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	courty.	delive.	electro	facade	kicker	meadow	office	pipes	playgr.	relief	relief.	terrace	terrai.

SED-MVS		88.94 1	90.98 1	86.56 1	92.53 7	95.09 1	88.55 6	76.83 8	94.16 1	86.57 2	90.85 7	87.07 1	86.18 1	86.36 8	85.08 14	88.67 37	98.21 3

DVP-MVS		88.07 2	90.73 2	84.97 6	91.98 10	95.01 2	87.86 13	76.88 7	93.90 2	85.15 3	90.11 9	86.90 2	79.46 15	86.26 11	84.67 19	88.50 45	98.25 2
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
DVP-MVS++		87.98 3	89.76 7	85.89 2	92.57 6	94.57 3	88.34 7	76.61 9	92.40 8	83.40 6	89.26 12	85.57 7	86.04 2	86.24 12	84.89 16	88.39 48	95.42 23

SF-MVS		87.30 8	88.71 8	85.64 4	94.57 1	94.55 4	91.01 1	79.94 1	89.15 14	79.85 10	92.37 5	83.29 13	79.75 12	83.52 29	82.72 36	88.75 36	95.37 26

TPM-MVS					94.34 2	93.91 5	89.34 3			75.49 21	82.52 22	83.34 12	83.53 4			89.62 12	90.78 99
Ray Leroy Khuboni and Hongjun Xu: Textureless Resilient Propagation Matching in Multiple View Stereosis (TPM-MVS). SATNAC 2025
DPE-MVS		87.60 7	90.44 4	84.29 9	92.09 9	93.44 6	88.69 5	75.11 11	93.06 6	80.80 9	94.23 4	86.70 3	81.44 9	84.84 19	83.52 30	87.64 74	97.28 5
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
CSCG		82.90 23	84.52 26	81.02 20	91.85 11	93.43 7	87.14 15	74.01 17	81.96 35	76.14 17	70.84 40	82.49 16	69.71 89	82.32 44	85.18 13	87.26 90	95.40 25

MED-MVS		87.93 5	90.38 5	85.08 5	91.74 12	93.20 8	89.12 4	75.00 12	93.69 3	85.03 4	94.60 2	86.09 4	81.66 6	84.58 22	84.07 23	87.93 62	96.41 14

MGCNet		83.82 19	86.88 18	80.26 23	88.48 34	93.17 9	82.93 35	67.66 49	88.28 17	74.90 22	77.08 35	80.93 23	78.09 20	85.83 15	85.88 7	89.53 17	96.96 10

MCST-MVS		85.75 11	86.99 15	84.31 8	94.07 3	92.80 10	88.15 12	79.10 2	85.66 24	70.72 33	76.50 36	80.45 25	82.17 5	88.35 2	87.49 3	91.63 2	97.65 4

DELS-MVS		79.49 34	79.84 43	79.08 30	88.26 40	92.49 11	84.12 29	70.63 30	65.27 93	69.60 39	61.29 68	66.50 63	72.75 49	88.07 4	88.03 2	89.13 28	97.22 6
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
CHOSEN 1792x2688		72.55 97	71.98 108	73.22 79	86.57 48	92.41 12	75.63 101	66.77 55	62.08 110	52.32 127	30.27 238	50.74 171	66.14 118	86.22 13	85.41 9	91.90 1	96.75 13

CNVR-MVS		85.96 10	87.58 13	84.06 10	92.58 5	92.40 13	87.62 14	77.77 6	88.44 16	75.93 19	79.49 28	81.97 20	81.65 7	87.04 7	86.58 4	88.79 34	97.18 7

CANet		80.90 30	82.93 31	78.53 32	86.83 47	92.26 14	81.19 47	66.95 53	81.60 38	69.90 36	66.93 51	74.80 34	76.79 25	84.68 20	84.77 18	89.50 19	95.50 21

aaEdge-Enhanced		87.94 4	89.84 6	85.72 3	91.74 12	92.20 15	88.32 9	77.84 4	92.47 7	85.03 4	94.60 2	85.70 6	81.31 10	83.94 27	83.57 29	90.10 7	96.41 14

QAPM		77.50 48	77.43 56	77.59 38	91.52 16	92.00 16	81.41 43	70.63 30	66.22 84	58.05 103	54.70 101	71.79 46	74.49 36	82.46 40	82.04 40	89.46 21	92.79 66

DPM-MVS		85.41 13	86.72 19	83.89 12	91.66 15	91.92 17	90.49 2	78.09 3	86.90 20	73.95 24	74.52 38	82.01 19	79.29 16	90.24 1	90.65 1	89.86 9	90.78 99

APDe-MVS		86.37 9	88.41 10	84.00 11	91.43 17	91.83 18	88.34 7	74.67 13	91.19 9	81.76 8	91.13 6	81.94 21	80.07 11	83.38 30	82.58 38	87.69 72	96.78 11
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
MSP-MVS		87.87 6	90.57 3	84.73 7	89.38 29	91.60 19	88.24 11	74.15 15	93.55 4	82.28 7	94.99 1	83.21 14	85.96 3	87.67 5	84.67 19	88.32 49	98.29 1
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
PHI-MVS		79.43 36	84.06 28	74.04 71	86.15 50	91.57 20	80.85 51	68.90 41	82.22 34	51.81 130	78.10 30	74.28 35	70.39 83	84.01 26	84.00 24	86.14 120	94.24 35

MVSMamba_PlusPlus		80.76 31	82.78 32	78.41 33	81.93 64	91.55 21	81.27 46	68.39 45	83.28 29	66.70 46	69.11 44	68.52 56	81.56 8	88.17 3	86.51 6	90.62 5	92.28 75

DeepPCF-MVS	76.94 1	83.08 22	87.77 12	77.60 37	90.11 22	90.96 22	78.48 65	72.63 25	93.10 5	65.84 49	80.67 26	81.55 22	74.80 32	85.94 14	85.39 10	83.75 189	96.77 12

SMA-MVS		85.24 14	88.27 11	81.72 17	91.74 12	90.71 23	86.71 16	73.16 22	90.56 12	74.33 23	83.07 20	85.88 5	77.16 24	86.28 10	85.58 8	87.23 91	95.77 16
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
MVS_111021_HR		77.42 49	78.40 52	76.28 43	86.95 45	90.68 24	77.41 84	70.56 33	66.21 86	62.48 73	66.17 55	63.98 74	72.08 58	82.87 36	83.15 31	88.24 52	95.71 18

MAR-MVS		77.19 51	78.37 53	75.81 47	89.87 24	90.58 25	79.33 59	65.56 64	77.62 53	58.33 102	59.24 78	67.98 58	74.83 31	82.37 43	83.12 32	86.95 98	87.67 142
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
NCCC		84.16 18	85.46 24	82.64 13	92.34 8	90.57 26	86.57 17	76.51 10	86.85 21	72.91 27	77.20 34	78.69 29	79.09 18	84.64 21	84.88 17	88.44 46	95.41 24

OpenMVS	67.62 8	74.92 67	73.91 87	76.09 45	90.10 23	90.38 27	78.01 76	66.35 58	66.09 87	62.80 68	46.33 161	64.55 72	71.77 63	79.92 74	80.88 71	87.52 78	89.20 123

3Dnovator	70.49 5	78.42 41	76.77 62	80.35 22	91.43 17	90.27 28	81.84 40	70.79 29	72.10 63	71.95 28	50.02 136	67.86 60	77.47 23	82.89 35	84.24 21	88.61 40	89.99 114

HPM-MVS++		85.64 12	88.43 9	82.39 14	92.65 4	90.24 29	85.83 20	74.21 14	90.68 11	75.63 20	86.77 15	84.15 10	78.68 19	86.33 9	85.26 11	87.32 86	95.60 20

EPNet		79.28 39	82.25 33	75.83 46	88.31 39	90.14 30	79.43 58	68.07 46	81.76 37	61.26 87	77.26 33	70.08 52	70.06 87	82.43 42	82.00 42	87.82 66	92.09 83
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
ACMMP_NAP		83.54 20	86.37 21	80.25 24	89.57 28	90.10 31	85.27 24	71.66 26	87.38 18	73.08 26	84.23 19	80.16 26	75.31 28	84.85 18	83.64 26	86.57 108	94.21 37

GG-mvs-BLEND		54.54 227	77.58 55	27.67 260	0.03 280	90.09 32	77.20 88	0.02 275	66.83 83	0.05 280	59.90 73	73.33 38	0.04 276	78.40 99	79.30 95	88.65 38	95.20 28

PVSNet_BlendedMVS		76.84 53	78.47 50	74.95 57	82.37 59	89.90 33	75.45 105	65.45 65	74.99 59	70.66 34	63.07 61	58.27 119	67.60 107	84.24 24	81.70 49	88.18 53	97.10 8

PVSNet_Blended		76.84 53	78.47 50	74.95 57	82.37 59	89.90 33	75.45 105	65.45 65	74.99 59	70.66 34	63.07 61	58.27 119	67.60 107	84.24 24	81.70 49	88.18 53	97.10 8

sasdasda		77.65 45	79.59 44	75.39 48	81.52 66	89.83 35	81.32 44	60.74 140	80.05 43	66.72 43	68.43 45	65.09 66	74.72 34	78.87 89	82.73 34	87.32 86	92.16 78

canonicalmvs		77.65 45	79.59 44	75.39 48	81.52 66	89.83 35	81.32 44	60.74 140	80.05 43	66.72 43	68.43 45	65.09 66	74.72 34	78.87 89	82.73 34	87.32 86	92.16 78

