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.

CSCG		74.68 18	79.22 18	69.40 19	75.69 15	80.01 11	79.12 28	52.83 44	79.34 19	63.99 10	70.49 28	82.02 14	60.35 34	77.48 26	77.22 20	84.38 1	87.97 17

MCST-MVS		73.67 26	77.39 28	69.33 20	76.26 12	78.19 19	78.77 30	54.54 33	75.33 29	59.99 30	67.96 34	79.23 24	62.43 18	78.00 19	75.71 32	84.02 2	87.30 21

SteuartSystems-ACMMP		75.23 15	79.60 17	70.13 15	76.81 8	78.92 14	81.74 11	57.99 7	75.30 31	59.83 31	75.69 20	78.45 26	60.48 31	80.58 2	79.77 2	83.94 3	88.52 12
Skip Steuart: Steuart Systems R&D Blog.
SMA-MVS		77.32 9	82.51 9	71.26 9	75.43 18	80.19 9	82.22 10	58.26 4	84.83 8	64.36 7	78.19 17	83.46 8	63.61 10	81.00 1	80.28 1	83.66 4	89.62 6
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
MED-MVS		78.72 4	83.98 4	72.58 2	78.62 3	81.11 5	84.28 1	59.29 1	86.43 3	64.24 9	87.31 6	86.02 4	65.39 4	79.79 8	78.18 12	83.65 5	89.06 9

DeepC-MVS	66.32 2	73.85 24	78.10 25	68.90 24	67.92 53	79.31 13	78.16 33	59.28 2	78.24 23	61.13 24	67.36 37	76.10 36	63.40 11	79.11 10	78.41 11	83.52 6	88.16 15
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
APDe-MVS		77.58 8	82.93 8	71.35 8	77.86 5	80.55 7	83.38 2	57.61 11	85.57 6	61.11 25	86.10 9	82.98 10	64.76 6	78.29 16	76.78 23	83.40 7	90.20 5
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
SF-MVS		77.13 10	81.70 10	71.79 4	79.32 1	80.76 6	82.96 3	57.49 12	82.82 11	64.79 5	83.69 12	84.46 7	62.83 15	77.13 28	75.21 34	83.35 8	87.85 18

TestfortrainingZip							82.75 8	57.21 14		62.96 15						83.21 9

aaEdge-Enhanced		77.69 7	83.11 7	71.36 7	77.52 7	80.15 10	82.75 8	57.21 14	84.71 9	62.22 21	87.31 6	85.76 6	65.28 5	78.00 19	76.77 24	83.21 9	89.06 9

CNVR-MVS		75.62 14	79.91 16	70.61 12	75.76 13	78.82 16	81.66 12	57.12 16	79.77 18	63.04 14	70.69 27	81.15 18	62.99 13	80.23 5	79.54 3	83.11 11	89.16 8

HFP-MVS		74.87 17	78.86 22	70.21 14	73.99 25	77.91 20	80.36 19	56.63 19	78.41 21	64.27 8	74.54 22	77.75 31	62.96 14	78.70 13	77.82 14	83.02 12	86.91 23

NCCC		74.27 21	77.83 26	70.13 15	75.70 14	77.41 25	80.51 18	57.09 17	78.25 22	62.28 20	65.54 40	78.26 27	62.18 20	79.13 9	78.51 10	83.01 13	87.68 19

ACMMP_NAP		76.15 11	81.17 11	70.30 13	74.09 24	79.47 12	81.59 15	57.09 17	81.38 13	63.89 11	79.02 15	80.48 21	62.24 19	80.05 6	79.12 4	82.94 14	88.64 11

ACMP	61.42 5	68.72 44	71.37 46	65.64 40	69.06 48	74.45 45	75.88 43	53.30 40	68.10 54	55.74 43	61.53 78	62.29 107	56.97 56	74.70 49	74.23 43	82.88 15	84.31 38
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
LGP-MVS_train		68.87 41	72.03 44	65.18 42	69.33 47	74.03 47	76.67 39	53.88 38	68.46 53	52.05 77	63.21 57	63.89 99	56.31 62	75.99 39	74.43 41	82.83 16	84.18 39

ACMMP		71.57 33	75.84 33	66.59 33	70.30 44	76.85 31	78.46 32	53.95 37	73.52 40	55.56 44	70.13 29	71.36 53	58.55 43	77.00 29	76.23 29	82.71 17	85.81 31
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
ACMMPR		73.79 25	78.41 23	68.40 26	72.35 31	77.79 22	79.32 24	56.38 21	77.67 25	58.30 37	74.16 23	76.66 33	61.40 24	78.32 15	77.80 15	82.68 18	86.51 24

