 59	91.49 6	71.72 16	70.84 105	88.09 147	57.29 21	92.63 44	69.24 123	75.13 149	91.91 49

testing91		78.30 32	77.54 38	80.61 23	88.16 35	57.12 25	87.94 60	91.07 15	71.43 19	70.75 106	88.04 151	55.82 28	92.65 42	69.61 119	75.00 153	92.05 44

casdiffmvs_mvg		77.75 40	77.28 41	79.16 47	80.42 197	54.44 91	87.76 61	85.46 109	71.67 17	71.38 97	88.35 140	51.58 52	91.22 77	79.02 52	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
sasdasda		78.17 33	77.86 33	79.12 50	84.30 88	54.22 94	87.71 62	84.57 143	67.70 53	77.70 39	92.11 52	50.90 59	89.95 113	78.18 63	77.54 113	93.20 15

canonicalmvs		78.17 33	77.86 33	79.12 50	84.30 88	54.22 94	87.71 62	84.57 143	67.70 53	77.70 39	92.11 52	50.90 59	89.95 113	78.18 63	77.54 113	93.20 15

UBG		78.86 24	78.86 22	78.86 57	87.80 40	55.43 55	87.67 64	91.21 11	72.83 10	72.10 88	88.40 137	58.53 17	89.08 138	73.21 103	77.98 108	92.08 41

VPA-MVSNet		71.12 157	70.66 145	72.49 234	78.75 226	44.43 317	87.64 65	90.02 20	63.97 119	65.02 161	81.58 252	42.14 169	87.42 211	63.42 167	63.38 257	85.63 220

test_8					85.72 59	55.31 61	87.60 66	83.88 159	57.84 239	72.84 78	90.99 75	44.99 126	88.34 172

TEST9					85.68 60	55.42 56	87.59 67	84.00 156	57.72 241	72.99 74	90.98 76	44.87 130	88.58 161

train_agg		76.91 50	76.40 54	78.45 72	85.68 60	55.42 56	87.59 67	84.00 156	57.84 239	72.99 74	90.98 76	44.99 126	88.58 161	78.19 61	85.32 44	91.34 70

SMA-MVS		79.10 23	78.76 24	80.12 35	84.42 85	55.87 49	87.58 69	86.76 83	61.48 167	80.26 25	93.10 29	46.53 101	92.41 48	79.97 47	88.77 11	92.08 41
Yufeng Yin; Xiaoyan Liu; Zichao Zhang: SMA-MVS: Segmentation-Guided Multi-Scale Anchor Deformation Patch Multi-View Stereo. IEEE Transactions on Circuits and Systems for Video Technology
plane_prior						49.57 204	87.43 70		64.57 104						72.84 172

EC-MVSNet		75.30 80	75.20 72	75.62 142	80.98 179	49.00 222	87.43 70	84.68 140	63.49 131	70.97 104	90.15 104	42.86 162	91.14 81	74.33 90	81.90 68	86.71 196

TR-MVS		69.71 185	67.85 195	75.27 163	82.94 126	48.48 240	87.40 72	80.86 215	57.15 255	64.61 168	87.08 167	32.67 293	89.64 123	46.38 304	71.55 186	87.68 174

CDPH-MVS		76.05 67	75.19 73	78.62 66	86.51 51	54.98 75	87.32 73	84.59 142	58.62 225	70.75 106	90.85 83	43.10 159	90.63 95	70.50 113	84.51 53	90.24 101

3Dnovator+	62.71 7	72.29 135	70.50 147	77.65 90	83.40 109	51.29 170	87.32 73	86.40 92	59.01 217	58.49 255	88.32 142	32.40 295	91.27 74	57.04 229	82.15 67	90.38 97

API-MVS		74.17 99	72.07 123	80.49 25	90.02 11	58.55 9	87.30 75	84.27 149	57.51 247	65.77 153	87.77 156	41.61 178	95.97 11	51.71 267	82.63 61	86.94 186

BH-RMVSNet		70.08 176	68.01 188	76.27 122	84.21 92	51.22 172	87.29 76	79.33 251	58.96 219	63.63 186	86.77 171	33.29 288	90.30 105	44.63 313	73.96 161	87.30 183

MTMP							87.27 77	15.34 439

APD-MVS		76.15 64	75.68 62	77.54 92	88.52 27	53.44 113	87.26 78	85.03 129	53.79 295	74.91 54	91.68 65	43.80 142	90.31 103	74.36 89	81.82 69	88.87 141
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
testing222		77.70 41	77.22 43	79.14 48	86.95 46	54.89 78	87.18 79	91.96 2	72.29 13	71.17 102	88.70 131	55.19 30	91.24 76	65.18 158	76.32 130	91.29 71

EIA-MVS		75.92 69	75.18 74	78.13 79	85.14 73	51.60 161	87.17 80	85.32 116	64.69 103	68.56 124	90.53 89	45.79 112	91.58 67	67.21 136	82.18 66	91.20 73

test_prior4						56.39 40	87.15 81

casdiffmvs		77.36 45	76.85 47	78.88 56	80.40 198	54.66 87	87.06 82	85.88 102	72.11 14	71.57 94	88.63 136	50.89 62	90.35 101	76.00 74	79.11 99	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
cascas		69.01 198	66.13 229	77.66 89	79.36 210	55.41 58	86.99 83	83.75 161	56.69 264	58.92 245	81.35 253	24.31 353	92.10 58	53.23 254	70.61 194	85.46 222

nrg030		72.27 137	71.56 130	74.42 181	75.93 282	50.60 178	86.97 84	83.21 173	62.75 143	67.15 135	84.38 198	50.07 67	86.66 232	71.19 109	62.37 270	85.99 210

114514_t		69.87 183	67.88 192	75.85 137	88.38 29	52.35 144	86.94 85	83.68 162	53.70 296	55.68 295	85.60 185	30.07 315	91.20 78	55.84 240	71.02 190	83.99 245

CP-MVS		72.59 129	71.46 132	76.00 134	82.93 127	52.32 145	86.93 86	82.48 185	55.15 282	63.65 185	90.44 94	35.03 269	88.53 165	68.69 127	77.83 111	87.15 184

ZNCC-MVS		75.82 74	75.02 77	78.23 77	83.88 99	53.80 103	86.91 87	86.05 100	59.71 196	67.85 131	90.55 88	42.23 167	91.02 83	72.66 105	85.29 45	89.87 116

PAPM		76.76 55	76.07 59	78.81 58	80.20 199	59.11 7	86.86 88	86.23 95	68.60 38	70.18 114	88.84 129	51.57 53	87.16 217	65.48 151	86.68 30	90.15 107

UWE-MVS		72.17 138	72.15 120	72.21 241	82.26 144	44.29 319	86.83 89	89.58 25	65.58 90	65.82 151	85.06 191	45.02 125	84.35 285	54.07 249	75.18 146	87.99 167

Fast-Effi-MVS+		72.73 125	71.15 139	77.48 93	82.75 134	54.76 79	86.77 90	80.64 218	63.05 139	65.93 149	84.01 203	44.42 137	89.03 141	56.45 236	76.36 129	88.64 147

thisisatest0515		73.64 112	72.20 118	77.97 82	81.63 162	53.01 129	86.69 91	88.81 42	62.53 147	64.06 177	85.65 184	52.15 51	92.50 46	58.43 207	69.84 200	88.39 157

SF-MVS		77.64 42	77.42 40	78.32 76	83.75 101	52.47 141	86.63 92	87.80 63	58.78 222	74.63 56	92.38 46	47.75 85	91.35 72	78.18 63	86.85 27	91.15 76

BH-w/o		70.02 178	68.51 180	74.56 177	82.77 133	50.39 185	86.60 93	78.14 274	59.77 195	59.65 228	85.57 186	39.27 204	87.30 214	49.86 278	74.94 154	85.99 210

DeepC-MVS	67.15 4	76.90 52	76.27 56	78.80 59	80.70 190	55.02 73	86.39 94	86.71 84	66.96 66	67.91 130	89.97 108	48.03 81	91.41 71	75.60 78	84.14 54	89.96 113
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
TransMVSNet (Re)		62.82 284	60.76 286	69.02 297	73.98 311	41.61 349	86.36 95	79.30 252	56.90 257	52.53 321	76.44 307	41.85 175	87.60 205	38.83 334	40.61 387	77.86 335

MSLP-MVS++		74.21 98	72.25 117	80.11 36	81.45 172	56.47 38	86.32 96	79.65 240	58.19 230	66.36 144	92.29 48	36.11 255	90.66 93	67.39 134	82.49 63	93.18 17

QAPM		71.88 144	69.33 171	79.52 40	82.20 146	54.30 93	86.30 97	88.77 43	56.61 266	59.72 227	87.48 160	33.90 282	95.36 13	47.48 295	81.49 72	88.90 139

WR-MVS		67.58 228	66.76 215	70.04 288	75.92 283	45.06 313	86.23 98	85.28 119	64.31 108	58.50 254	81.00 254	44.80 134	82.00 308	49.21 284	55.57 329	83.06 267

PVSNet_BlendedMVS		73.42 114	73.30 99	73.76 204	85.91 57	51.83 156	86.18 99	84.24 152	65.40 94	69.09 120	80.86 257	46.70 99	88.13 181	75.43 79	65.92 235	81.33 294

ETV-MVS		77.17 47	76.74 49	78.48 70	81.80 154	54.55 89	86.13 100	85.33 115	68.20 41	73.10 73	90.52 90	45.23 122	90.66 93	79.37 49	80.95 74	90.22 102

AdaColmap		67.86 221	65.48 245	75.00 170	88.15 36	54.99 74	86.10 101	76.63 303	49.30 327	57.80 264	86.65 175	29.39 318	88.94 149	45.10 310	70.21 198	81.06 299

myMVS_eth3d28		77.77 39	77.94 31	77.27 99	87.58 42	52.89 133	86.06 102	91.33 10	74.15 7	68.16 128	88.24 144	58.17 18	88.31 175	69.88 118	77.87 109	90.61 90

OPM-MVS		70.75 167	69.58 166	74.26 187	75.55 288	51.34 168	86.05 103	83.29 172	61.94 158	62.95 194	85.77 183	34.15 279	88.44 167	65.44 155	71.07 189	82.99 268
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
Vis-MVSNet		70.61 169	69.34 170	74.42 181	80.95 184	48.49 239	86.03 104	77.51 285	58.74 223	65.55 155	87.78 155	34.37 277	85.95 261	52.53 265	80.61 78	88.80 143
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
Anonymous20231211		66.08 262	63.67 265	73.31 215	83.07 119	48.75 231	86.01 105	84.67 141	45.27 356	56.54 287	76.67 305	28.06 324	88.95 147	52.78 261	59.95 279	82.23 276

fmvsm_s_conf0.5_n_4		74.92 91	74.88 80	75.03 168	75.96 281	47.53 272	85.84 106	73.19 339	67.07 63	79.43 30	92.60 42	46.12 105	88.03 186	84.70 16	69.01 206	89.53 123

EG-PatchMatch MVS		62.40 291	59.59 295	70.81 274	73.29 316	49.05 219	85.81 107	84.78 136	51.85 312	44.19 364	73.48 338	15.52 396	89.85 115	40.16 331	67.24 219	73.54 374

PVSNet_Blended_VisFu		73.40 115	72.44 111	76.30 121	81.32 176	54.70 83	85.81 107	78.82 258	63.70 124	64.53 170	85.38 188	47.11 92	87.38 213	67.75 133	77.55 112	86.81 195

HQP_MVS		70.96 163	69.91 162	74.12 191	77.95 242	49.57 204	85.76 109	82.59 183	63.60 127	62.15 203	83.28 218	36.04 258	88.30 176	65.46 152	72.34 178	84.49 234

plane_prior2							85.76 109		63.60 127

GST-MVS		74.87 92	73.90 94	77.77 86	83.30 111	53.45 112	85.75 111	85.29 118	59.22 209	66.50 143	89.85 110	40.94 184	90.76 90	70.94 111	83.35 58	89.10 136