SteuartSystems-ACMMP		82.51 24	85.35 25	79.20 28	90.25 20	89.39 37	84.79 25	70.95 28	82.86 31	68.32 41	86.44 16	77.19 30	73.07 45	83.63 28	83.64 26	87.82 66	94.34 34
Skip Steuart: Steuart Systems R&D Blog.
casdiffmvs_mvg		75.57 60	76.04 67	75.02 56	80.48 77	89.31 38	80.79 52	64.04 77	66.95 82	63.87 59	57.52 84	61.33 87	72.90 47	82.01 50	81.99 43	88.03 58	93.16 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
APD-MVS		84.83 15	87.00 14	82.30 15	89.61 27	89.21 39	86.51 18	73.64 19	90.98 10	77.99 15	89.89 10	80.04 27	79.18 17	82.00 51	81.37 57	86.88 100	95.49 22
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
hybridcas		74.86 68	74.70 79	75.04 55	79.57 82	89.12 40	78.97 60	64.02 78	65.29 92	65.36 51	54.81 100	60.39 99	73.16 43	80.41 66	80.49 83	89.18 27	92.39 73

E2		75.18 65	75.21 73	75.15 53	79.77 80	89.10 41	78.62 62	64.19 73	65.19 94	65.90 48	58.15 81	58.36 117	72.56 51	80.74 63	81.78 46	89.84 10	93.19 55

viewdifsd2359ckpt13		74.11 76	74.06 86	74.18 69	79.34 89	89.07 42	78.31 71	64.25 72	62.52 106	62.06 76	55.80 93	56.70 135	72.29 53	80.35 69	81.47 55	88.80 33	92.47 71

casdiffmvs		75.20 63	75.69 70	74.63 62	79.26 92	89.07 42	78.47 66	63.59 89	67.05 81	63.79 60	55.72 95	60.32 100	73.58 39	82.16 46	81.78 46	89.08 30	93.72 47
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
IB-MVS	64.48 11	69.02 125	68.97 134	69.09 117	81.75 65	89.01 44	64.50 191	64.91 68	56.65 141	62.59 72	47.89 145	45.23 184	51.99 194	69.18 207	81.88 45	88.77 35	92.93 60
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
viewcassd2359sk11		74.75 69	74.61 83	74.90 59	79.62 81	88.96 45	78.47 66	64.08 75	63.51 100	65.27 52	57.02 87	57.89 123	72.25 54	80.30 70	81.57 53	89.72 11	93.04 59

viewmanbaseed2359cas		74.53 70	74.69 81	74.35 65	79.37 88	88.90 46	78.96 61	64.07 76	63.67 97	62.19 75	56.95 88	58.42 116	72.04 59	80.08 71	81.92 44	89.47 20	92.91 61

MVS_Test		75.22 62	76.69 63	73.51 72	79.30 90	88.82 47	80.06 55	58.74 151	69.77 71	57.50 107	59.78 75	61.35 85	75.31 28	82.07 48	83.60 28	90.13 6	91.41 91

E3new		74.17 74	73.83 89	74.57 63	79.40 86	88.76 48	78.30 72	63.89 83	61.21 113	64.38 58	55.65 96	57.34 128	71.87 60	79.73 78	81.28 60	89.55 15	92.86 62

E3		74.17 74	73.83 89	74.57 63	79.40 86	88.76 48	78.30 72	63.89 83	61.22 112	64.40 57	55.64 97	57.35 127	71.86 61	79.73 78	81.27 61	89.55 15	92.86 62

SD-MVS		84.31 17	86.96 16	81.22 18	88.98 33	88.68 50	85.65 21	73.85 18	89.09 15	79.63 11	87.34 14	84.84 8	73.71 38	82.66 38	81.60 52	85.48 143	94.51 32
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
Casviewmamba		75.20 63	75.26 72	75.13 54	80.13 79	88.67 51	78.61 63	64.02 78	67.43 80	66.72 43	56.60 90	60.53 92	73.45 42	80.41 66	81.03 66	87.84 64	92.13 82

gg-mvs-nofinetune		62.34 178	66.19 159	57.86 203	76.15 130	88.61 52	71.18 149	41.24 259	25.74 259	13.16 264	22.91 256	63.97 75	54.52 186	85.06 17	85.25 12	90.92 3	91.78 87

E5new		73.48 85	72.84 98	74.23 67	79.06 94	88.52 53	78.32 69	63.99 80	58.33 128	63.34 64	54.07 111	56.89 131	71.29 70	78.99 86	80.82 74	89.35 22	92.26 76

E5		73.48 85	72.84 98	74.23 67	79.06 94	88.52 53	78.32 69	63.99 80	58.33 128	63.34 64	54.07 111	56.89 131	71.29 70	78.99 86	80.82 74	89.35 22	92.26 76

DeepC-MVS	74.46 3	80.30 33	81.05 38	79.42 26	87.42 43	88.50 55	83.23 31	73.27 21	82.78 32	71.01 32	62.86 63	69.93 53	74.80 32	84.30 23	84.20 22	86.79 103	94.77 29
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
E4		73.32 88	72.68 100	74.06 70	79.06 94	88.47 56	77.98 77	63.57 90	57.73 137	63.18 66	53.48 114	56.74 134	71.26 72	78.95 88	80.84 72	89.30 24	92.55 67

viewmacassd2359aftdt		73.00 90	72.63 101	73.44 75	78.70 103	88.45 57	78.52 64	63.49 91	57.74 136	60.15 98	52.57 120	57.01 130	70.69 79	78.85 92	81.29 59	89.10 29	92.48 69

train_agg		83.35 21	86.93 17	79.17 29	89.70 26	88.41 58	85.60 23	72.89 24	86.31 22	66.58 47	90.48 8	82.24 18	73.06 46	83.10 34	82.64 37	87.21 95	95.30 27

viewdifsd2359ckpt09		73.89 80	73.57 91	74.26 66	78.54 107	88.37 59	78.34 68	63.79 85	63.31 101	64.90 54	57.29 86	56.53 137	72.15 57	79.12 83	77.91 116	87.83 65	92.48 69

CDPH-MVS		79.39 38	82.13 34	76.19 44	89.22 32	88.34 60	84.20 28	71.00 27	79.67 47	56.97 108	77.77 31	72.24 44	68.50 103	81.33 55	82.74 33	87.23 91	92.84 64

3Dnovator+	70.16 6	77.87 44	77.29 58	78.55 31	89.25 31	88.32 61	80.09 54	67.95 47	74.89 61	71.83 29	52.05 126	70.68 50	76.27 27	82.27 45	82.04 40	85.92 125	90.77 101

E6new		72.71 95	72.05 105	73.49 73	79.01 98	88.31 62	77.06 89	62.71 109	56.63 142	62.00 77	52.31 121	55.75 144	70.93 75	78.51 96	80.72 77	89.20 25	92.14 80

E6		72.71 95	72.05 105	73.49 73	79.01 98	88.31 62	77.06 89	62.71 109	56.63 142	62.00 77	52.31 121	55.75 144	70.93 75	78.51 96	80.72 77	89.20 25	92.14 80

TSAR-MVS + GP.		82.27 26	85.98 22	77.94 35	80.72 74	88.25 64	81.12 48	67.71 48	87.10 19	73.31 25	85.23 17	83.68 11	76.64 26	80.43 65	81.47 55	88.15 55	95.66 19

MP-MVS		80.94 29	83.49 29	77.96 34	88.48 34	88.16 65	82.82 36	69.34 37	80.79 41	69.67 37	82.35 23	77.13 31	71.60 65	80.97 61	80.96 69	85.87 128	94.06 40
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
viewdifsd2359ckpt07		72.78 93	72.24 103	73.41 78	78.58 106	88.14 66	76.95 91	63.73 87	57.28 138	63.47 62	54.45 106	56.62 136	69.16 98	78.86 91	79.98 85	88.58 43	90.33 108

HyFIR lowres test		68.39 130	68.28 142	68.52 123	80.85 71	88.11 67	71.08 151	58.09 156	54.87 159	47.80 149	27.55 246	55.80 143	64.97 122	79.11 84	79.14 98	88.31 50	93.35 52

CLD-MVS		77.36 50	77.29 58	77.45 39	82.21 61	88.11 67	81.92 39	68.96 40	77.97 51	69.62 38	62.08 64	59.44 110	73.57 40	81.75 53	81.27 61	88.41 47	90.39 107
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
ET-MVSNet_ETH3D		71.38 107	74.70 79	67.51 133	51.61 248	88.06 69	77.29 85	60.95 139	63.61 98	48.36 146	66.60 53	60.67 90	79.55 13	73.56 160	80.58 80	87.30 89	89.80 116

PCF-MVS	70.85 4	75.73 59	76.55 65	74.78 61	83.67 55	88.04 70	81.47 41	70.62 32	69.24 77	57.52 106	60.59 72	69.18 55	70.65 80	77.11 114	77.65 118	84.75 170	94.01 41
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
ETV-MVS		76.25 55	80.22 41	71.63 99	78.23 109	87.95 71	72.75 129	60.27 146	77.50 54	57.73 104	71.53 39	66.60 62	73.16 43	80.99 60	81.23 63	87.63 75	95.73 17

DeepC-MVS_fast	75.41 2	81.69 27	82.10 35	81.20 19	91.04 19	87.81 72	83.42 30	74.04 16	83.77 28	71.09 31	66.88 52	72.44 40	79.48 14	85.08 16	84.97 15	88.12 56	93.78 44
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
HFP-MVS		82.48 25	84.12 27	80.56 21	90.15 21	87.55 73	84.28 27	69.67 35	85.22 25	77.95 16	84.69 18	75.94 33	75.04 30	81.85 52	81.17 64	86.30 116	92.40 72

baseline		72.89 91	74.46 85	71.07 100	75.99 132	87.50 74	74.57 111	60.49 143	70.72 67	57.60 105	60.63 71	60.97 88	70.79 78	75.27 138	76.33 131	86.94 99	89.79 117

onestephybrid01		73.58 83	74.69 81	72.29 90	76.11 131	87.32 75	76.53 97	62.91 101	68.13 79	63.40 63	58.47 79	60.61 91	68.74 102	76.69 121	78.09 111	86.05 123	93.54 49

MGCFI-Net		74.26 72	78.69 48	69.10 115	80.64 75	87.32 75	73.21 128	59.20 149	79.76 46	50.18 140	68.10 47	64.86 71	64.65 126	78.28 102	80.83 73	86.69 105	91.69 88

diffmvs		74.32 71	75.42 71	73.04 81	75.60 137	87.27 77	78.20 74	62.96 97	68.66 78	61.89 79	59.79 74	59.84 106	71.80 62	78.30 101	79.87 86	87.80 68	94.23 36
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
casdiffseed414692147		71.49 104	70.06 128	73.15 80	79.11 93	87.26 78	77.82 80	62.34 116	58.44 127	60.33 97	46.19 162	51.26 167	71.53 66	77.07 115	79.56 92	87.80 68	90.61 104

hybridnocas07		74.06 77	75.21 73	72.71 84	75.43 139	87.22 79	76.90 93	62.70 111	69.87 69	62.72 70	59.53 76	59.98 105	71.03 74	77.21 113	79.23 96	87.49 79	93.44 51

EIA-MVS		73.48 85	76.05 66	70.47 105	78.12 110	87.21 80	71.78 139	60.63 142	69.66 72	55.56 113	64.86 57	60.69 89	69.53 92	77.35 112	78.59 102	87.22 93	94.01 41

PVSNet_Blended_VisFu		71.76 103	73.54 93	69.69 110	79.01 98	87.16 81	72.05 136	61.80 123	56.46 145	59.66 99	53.88 113	62.48 77	59.08 163	81.17 57	78.90 99	86.53 110	94.74 30

diffmvs_AUTHOR		73.73 82	74.73 78	72.56 88	75.05 141	87.15 82	77.82 80	62.29 117	66.22 84	61.10 90	57.92 82	59.72 108	71.43 67	78.25 103	79.68 89	87.71 71	94.17 38

viewmamba		73.51 84	74.57 84	72.28 91	75.68 136	87.10 83	76.82 94	62.81 103	69.38 74	61.26 87	58.32 80	59.73 107	70.35 84	76.34 124	78.81 101	86.77 104	92.32 74

ACMMPR		80.62 32	82.98 30	77.87 36	88.41 36	87.05 84	83.02 32	69.18 38	83.91 27	68.35 40	82.89 21	73.64 37	72.16 56	80.78 62	81.13 65	86.10 121	91.43 89

hybrid		73.86 81	75.13 75	72.38 89	75.05 141	87.04 85	76.72 95	62.53 113	69.51 73	62.37 74	59.27 77	60.40 98	70.21 86	77.07 115	79.17 97	87.39 82	93.46 50

SPE-MVS-test		75.09 66	77.84 54	71.87 98	79.27 91	86.92 86	70.53 158	60.36 144	75.13 58	63.13 67	67.92 48	65.08 68	71.43 67	78.15 104	78.51 105	86.53 110	93.16 57

DI_MVS_pp		73.94 79	74.85 77	72.88 82	76.57 127	86.80 87	80.41 53	61.47 129	62.35 108	59.44 100	47.91 144	68.12 57	72.24 55	82.84 37	81.50 54	87.15 97	94.42 33

CS-MVS		75.84 58	78.61 49	72.61 87	79.03 97	86.74 88	74.43 119	60.27 146	74.15 62	62.78 69	66.26 54	64.25 73	72.81 48	83.36 31	81.69 51	86.32 114	93.85 43

PGM-MVS		79.42 37	81.84 36	76.60 42	88.38 38	86.69 89	82.97 34	65.75 62	80.39 42	64.94 53	81.95 25	72.11 45	71.41 69	80.45 64	80.55 81	86.18 118	90.76 102

test1111		66.72 145	67.80 145	65.45 144	77.42 120	86.63 90	69.69 162	62.98 96	55.29 153	39.47 188	40.12 191	47.11 179	55.70 181	79.96 73	80.00 84	87.47 80	85.49 163

EC-MVSNet		76.05 57	78.87 47	72.77 83	78.87 102	86.63 90	77.50 83	57.04 180	75.34 57	61.68 83	64.20 58	69.56 54	73.96 37	82.12 47	80.65 79	87.57 76	93.57 48

CANet_DTU		72.84 92	76.63 64	68.43 126	76.81 124	86.62 92	75.54 104	54.71 207	72.06 64	43.54 166	67.11 50	58.46 114	72.40 52	81.13 59	80.82 74	87.57 76	90.21 110

dtuplus		72.12 101	72.21 104	72.01 95	74.74 146	86.54 93	77.22 87	61.74 127	60.26 119	61.52 85	54.43 107	57.46 126	70.32 85	75.64 134	77.35 121	86.51 112	93.75 45

TSAR-MVS + ACMM		81.59 28	85.84 23	76.63 41	89.82 25	86.53 94	86.32 19	66.72 56	85.96 23	65.43 50	88.98 13	82.29 17	67.57 110	82.06 49	81.33 58	83.93 187	93.75 45

TSAR-MVS + MP.		84.39 16	86.58 20	81.83 16	88.09 41	86.47 95	85.63 22	73.62 20	90.13 13	79.24 12	89.67 11	82.99 15	77.72 22	81.22 56	80.92 70	86.68 106	94.66 31
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
viewmambaseed2359dif		72.54 98	72.88 97	72.13 93	74.78 145	86.45 96	77.24 86	61.65 128	62.61 105	61.83 80	55.85 91	57.51 125	70.64 81	75.71 132	77.90 117	86.65 107	94.16 39

test2506		69.26 119	70.79 121	67.48 134	78.64 104	86.40 97	72.22 134	62.75 107	58.05 132	45.24 156	50.76 131	54.93 151	58.05 169	79.82 75	79.70 87	87.96 60	85.90 158

ECVR-MVS		67.93 135	68.49 137	67.28 137	78.64 104	86.40 97	72.22 134	62.75 107	58.05 132	44.06 164	40.92 186	48.20 176	58.05 169	79.82 75	79.70 87	87.96 60	86.32 152

baseline2		71.22 109	73.01 96	69.13 114	75.76 134	86.34 99	71.23 147	62.78 105	62.62 104	52.85 126	57.32 85	54.31 154	63.27 134	79.74 77	79.31 94	88.89 32	91.43 89

XVS					82.43 57	86.27 100	75.70 99			61.07 91		72.27 41				85.67 137

X-MVStestdata					82.43 57	86.27 100	75.70 99			61.07 91		72.27 41				85.67 137

X-MVS		78.16 43	80.55 40	75.38 50	87.99 42	86.27 100	81.05 49	68.98 39	78.33 49	61.07 91	75.25 37	72.27 41	67.52 112	80.03 72	80.52 82	85.66 140	91.20 93

CostFormer		72.18 99	73.90 88	70.18 107	79.47 84	86.19 103	76.94 92	48.62 230	66.07 88	60.40 96	54.14 109	65.82 64	67.98 104	75.84 131	76.41 130	87.67 73	92.83 65

FA-MVS(training)		70.24 115	71.77 111	68.45 125	77.52 118	86.03 104	73.33 126	49.12 229	63.55 99	55.77 110	48.91 141	56.26 139	67.78 106	77.60 107	79.62 90	87.19 96	90.40 106

CP-MVS		79.44 35	81.51 37	77.02 40	86.95 45	85.96 105	82.00 38	68.44 44	81.82 36	67.39 42	77.43 32	73.68 36	71.62 64	79.56 81	79.58 91	85.73 133	92.51 68

ACMMP		77.61 47	79.59 44	75.30 51	85.87 51	85.58 106	81.42 42	67.38 52	79.38 48	62.61 71	78.53 29	65.79 65	68.80 101	78.56 95	78.50 106	85.75 130	90.80 98
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
MS-PatchMatch		70.34 114	69.00 133	71.91 97	85.20 54	85.35 107	77.84 79	61.77 124	58.01 134	55.40 114	41.26 182	58.34 118	61.69 143	81.70 54	78.29 107	89.56 14	80.02 206