SD-MVS		76.18 62	74.85 81	80.18 32	85.39 68	56.90 28	85.75 111	82.45 186	56.79 262	74.48 59	91.81 60	43.72 146	90.75 91	74.61 87	78.65 102	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
CHOSEN 1792x2688		76.24 61	74.03 93	82.88 1	83.09 118	62.84 2	85.73 113	85.39 112	69.79 30	64.87 164	83.49 213	41.52 180	93.69 29	70.55 112	81.82 69	92.12 40

WB-MVSnew		69.36 194	68.24 185	72.72 228	79.26 214	49.40 213	85.72 114	88.85 40	61.33 168	64.59 169	82.38 237	34.57 275	87.53 207	46.82 301	70.63 193	81.22 298

FMVSNet3		68.84 201	67.40 205	73.19 218	85.05 74	48.53 237	85.71 115	85.36 113	60.90 181	57.58 270	79.15 274	42.16 168	86.77 228	47.25 297	63.40 254	84.27 238

MP-MVS		74.99 89	74.33 88	76.95 111	82.89 129	53.05 128	85.63 116	83.50 167	57.86 238	67.25 134	90.24 98	43.38 154	88.85 154	76.03 73	82.23 65	88.96 138
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
HFP-MVS		74.37 96	73.13 105	78.10 80	84.30 88	53.68 106	85.58 117	84.36 147	56.82 260	65.78 152	90.56 87	40.70 189	90.90 88	69.18 124	80.88 75	89.71 117

ACMMPR		73.76 107	72.61 107	77.24 102	83.92 97	52.96 131	85.58 117	84.29 148	56.82 260	65.12 158	90.45 91	37.24 233	90.18 108	69.18 124	80.84 76	88.58 149

BH-untuned		68.28 214	66.40 222	73.91 198	81.62 163	50.01 196	85.56 119	77.39 287	57.63 244	57.47 275	83.69 210	36.36 252	87.08 219	44.81 311	73.08 171	84.65 233

ETVMVS		75.80 75	75.44 68	76.89 113	86.23 55	50.38 186	85.55 120	91.42 7	71.30 22	68.80 122	87.94 153	56.42 25	89.24 133	56.54 232	74.75 157	91.07 78

region2R		73.75 108	72.55 109	77.33 96	83.90 98	52.98 130	85.54 121	84.09 154	56.83 259	65.10 159	90.45 91	37.34 230	90.24 106	68.89 126	80.83 77	88.77 145

fmvsm_s_conf0.5_n_6		76.17 63	76.84 48	74.15 190	77.42 252	46.46 288	85.53 122	77.86 278	69.78 31	79.78 28	92.90 36	46.80 96	84.81 280	84.67 17	76.86 122	91.17 75

testing3-2		72.30 134	72.35 113	72.15 243	83.07 119	47.64 270	85.46 123	89.81 24	66.17 79	61.96 206	84.88 196	58.93 12	82.27 303	55.87 238	64.97 239	86.54 198

fmvsm_l_conf0.5_n_3		75.73 76	75.78 61	75.61 143	76.03 278	48.33 247	85.34 124	72.92 340	67.16 59	78.55 35	93.85 10	46.22 103	87.53 207	85.61 12	76.30 131	90.98 81

xiu_mvs_v1_base_debu		71.60 150	70.29 155	75.55 147	77.26 255	53.15 123	85.34 124	79.37 245	55.83 274	72.54 80	90.19 101	22.38 364	86.66 232	73.28 100	76.39 126	86.85 190

xiu_mvs_v1_base		71.60 150	70.29 155	75.55 147	77.26 255	53.15 123	85.34 124	79.37 245	55.83 274	72.54 80	90.19 101	22.38 364	86.66 232	73.28 100	76.39 126	86.85 190

xiu_mvs_v1_base_debi		71.60 150	70.29 155	75.55 147	77.26 255	53.15 123	85.34 124	79.37 245	55.83 274	72.54 80	90.19 101	22.38 364	86.66 232	73.28 100	76.39 126	86.85 190

fmvsm_s_conf0.5_n		74.48 93	74.12 90	75.56 146	76.96 262	47.85 266	85.32 128	69.80 365	64.16 113	78.74 32	93.48 19	45.51 118	89.29 131	86.48 9	66.62 224	89.55 121

NR-MVSNet		67.25 239	65.99 233	71.04 271	73.27 318	43.91 324	85.32 128	84.75 138	66.05 85	53.65 316	82.11 244	45.05 124	85.97 260	47.55 294	56.18 321	83.24 262

fmvsm_l_conf0.5_n_a		75.88 70	76.07 59	75.31 157	76.08 275	48.34 245	85.24 130	70.62 358	63.13 138	81.45 19	93.62 17	49.98 70	87.40 212	87.76 6	76.77 123	90.20 104

GDP-MVS		75.27 82	74.38 87	77.95 84	79.04 219	52.86 134	85.22 131	86.19 97	62.43 151	70.66 109	90.40 95	53.51 42	91.60 66	69.25 122	72.68 174	89.39 127

Effi-MVS+		75.24 83	73.61 96	80.16 33	81.92 151	57.42 21	85.21 132	76.71 301	60.68 185	73.32 71	89.34 119	47.30 89	91.63 65	68.28 130	79.72 93	91.42 65

无先验							85.19 133	78.00 276	49.08 328				85.13 275	52.78 261		87.45 179

fmvsm_s_conf0.5_n_8		76.50 58	76.68 51	75.94 135	78.67 228	47.92 264	85.18 134	74.71 319	68.09 42	80.67 23	94.26 3	47.09 93	89.26 132	86.62 8	74.85 155	90.65 88

FMVSNet2		67.57 229	65.79 238	72.90 223	82.71 135	47.97 261	85.15 135	84.93 131	58.55 226	56.71 285	78.26 281	36.72 247	86.67 231	46.15 306	62.94 265	84.07 242

test-LLR		69.65 189	69.01 175	71.60 260	78.67 228	48.17 252	85.13 136	79.72 237	59.18 212	63.13 191	82.58 231	36.91 242	80.24 326	60.56 190	75.17 147	86.39 204

TESTMET0.1,1		72.86 123	72.33 114	74.46 179	81.98 148	50.77 174	85.13 136	85.47 108	66.09 82	67.30 133	83.69 210	37.27 231	83.57 295	65.06 160	78.97 101	89.05 137

test-mter		68.36 211	67.29 206	71.60 260	78.67 228	48.17 252	85.13 136	79.72 237	53.38 299	63.13 191	82.58 231	27.23 331	80.24 326	60.56 190	75.17 147	86.39 204

1112_ss		70.05 177	69.37 169	72.10 244	80.77 189	42.78 339	85.12 139	76.75 298	59.69 197	61.19 213	92.12 50	47.48 88	83.84 290	53.04 257	68.21 211	89.66 118

XXY-MVS		70.18 173	69.28 173	72.89 225	77.64 246	42.88 338	85.06 140	87.50 73	62.58 146	62.66 198	82.34 241	43.64 148	89.83 116	58.42 209	63.70 252	85.96 212

MSP-MVS		82.30 6	83.47 1	78.80 59	82.99 124	52.71 136	85.04 141	88.63 48	66.08 83	86.77 3	92.75 38	72.05 1	91.46 70	83.35 25	93.53 1	92.23 37
Zhenlong Yuan, Cong Liu, Fei Shen, Zhaoxin Li, Jingguo luo, Tianlu Mao and Zhaoqi Wang: MSP-MVS: Multi-granularity Segmentation Prior Guided Multi-View Stereo. AAAI2025
thres200		68.71 206	67.27 208	73.02 219	84.73 79	46.76 283	85.03 142	87.73 67	62.34 152	59.87 224	83.45 214	43.15 156	88.32 174	31.25 371	67.91 215	83.98 247

MVP-Stereo		70.97 162	70.44 148	72.59 231	76.03 278	51.36 167	85.02 143	86.99 79	60.31 189	56.53 288	78.92 276	40.11 196	90.00 111	60.00 198	90.01 7	76.41 351
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
fmvsm_l_conf0.5_n		75.95 68	76.16 58	75.31 157	76.01 280	48.44 242	84.98 144	71.08 355	63.50 130	81.70 18	93.52 18	50.00 68	87.18 216	87.80 5	76.87 121	90.32 99

DVP-MVS++		82.44 3	82.38 6	82.62 4	91.77 4	57.49 17	84.98 144	88.88 37	58.00 234	83.60 6	93.39 22	67.21 2	96.39 4	81.64 38	91.98 4	93.98 5

FOURS1					83.24 113	49.90 199	84.98 144	78.76 260	47.71 339	73.42 69

PS-MVSNAJss		68.78 205	67.17 209	73.62 210	73.01 321	48.33 247	84.95 147	84.81 135	59.30 208	58.91 246	79.84 266	37.77 216	88.86 151	62.83 170	63.12 263	83.67 256

v2v482		69.55 191	67.64 198	75.26 164	72.32 331	53.83 102	84.93 148	81.94 192	65.37 96	60.80 217	79.25 272	41.62 177	88.98 146	63.03 169	59.51 285	82.98 269

XVS		72.92 121	71.62 129	76.81 114	83.41 106	52.48 139	84.88 149	83.20 174	58.03 232	63.91 180	89.63 114	35.50 262	89.78 117	65.50 149	80.50 80	88.16 160

X-MVStestdata		65.85 264	62.20 272	76.81 114	83.41 106	52.48 139	84.88 149	83.20 174	58.03 232	63.91 180	4.82 435	35.50 262	89.78 117	65.50 149	80.50 80	88.16 160

dcpmvs_2		79.33 21	78.94 21	80.49 25	89.75 12	56.54 36	84.83 151	83.68 162	67.85 49	69.36 116	90.24 98	60.20 8	92.10 58	84.14 20	80.40 82	92.82 25

test1111		71.06 160	70.42 151	72.97 221	79.48 209	41.49 351	84.82 152	82.74 182	64.20 112	62.98 193	87.43 162	35.20 265	87.92 188	58.54 206	78.42 105	89.49 125

Fast-Effi-MVS+-dtu		66.53 255	64.10 264	73.84 201	72.41 329	52.30 146	84.73 153	75.66 310	59.51 200	56.34 290	79.11 275	28.11 323	85.85 263	57.74 224	63.29 258	83.35 258

BP-MVS1		76.09 65	75.55 65	77.71 88	79.49 208	52.27 147	84.70 154	90.49 18	64.44 105	69.86 115	90.31 97	55.05 34	91.35 72	70.07 116	75.58 142	89.53 123

ECVR-MVS		71.81 145	71.00 141	74.26 187	80.12 201	43.49 328	84.69 155	82.16 187	64.02 115	64.64 166	87.43 162	35.04 268	89.21 136	61.24 183	79.66 94	90.08 109

h-mvs33		73.95 102	72.89 106	77.15 103	80.17 200	50.37 187	84.68 156	83.33 168	68.08 43	71.97 89	88.65 135	42.50 163	91.15 80	78.82 54	57.78 310	89.91 115

v1144		68.81 203	66.82 213	74.80 175	72.34 330	53.46 110	84.68 156	81.77 199	64.25 110	60.28 221	77.91 283	40.23 193	88.95 147	60.37 195	59.52 284	81.97 278

CANet_DTU		73.71 109	73.14 103	75.40 153	82.61 139	50.05 195	84.67 158	79.36 248	69.72 33	75.39 50	90.03 107	29.41 317	85.93 262	67.99 132	79.11 99	90.22 102

test_vis1_n_1920		68.59 209	68.31 183	69.44 294	69.16 358	41.51 350	84.63 159	68.58 371	58.80 221	73.26 72	88.37 138	25.30 344	80.60 321	79.10 51	67.55 217	86.23 206