Effi-MVS+		70.42 110	71.23 115	69.47 111	78.04 111	85.24 108	75.57 103	58.88 150	59.56 122	48.47 145	52.73 119	54.94 150	69.69 90	78.34 100	77.06 123	86.18 118	90.73 103

MVS_111021_LR		74.26 72	75.95 68	72.27 92	79.43 85	85.04 109	72.71 130	65.27 67	70.92 66	63.58 61	69.32 42	60.31 102	69.43 94	77.01 117	77.15 122	83.22 197	91.93 86

AdaColmap		76.23 56	73.55 92	79.35 27	89.38 29	85.00 110	79.99 56	73.04 23	76.60 55	71.17 30	55.18 99	57.99 121	77.87 21	76.82 119	76.82 125	84.67 172	86.45 149

0.4-1-1-0.2		70.06 116	70.92 120	69.06 118	67.65 189	84.98 111	74.41 121	62.76 106	63.03 102	53.95 119	51.07 130	60.32 100	67.52 112	73.73 158	74.85 148	88.04 57	88.45 135

0.3-1-1-0.015		70.01 117	70.93 118	68.93 119	67.63 191	84.94 112	74.17 122	62.69 112	62.88 103	53.78 121	51.37 129	60.47 93	67.27 114	73.70 159	74.70 150	88.00 59	88.47 134

MSLP-MVS++		78.57 40	77.33 57	80.02 25	88.39 37	84.79 113	84.62 26	66.17 60	75.96 56	78.40 13	61.59 66	71.47 47	73.54 41	78.43 98	78.88 100	88.97 31	90.18 111

0.4-1-1-0.1		69.62 118	70.57 123	68.51 124	67.55 193	84.77 114	73.54 124	62.45 115	62.23 109	53.25 125	50.57 134	60.25 103	66.36 116	73.49 162	74.34 158	87.90 63	88.30 137

Vis-MVSNet		65.53 153	69.83 129	60.52 184	70.80 171	84.59 115	66.37 187	55.47 197	48.40 183	40.62 185	57.67 83	58.43 115	45.37 225	77.49 108	76.24 133	84.47 178	85.99 157
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
baseline1		71.47 105	72.02 107	70.82 102	80.56 76	84.51 116	76.61 96	66.93 54	56.22 147	48.66 144	55.40 98	60.43 97	62.55 139	83.35 32	80.99 67	89.60 13	83.28 183

thisisatest0530		68.38 131	70.98 117	65.35 145	72.61 158	84.42 117	68.21 171	57.98 158	59.77 121	50.80 135	54.63 102	58.48 113	57.92 171	76.99 118	77.47 119	84.60 175	85.07 165

Anonymous202405211			66.35 158		78.00 112	84.41 118	74.85 109	63.18 94	51.00 172		31.37 235	53.73 158	69.67 91	76.28 125	76.84 124	83.21 199	90.85 97

OPM-MVS		72.74 94	70.93 118	74.85 60	85.30 53	84.34 119	82.82 36	69.79 34	49.96 176	55.39 115	54.09 110	60.14 104	70.04 88	80.38 68	79.43 93	85.74 132	88.20 138
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
HQP-MVS		78.26 42	80.91 39	75.17 52	85.67 52	84.33 120	83.01 33	69.38 36	79.88 45	55.83 109	79.85 27	64.90 70	70.81 77	82.46 40	81.78 46	86.30 116	93.18 56

IS_MVSNet		67.29 142	71.98 108	61.82 177	76.92 123	84.32 121	65.90 189	58.22 154	55.75 151	39.22 191	54.51 104	62.47 78	45.99 222	78.83 93	78.52 104	84.70 171	89.47 120

EPMVS		66.21 147	67.49 148	64.73 150	75.81 133	84.20 122	68.94 167	44.37 245	61.55 111	48.07 148	49.21 140	54.87 152	62.88 135	71.82 180	71.40 197	88.28 51	79.37 209

tttt0517		67.99 134	70.61 122	64.94 148	71.94 163	83.96 123	67.62 175	57.98 158	59.30 123	49.90 141	54.50 105	57.98 122	57.92 171	76.48 123	77.47 119	84.24 182	84.58 169

thres100view900		67.14 144	66.09 160	68.38 127	77.70 113	83.84 124	74.52 115	66.33 59	49.16 180	43.40 168	43.24 166	41.34 194	62.59 138	79.31 82	75.92 136	85.73 133	89.81 115

Anonymous20231211		68.44 129	66.37 157	70.86 101	77.58 116	83.49 125	75.15 108	61.89 121	52.54 169	58.50 101	28.89 240	56.78 133	69.29 97	74.96 142	76.61 126	82.73 203	91.36 92

EPP-MVSNet		67.58 138	71.10 116	63.48 162	75.71 135	83.35 126	66.85 181	57.83 163	53.02 167	41.15 181	55.82 92	67.89 59	56.01 180	74.40 147	72.92 179	83.33 195	90.30 109

GeoE		68.96 126	69.32 130	68.54 122	76.61 126	83.12 127	71.78 139	56.87 182	60.21 120	54.86 117	45.95 163	54.79 153	64.27 127	74.59 144	75.54 142	86.84 102	91.01 96

MVSTER		76.92 52	79.92 42	73.42 77	74.98 143	82.97 128	78.15 75	63.41 92	78.02 50	64.41 56	67.54 49	72.80 39	71.05 73	83.29 33	83.73 25	88.53 44	91.12 94

PatchmatchNet		65.43 154	67.71 146	62.78 168	73.49 153	82.83 129	66.42 186	45.40 240	60.40 118	45.27 155	49.22 139	57.60 124	60.01 155	70.61 193	71.38 198	86.08 122	81.91 199
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
viewdifsd2359ckpt11		69.15 122	68.30 139	70.14 108	73.44 155	82.79 130	72.24 132	61.20 132	54.59 162	61.70 82	53.16 115	52.89 163	67.57 110	71.81 182	72.73 182	84.66 173	90.10 112

viewmsd2359difaftdt		69.14 123	68.29 140	70.13 109	73.44 155	82.79 130	72.24 132	61.20 132	54.60 161	61.68 83	53.16 115	52.87 164	67.58 109	71.82 180	72.73 182	84.66 173	90.10 112

thres400		65.18 156	64.44 168	66.04 140	76.40 128	82.63 132	71.52 144	64.27 71	44.93 198	40.69 184	41.86 179	40.79 200	58.12 167	77.67 106	74.64 151	85.26 152	88.56 131

UGNet		67.57 139	71.69 112	62.76 169	69.88 173	82.58 133	66.43 185	58.64 152	54.71 160	51.87 129	61.74 65	62.01 82	45.46 224	74.78 143	74.99 145	84.24 182	91.02 95
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
CPTT-MVS		75.43 61	77.13 60	73.44 75	81.43 68	82.55 134	80.96 50	64.35 70	77.95 52	61.39 86	69.20 43	70.94 49	69.38 96	73.89 154	73.32 171	83.14 200	92.06 84

TSAR-MVS + COLMAP		73.09 89	76.86 61	68.71 120	74.97 144	82.49 135	74.51 116	61.83 122	83.16 30	49.31 143	82.22 24	51.62 166	68.94 100	78.76 94	75.52 143	82.67 205	84.23 173

PMMVS		70.37 113	75.06 76	64.90 149	71.46 164	81.88 136	64.10 193	55.64 192	71.31 65	46.69 150	70.69 41	58.56 111	69.53 92	79.03 85	75.63 139	81.96 215	88.32 136

MDTV_nov1_ep13		65.21 155	67.28 149	62.79 167	70.91 169	81.72 137	69.28 166	49.50 227	58.08 131	43.94 165	50.50 135	56.02 141	58.86 164	70.72 192	73.37 169	84.24 182	80.52 205

thres600view7		63.77 166	63.14 178	64.51 152	75.49 138	81.61 138	69.59 163	62.95 98	43.96 201	38.90 193	41.09 183	40.24 209	55.25 184	76.24 126	71.54 192	84.89 162	87.30 143

thres200		65.58 151	64.74 166	66.56 139	77.52 118	81.61 138	73.44 125	62.95 98	46.23 192	42.45 175	42.76 168	41.18 196	58.12 167	76.24 126	75.59 140	84.89 162	89.58 118

tfpn200view9		65.90 150	64.96 164	67.00 138	77.70 113	81.58 140	71.71 142	62.94 100	49.16 180	43.40 168	43.24 166	41.34 194	61.42 145	76.24 126	74.63 152	84.84 164	88.52 132

GA-MVS		64.55 160	65.76 163	63.12 164	69.68 174	81.56 141	69.59 163	58.16 155	45.23 197	35.58 217	47.01 156	41.82 191	59.41 159	79.62 80	78.54 103	86.32 114	86.56 148

tpm cat1		67.47 140	67.05 152	67.98 129	76.63 125	81.51 142	74.49 117	47.65 235	61.18 114	61.12 89	42.51 173	53.02 162	64.74 125	70.11 201	71.50 193	83.22 197	89.49 119