PVSNet	62.49 8	69.27 195	67.81 196	73.64 208	84.41 86	51.85 155	84.63 159	77.80 279	66.42 73	59.80 226	84.95 194	22.14 368	80.44 324	55.03 243	75.11 150	88.62 148

fmvsm_s_conf0.1_n		73.80 106	73.26 100	75.43 152	73.28 317	47.80 268	84.57 161	69.43 367	63.34 133	78.40 36	93.29 26	44.73 135	89.22 135	85.99 10	66.28 232	89.26 129

fmvsm_s_conf0.5_n_2		72.02 140	71.72 128	72.92 222	76.79 264	45.90 299	84.48 162	66.11 378	64.26 109	76.12 48	93.40 21	36.26 253	86.04 255	81.47 40	66.54 227	86.82 194

mPP-MVS		71.79 147	70.38 152	76.04 132	82.65 138	52.06 149	84.45 163	81.78 198	55.59 277	62.05 205	89.68 113	33.48 286	88.28 178	65.45 154	78.24 107	87.77 171

CL-MVSNet_self_test		62.98 282	61.14 283	68.50 309	65.86 375	42.96 336	84.37 164	82.98 178	60.98 177	53.95 312	72.70 345	40.43 191	83.71 293	41.10 328	47.93 363	78.83 321

OpenMVS	61.00 11	69.99 180	67.55 201	77.30 97	78.37 238	54.07 101	84.36 165	85.76 105	57.22 253	56.71 285	87.67 158	30.79 310	92.83 36	43.04 321	84.06 56	85.01 227

MP-MVS-pluss		75.54 79	75.03 76	77.04 105	81.37 174	52.65 138	84.34 166	84.46 145	61.16 171	69.14 119	91.76 61	39.98 199	88.99 145	78.19 61	84.89 49	89.48 126
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
PAPR		75.20 85	74.13 89	78.41 73	88.31 32	55.10 71	84.31 167	85.66 106	63.76 123	67.55 132	90.73 86	43.48 151	89.40 127	66.36 142	77.03 117	90.73 87

SR-MVS		70.92 164	69.73 164	74.50 178	83.38 110	50.48 182	84.27 168	79.35 249	48.96 330	66.57 142	90.45 91	33.65 285	87.11 218	66.42 140	74.56 158	85.91 213

v148		68.24 216	66.35 223	73.88 199	71.76 335	51.47 165	84.23 169	81.90 196	63.69 125	58.94 243	76.44 307	43.72 146	87.78 196	60.63 188	55.86 326	82.39 275

UniMVSNet_NR-MVSNet		68.82 202	68.29 184	70.40 281	75.71 285	42.59 341	84.23 169	86.78 82	66.31 75	58.51 252	82.45 234	51.57 53	84.64 283	53.11 255	55.96 324	83.96 249

fmvsm_s_conf0.1_n_2		71.45 153	71.01 140	72.78 226	75.37 290	45.82 303	84.18 171	64.59 383	64.02 115	75.67 49	93.02 34	34.99 270	85.99 257	81.18 44	66.04 234	86.52 200

GeoE		69.96 181	67.88 192	76.22 124	81.11 178	51.71 159	84.15 172	76.74 300	59.83 194	60.91 215	84.38 198	41.56 179	88.10 183	51.67 268	70.57 195	88.84 142

v144192		67.86 221	65.76 239	74.16 189	71.68 336	53.09 126	84.14 173	80.83 216	62.85 142	59.21 240	77.28 294	39.30 203	88.00 187	58.67 205	57.88 308	81.40 291

UGNet		68.71 206	67.11 210	73.50 213	80.55 195	47.61 271	84.08 174	78.51 267	59.45 201	65.68 154	82.73 227	23.78 355	85.08 276	52.80 260	76.40 125	87.80 170
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
PMMVS		72.98 120	72.05 124	75.78 138	83.57 102	48.60 234	84.08 174	82.85 181	61.62 163	68.24 127	90.33 96	28.35 321	87.78 196	72.71 104	76.69 124	90.95 82

ACMMP_NAP		76.43 59	75.66 63	78.73 61	81.92 151	54.67 86	84.06 176	85.35 114	61.10 174	72.99 74	91.50 70	40.25 192	91.00 84	76.84 71	86.98 25	90.51 94

v1192		67.96 220	65.74 240	74.63 176	71.79 334	53.43 115	84.06 176	80.99 214	63.19 137	59.56 231	77.46 290	37.50 227	88.65 157	58.20 213	58.93 291	81.79 281

fmvsm_s_conf0.5_n_5		75.02 88	75.07 75	74.88 173	74.33 306	47.83 267	83.99 178	73.54 333	67.10 61	76.32 47	92.43 45	45.42 119	86.35 244	82.98 27	79.50 97	90.47 95

FIs		70.00 179	70.24 158	69.30 295	77.93 244	38.55 365	83.99 178	87.72 68	66.86 67	57.66 268	84.17 201	52.28 49	85.31 269	52.72 264	68.80 208	84.02 243

MVS_Test		75.85 71	74.93 79	78.62 66	84.08 93	55.20 67	83.99 178	85.17 124	68.07 45	73.38 70	82.76 224	50.44 65	89.00 143	65.90 147	80.61 78	91.64 56

reproduce_monomvs		69.71 185	68.52 179	73.29 217	86.43 53	48.21 251	83.91 181	86.17 98	68.02 47	54.91 300	77.46 290	42.96 160	88.86 151	68.44 128	48.38 360	82.80 272

baseline		76.86 53	76.24 57	78.71 62	80.47 196	54.20 98	83.90 182	84.88 133	71.38 21	71.51 95	89.15 124	50.51 64	90.55 97	75.71 76	78.65 102	91.39 66

fmvsm_s_conf0.5_n_a		73.68 111	73.15 101	75.29 160	75.45 289	48.05 258	83.88 183	68.84 370	63.43 132	78.60 33	93.37 24	45.32 120	88.92 150	85.39 13	64.04 247	88.89 140

baseline2		75.15 86	74.54 86	76.98 110	81.67 161	51.74 158	83.84 184	91.94 3	69.97 29	58.98 242	86.02 180	59.73 9	91.73 64	68.37 129	70.40 197	87.48 177

EPP-MVSNet		71.14 156	70.07 160	74.33 184	79.18 216	46.52 287	83.81 185	86.49 89	56.32 271	57.95 261	84.90 195	54.23 39	89.14 137	58.14 214	69.65 203	87.33 181

原ACMM2							83.77 186

v1921920		67.45 232	65.23 252	74.10 192	71.51 339	52.90 132	83.75 187	80.44 222	62.48 150	59.12 241	77.13 295	36.98 240	87.90 189	57.53 225	58.14 302	81.49 286

OpenMVS_ROB	53.19 17	59.20 308	56.00 320	68.83 300	71.13 344	44.30 318	83.64 188	75.02 316	46.42 349	46.48 360	73.03 341	18.69 381	88.14 180	27.74 386	61.80 272	74.05 370

MVSTER		73.25 117	72.33 114	76.01 133	85.54 65	53.76 105	83.52 189	87.16 76	67.06 64	63.88 182	81.66 250	52.77 46	90.44 98	64.66 162	64.69 243	83.84 252

GBi-Net		67.09 244	65.47 246	71.96 250	82.71 135	46.36 290	83.52 189	83.31 169	58.55 226	57.58 270	76.23 311	36.72 247	86.20 245	47.25 297	63.40 254	83.32 259

test1		67.09 244	65.47 246	71.96 250	82.71 135	46.36 290	83.52 189	83.31 169	58.55 226	57.58 270	76.23 311	36.72 247	86.20 245	47.25 297	63.40 254	83.32 259

FMVSNet1		64.57 267	62.11 273	71.96 250	77.32 253	46.36 290	83.52 189	83.31 169	52.43 307	54.42 306	76.23 311	27.80 327	86.20 245	42.59 325	61.34 275	83.32 259

baseline1		72.51 130	72.12 122	73.69 207	85.05 74	44.46 315	83.51 193	86.13 99	71.61 18	64.64 166	87.97 152	55.00 35	89.48 125	59.07 201	56.05 323	87.13 185

CDS-MVSNet		70.48 171	69.43 167	73.64 208	77.56 249	48.83 228	83.51 193	77.45 286	63.27 135	62.33 200	85.54 187	43.85 140	83.29 300	57.38 228	74.00 160	88.79 144
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
thisisatest0530		70.47 172	68.56 178	76.20 126	79.78 205	51.52 164	83.49 195	88.58 52	57.62 245	58.60 251	82.79 223	51.03 58	91.48 69	52.84 259	62.36 271	85.59 221

Test_1112_low_res		67.18 241	66.23 227	70.02 289	78.75 226	41.02 355	83.43 196	73.69 330	57.29 251	58.45 257	82.39 236	45.30 121	80.88 315	50.50 274	66.26 233	88.16 160

ACMMP		70.81 166	69.29 172	75.39 154	81.52 170	51.92 154	83.43 196	83.03 177	56.67 265	58.80 249	88.91 127	31.92 302	88.58 161	65.89 148	73.39 165	85.67 217
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
tfpn200view9		67.57 229	66.13 229	71.89 257	84.05 94	45.07 310	83.40 198	87.71 69	60.79 182	57.79 265	82.76 224	43.53 149	87.80 193	28.80 378	66.36 229	82.78 273

thres400		67.40 237	66.13 229	71.19 268	84.05 94	45.07 310	83.40 198	87.71 69	60.79 182	57.79 265	82.76 224	43.53 149	87.80 193	28.80 378	66.36 229	80.71 304

v1240		66.99 247	64.68 257	73.93 197	71.38 342	52.66 137	83.39 200	79.98 230	61.97 157	58.44 258	77.11 296	35.25 264	87.81 191	56.46 235	58.15 300	81.33 294

Baseline_NR-MVSNet		65.49 266	64.27 262	69.13 296	74.37 305	41.65 348	83.39 200	78.85 256	59.56 199	59.62 230	76.88 302	40.75 186	87.44 210	49.99 276	55.05 331	78.28 331

miper_enhance_ethall		69.77 184	68.90 176	72.38 237	78.93 223	49.91 198	83.29 202	78.85 256	64.90 101	59.37 235	79.46 269	52.77 46	85.16 274	63.78 164	58.72 292	82.08 277

fmvsm_s_conf0.5_n_7		73.10 119	73.89 95	70.72 275	74.17 308	46.03 298	83.28 203	74.19 323	67.10 61	73.94 64	91.73 62	43.42 153	77.61 354	83.92 23	73.26 166	88.53 152

diffmvs		75.11 87	74.65 84	76.46 120	78.52 234	53.35 117	83.28 203	79.94 232	70.51 26	71.64 93	88.72 130	46.02 109	86.08 254	77.52 67	75.75 140	89.96 113
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_cas_vis1_n_1920		67.10 243	66.60 220	68.59 307	65.17 380	43.23 334	83.23 205	69.84 364	55.34 281	70.67 108	87.71 157	24.70 351	76.66 362	78.57 58	64.20 246	85.89 214

test2506		72.91 122	72.43 112	74.32 185	80.12 201	44.18 322	83.19 206	84.77 137	64.02 115	65.97 148	87.43 162	47.67 86	88.72 155	59.08 200	79.66 94	90.08 109

ACMP	61.11 9	66.24 260	64.33 261	72.00 249	74.89 297	49.12 217	83.18 207	79.83 235	55.41 280	52.29 323	82.68 228	25.83 340	86.10 251	60.89 185	63.94 250	80.78 302
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
fmvsm_s_conf0.5_n_3		74.97 90	75.42 69	73.62 210	76.99 261	46.67 284	83.13 208	71.14 354	66.20 78	82.13 13	93.76 12	47.49 87	84.00 288	81.95 35	76.02 133	90.19 106

GA-MVS		69.04 197	66.70 217	76.06 131	75.11 292	52.36 143	83.12 209	80.23 226	63.32 134	60.65 219	79.22 273	30.98 309	88.37 169	61.25 182	66.41 228	87.46 178

3Dnovator	64.70 6	74.46 94	72.48 110	80.41 29	82.84 132	55.40 59	83.08 210	88.61 50	67.61 55	59.85 225	88.66 132	34.57 275	93.97 24	58.42 209	88.70 12	91.85 52

PGM-MVS		72.60 127	71.20 138	76.80 116	82.95 125	52.82 135	83.07 211	82.14 188	56.51 268	63.18 190	89.81 111	35.68 261	89.76 119	67.30 135	80.19 85	87.83 169

LPG-MVS_test		66.44 257	64.58 258	72.02 247	74.42 303	48.60 234	83.07 211	80.64 218	54.69 289	53.75 314	83.83 206	25.73 342	86.98 221	60.33 196	64.71 241	80.48 306

TranMVSNet+NR-MVSNet		66.94 249	65.61 243	70.93 273	73.45 314	43.38 331	83.02 213	84.25 150	65.31 98	58.33 259	81.90 248	39.92 200	85.52 265	49.43 281	54.89 333	83.89 251

test0.0.03 1		62.54 286	62.44 270	62.86 350	72.28 333	29.51 403	82.93 214	78.78 259	59.18 212	53.07 319	82.41 235	36.91 242	77.39 355	37.45 337	58.96 290	81.66 284

pm-mvs1		64.12 271	62.56 269	68.78 302	71.68 336	38.87 363	82.89 215	81.57 200	55.54 279	53.89 313	77.82 285	37.73 219	86.74 229	48.46 290	53.49 345	80.72 303

EPNet_dtu		66.25 259	66.71 216	64.87 338	78.66 231	34.12 382	82.80 216	75.51 311	61.75 160	64.47 174	86.90 169	37.06 238	72.46 381	43.65 319	69.63 204	88.02 166
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
fmvsm_s_conf0.1_n_a		72.82 124	72.05 124	75.12 166	70.95 346	47.97 261	82.72 217	68.43 372	62.52 148	78.17 37	93.08 32	44.21 138	88.86 151	84.82 15	63.54 253	88.54 151

test_fmvsmconf_n		74.41 95	74.05 92	75.49 151	74.16 309	48.38 243	82.66 218	72.57 341	67.05 65	75.11 52	92.88 37	46.35 102	87.81 191	83.93 22	71.71 183	90.28 100

pmmvs5		62.80 285	61.18 282	67.66 313	69.53 355	42.37 346	82.65 219	75.19 315	54.30 294	52.03 326	78.51 279	31.64 305	80.67 319	48.60 288	58.15 300	79.95 313

cl____		67.43 233	65.93 235	71.95 253	76.33 269	48.02 259	82.58 220	79.12 253	61.30 170	56.72 284	76.92 300	46.12 105	86.44 240	57.98 216	56.31 318	81.38 293

DIV-MVS_self_test		67.43 233	65.93 235	71.94 254	76.33 269	48.01 260	82.57 221	79.11 254	61.31 169	56.73 283	76.92 300	46.09 107	86.43 241	57.98 216	56.31 318	81.39 292

TAMVS		69.51 192	68.16 187	73.56 212	76.30 271	48.71 233	82.57 221	77.17 291	62.10 154	61.32 212	84.23 200	41.90 174	83.46 297	54.80 246	73.09 170	88.50 154

EI-MVSNet-Vis-set		73.19 118	72.60 108	74.99 171	82.56 140	49.80 202	82.55 223	89.00 34	66.17 79	65.89 150	88.98 125	43.83 141	92.29 51	65.38 157	69.01 206	82.87 271

reproduce-ours		71.77 148	70.43 149	75.78 138	81.96 149	49.54 209	82.54 224	81.01 212	48.77 332	69.21 117	90.96 78	37.13 236	89.40 127	66.28 143	76.01 134	88.39 157

our_new_method		71.77 148	70.43 149	75.78 138	81.96 149	49.54 209	82.54 224	81.01 212	48.77 332	69.21 117	90.96 78	37.13 236	89.40 127	66.28 143	76.01 134	88.39 157

DP-MVS		59.24 307	56.12 319	68.63 305	88.24 34	50.35 189	82.51 226	64.43 384	41.10 376	46.70 358	78.77 277	24.75 350	88.57 164	22.26 402	56.29 320	66.96 394

miper_ehance_all_eth		68.70 208	67.58 199	72.08 245	76.91 263	49.48 212	82.47 227	78.45 269	62.68 145	58.28 260	77.88 284	50.90 59	85.01 277	61.91 177	58.72 292	81.75 282

cl22		68.85 200	67.69 197	72.35 238	78.07 241	49.98 197	82.45 228	78.48 268	62.50 149	58.46 256	77.95 282	49.99 69	85.17 273	62.55 171	58.72 292	81.90 280

UniMVSNet (Re)		67.71 225	66.80 214	70.45 279	74.44 302	42.93 337	82.42 229	84.90 132	63.69 125	59.63 229	80.99 255	47.18 90	85.23 272	51.17 272	56.75 315	83.19 264

v8		67.25 239	64.99 255	74.04 193	72.89 324	53.31 120	82.37 230	80.11 228	61.54 165	54.29 309	76.02 316	42.89 161	88.41 168	58.43 207	56.36 316	80.39 308

ACMM	58.35 12	64.35 269	62.01 274	71.38 264	74.21 307	48.51 238	82.25 231	79.66 239	47.61 340	54.54 305	80.11 262	25.26 345	86.00 256	51.26 270	63.16 261	79.64 315
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
test_fmvsmconf0.1_n		73.69 110	73.15 101	75.34 155	70.71 347	48.26 249	82.15 232	71.83 346	66.75 68	74.47 60	92.59 43	44.89 129	87.78 196	83.59 24	71.35 187	89.97 112

thres600view7		66.46 256	65.12 253	70.47 278	83.41 106	43.80 326	82.15 232	87.78 64	59.37 204	56.02 292	82.21 242	43.73 144	86.90 226	26.51 390	64.94 240	80.71 304

c3_l		67.97 219	66.66 218	71.91 256	76.20 274	49.31 215	82.13 234	78.00 276	61.99 156	57.64 269	76.94 299	49.41 74	84.93 278	60.62 189	57.01 314	81.49 286

SSC-MVS3.2		68.13 218	66.89 211	71.85 258	82.26 144	43.97 323	82.09 235	89.29 28	71.74 15	61.12 214	79.83 267	34.60 274	87.45 209	41.23 327	59.85 282	84.14 239

Effi-MVS+-dtu		66.24 260	64.96 256	70.08 286	75.17 291	49.64 203	82.01 236	74.48 321	62.15 153	57.83 263	76.08 315	30.59 311	83.79 291	65.40 156	60.93 277	76.81 344

our_test_3		59.11 310	55.08 326	71.18 269	71.42 340	53.29 121	81.96 237	74.52 320	48.32 334	42.08 373	69.28 369	28.14 322	82.15 305	34.35 358	45.68 377	78.11 334

CPTT-MVS		67.15 242	65.84 237	71.07 270	80.96 181	50.32 190	81.94 238	74.10 324	46.18 352	57.91 262	87.64 159	29.57 316	81.31 311	64.10 163	70.18 199	81.56 285

APD-MVS_3200maxsize		69.62 190	68.23 186	73.80 203	81.58 166	48.22 250	81.91 239	79.50 243	48.21 336	64.24 176	89.75 112	31.91 303	87.55 206	63.08 168	73.85 163	85.64 219

v10		66.61 254	64.20 263	73.83 202	72.59 327	53.37 116	81.88 240	79.91 234	61.11 173	54.09 311	75.60 318	40.06 197	88.26 179	56.47 234	56.10 322	79.86 314

EI-MVSNet-UG-set		72.37 131	71.73 127	74.29 186	81.60 164	49.29 216	81.85 241	88.64 47	65.29 99	65.05 160	88.29 143	43.18 155	91.83 62	63.74 165	67.97 214	81.75 282

ppachtmachnet_test		58.56 318	54.34 328	71.24 266	71.42 340	54.74 80	81.84 242	72.27 343	49.02 329	45.86 363	68.99 370	26.27 336	83.30 299	30.12 373	43.23 382	75.69 354

test_fmvsm_n_1920		75.56 78	75.54 66	75.61 143	74.60 301	49.51 211	81.82 243	74.08 325	66.52 72	80.40 24	93.46 20	46.95 94	89.72 120	86.69 7	75.30 144	87.61 175

test_0402		56.45 331	53.03 335	66.69 324	76.78 265	50.31 191	81.76 244	69.61 366	42.79 372	43.88 365	72.13 352	22.82 362	86.46 239	16.57 416	50.94 354	63.31 403

testing3		59.97 302	60.19 292	59.32 365	77.60 247	30.01 400	81.75 245	81.79 197	53.54 297	50.34 336	79.94 263	48.99 77	76.91 358	17.19 415	50.59 355	71.03 388

reproduce_model		71.07 159	69.67 165	75.28 162	81.51 171	48.82 229	81.73 246	80.57 221	47.81 338	68.26 126	90.78 85	36.49 251	88.60 160	65.12 159	74.76 156	88.42 156

旧先验2							81.73 246		45.53 355	74.66 55			70.48 388	58.31 211

thres100view900		66.87 250	65.42 249	71.24 266	83.29 112	43.15 335	81.67 248	87.78 64	59.04 216	55.92 293	82.18 243	43.73 144	87.80 193	28.80 378	66.36 229	82.78 273

MVSFormer		73.53 113	72.19 119	77.57 91	83.02 122	55.24 63	81.63 249	81.44 203	50.28 320	76.67 44	90.91 81	44.82 132	86.11 249	60.83 186	80.09 86	91.36 68

test_djsdf		63.84 273	61.56 277	70.70 276	68.78 360	44.69 314	81.63 249	81.44 203	50.28 320	52.27 324	76.26 310	26.72 334	86.11 249	60.83 186	55.84 327	81.29 297

新几何2							81.61 251

TSAR-MVS + MP.		78.31 31	78.26 26	78.48 70	81.33 175	56.31 42	81.59 252	86.41 91	69.61 34	81.72 17	88.16 146	55.09 33	88.04 185	74.12 92	86.31 34	91.09 77
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
SR-MVS-dyc-post		68.27 215	66.87 212	72.48 235	80.96 181	48.14 254	81.54 253	76.98 294	46.42 349	62.75 196	89.42 117	31.17 308	86.09 253	60.52 192	72.06 181	83.19 264

RE-MVS-def			66.66 218		80.96 181	48.14 254	81.54 253	76.98 294	46.42 349	62.75 196	89.42 117	29.28 319		60.52 192	72.06 181	83.19 264

V42		67.66 226	65.60 244	73.86 200	70.69 349	53.63 107	81.50 255	78.61 265	63.85 121	59.49 234	77.49 289	37.98 213	87.65 201	62.33 172	58.43 295	80.29 309

DU-MVS		66.84 251	65.74 240	70.16 284	73.27 318	42.59 341	81.50 255	82.92 180	63.53 129	58.51 252	82.11 244	40.75 186	84.64 283	53.11 255	55.96 324	83.24 262

HyFIR lowres test		69.94 182	67.58 199	77.04 105	77.11 260	57.29 22	81.49 257	79.11 254	58.27 229	58.86 247	80.41 260	42.33 165	86.96 223	61.91 177	68.68 210	86.87 188

IterMVS-LS		66.63 253	65.36 250	70.42 280	75.10 293	48.90 226	81.45 258	76.69 302	61.05 175	55.71 294	77.10 297	45.86 111	83.65 294	57.44 226	57.88 308	78.70 322
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
jajsoiax		63.21 280	60.84 285	70.32 282	68.33 365	44.45 316	81.23 259	81.05 209	53.37 300	50.96 333	77.81 286	17.49 387	85.49 267	59.31 199	58.05 303	81.02 300

HPM-MVS_fast		67.86 221	66.28 226	72.61 230	80.67 192	48.34 245	81.18 260	75.95 309	50.81 318	59.55 232	88.05 150	27.86 326	85.98 258	58.83 203	73.58 164	83.51 257

tfpnnormal		61.47 296	59.09 300	68.62 306	76.29 272	41.69 347	81.14 261	85.16 125	54.48 291	51.32 329	73.63 336	32.32 296	86.89 227	21.78 404	55.71 328	77.29 341