UA-Net		64.62 158	68.23 143	60.42 186	77.53 117	81.38 143	60.08 221	57.47 168	47.01 187	44.75 160	60.68 70	71.32 48	41.84 232	73.27 163	72.25 187	80.83 225	71.68 234

CNLPA		71.37 108	70.27 126	72.66 86	80.79 73	81.33 144	71.07 152	65.75 62	82.36 33	64.80 55	42.46 174	56.49 138	72.70 50	73.00 168	70.52 206	80.84 224	85.76 160

test-LLR		68.23 132	71.61 113	64.28 156	71.37 165	81.32 145	63.98 196	61.03 134	58.62 125	42.96 171	52.74 117	61.65 83	57.74 174	75.64 134	78.09 111	88.61 40	93.21 53

TESTMET0.1,1		67.38 141	71.61 113	62.45 172	66.05 202	81.32 145	63.98 196	55.36 198	58.62 125	42.96 171	52.74 117	61.65 83	57.74 174	75.64 134	78.09 111	88.61 40	93.21 53

Fast-Effi-MVS+		67.59 137	67.56 147	67.62 132	73.67 151	81.14 147	71.12 150	54.79 206	58.88 124	50.61 137	46.70 159	47.05 180	69.12 99	76.06 129	76.44 129	86.43 113	86.65 147

tpmrst		67.15 143	68.12 144	66.03 141	76.21 129	80.98 148	71.27 146	45.05 241	60.69 117	50.63 136	46.95 157	54.15 156	65.30 120	71.80 183	71.77 189	87.72 70	90.48 105

OMC-MVS		74.03 78	75.82 69	71.95 96	79.56 83	80.98 148	75.35 107	63.21 93	84.48 26	61.83 80	61.54 67	66.89 61	69.41 95	76.60 122	74.07 161	82.34 211	86.15 153

ACMP	68.86 7	72.15 100	72.25 102	72.03 94	80.96 70	80.87 150	77.93 78	64.13 74	69.29 75	60.79 94	64.04 59	53.54 159	63.91 129	73.74 157	75.27 144	84.45 179	88.98 125
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
TAPA-MVS	67.10 9	71.45 106	73.47 94	69.10 115	77.04 122	80.78 151	73.81 123	62.10 118	80.80 40	51.28 131	60.91 69	63.80 76	67.98 104	74.59 144	72.42 185	82.37 210	80.97 203
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
CDS-MVSNet		64.22 162	65.89 162	62.28 174	70.05 172	80.59 152	69.91 161	57.98 158	43.53 202	46.58 151	48.22 143	50.76 170	46.45 219	75.68 133	76.08 134	82.70 204	86.34 151
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
usedtu_dtu_shiyan1		62.43 177	64.08 169	60.50 185	59.68 231	80.58 153	66.18 188	61.75 126	53.08 166	36.05 213	36.33 213	41.74 192	51.86 195	77.70 105	77.95 115	87.47 80	81.17 202

EG-PatchMatch MVS		58.73 207	58.03 214	59.55 192	72.32 159	80.49 154	63.44 202	55.55 194	32.49 247	38.31 200	28.87 241	37.22 220	42.84 230	74.30 151	75.70 138	84.84 164	77.14 215

v2v482		63.68 167	62.85 183	64.65 151	68.01 185	80.46 155	71.90 137	57.60 165	44.26 199	42.82 173	39.80 193	38.62 215	61.56 144	73.06 166	74.86 147	86.03 124	88.90 128

v1144		63.00 172	62.39 187	63.70 161	67.72 188	80.27 156	71.23 147	56.40 183	42.51 204	40.81 183	38.12 201	37.73 216	60.42 153	74.46 146	74.55 154	85.64 141	89.12 124

LGP-MVS_train		72.02 102	73.18 95	70.67 104	82.13 62	80.26 157	79.58 57	63.04 95	70.09 68	51.98 128	65.06 56	55.62 147	62.49 140	75.97 130	76.32 132	84.80 169	88.93 126

FC-MVSNet-train		68.83 127	68.29 140	69.47 111	78.35 108	79.94 158	64.72 190	66.38 57	54.96 156	54.51 118	56.75 89	47.91 178	66.91 115	75.57 137	75.75 137	85.92 125	87.12 144

v144192		62.05 185	61.46 194	62.73 171	66.59 200	79.87 159	69.30 165	55.88 188	41.50 211	39.41 190	37.23 204	36.45 224	59.62 157	72.69 173	73.51 166	85.61 142	88.93 126

v1192		62.25 181	61.64 192	62.96 165	66.88 196	79.72 160	69.96 160	55.77 190	41.58 209	39.42 189	37.05 206	35.96 229	60.50 152	74.30 151	74.09 160	85.24 153	88.76 129

dps		64.08 163	63.22 177	65.08 147	75.27 140	79.65 161	66.68 183	46.63 239	56.94 139	55.67 112	43.96 165	43.63 189	64.00 128	69.50 206	69.82 208	82.25 212	79.02 210

v1921920		61.66 189	61.10 197	62.31 173	66.32 201	79.57 162	68.41 170	55.49 196	41.03 212	38.69 194	36.64 212	35.27 232	59.60 158	73.23 164	73.41 168	85.37 148	88.51 133

v148		62.00 186	61.19 196	62.96 165	67.46 194	79.49 163	67.87 172	57.66 164	42.30 205	45.02 159	38.20 200	38.89 214	54.77 185	69.83 203	72.60 184	84.96 158	87.01 145

FMVSNet3		70.41 112	71.89 110	68.68 121	70.89 170	79.42 164	75.63 101	60.97 136	65.32 89	51.06 132	47.37 149	62.05 79	64.90 123	82.49 39	82.27 39	88.64 39	84.34 172

v1240		61.09 192	60.55 201	61.72 178	65.92 205	79.28 165	67.16 180	54.91 203	39.79 218	38.10 201	36.08 215	34.64 234	59.15 162	72.86 169	73.36 170	85.10 155	87.84 140

dmvs_re		67.60 136	67.21 151	68.06 128	74.07 148	79.01 166	73.31 127	68.74 42	58.27 130	42.07 177	49.72 137	43.96 187	60.66 149	76.79 120	78.04 114	89.51 18	84.69 168

CMPMVS	43.63 17	57.67 215	55.43 226	60.28 188	72.01 161	79.00 167	62.77 211	53.23 216	41.77 208	45.42 154	30.74 237	39.03 212	53.01 192	64.81 230	64.65 237	75.26 250	68.03 245
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
V42		62.86 174	62.97 180	62.74 170	60.84 226	78.99 168	71.46 145	57.13 179	46.85 188	44.28 163	38.87 195	40.73 202	57.63 176	72.60 174	74.14 159	85.09 157	88.63 130

Vis-MVSNet (Re-imp)		62.25 181	68.74 135	54.68 223	73.70 150	78.74 169	56.51 230	57.49 167	55.22 154	26.86 239	54.56 103	61.35 85	31.06 242	73.10 165	74.90 146	82.49 207	83.31 181

GBi-Net		69.21 120	70.40 124	67.81 130	69.49 175	78.65 170	74.54 112	60.97 136	65.32 89	51.06 132	47.37 149	62.05 79	63.43 131	77.49 108	78.22 108	87.37 83	83.73 175

test1		69.21 120	70.40 124	67.81 130	69.49 175	78.65 170	74.54 112	60.97 136	65.32 89	51.06 132	47.37 149	62.05 79	63.43 131	77.49 108	78.22 108	87.37 83	83.73 175

FMVSNet2		68.06 133	68.57 136	67.45 135	69.49 175	78.65 170	74.54 112	60.23 148	56.29 146	49.64 142	42.13 178	57.08 129	63.43 131	81.15 58	80.99 67	87.37 83	83.73 175

tpm		64.85 157	66.02 161	63.48 162	74.52 147	78.38 173	70.98 153	44.99 243	51.61 171	43.28 170	47.66 147	53.18 160	60.57 150	70.58 195	71.30 200	86.54 109	89.45 121

ACMH	59.42 14	61.59 190	59.22 209	64.36 155	78.92 101	78.26 174	67.65 174	67.48 51	39.81 217	30.98 233	38.25 199	34.59 235	61.37 147	70.55 196	73.47 167	79.74 231	79.59 207
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
v8		63.44 169	62.58 185	64.43 153	68.28 183	78.07 175	71.82 138	54.85 204	46.70 190	45.20 157	39.40 194	40.91 199	60.54 151	72.85 170	74.39 157	85.92 125	85.76 160

Patchmtry						78.06 176	67.53 176	43.18 249		41.40 178

UniMVSNet (Re)		60.62 195	62.93 182	57.92 202	67.64 190	77.90 177	61.75 215	61.24 131	49.83 177	29.80 235	42.57 171	40.62 203	43.36 228	70.49 197	73.27 173	83.76 188	85.81 159

UniMVSNet_NR-MVSNet		62.30 180	63.51 174	60.89 182	69.48 178	77.83 178	64.07 194	63.94 82	50.03 175	31.17 231	44.82 164	41.12 197	51.37 200	71.02 189	74.81 149	85.30 151	84.95 166

v10		63.00 172	62.22 188	63.90 160	67.88 187	77.78 179	71.59 143	54.34 208	45.37 196	42.76 174	38.53 196	38.93 213	61.05 148	74.39 148	74.52 155	85.75 130	86.04 155