IS-MVSNet		68.80 204	67.55 201	72.54 232	78.50 235	43.43 330	81.03 262	79.35 249	59.12 215	57.27 278	86.71 172	46.05 108	87.70 199	44.32 316	75.60 141	86.49 201

eth_miper_zixun_eth		66.98 248	65.28 251	72.06 246	75.61 287	50.40 184	81.00 263	76.97 297	62.00 155	56.99 281	76.97 298	44.84 131	85.58 264	58.75 204	54.42 337	80.21 310

Syy-MVS		61.51 295	61.35 280	62.00 353	81.73 156	30.09 398	80.97 264	81.02 210	60.93 179	55.06 298	82.64 229	35.09 267	80.81 317	16.40 417	58.32 296	75.10 362

myMVS_eth3d		63.52 276	63.56 267	63.40 345	81.73 156	34.28 379	80.97 264	81.02 210	60.93 179	55.06 298	82.64 229	48.00 84	80.81 317	23.42 400	58.32 296	75.10 362

mvs_tets		62.96 283	60.55 287	70.19 283	68.22 368	44.24 321	80.90 266	80.74 217	52.99 303	50.82 335	77.56 287	16.74 391	85.44 268	59.04 202	57.94 305	80.89 301

tttt0517		68.33 213	66.29 225	74.46 179	78.08 240	49.06 218	80.88 267	89.08 33	54.40 293	54.75 303	80.77 258	51.31 55	90.33 102	49.35 282	58.01 304	83.99 245

FC-MVSNet-test		67.49 231	67.91 190	66.21 327	76.06 276	33.06 387	80.82 268	87.18 75	64.44 105	54.81 301	82.87 221	50.40 66	82.60 302	48.05 292	66.55 226	82.98 269

sss		70.49 170	70.13 159	71.58 262	81.59 165	39.02 362	80.78 269	84.71 139	59.34 205	66.61 140	88.09 147	37.17 235	85.52 265	61.82 179	71.02 190	90.20 104

HPM-MVS		72.60 127	71.50 131	75.89 136	82.02 147	51.42 166	80.70 270	83.05 176	56.12 272	64.03 178	89.53 115	37.55 224	88.37 169	70.48 114	80.04 88	87.88 168
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
pmmvs6		59.64 304	57.15 311	67.09 318	66.01 373	36.86 373	80.50 271	78.64 263	45.05 358	49.05 342	73.94 330	27.28 330	86.10 251	43.96 318	49.94 357	78.31 330

balanced_conf03		80.28 16	79.73 15	81.90 11	86.47 52	59.34 6	80.45 272	89.51 26	69.76 32	71.05 103	86.66 174	58.68 16	93.24 31	84.64 18	90.40 6	93.14 18

IterMVS		63.77 275	61.67 275	70.08 286	72.68 326	51.24 171	80.44 273	75.51 311	60.51 187	51.41 328	73.70 335	32.08 299	78.91 337	54.30 248	54.35 338	80.08 312
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
IterMVS-SCA-FT		59.12 309	58.81 303	60.08 363	70.68 350	45.07 310	80.42 274	74.25 322	43.54 369	50.02 337	73.73 332	31.97 300	56.74 409	51.06 273	53.60 344	78.42 328

test_fmvsmconf0.01_n		71.97 142	70.95 142	75.04 167	66.21 372	47.87 265	80.35 275	70.08 362	65.85 88	72.69 79	91.68 65	39.99 198	87.67 200	82.03 34	69.66 202	89.58 120

ACMH+	54.58 15	58.55 319	55.24 323	68.50 309	74.68 299	45.80 304	80.27 276	70.21 361	47.15 343	42.77 372	75.48 319	16.73 392	85.98 258	35.10 356	54.78 334	73.72 372

Anonymous20231206		59.08 311	57.59 308	63.55 343	68.77 361	32.14 392	80.26 277	79.78 236	50.00 324	49.39 340	72.39 349	26.64 335	78.36 341	33.12 364	57.94 305	80.14 311

1314		71.11 158	69.41 168	76.22 124	79.32 212	50.49 181	80.23 278	85.14 127	59.44 202	58.93 244	88.89 128	33.83 284	89.60 124	61.49 181	77.42 115	88.57 150

MVS		76.91 50	75.48 67	81.23 19	84.56 83	55.21 65	80.23 278	91.64 4	58.65 224	65.37 156	91.48 71	45.72 113	95.05 16	72.11 107	89.52 10	93.44 9

ACMH	53.70 16	59.78 303	55.94 321	71.28 265	76.59 266	48.35 244	80.15 280	76.11 307	49.74 325	41.91 375	73.45 339	16.50 393	90.31 103	31.42 369	57.63 311	75.17 360
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
MGCFI-Net		74.07 100	74.64 85	72.34 239	82.90 128	43.33 333	80.04 281	79.96 231	65.61 89	74.93 53	91.85 59	48.01 82	80.86 316	71.41 108	77.10 116	92.84 24

UWE-MVS-28		67.43 233	67.98 189	65.75 329	75.66 286	34.74 377	80.00 282	88.17 57	64.21 111	57.27 278	84.14 202	45.68 115	78.82 339	44.33 314	72.40 177	83.70 254

pmmvs4		63.34 279	61.07 284	70.16 284	70.14 351	50.53 180	79.97 283	71.41 353	55.08 283	54.12 310	78.58 278	32.79 292	82.09 307	50.33 275	57.22 313	77.86 335

MVS_111021_LR		69.07 196	67.91 190	72.54 232	77.27 254	49.56 206	79.77 284	73.96 328	59.33 207	60.73 218	87.82 154	30.19 314	81.53 309	69.94 117	72.19 180	86.53 199

CNLPA		60.59 300	58.44 304	67.05 320	79.21 215	47.26 278	79.75 285	64.34 385	42.46 374	51.90 327	83.94 204	27.79 328	75.41 367	37.12 339	59.49 286	78.47 326

EI-MVSNet		69.70 188	68.70 177	72.68 229	75.00 295	48.90 226	79.54 286	87.16 76	61.05 175	63.88 182	83.74 208	45.87 110	90.44 98	57.42 227	64.68 244	78.70 322

CVMVSNet		60.85 299	60.44 289	62.07 351	75.00 295	32.73 389	79.54 286	73.49 334	36.98 387	56.28 291	83.74 208	29.28 319	69.53 390	46.48 303	63.23 259	83.94 250

AUN-MVS		68.20 217	66.35 223	73.76 204	76.37 267	47.45 274	79.52 288	79.52 242	60.98 177	62.34 199	86.02 180	36.59 250	86.94 224	62.32 173	53.47 346	86.89 187

hse-mvs2		71.44 154	70.68 144	73.73 206	76.34 268	47.44 275	79.45 289	79.47 244	68.08 43	71.97 89	86.01 182	42.50 163	86.93 225	78.82 54	53.46 347	86.83 193

PVSNet_0	57.04 13	61.19 297	57.24 310	73.02 219	77.45 251	50.31 191	79.43 290	77.36 289	63.96 120	47.51 354	72.45 348	25.03 347	83.78 292	52.76 263	19.22 423	84.96 229

PCF-MVS	61.03 10	70.10 175	68.40 182	75.22 165	77.15 259	51.99 151	79.30 291	82.12 189	56.47 269	61.88 207	86.48 178	43.98 139	87.24 215	55.37 242	72.79 173	86.43 203
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
test_fmvsmvis_n_1920		71.29 155	70.38 152	74.00 195	71.04 345	48.79 230	79.19 292	64.62 382	62.75 143	66.73 136	91.99 56	40.94 184	88.35 171	83.00 26	73.18 167	84.85 232

PLC	52.38 18	60.89 298	58.97 302	66.68 325	81.77 155	45.70 305	78.96 293	74.04 327	43.66 368	47.63 351	83.19 220	23.52 358	77.78 353	37.47 336	60.46 278	76.55 350
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
D2MVS		63.49 277	61.39 279	69.77 290	69.29 357	48.93 225	78.89 294	77.71 282	60.64 186	49.70 338	72.10 354	27.08 332	83.48 296	54.48 247	62.65 267	76.90 343

OMC-MVS		65.97 263	65.06 254	68.71 304	72.97 322	42.58 343	78.61 295	75.35 314	54.72 288	59.31 237	86.25 179	33.30 287	77.88 350	57.99 215	67.05 220	85.66 218

PAPM_NR		71.80 146	69.98 161	77.26 101	81.54 168	53.34 118	78.60 296	85.25 121	53.46 298	60.53 220	88.66 132	45.69 114	89.24 133	56.49 233	79.62 96	89.19 133

mvs_anonymous		72.29 135	70.74 143	76.94 112	82.85 131	54.72 82	78.43 297	81.54 201	63.77 122	61.69 208	79.32 271	51.11 56	85.31 269	62.15 176	75.79 138	90.79 86

RRT-MVS		73.29 116	71.37 135	79.07 52	84.63 81	54.16 99	78.16 298	86.64 88	61.67 162	60.17 222	82.35 240	40.63 190	92.26 53	70.19 115	77.87 109	90.81 85

tt0805		63.39 278	61.31 281	69.64 291	69.36 356	38.87 363	78.00 299	85.48 107	48.82 331	55.66 297	81.66 250	24.38 352	86.37 242	49.04 285	59.36 288	83.68 255

test222					79.36 210	50.97 173	77.99 300	67.84 373	42.54 373	62.84 195	86.53 176	30.26 313			76.91 119	85.23 224

v7n		62.50 288	59.27 299	72.20 242	67.25 371	49.83 201	77.87 301	80.12 227	52.50 306	48.80 344	73.07 340	32.10 298	87.90 189	46.83 300	54.92 332	78.86 320

test20.03		55.22 338	54.07 331	58.68 368	63.14 391	25.00 412	77.69 302	74.78 318	52.64 304	43.43 368	72.39 349	26.21 337	74.76 369	29.31 376	47.05 371	76.28 352

testdata1							77.55 303		64.14 114

PEN-MVS		58.35 321	57.15 311	61.94 354	67.55 370	34.39 378	77.01 304	78.35 271	51.87 311	47.72 350	76.73 304	33.91 281	73.75 374	34.03 359	47.17 369	77.68 337

WR-MVS_H		58.91 314	58.04 306	61.54 357	69.07 359	33.83 384	76.91 305	81.99 191	51.40 315	48.17 345	74.67 323	40.23 193	74.15 370	31.78 368	48.10 361	76.64 348

CP-MVSNet		58.54 320	57.57 309	61.46 358	68.50 363	33.96 383	76.90 306	78.60 266	51.67 314	47.83 349	76.60 306	34.99 270	72.79 379	35.45 349	47.58 365	77.64 339

PS-CasMVS		58.12 322	57.03 313	61.37 359	68.24 367	33.80 385	76.73 307	78.01 275	51.20 316	47.54 353	76.20 314	32.85 290	72.76 380	35.17 354	47.37 367	77.55 340

tpm		68.36 211	67.48 204	70.97 272	79.93 204	51.34 168	76.58 308	78.75 261	67.73 51	63.54 189	74.86 322	48.33 78	72.36 382	53.93 251	63.71 251	89.21 132

MonoMVSNet		66.80 252	64.41 260	73.96 196	76.21 273	48.07 257	76.56 309	78.26 272	64.34 107	54.32 308	74.02 329	37.21 234	86.36 243	64.85 161	53.96 340	87.45 179

DTE-MVSNet		57.03 327	55.73 322	60.95 362	65.94 374	32.57 390	75.71 310	77.09 293	51.16 317	46.65 359	76.34 309	32.84 291	73.22 378	30.94 372	44.87 378	77.06 342

tpmrst		71.04 161	69.77 163	74.86 174	83.19 115	55.86 50	75.64 311	78.73 262	67.88 48	64.99 163	73.73 332	49.96 71	79.56 336	65.92 146	67.85 216	89.14 135

CostFormer		73.89 105	72.30 116	78.66 65	82.36 143	56.58 33	75.56 312	85.30 117	66.06 84	70.50 113	76.88 302	57.02 22	89.06 139	68.27 131	68.74 209	90.33 98