ACMM	66.70 10	70.42 110	68.49 137	72.67 85	82.85 56	77.76 180	77.70 82	64.76 69	64.61 95	60.74 95	49.29 138	53.97 157	65.86 119	74.97 140	75.57 141	84.13 186	83.29 182
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
TAMVS		58.86 205	60.91 198	56.47 217	62.38 221	77.57 181	58.97 225	52.98 217	38.76 227	36.17 211	42.26 177	47.94 177	46.45 219	70.23 200	70.79 203	81.86 216	78.82 211

DCV-MVSNet		69.13 124	69.07 132	69.21 113	77.65 115	77.52 182	74.68 110	57.85 162	54.92 157	55.34 116	55.74 94	55.56 148	66.35 117	75.05 139	76.56 128	83.35 194	88.13 139

test-mter		64.06 164	69.24 131	58.01 201	59.07 233	77.40 183	59.13 224	48.11 233	55.64 152	39.18 192	51.56 128	58.54 112	55.38 183	73.52 161	76.00 135	87.22 93	92.05 85

EPNet_dtu		66.17 148	70.13 127	61.54 179	81.04 69	77.39 184	68.87 168	62.50 114	69.78 70	33.51 225	63.77 60	56.22 140	37.65 238	72.20 176	72.18 188	85.69 136	79.38 208
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
pmmvs5		59.72 199	60.24 203	59.11 197	62.77 219	77.33 185	63.17 204	54.00 211	40.21 216	37.23 205	40.41 188	35.99 228	51.75 196	72.55 175	72.74 181	85.72 135	82.45 195

MIMVSNet		57.78 212	59.71 207	55.53 220	54.79 242	77.10 186	63.89 198	45.02 242	46.59 191	36.79 208	28.36 243	40.77 201	45.84 223	74.97 140	76.58 127	86.87 101	73.60 226

pm-mvs1		59.21 203	59.58 208	58.77 199	67.97 186	77.07 187	64.12 192	57.20 176	34.73 242	36.86 206	35.34 218	40.54 204	43.34 229	74.32 150	73.30 172	83.13 201	81.77 200

Fast-Effi-MVS+-dtu		63.05 171	64.72 167	61.11 181	71.21 168	76.81 188	70.72 155	43.13 251	52.51 170	35.34 218	46.55 160	46.36 181	61.40 146	71.57 187	71.44 195	84.84 164	87.79 141

MSDG		65.57 152	61.57 193	70.24 106	82.02 63	76.47 189	74.46 118	68.73 43	56.52 144	50.33 138	38.47 197	41.10 198	62.42 141	72.12 177	72.94 178	83.47 193	73.37 228

pmmvs4		63.14 170	62.46 186	63.94 159	66.03 203	76.40 190	66.82 182	57.60 165	56.74 140	50.26 139	40.81 187	37.51 218	59.26 161	71.75 185	71.48 194	83.68 192	82.53 193

FMVSNet1		63.48 168	63.07 179	63.97 158	65.31 207	76.37 191	71.77 141	57.90 161	43.32 203	45.66 153	35.06 221	49.43 173	58.57 165	77.49 108	78.22 108	84.59 176	81.60 201

blend_shiyan4		66.60 146	67.24 150	65.85 142	68.02 184	76.25 192	75.94 98	58.03 157	64.52 96	53.78 121	52.14 123	60.47 93	53.51 189	67.10 214	66.76 221	85.79 129	83.46 179

tfpnnormal		58.97 204	56.48 224	61.89 176	71.27 167	76.21 193	66.65 184	61.76 125	32.90 245	36.41 210	27.83 244	29.14 252	50.64 206	73.06 166	73.05 177	84.58 177	83.15 186

DU-MVS		60.87 194	61.82 191	59.76 191	66.69 197	75.87 194	64.07 194	61.96 119	49.31 178	31.17 231	42.76 168	36.95 221	51.37 200	69.67 204	73.20 176	83.30 196	84.95 166

NR-MVSNet		61.08 193	62.09 190	59.90 189	71.96 162	75.87 194	63.60 200	61.96 119	49.31 178	27.95 236	42.76 168	33.85 239	48.82 209	74.35 149	74.05 162	85.13 154	84.45 170

LS3D		64.54 161	62.14 189	67.34 136	80.85 71	75.79 196	69.99 159	65.87 61	60.77 116	44.35 162	42.43 175	45.95 183	65.01 121	69.88 202	68.69 213	77.97 239	71.43 236

PatchMatch-RL		62.22 184	60.69 199	64.01 157	68.74 180	75.75 197	59.27 223	60.35 145	56.09 148	53.80 120	47.06 155	36.45 224	64.80 124	68.22 210	67.22 217	77.10 242	74.02 223

PatchT		60.46 196	63.85 172	56.51 216	65.95 204	75.68 198	47.34 247	41.39 256	53.89 165	41.40 178	37.84 202	50.30 172	57.29 177	72.76 171	73.27 173	85.67 137	83.23 184

thisisatest0515		59.37 202	60.68 200	57.84 204	64.39 211	75.65 199	58.56 226	53.86 212	41.55 210	42.12 176	40.40 189	39.59 210	47.09 217	71.69 186	73.79 163	81.02 223	82.08 198

TranMVSNet+NR-MVSNet		60.38 197	61.30 195	59.30 195	68.34 182	75.57 200	63.38 203	63.78 86	46.74 189	27.73 237	42.56 172	36.84 222	47.66 214	70.36 198	74.59 153	84.91 161	82.46 194

wanda-best-256-512		57.69 213	57.90 216	57.46 208	48.58 253	75.44 201	63.15 205	57.47 168	39.27 221	38.64 195	34.66 223	40.34 205	51.44 198	66.38 216	66.54 223	85.46 144	82.64 188

FE-blended-shiyan7		57.69 213	57.90 216	57.46 208	48.58 253	75.44 201	63.15 205	57.47 168	39.27 221	38.64 195	34.66 223	40.34 205	51.44 198	66.38 216	66.54 223	85.46 144	82.64 188

usedtu_blend_shiyan5		62.84 175	63.39 175	62.21 175	48.58 253	75.44 201	74.43 119	57.47 168	39.26 224	53.78 121	52.14 123	60.47 93	53.51 189	66.38 216	66.54 223	85.46 144	83.46 179

FE-MVSNET3		61.91 187	63.26 176	60.33 187	48.58 253	75.44 201	63.15 205	57.47 168	39.27 221	53.78 121	52.14 123	60.47 93	53.51 189	66.38 216	66.54 223	85.46 144	82.59 190

blended_shiyan8		57.49 217	57.71 219	57.24 211	48.52 257	75.34 205	62.85 209	57.32 175	38.77 226	38.43 198	34.41 226	40.31 207	50.92 203	66.25 221	66.37 228	85.37 148	82.55 192

blended_shiyan6		57.50 216	57.73 218	57.23 212	48.51 258	75.34 205	62.85 209	57.33 173	38.78 225	38.38 199	34.46 225	40.29 208	50.91 204	66.27 220	66.37 228	85.37 148	82.59 190

Effi-MVS+-dtu		64.58 159	64.08 169	65.16 146	73.04 157	75.17 207	70.68 157	56.23 186	54.12 164	44.71 161	47.42 148	51.10 168	63.82 130	68.08 211	66.32 231	82.47 208	86.38 150

IterMVS-LS		66.08 149	66.56 156	65.51 143	73.67 151	74.88 208	70.89 154	53.55 214	50.42 174	48.32 147	50.59 133	55.66 146	61.83 142	73.93 153	74.42 156	84.82 168	86.01 156
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
PLC	64.00 12	68.54 128	66.66 154	70.74 103	80.28 78	74.88 208	72.64 131	63.70 88	69.26 76	55.71 111	47.24 152	55.31 149	70.42 82	72.05 179	70.67 204	81.66 218	77.19 214
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
v7n		57.04 219	56.64 223	57.52 206	62.85 218	74.75 210	61.76 214	51.80 222	35.58 241	36.02 214	32.33 232	33.61 240	50.16 207	67.73 212	70.34 207	82.51 206	82.12 197

gbinet_0.2-2-1-0.02		56.72 220	57.64 220	55.64 219	45.57 261	74.69 211	62.04 213	57.17 178	35.71 240	35.71 215	33.73 228	41.66 193	48.54 210	66.06 223	66.43 227	84.83 167	85.22 164

TransMVSNet (Re)		57.83 210	56.90 222	58.91 198	72.26 160	74.69 211	63.57 201	61.42 130	32.30 248	32.65 227	33.97 227	35.96 229	39.17 236	73.84 156	72.84 180	84.37 180	74.69 221

ADS-MVSNet		58.40 209	59.16 210	57.52 206	65.80 206	74.57 213	60.26 219	40.17 260	50.51 173	38.01 202	40.11 192	44.72 185	59.36 160	64.91 228	66.55 222	81.53 219	72.72 231

ACMH+	60.36 13	61.16 191	58.38 211	64.42 154	77.37 121	74.35 214	68.45 169	62.81 103	45.86 194	38.48 197	35.71 216	37.35 219	59.81 156	67.24 213	69.80 210	79.58 232	78.32 212

Baseline_NR-MVSNet		59.47 201	60.28 202	58.54 200	66.69 197	73.90 215	61.63 216	62.90 102	49.15 182	26.87 238	35.18 220	37.62 217	48.20 212	69.67 204	73.61 165	84.92 159	82.82 187

MDTV_nov1_ep13_2view		54.47 228	54.61 227	54.30 227	60.50 227	73.82 216	57.92 227	43.38 248	39.43 220	32.51 228	33.23 229	34.05 237	47.26 216	62.36 236	66.21 232	84.24 182	73.19 229

test0.0.03 1		57.35 218	59.89 206	54.38 226	71.37 165	73.45 217	52.71 237	61.03 134	46.11 193	26.33 240	41.73 180	44.08 186	29.72 244	71.43 188	70.90 201	85.10 155	71.56 235

UniMVSNet_ETH3D		57.83 210	56.46 225	59.43 194	63.24 216	73.22 218	67.70 173	55.58 193	36.17 236	36.84 207	32.64 230	35.14 233	51.50 197	65.81 224	69.81 209	81.73 217	82.44 196

pmmvs6		54.20 229	53.54 231	54.97 221	63.22 217	72.98 219	60.17 220	52.32 221	26.77 258	34.30 222	23.29 255	36.23 226	40.33 235	68.77 208	68.76 212	79.47 234	78.00 213

MVS-HIRNet		53.86 231	53.02 233	54.85 222	60.30 228	72.36 220	44.63 256	42.20 254	39.45 219	43.47 167	21.66 259	34.00 238	55.47 182	65.42 226	67.16 218	83.02 202	71.08 239

IterMVS		61.87 188	63.55 173	59.90 189	67.29 195	72.20 221	67.34 179	48.56 231	47.48 186	37.86 204	47.07 154	48.27 174	54.08 187	72.12 177	73.71 164	84.30 181	83.99 174
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
IterMVS-SCA-FT		60.21 198	62.97 180	57.00 214	66.64 199	71.84 222	67.53 176	46.93 238	47.56 185	36.77 209	46.85 158	48.21 175	52.51 193	70.36 198	72.40 186	71.63 258	83.53 178

USDC		59.69 200	60.03 205	59.28 196	64.04 212	71.84 222	63.15 205	55.36 198	54.90 158	35.02 219	48.34 142	29.79 251	58.16 166	70.60 194	71.33 199	79.99 229	73.42 227

SCA		63.90 165	66.67 153	60.66 183	73.75 149	71.78 224	59.87 222	43.66 247	61.13 115	45.03 158	51.64 127	59.45 109	57.92 171	70.96 190	70.80 202	83.71 190	80.92 204

anonymousdsp		54.99 224	57.24 221	52.36 230	53.82 244	71.75 225	51.49 239	48.14 232	33.74 243	33.66 224	38.34 198	36.13 227	47.54 215	64.53 232	70.60 205	79.53 233	85.59 162

dtuonly		62.74 176	63.91 171	61.36 180	61.12 225	71.54 226	70.69 156	50.99 224	52.81 168	40.13 186	42.43 175	51.07 169	62.78 136	71.77 184	71.63 191	82.47 208	86.15 153

pmnet_mix02		53.92 230	53.30 232	54.65 225	61.89 222	71.33 227	54.54 235	54.17 210	40.38 214	34.65 220	34.76 222	30.68 250	40.44 234	60.97 238	63.71 239	82.19 213	71.24 238

CR-MVSNet		62.31 179	64.75 165	59.47 193	68.63 181	71.29 228	67.53 176	43.18 249	55.83 149	41.40 178	41.04 184	55.85 142	57.29 177	72.76 171	73.27 173	78.77 236	83.23 184

RPMNet		58.63 208	62.80 184	53.76 228	67.59 192	71.29 228	54.60 234	38.13 261	55.83 149	35.70 216	41.58 181	53.04 161	47.89 213	66.10 222	67.38 215	78.65 238	84.40 171

our_test_3					63.32 214	71.07 230	55.90 231

LTVRE_ROB	47.26 16	49.41 244	49.91 246	48.82 237	64.76 209	69.79 231	49.05 242	47.12 237	20.36 265	16.52 256	36.65 211	26.96 256	50.76 205	60.47 239	63.16 242	64.73 261	72.00 233
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
Anonymous20231206		52.23 234	52.80 236	51.56 232	64.70 210	69.41 232	51.01 240	58.60 153	36.63 233	22.44 247	21.80 258	31.42 246	30.52 243	66.79 215	67.83 214	82.10 214	75.73 217

WR-MVS		51.02 236	54.56 228	46.90 244	63.84 213	69.23 233	44.78 255	56.38 184	38.19 228	14.19 260	37.38 203	36.82 223	22.39 256	60.14 240	66.20 233	79.81 230	73.95 225

FE-MVSNET2		50.42 238	51.98 240	48.61 239	44.79 262	68.96 234	52.01 238	55.50 195	32.55 246	19.88 252	21.60 260	28.20 254	35.80 239	68.31 209	71.76 190	83.69 191	72.45 232

CHOSEN 280x420		62.23 183	66.57 155	57.17 213	59.88 229	68.92 235	61.20 218	42.28 253	54.17 163	39.57 187	47.78 146	64.97 69	62.68 137	73.85 155	69.52 211	77.43 240	86.75 146

CVMVSNet		54.92 226	58.16 212	51.13 234	62.61 220	68.44 236	55.45 233	52.38 220	42.28 206	21.45 248	47.10 153	46.10 182	37.96 237	64.42 233	63.81 238	76.92 243	75.01 220

dtuonlycased		50.09 241	48.12 249	52.39 229	52.04 247	68.20 237	55.54 232	49.33 228	36.78 231	32.91 226	24.24 251	39.38 211	48.29 211	46.71 258	50.09 259	76.23 244	71.43 236

pmmvs-eth3d		55.20 221	53.95 230	56.65 215	57.34 239	67.77 238	57.54 228	53.74 213	40.93 213	41.09 182	31.19 236	29.10 253	49.07 208	65.54 225	67.28 216	81.14 221	75.81 216

WR-MVS_H		49.62 243	52.63 237	46.11 247	58.80 234	67.58 239	46.14 253	54.94 201	36.51 234	13.63 263	36.75 210	35.67 231	22.10 257	56.43 249	62.76 243	81.06 222	72.73 230

COLMAP_ROB	51.17 15	55.13 222	52.90 235	57.73 205	73.47 154	67.21 240	62.13 212	55.82 189	47.83 184	34.39 221	31.60 234	34.24 236	44.90 226	63.88 235	62.52 244	75.67 248	63.02 255
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
testgi		48.51 246	50.53 243	46.16 246	64.78 208	67.15 241	41.54 259	54.81 205	29.12 253	17.03 254	32.07 233	31.98 242	20.15 260	65.26 227	67.00 219	78.67 237	61.10 260

FMVSNet5		58.86 205	60.24 203	57.25 210	52.66 246	66.25 242	63.77 199	52.86 219	57.85 135	37.92 203	36.12 214	52.22 165	51.37 200	70.88 191	71.43 196	84.92 159	66.91 247

PEN-MVS		51.04 235	52.94 234	48.82 237	61.45 224	66.00 243	48.68 243	57.20 176	36.87 230	15.36 258	36.98 207	32.72 241	28.77 248	57.63 245	66.37 228	81.44 220	74.00 224

CP-MVSNet		50.57 237	52.60 238	48.21 241	58.77 235	65.82 244	48.17 244	56.29 185	37.41 229	16.59 255	37.14 205	31.95 243	29.21 245	56.60 248	63.71 239	80.22 227	75.56 218

PS-CasMVS		50.17 239	52.02 239	48.02 242	58.60 236	65.54 245	48.04 246	56.19 187	36.42 235	16.42 257	35.68 217	31.33 247	28.85 247	56.42 250	63.54 241	80.01 228	75.18 219

TDRefinement		52.70 232	51.02 242	54.66 224	57.41 238	65.06 246	61.47 217	54.94 201	44.03 200	33.93 223	30.13 239	27.57 255	46.17 221	61.86 237	62.48 245	74.01 254	66.06 248

test20.03		47.23 249	48.69 248	45.53 248	63.28 215	64.39 247	41.01 260	56.93 181	29.16 252	15.21 259	23.90 252	30.76 249	17.51 263	64.63 231	65.26 234	79.21 235	62.71 257

DTE-MVSNet		49.82 242	51.92 241	47.37 243	61.75 223	64.38 248	45.89 254	57.33 173	36.11 237	12.79 265	36.87 208	31.93 244	25.73 253	58.01 243	65.22 235	80.75 226	70.93 240

PatchmatchNet2					56.14 240	64.21 249	48.11 245
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
SixPastTwentyTwo		49.11 245	49.22 247	48.99 236	58.54 237	64.14 250	47.18 248	47.75 234	31.15 250	24.42 243	41.01 185	26.55 257	44.04 227	54.76 254	58.70 251	71.99 257	68.21 243

TinyColmap		52.66 233	50.09 245	55.65 218	59.72 230	64.02 251	57.15 229	52.96 218	40.28 215	32.51 228	32.42 231	20.97 266	56.65 179	63.95 234	65.15 236	74.91 251	63.87 253