HY-MVS	67.03 5	73.90 104	73.14 103	76.18 128	84.70 80	47.36 276	75.56 312	86.36 93	66.27 76	70.66 109	83.91 205	51.05 57	89.31 130	67.10 137	72.61 175	91.88 51

K. test v3		54.04 343	49.42 355	67.92 312	68.55 362	42.57 344	75.51 314	63.07 388	52.07 308	39.21 387	64.59 384	19.34 378	82.21 304	37.11 340	25.31 414	78.97 319

Vis-MVSNet (Re-imp)		65.52 265	65.63 242	65.17 336	77.49 250	30.54 394	75.49 315	77.73 281	59.34 205	52.26 325	86.69 173	49.38 75	80.53 323	37.07 341	75.28 145	84.42 236

pmmvs-eth3d		55.97 335	52.78 339	65.54 332	61.02 396	46.44 289	75.36 316	67.72 374	49.61 326	43.65 367	67.58 374	21.63 370	77.04 356	44.11 317	44.33 379	73.15 378

TAPA-MVS	56.12 14	61.82 294	60.18 293	66.71 323	78.48 236	37.97 369	75.19 317	76.41 306	46.82 345	57.04 280	86.52 177	27.67 329	77.03 357	26.50 391	67.02 221	85.14 225
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
FMVSNet5		58.61 317	56.45 315	65.10 337	77.20 258	39.74 359	74.77 318	77.12 292	50.27 322	43.28 370	67.71 373	26.15 339	76.90 360	36.78 344	54.78 334	78.65 324

FA-MVS(test-final)		69.00 199	66.60 220	76.19 127	83.48 105	47.96 263	74.73 319	82.07 190	57.27 252	62.18 202	78.47 280	36.09 256	92.89 34	53.76 253	71.32 188	87.73 172

SixPastTwentyTwo		54.37 340	50.10 349	67.21 317	70.70 348	41.46 352	74.73 319	64.69 381	47.56 341	39.12 388	69.49 365	18.49 384	84.69 282	31.87 367	34.20 402	75.48 356

F-COLMAP		55.96 336	53.65 334	62.87 349	72.76 325	42.77 340	74.70 321	70.37 360	40.03 377	41.11 381	79.36 270	17.77 386	73.70 375	32.80 365	53.96 340	72.15 380

MVSMamba_PlusPlus		75.28 81	73.39 97	80.96 21	80.85 186	58.25 10	74.47 322	87.61 71	50.53 319	65.24 157	83.41 215	57.38 20	92.83 36	73.92 95	87.13 21	91.80 54

MSDG		59.44 305	55.14 325	72.32 240	74.69 298	50.71 175	74.39 323	73.58 331	44.44 363	43.40 369	77.52 288	19.45 377	90.87 89	31.31 370	57.49 312	75.38 357

tpm2		70.82 165	68.44 181	77.98 81	80.78 188	56.11 44	74.21 324	81.28 207	60.24 190	68.04 129	75.27 320	52.26 50	88.50 166	55.82 241	68.03 213	89.33 128

SDMVSNet		71.89 143	70.62 146	75.70 141	81.70 158	51.61 160	73.89 325	88.72 45	66.58 69	61.64 209	82.38 237	37.63 221	89.48 125	77.44 68	65.60 236	86.01 208

UniMVSNet_ETH3D		62.51 287	60.49 288	68.57 308	68.30 366	40.88 357	73.89 325	79.93 233	51.81 313	54.77 302	79.61 268	24.80 349	81.10 312	49.93 277	61.35 274	83.73 253

UA-Net		67.32 238	66.23 227	70.59 277	78.85 224	41.23 354	73.60 327	75.45 313	61.54 165	66.61 140	84.53 197	38.73 209	86.57 237	42.48 326	74.24 159	83.98 247

Anonymous20240521		51.65 354	48.42 357	61.34 360	56.43 405	39.65 361	73.57 328	73.47 337	36.64 389	36.59 394	63.98 385	10.75 404	72.25 383	35.35 350	49.01 358	72.11 381

ab-mvs		70.65 168	69.11 174	75.29 160	80.87 185	46.23 296	73.48 329	85.24 122	59.99 192	66.65 138	80.94 256	43.13 158	88.69 156	63.58 166	68.07 212	90.95 82

LS3D		56.40 332	53.82 332	64.12 340	81.12 177	45.69 306	73.42 330	66.14 377	35.30 395	43.24 371	79.88 264	22.18 367	79.62 335	19.10 411	64.00 249	67.05 393

testmvs		6.14 405	8.18 408	0.01 419	0.01 442	0.00 445	73.40 331	0.00 443	0.00 437	0.02 438	0.15 437	0.00 442	0.00 438	0.02 437	0.00 436	0.02 434

UnsupCasMVSNet_eth		57.56 325	55.15 324	64.79 339	64.57 385	33.12 386	73.17 332	83.87 160	58.98 218	41.75 376	70.03 364	22.54 363	79.92 330	46.12 307	35.31 396	81.32 296

anonymousdsp		60.46 301	57.65 307	68.88 298	63.63 389	45.09 309	72.93 333	78.63 264	46.52 347	51.12 330	72.80 344	21.46 371	83.07 301	57.79 222	53.97 339	78.47 326

mmtdpeth		57.93 323	54.78 327	67.39 316	72.32 331	43.38 331	72.72 334	68.93 369	54.45 292	56.85 282	62.43 389	17.02 389	83.46 297	57.95 218	30.31 408	75.31 358

EU-MVSNet		52.63 350	50.72 347	58.37 369	62.69 393	28.13 409	72.60 335	75.97 308	30.94 402	40.76 383	72.11 353	20.16 375	70.80 386	35.11 355	46.11 375	76.19 353

dp		64.41 268	61.58 276	72.90 223	82.40 141	54.09 100	72.53 336	76.59 304	60.39 188	55.68 295	70.39 363	35.18 266	76.90 360	39.34 333	61.71 273	87.73 172

N_pmnet		41.25 373	39.77 376	45.66 391	68.50 363	0.82 443	72.51 337	0.38 442	35.61 392	35.26 399	61.51 392	20.07 376	67.74 391	23.51 398	40.63 386	68.42 392

MDTV_nov1_ep13			61.56 277		81.68 160	55.12 69	72.41 338	78.18 273	59.19 210	58.85 248	69.29 368	34.69 273	86.16 248	36.76 345	62.96 264

YYNet1		53.82 345	49.96 351	65.41 334	70.09 353	48.95 223	72.30 339	71.66 350	44.25 365	31.89 408	63.07 388	23.73 356	73.95 372	33.26 362	39.40 389	73.34 375

MDA-MVSNet_test_wron		53.82 345	49.95 352	65.43 333	70.13 352	49.05 219	72.30 339	71.65 351	44.23 366	31.85 409	63.13 387	23.68 357	74.01 371	33.25 363	39.35 390	73.23 377

testgi		54.25 342	52.57 341	59.29 366	62.76 392	21.65 421	72.21 341	70.47 359	53.25 301	41.94 374	77.33 293	14.28 397	77.95 349	29.18 377	51.72 353	78.28 331

KD-MVS_2432*1600		59.04 312	56.44 316	66.86 321	79.07 217	45.87 301	72.13 342	80.42 223	55.03 284	48.15 346	71.01 357	36.73 245	78.05 346	35.21 352	30.18 409	76.67 345

miper_refine_blended		59.04 312	56.44 316	66.86 321	79.07 217	45.87 301	72.13 342	80.42 223	55.03 284	48.15 346	71.01 357	36.73 245	78.05 346	35.21 352	30.18 409	76.67 345

PatchmatchNet		67.07 246	63.63 266	77.40 95	83.10 116	58.03 11	72.11 344	77.77 280	58.85 220	59.37 235	70.83 359	37.84 215	84.93 278	42.96 322	69.83 201	89.26 129
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
test123		6.01 406	8.01 409	0.01 419	0.00 443	0.01 444	71.93 345	0.00 443	0.00 437	0.02 438	0.11 438	0.00 442	0.00 438	0.02 437	0.00 436	0.02 434

EPMVS		68.45 210	65.44 248	77.47 94	84.91 77	56.17 43	71.89 346	81.91 195	61.72 161	60.85 216	72.49 346	36.21 254	87.06 220	47.32 296	71.62 184	89.17 134

UnsupCasMVSNet_bld		53.86 344	50.53 348	63.84 341	63.52 390	34.75 376	71.38 347	81.92 194	46.53 346	38.95 389	57.93 402	20.55 374	80.20 328	39.91 332	34.09 403	76.57 349

COLMAP_ROB	43.60 20	50.90 358	48.05 359	59.47 364	67.81 369	40.57 358	71.25 348	62.72 390	36.49 390	36.19 396	73.51 337	13.48 398	73.92 373	20.71 406	50.26 356	63.92 402
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
MDTV_nov1_ep13_2view						43.62 327	71.13 349		54.95 286	59.29 239		36.76 244		46.33 305		87.32 182

test_post1							70.84 350				14.72 434	34.33 278	83.86 289	48.80 286

new-patchmatchnet		48.21 363	46.55 365	53.18 380	57.73 402	18.19 429	70.24 351	71.02 357	45.70 353	33.70 402	60.23 396	18.00 385	69.86 389	27.97 385	34.35 400	71.49 386

pmmvs3		45.53 369	41.55 375	57.44 371	48.97 418	39.68 360	70.06 352	57.66 394	28.32 406	34.06 401	57.29 403	8.50 412	66.85 393	34.86 357	34.26 401	65.80 398

tpmvs		62.45 290	59.42 297	71.53 263	83.93 96	54.32 92	70.03 353	77.61 283	51.91 310	53.48 317	68.29 372	37.91 214	86.66 232	33.36 361	58.27 298	73.62 373

tpm cat1		66.28 258	62.78 268	76.77 118	81.40 173	57.14 24	70.03 353	77.19 290	53.00 302	58.76 250	70.73 362	46.17 104	86.73 230	43.27 320	64.46 245	86.44 202

PatchMatch-RL		56.66 328	53.75 333	65.37 335	77.91 245	45.28 308	69.78 355	60.38 391	41.35 375	47.57 352	73.73 332	16.83 390	76.91 358	36.99 342	59.21 289	73.92 371

MDA-MVSNet-bldmvs		51.56 355	47.75 362	63.00 347	71.60 338	47.32 277	69.70 356	72.12 344	43.81 367	27.65 416	63.38 386	21.97 369	75.96 364	27.30 388	32.19 404	65.70 399

miper_lstm_enhance		63.91 272	62.30 271	68.75 303	75.06 294	46.78 282	69.02 357	81.14 208	59.68 198	52.76 320	72.39 349	40.71 188	77.99 348	56.81 231	53.09 348	81.48 288

sd_testset		67.79 224	65.95 234	73.32 214	81.70 158	46.33 293	68.99 358	80.30 225	66.58 69	61.64 209	82.38 237	30.45 312	87.63 202	55.86 239	65.60 236	86.01 208

test_fmvs1		53.60 347	52.54 342	56.78 372	58.07 400	30.26 396	68.95 359	42.19 412	32.46 398	63.59 187	82.56 233	11.55 401	60.81 399	58.25 212	55.27 330	79.28 316

GG-mvs-BLEND				77.77 86	86.68 49	50.61 177	68.67 360	88.45 54		68.73 123	87.45 161	59.15 11	90.67 92	54.83 244	87.67 17	92.03 45

OurMVSNet-221017-0		52.39 352	48.73 356	63.35 346	65.21 379	38.42 366	68.54 361	64.95 380	38.19 382	39.57 386	71.43 356	13.23 399	79.92 330	37.16 338	40.32 388	71.72 383

FE-MVS		64.15 270	60.43 290	75.30 159	80.85 186	49.86 200	68.28 362	78.37 270	50.26 323	59.31 237	73.79 331	26.19 338	91.92 61	40.19 330	66.67 223	84.12 240

test_fmvs1_n		52.55 351	51.19 346	56.65 373	51.90 411	30.14 397	67.66 363	42.84 411	32.27 399	62.30 201	82.02 247	9.12 410	60.84 398	57.82 221	54.75 336	78.99 318