N_pmnet		47.67 247	47.00 251	48.45 240	54.72 243	62.78 252	46.95 249	51.25 223	36.01 238	26.09 242	26.59 248	25.93 261	35.50 241	55.67 252	59.01 249	76.22 246	63.04 254

MDA-MVSNet-bldmvs		44.15 252	42.27 257	46.34 245	38.34 264	62.31 253	46.28 251	55.74 191	29.83 251	20.98 250	27.11 247	16.45 272	41.98 231	41.11 264	57.47 252	74.72 252	61.65 259

PM-MVS		50.11 240	50.38 244	49.80 235	47.23 260	62.08 254	50.91 241	44.84 244	41.90 207	36.10 212	35.22 219	26.05 259	46.83 218	57.64 244	55.42 256	72.90 255	74.32 222

FE-MVSNET		44.36 251	46.68 252	41.65 250	37.55 265	61.05 255	42.06 258	54.34 208	27.09 256	9.86 270	20.55 261	25.56 262	28.72 249	60.12 241	66.83 220	77.36 241	65.56 250

new-patchmatchnet		42.21 253	42.97 254	41.33 252	53.05 245	59.89 256	39.38 261	49.61 226	28.26 255	12.10 266	22.17 257	21.54 265	19.22 261	50.96 257	56.04 254	74.61 253	61.92 258

usedtu_dtu_shiyan2		40.99 255	42.22 258	39.56 254	22.63 271	59.44 257	46.80 250	43.69 246	19.05 267	21.04 249	16.27 269	23.77 263	27.46 251	53.16 256	55.09 257	75.73 247	68.78 241

RPSCF		55.07 223	58.06 213	51.57 231	48.87 252	58.95 258	53.68 236	41.26 258	62.42 107	45.88 152	54.38 108	54.26 155	53.75 188	57.15 246	53.53 258	66.01 260	65.75 249

MIMVSNet1		40.84 256	43.46 253	37.79 256	32.14 266	58.92 259	39.24 262	50.83 225	27.00 257	11.29 267	16.76 267	26.53 258	17.75 262	57.14 247	61.12 247	75.46 249	56.78 261

FC-MVSNet-test		47.24 248	54.37 229	38.93 255	59.49 232	58.25 260	34.48 265	53.36 215	45.66 195	6.66 271	50.62 132	42.02 190	16.62 264	58.39 242	61.21 246	62.99 262	64.40 252

EU-MVSNet		44.84 250	47.85 250	41.32 253	49.26 251	56.59 261	43.07 257	47.64 236	33.03 244	13.82 261	36.78 209	30.99 248	24.37 254	53.80 255	55.57 255	69.78 259	68.21 243

gm-plane-assit		54.99 224	57.99 215	51.49 233	69.27 179	54.42 262	32.32 266	42.59 252	21.18 263	13.71 262	23.61 253	43.84 188	60.21 154	87.09 6	86.55 5	90.81 4	89.28 122

pmmvs3		41.86 254	42.29 256	41.36 251	39.80 263	52.66 263	38.93 263	35.85 265	23.40 262	20.22 251	19.30 262	20.84 267	40.56 233	55.98 251	58.79 250	72.80 256	65.03 251

ambc			42.30 255		50.36 250	49.51 264	35.47 264		32.04 249	23.53 244	17.36 264	8.95 276	29.06 246	64.88 229	56.26 253	61.29 263	67.12 246

FPMVS		39.11 257	36.39 259	42.28 249	55.97 241	45.94 265	46.23 252	41.57 255	35.73 239	22.61 245	23.46 254	19.82 268	28.32 250	43.57 261	40.67 263	58.96 264	45.54 263

new_pmnet		33.19 258	35.52 260	30.47 258	27.55 270	45.31 266	29.29 267	30.92 266	29.00 254	9.88 269	18.77 263	17.64 270	26.77 252	44.07 260	45.98 261	58.41 265	47.87 262

WB-MVS		30.42 260	32.63 262	27.84 259	51.51 249	41.64 267	17.75 271	55.06 200	20.11 266	2.46 276	26.13 250	16.63 271	3.90 272	44.91 259	44.54 262	36.34 270	34.48 267

PMMVS2		20.45 263	22.31 265	18.27 265	20.52 272	26.73 268	14.85 273	28.43 268	13.69 270	0.79 277	10.35 271	9.10 275	3.83 274	27.64 267	32.87 265	41.17 267	35.81 265

PMVS	27.44 18	32.08 259	29.07 263	35.60 257	48.33 259	24.79 269	26.97 268	41.34 257	20.45 264	22.50 246	17.11 266	18.64 269	20.44 259	41.99 263	38.06 264	54.02 266	42.44 264
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
Gipuma		24.91 262	24.61 264	25.26 261	31.47 267	21.59 270	18.06 270	37.53 262	25.43 260	10.03 268	4.18 275	4.25 279	14.85 265	43.20 262	47.03 260	39.62 268	26.55 271
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
test_method		28.15 261	34.48 261	20.76 262	6.76 275	21.18 271	21.03 269	18.41 269	36.77 232	17.52 253	15.67 270	31.63 245	24.05 255	41.03 265	26.69 267	36.82 269	68.38 242

MVE	15.98 19	14.37 266	16.36 267	12.04 267	7.72 274	20.24 272	5.90 277	29.05 267	8.28 274	3.92 273	4.72 274	2.42 280	9.57 268	18.89 269	31.46 266	16.07 275	28.53 269
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
DeepMVS_CX						19.81 273	17.01 272	10.02 270	23.61 261	5.85 272	17.21 265	8.03 277	21.13 258	22.60 268		21.42 274	30.01 268

E-PMN		15.08 264	11.65 269	19.08 263	28.73 268	12.31 274	6.95 276	36.87 264	10.71 273	3.63 274	5.13 272	2.22 283	13.81 267	11.34 271	18.50 269	24.49 272	21.32 272

EMVS		14.40 265	10.71 271	18.70 264	28.15 269	12.09 275	7.06 275	36.89 263	11.00 272	3.56 275	4.95 273	2.27 282	13.91 266	10.13 273	16.06 270	22.63 273	18.51 273

tmp_tt				16.09 266	13.07 273	8.12 276	13.61 274	2.08 271	55.09 155	30.10 234	40.26 190	22.83 264	5.35 270	29.91 266	25.25 268	32.33 271

VLMVS_CLIP		11.46 267	18.27 266	3.50 268	3.73 276	5.54 277	2.13 279	0.48 272	18.85 268	0.26 279	28.51 242	9.68 274	7.31 269	17.28 270	13.56 271	7.11 276	34.49 266

VLMVS		9.08 268	15.28 268	1.84 269	1.39 277	3.31 278	1.20 280	0.09 274	18.54 269	0.39 278	27.68 245	12.43 273	3.90 272	9.16 274	8.34 273	4.04 277	27.51 270

MVS_clip		6.46 269	10.77 270	1.43 270	0.96 278	2.36 279	0.77 281	0.18 273	11.97 271	0.04 281	16.38 268	7.57 278	5.17 271	10.69 272	8.74 272	1.48 278	17.71 274

MVS_baseline		1.61 270	2.81 272	0.21 271	0.06 279	0.07 280	0.02 283	0.00 277	2.84 275	0.00 282	4.11 276	2.29 281	1.18 275	1.23 275	1.30 274	0.00 280	7.85 275

testmvs		0.05 271	0.08 273	0.01 272	0.00 281	0.01 281	0.03 282	0.01 276	0.05 276	0.00 282	0.14 278	0.01 284	0.03 278	0.05 276	0.05 275	0.01 279	0.24 277

test123		0.05 271	0.08 273	0.01 272	0.00 281	0.01 281	0.01 284	0.00 277	0.05 276	0.00 282	0.16 277	0.00 285	0.04 276	0.02 277	0.05 275	0.00 280	0.26 276

uanet_test		0.00 273	0.00 275	0.00 274	0.00 281	0.00 283	0.00 285	0.00 277	0.00 278	0.00 282	0.00 279	0.00 285	0.00 279	0.00 278	0.00 277	0.00 280	0.00 278

sosnet-low-res		0.00 273	0.00 275	0.00 274	0.00 281	0.00 283	0.00 285	0.00 277	0.00 278	0.00 282	0.00 279	0.00 285	0.00 279	0.00 278	0.00 277	0.00 280	0.00 278

sosnet		0.00 273	0.00 275	0.00 274	0.00 281	0.00 283	0.00 285	0.00 277	0.00 278	0.00 282	0.00 279	0.00 285	0.00 279	0.00 278	0.00 277	0.00 280	0.00 278

PatchmatchNet1												25.98 260	35.57 240	55.54 253	59.02 248	76.23 244	62.78 256
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
PatchmatchNet3										26.10 241	26.55 249
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
TestfortrainingZip							88.32 9	77.84 4		88.26 1						90.10 7

RE-MVS-def										31.47 230

9.14												84.47 9

SR-MVS					86.33 49			67.54 50				80.78 24

MTAPA										78.32 14		79.42 28

MTMP										76.04 18		76.65 32

Patchmatch-RL test							2.17 278

mPP-MVS					86.96 44							70.61 51

NP-MVS									81.60 38

High-resolution multi-view benchmark