MIMVSNet1		50.35 359	47.81 360	57.96 370	61.53 395	27.80 410	67.40 364	74.06 326	43.25 370	33.31 407	65.38 383	16.03 394	71.34 384	21.80 403	47.55 366	74.75 364

mvsmamba		69.38 193	67.52 203	74.95 172	82.86 130	52.22 148	67.36 365	76.75 298	61.14 172	49.43 339	82.04 246	37.26 232	84.14 286	73.93 94	76.91 119	88.50 154

test_vis1_n		51.19 356	49.66 354	55.76 377	51.26 413	29.85 401	67.20 366	38.86 417	32.12 400	59.50 233	79.86 265	8.78 411	58.23 406	56.95 230	52.46 350	79.19 317

MTAPA		72.73 125	71.22 137	77.27 99	81.54 168	53.57 108	67.06 367	81.31 205	59.41 203	68.39 125	90.96 78	36.07 257	89.01 142	73.80 97	82.45 64	89.23 131

WB-MVS		37.41 380	36.37 380	40.54 398	54.23 407	10.43 436	65.29 368	43.75 409	34.86 396	27.81 415	54.63 405	24.94 348	63.21 395	6.81 431	15.00 426	47.98 417

kuosan		50.20 360	50.09 350	50.52 384	73.09 320	29.09 406	65.25 369	74.89 317	48.27 335	41.34 378	60.85 395	43.45 152	67.48 392	18.59 413	25.07 415	55.01 409

MIMVSNet		63.12 281	60.29 291	71.61 259	75.92 283	46.65 285	65.15 370	81.94 192	59.14 214	54.65 304	69.47 366	25.74 341	80.63 320	41.03 329	69.56 205	87.55 176

XVG-OURS-SEG-HR		62.02 292	59.54 296	69.46 293	65.30 378	45.88 300	65.06 371	73.57 332	46.45 348	57.42 276	83.35 217	26.95 333	78.09 344	53.77 252	64.03 248	84.42 236

XVG-OURS		61.88 293	59.34 298	69.49 292	65.37 377	46.27 294	64.80 372	73.49 334	47.04 344	57.41 277	82.85 222	25.15 346	78.18 342	53.00 258	64.98 238	84.01 244

dmvs_re		67.61 227	66.00 232	72.42 236	81.86 153	43.45 329	64.67 373	80.00 229	69.56 35	60.07 223	85.00 193	34.71 272	87.63 202	51.48 269	66.68 222	86.17 207

gg-mvs-nofinetune		67.43 233	64.53 259	76.13 129	85.95 56	47.79 269	64.38 374	88.28 56	39.34 379	66.62 139	41.27 416	58.69 15	89.00 143	49.64 280	86.62 31	91.59 58

dongtai		43.51 370	44.07 371	41.82 395	63.75 388	21.90 419	63.80 375	72.05 345	39.59 378	33.35 406	54.54 406	41.04 183	57.30 407	10.75 424	17.77 424	46.26 418

dmvs_testset		57.65 324	58.21 305	55.97 376	74.62 300	9.82 437	63.75 376	63.34 387	67.23 58	48.89 343	83.68 212	39.12 205	76.14 363	23.43 399	59.80 283	81.96 279

XVG-ACMP-BASELINE		56.03 334	52.85 338	65.58 331	61.91 394	40.95 356	63.36 377	72.43 342	45.20 357	46.02 361	74.09 327	9.20 409	78.12 343	45.13 309	58.27 298	77.66 338

TinyColmap		48.15 364	44.49 368	59.13 367	65.73 376	38.04 367	63.34 378	62.86 389	38.78 380	29.48 411	67.23 376	6.46 419	73.30 377	24.59 395	41.90 385	66.04 397

MVS-HIRNet		49.01 362	44.71 366	61.92 355	76.06 276	46.61 286	63.23 379	54.90 398	24.77 411	33.56 403	36.60 420	21.28 372	75.88 365	29.49 375	62.54 268	63.26 404

PM-MVS		46.92 366	43.76 373	56.41 375	52.18 410	32.26 391	63.21 380	38.18 418	37.99 384	40.78 382	66.20 377	5.09 423	65.42 394	48.19 291	41.99 384	71.54 385

AllTest		47.32 365	44.66 367	55.32 378	65.08 381	37.50 371	62.96 381	54.25 400	35.45 393	33.42 404	72.82 342	9.98 406	59.33 402	24.13 396	43.84 380	69.13 389

USDC		54.36 341	51.23 345	63.76 342	64.29 386	37.71 370	62.84 382	73.48 336	56.85 258	35.47 398	71.94 355	9.23 408	78.43 340	38.43 335	48.57 359	75.13 361

mvs5depth		50.97 357	46.98 363	62.95 348	56.63 404	34.23 381	62.73 383	67.35 376	45.03 359	48.00 348	65.41 382	10.40 405	79.88 334	36.00 346	31.27 407	74.73 365

SSC-MVS		35.20 382	34.30 384	37.90 401	52.58 409	8.65 439	61.86 384	41.64 413	31.81 401	25.54 418	52.94 411	23.39 359	59.28 404	6.10 432	12.86 427	45.78 420

Patchmatch-RL test		58.72 316	54.32 329	71.92 255	63.91 387	44.25 320	61.73 385	55.19 397	57.38 250	49.31 341	54.24 407	37.60 223	80.89 314	62.19 175	47.28 368	90.63 89

SCA		63.84 273	60.01 294	75.32 156	78.58 233	57.92 12	61.61 386	77.53 284	56.71 263	57.75 267	70.77 360	31.97 300	79.91 332	48.80 286	56.36 316	88.13 163

CMPMVS	40.41 21	55.34 337	52.64 340	63.46 344	60.88 397	43.84 325	61.58 387	71.06 356	30.43 403	36.33 395	74.63 324	24.14 354	75.44 366	48.05 292	66.62 224	71.12 387
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
LCM-MVSNet-Re		58.82 315	56.54 314	65.68 330	79.31 213	29.09 406	61.39 388	45.79 406	60.73 184	37.65 393	72.47 347	31.42 306	81.08 313	49.66 279	70.41 196	86.87 188

CR-MVSNet		62.47 289	59.04 301	72.77 227	73.97 312	56.57 34	60.52 389	71.72 348	60.04 191	57.49 273	65.86 378	38.94 206	80.31 325	42.86 323	59.93 280	81.42 289

RPMNet		59.29 306	54.25 330	74.42 181	73.97 312	56.57 34	60.52 389	76.98 294	35.72 391	57.49 273	58.87 401	37.73 219	85.26 271	27.01 389	59.93 280	81.42 289

EGC-MVSNET		33.75 384	30.42 388	43.75 394	64.94 383	36.21 374	60.47 391	40.70 415	0.02 436	0.10 437	53.79 408	7.39 413	60.26 400	11.09 423	35.23 398	34.79 422

test_vis1_rt		40.29 376	38.64 377	45.25 392	48.91 419	30.09 398	59.44 392	27.07 431	24.52 412	38.48 391	51.67 412	6.71 417	49.44 415	44.33 314	46.59 374	56.23 407

Patchmtry		56.56 330	52.95 337	67.42 315	72.53 328	50.59 179	59.05 393	71.72 348	37.86 385	46.92 356	65.86 378	38.94 206	80.06 329	36.94 343	46.72 373	71.60 384

TDRefinement		40.91 374	38.37 378	48.55 388	50.45 415	33.03 388	58.98 394	50.97 403	28.50 404	29.89 410	67.39 375	6.21 421	54.51 411	17.67 414	35.25 397	58.11 406

test_fmvs2		45.89 367	44.32 369	50.62 383	45.85 422	24.70 413	58.87 395	37.84 420	25.22 409	52.46 322	74.56 325	7.07 414	54.69 410	49.28 283	47.70 364	72.48 379

KD-MVS_self_test		49.24 361	46.85 364	56.44 374	54.32 406	22.87 415	57.39 396	73.36 338	44.36 364	37.98 392	59.30 400	18.97 380	71.17 385	33.48 360	42.44 383	75.26 359

PatchT		56.60 329	52.97 336	67.48 314	72.94 323	46.16 297	57.30 397	73.78 329	38.77 381	54.37 307	57.26 404	37.52 225	78.06 345	32.02 366	52.79 349	78.23 333

ttmdpeth		40.58 375	37.50 379	49.85 385	49.40 416	22.71 416	56.65 398	46.78 404	28.35 405	40.29 385	69.42 367	5.35 422	61.86 397	20.16 408	21.06 421	64.96 400

mvsany_test1		43.38 371	42.57 374	45.82 390	50.96 414	26.10 411	55.80 399	27.74 430	27.15 407	47.41 355	74.39 326	18.67 382	44.95 421	44.66 312	36.31 394	66.40 396

ANet_high		34.39 383	29.59 389	48.78 387	30.34 432	22.28 417	55.53 400	63.79 386	38.11 383	15.47 424	36.56 421	6.94 415	59.98 401	13.93 420	5.64 435	64.08 401

ADS-MVSNet2		55.21 339	51.44 344	66.51 326	80.60 193	49.56 206	55.03 401	65.44 379	44.72 360	51.00 331	61.19 393	22.83 360	75.41 367	28.54 381	53.63 342	74.57 367

ADS-MVSNet		56.17 333	51.95 343	68.84 299	80.60 193	53.07 127	55.03 401	70.02 363	44.72 360	51.00 331	61.19 393	22.83 360	78.88 338	28.54 381	53.63 342	74.57 367

RPSCF		45.77 368	44.13 370	50.68 382	57.67 403	29.66 402	54.92 403	45.25 408	26.69 408	45.92 362	75.92 317	17.43 388	45.70 420	27.44 387	45.95 376	76.67 345

new_pmnet		33.56 385	31.89 387	38.59 399	49.01 417	20.42 422	51.01 404	37.92 419	20.58 413	23.45 419	46.79 414	6.66 418	49.28 417	20.00 410	31.57 406	46.09 419

MVStest1		38.35 377	34.53 383	49.82 386	51.43 412	30.41 395	50.39 405	55.25 396	17.56 419	26.45 417	65.85 380	11.72 400	57.00 408	14.79 418	17.31 425	62.05 405

test_fmvs3		37.95 379	35.75 381	44.55 393	35.50 428	18.92 425	48.32 406	34.00 425	18.36 418	41.31 380	61.58 391	2.29 430	48.06 419	42.72 324	37.71 392	66.66 395

E-PMN		19.16 398	18.40 402	21.44 414	36.19 427	13.63 434	47.59 407	30.89 426	10.73 427	5.91 434	16.59 430	3.66 426	39.77 424	5.95 433	8.14 430	10.92 430

EMVS		18.42 399	17.66 403	20.71 415	34.13 429	12.64 435	46.94 408	29.94 428	10.46 429	5.58 435	14.93 433	4.23 425	38.83 425	5.24 435	7.51 432	10.67 431

CHOSEN 280x420		57.53 326	56.38 318	60.97 361	74.01 310	48.10 256	46.30 409	54.31 399	48.18 337	50.88 334	77.43 292	38.37 212	59.16 405	54.83 244	63.14 262	75.66 355

LTVRE_ROB	45.45 19	52.73 349	49.74 353	61.69 356	69.78 354	34.99 375	44.52 410	67.60 375	43.11 371	43.79 366	74.03 328	18.54 383	81.45 310	28.39 383	57.94 305	68.62 391
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
LF4IMVS		33.04 386	32.55 386	34.52 404	40.96 423	22.03 418	44.45 411	35.62 422	20.42 414	28.12 414	62.35 390	5.03 424	31.88 433	21.61 405	34.42 399	49.63 415

mamv4		42.60 372	44.05 372	38.26 400	59.21 399	38.00 368	44.14 412	39.03 416	25.03 410	40.61 384	68.39 371	37.01 239	24.28 434	46.62 302	36.43 393	52.50 412

Patchmatch-test		53.33 348	48.17 358	68.81 301	73.31 315	42.38 345	42.98 413	58.23 393	32.53 397	38.79 390	70.77 360	39.66 201	73.51 376	25.18 393	52.06 352	90.55 91

PMMVS2		26.71 391	22.98 396	37.87 402	36.89 426	8.51 440	42.51 414	29.32 429	19.09 417	13.01 426	37.54 417	2.23 431	53.11 412	14.54 419	11.71 428	51.99 414

FPMVS		35.40 381	33.67 385	40.57 397	46.34 421	28.74 408	41.05 415	57.05 395	20.37 415	22.27 420	53.38 409	6.87 416	44.94 422	8.62 425	47.11 370	48.01 416

PMVS	19.57 22	25.07 393	22.43 398	32.99 408	23.12 439	22.98 414	40.98 416	35.19 423	15.99 421	11.95 430	35.87 422	1.47 436	49.29 416	5.41 434	31.90 405	26.70 427
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
APD_test1		26.46 392	24.41 393	32.62 409	37.58 425	21.74 420	40.50 417	30.39 427	11.45 426	16.33 423	43.76 415	1.63 435	41.62 423	11.24 422	26.82 413	34.51 423

JIA-IIPM		52.33 353	47.77 361	66.03 328	71.20 343	46.92 281	40.00 418	76.48 305	37.10 386	46.73 357	37.02 418	32.96 289	77.88 350	35.97 347	52.45 351	73.29 376

DSMNet-mixed		38.35 377	35.36 382	47.33 389	48.11 420	14.91 433	37.87 419	36.60 421	19.18 416	34.37 400	59.56 399	15.53 395	53.01 413	20.14 409	46.89 372	74.07 369

test_vis3_rt		24.79 394	22.95 397	30.31 410	28.59 434	18.92 425	37.43 420	17.27 438	12.90 423	21.28 421	29.92 427	1.02 437	36.35 426	28.28 384	29.82 411	35.65 421

ambc				62.06 352	53.98 408	29.38 404	35.08 421	79.65 240		41.37 377	59.96 397	6.27 420	82.15 305	35.34 351	38.22 391	74.65 366

mvsany_test3		28.00 388	25.98 390	34.05 405	28.97 433	15.31 431	34.54 422	18.17 436	16.24 420	29.30 412	53.37 410	2.79 428	33.38 432	30.01 374	20.41 422	53.45 411

testf1		21.11 396	19.08 400	27.18 412	30.56 430	18.28 427	33.43 423	24.48 432	8.02 430	12.02 428	33.50 424	0.75 439	35.09 429	7.68 427	21.32 418	28.17 425

APD_test2		21.11 396	19.08 400	27.18 412	30.56 430	18.28 427	33.43 423	24.48 432	8.02 430	12.02 428	33.50 424	0.75 439	35.09 429	7.68 427	21.32 418	28.17 425

LCM-MVSNet		28.07 387	23.85 395	40.71 396	27.46 437	18.93 424	30.82 425	46.19 405	12.76 424	16.40 422	34.70 423	1.90 433	48.69 418	20.25 407	24.22 416	54.51 410

test_f		27.12 390	24.85 391	33.93 406	26.17 438	15.25 432	30.24 426	22.38 435	12.53 425	28.23 413	49.43 413	2.59 429	34.34 431	25.12 394	26.99 412	52.20 413

test_method		24.09 395	21.07 399	33.16 407	27.67 436	8.35 441	26.63 427	35.11 424	3.40 433	14.35 425	36.98 419	3.46 427	35.31 428	19.08 412	22.95 417	55.81 408

wuyk23d		9.11 403	8.77 407	10.15 417	40.18 424	16.76 430	20.28 428	1.01 441	2.58 434	2.66 436	0.98 436	0.23 441	12.49 436	4.08 436	6.90 433	1.19 433

MVE	16.60 23	17.34 401	13.39 404	29.16 411	28.43 435	19.72 423	13.73 429	23.63 434	7.23 432	7.96 432	21.41 428	0.80 438	36.08 427	6.97 429	10.39 429	31.69 424
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
Gipuma		27.47 389	24.26 394	37.12 403	60.55 398	29.17 405	11.68 430	60.00 392	14.18 422	10.52 431	15.12 432	2.20 432	63.01 396	8.39 426	35.65 395	19.18 428
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
tmp_tt		9.44 402	10.68 405	5.73 418	2.49 441	4.21 442	10.48 431	18.04 437	0.34 435	12.59 427	20.49 429	11.39 402	7.03 437	13.84 421	6.46 434	5.95 432

mmdepth		0.00 408	0.00 411	0.00 421	0.00 443	0.00 445	0.00 432	0.00 443	0.00 437	0.00 440	0.00 439	0.00 442	0.00 438	0.00 439	0.00 436	0.00 436

monomultidepth		0.00 408	0.00 411	0.00 421	0.00 443	0.00 445	0.00 432	0.00 443	0.00 437	0.00 440	0.00 439	0.00 442	0.00 438	0.00 439	0.00 436	0.00 436

test_blank		0.00 408	0.00 411	0.00 421	0.00 443	0.00 445	0.00 432	0.00 443	0.00 437	0.00 440	0.00 439	0.00 442	0.00 438	0.00 439	0.00 436	0.00 436

uanet_test		0.00 408	0.00 411	0.00 421	0.00 443	0.00 445	0.00 432	0.00 443	0.00 437	0.00 440	0.00 439	0.00 442	0.00 438	0.00 439	0.00 436	0.00 436

DCPMVS		0.00 408	0.00 411	0.00 421	0.00 443	0.00 445	0.00 432	0.00 443	0.00 437	0.00 440	0.00 439	0.00 442	0.00 438	0.00 439	0.00 436	0.00 436

cdsmvs_eth3d_5k		18.33 400	24.44 392	0.00 421	0.00 443	0.00 445	0.00 432	89.40 27	0.00 437	0.00 440	92.02 54	38.55 210	0.00 438	0.00 439	0.00 436	0.00 436

pcd_1.5k_mvsjas		3.15 407	4.20 410	0.00 421	0.00 443	0.00 445	0.00 432	0.00 443	0.00 437	0.00 440	0.00 439	37.77 216	0.00 438	0.00 439	0.00 436	0.00 436

sosnet-low-res		0.00 408	0.00 411	0.00 421	0.00 443	0.00 445	0.00 432	0.00 443	0.00 437	0.00 440	0.00 439	0.00 442	0.00 438	0.00 439	0.00 436	0.00 436

sosnet		0.00 408	0.00 411	0.00 421	0.00 443	0.00 445	0.00 432	0.00 443	0.00 437	0.00 440	0.00 439	0.00 442	0.00 438	0.00 439	0.00 436	0.00 436

uncertanet		0.00 408	0.00 411	0.00 421	0.00 443	0.00 445	0.00 432	0.00 443	0.00 437	0.00 440	0.00 439	0.00 442	0.00 438	0.00 439	0.00 436	0.00 436

Regformer		0.00 408	0.00 411	0.00 421	0.00 443	0.00 445	0.00 432	0.00 443	0.00 437	0.00 440	0.00 439	0.00 442	0.00 438	0.00 439	0.00 436	0.00 436

ab-mvs-re		7.68 404	10.24 406	0.00 421	0.00 443	0.00 445	0.00 432	0.00 443	0.00 437	0.00 440	92.12 50	0.00 442	0.00 438	0.00 439	0.00 436	0.00 436

uanet		0.00 408	0.00 411	0.00 421	0.00 443	0.00 445	0.00 432	0.00 443	0.00 437	0.00 440	0.00 439	0.00 442	0.00 438	0.00 439	0.00 436	0.00 436

WAC-MVS						34.28 379								22.56 401

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

PC_three_1452									66.58 69	87.27 2	93.70 13	66.82 4	94.95 17	89.74 4	91.98 4	93.98 5

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

test_one_0601					89.39 22	57.29 22		88.09 59	57.21 254	82.06 14	93.39 22	54.94 36

eth-test2					0.00 443

eth-test					0.00 443

ZD-MVS					89.55 14	53.46 110		84.38 146	57.02 256	73.97 63	91.03 74	44.57 136	91.17 79	75.41 82	81.78 71

IU-MVS					89.48 17	57.49 17		91.38 9	66.22 77	88.26 1				82.83 28	87.60 18	92.44 32

test_241102_TWO								88.76 44	57.50 248	83.60 6	94.09 4	56.14 27	96.37 6	82.28 32	87.43 20	92.55 30

test_241102_ONE					89.48 17	56.89 29		88.94 35	57.53 246	84.61 4	93.29 26	58.81 13	96.45 1

test_0728_THIRD									58.00 234	81.91 15	93.64 15	56.54 23	96.44 2	81.64 38	86.86 26	92.23 37

GSMVS																88.13 163

test_part2					89.33 23	55.48 54				82.27 12

sam_mvs1												38.86 208				88.13 163

sam_mvs												35.99 260

MTGPA								81.31 205

test_post											16.22 431	37.52 225	84.72 281

patchmatchnet-post											59.74 398	38.41 211	79.91 332

gm-plane-assit					83.24 113	54.21 96			70.91 23		88.23 145		95.25 14	66.37 141

test9_res														78.72 57	85.44 43	91.39 66

agg_prior2														75.65 77	85.11 47	91.01 79

agg_prior					85.64 63	54.92 76		83.61 166		72.53 83			88.10 183

TestCases				55.32 378	65.08 381	37.50 371		54.25 400	35.45 393	33.42 404	72.82 342	9.98 406	59.33 402	24.13 396	43.84 380	69.13 389

test_prior				78.39 74	86.35 54	54.91 77		85.45 110					89.70 121			90.55 91

新几何1				73.30 216	83.10 116	53.48 109		71.43 352	45.55 354	66.14 145	87.17 166	33.88 283	80.54 322	48.50 289	80.33 84	85.88 215

旧先验1					81.57 167	47.48 273		71.83 346			88.66 132	36.94 241			78.34 106	88.67 146

原ACMM1				76.13 129	84.89 78	54.59 88		85.26 120	51.98 309	66.70 137	87.07 168	40.15 195	89.70 121	51.23 271	85.06 48	84.10 241

testdata2													77.81 352	45.64 308

segment_acmp												44.97 128

testdata				67.08 319	77.59 248	45.46 307		69.20 368	44.47 362	71.50 96	88.34 141	31.21 307	70.76 387	52.20 266	75.88 137	85.03 226

test12				79.24 44	86.89 47	56.08 45		85.16 125		72.27 87		47.15 91	91.10 82		85.93 37	90.54 93

plane_prior7					77.95 242	48.46 241

plane_prior6					78.42 237	49.39 214						36.04 258

plane_prior5								82.59 183					88.30 176	65.46 152	72.34 178	84.49 234

plane_prior4											83.28 218

plane_prior3						48.95 223			64.01 118	62.15 203

plane_prior1					78.31 239

n2								0.00 443

nn								0.00 443

door-mid								41.31 414

lessismore_v0				67.98 311	64.76 384	41.25 353		45.75 407		36.03 397	65.63 381	19.29 379	84.11 287	35.67 348	21.24 420	78.59 325

LGP-MVS_train				72.02 247	74.42 303	48.60 234		80.64 218	54.69 289	53.75 314	83.83 206	25.73 342	86.98 221	60.33 196	64.71 241	80.48 306

test11								84.25 150

door								43.27 410

HQP5-MVS						51.56 162

BP-MVS														66.70 138

HQP4-MVS										64.47 174			88.61 159			84.91 230

HQP3-MVS								83.68 162							73.12 168

HQP2-MVS												37.35 228

NP-MVS					78.76 225	50.43 183					85.12 190

ACMMP++_ref															63.20 260

ACMMP++															59.38 287

Test By Simon												39.38 202

ITE_SJBPF				51.84 381	58.03 401	31.94 393		53.57 402	36.67 388	41.32 379	75.23 321	11.17 403	51.57 414	25.81 392	48.04 362	72.02 382

DeepMVS_CX				13.10 416	21.34 440	8.99 438		10.02 440	10.59 428	7.53 433	30.55 426	1.82 434	14.55 435	6.83 430	7.52 431	15.75 429

High-resolution multi-view benchmark