SED-MVS		79.21 1	84.74 2	72.75 1	78.66 2	81.96 2	82.94 5	58.16 5	86.82 2	67.66 1	88.29 4	86.15 3	66.42 2	80.41 4	78.65 6	82.65 19	90.92 2

CDPH-MVS		71.47 34	75.82 34	66.41 34	72.97 29	77.15 27	78.14 34	54.71 30	69.88 52	53.07 70	70.98 26	74.83 40	56.95 57	76.22 36	76.57 26	82.62 20	85.09 37

MGCNet		72.45 31	77.44 27	66.61 32	71.08 38	77.81 21	76.74 38	49.30 64	73.12 41	61.17 23	73.70 24	78.08 28	58.78 40	76.75 34	76.52 27	82.61 21	86.14 27

DPM-MVS		72.80 28	75.90 32	69.19 22	75.51 16	77.68 23	81.62 14	54.83 29	75.96 27	62.06 22	63.96 53	76.58 34	58.55 43	76.66 35	76.77 24	82.60 22	83.68 43

PGM-MVS		72.89 27	77.13 29	67.94 27	72.47 30	77.25 26	79.27 26	54.63 32	73.71 38	57.95 39	72.38 25	75.33 38	60.75 29	78.25 17	77.36 19	82.57 23	85.62 32

EC-MVSNet		67.01 53	70.27 56	63.21 50	67.21 55	70.47 64	69.01 77	46.96 77	59.16 81	53.23 69	64.01 51	69.71 61	60.37 33	74.92 47	71.24 58	82.50 24	82.41 48

SD-MVS		74.43 19	78.87 20	69.26 21	74.39 23	73.70 48	79.06 29	55.24 28	81.04 14	62.71 16	80.18 14	82.61 12	61.70 23	75.43 43	73.92 45	82.44 25	85.22 35
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
DVP-MVS		78.77 2	84.89 1	71.62 5	78.04 4	82.05 1	81.64 13	57.96 8	87.53 1	66.64 2	88.77 1	86.31 1	63.16 12	79.99 7	78.56 7	82.31 26	91.03 1
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
DPE-MVS		78.11 5	83.84 5	71.42 6	77.82 6	81.32 4	82.92 6	57.81 10	84.04 10	63.19 13	88.63 2	86.00 5	64.52 7	78.71 12	77.63 16	82.26 27	90.57 3
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
XVS					70.49 42	76.96 28	74.36 49			54.48 63		74.47 41				82.24 28

X-MVStestdata					70.49 42	76.96 28	74.36 49			54.48 63		74.47 41				82.24 28

X-MVS		71.18 35	75.66 35	65.96 38	71.71 33	76.96 28	77.26 37	55.88 25	72.75 43	54.48 63	64.39 47	74.47 41	54.19 86	77.84 22	77.37 18	82.21 30	85.85 30

DVP-MVS++		78.76 3	84.44 3	72.14 3	76.63 9	81.93 3	82.92 6	58.10 6	85.86 5	66.53 3	87.86 5	86.16 2	66.45 1	80.46 3	78.53 9	82.19 31	90.29 4

OPM-MVS		69.33 39	71.05 49	67.32 29	72.34 32	75.70 36	79.57 23	56.34 22	55.21 102	53.81 67	59.51 92	68.96 64	59.67 36	77.61 25	76.44 28	82.19 31	83.88 42
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
MP-MVS		74.31 20	78.87 20	68.99 23	73.49 27	78.56 17	79.25 27	56.51 20	75.33 29	60.69 28	75.30 21	79.12 25	61.81 22	77.78 23	77.93 13	82.18 33	88.06 16
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
DeepC-MVS_fast	65.08 3	72.00 32	76.11 31	67.21 30	68.93 49	77.46 24	76.54 40	54.35 34	74.92 33	58.64 36	65.18 42	74.04 46	62.62 16	77.92 21	77.02 22	82.16 34	86.21 25
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
TPM-MVS					75.48 17	76.70 32	79.31 25			62.34 19	64.71 45	77.88 30	56.94 58			81.88 35	83.68 43
Ray Leroy Khuboni and Hongjun Xu: Textureless Resilient Propagation Matching in Multiple View Stereosis (TPM-MVS). SATNAC 2025
ACMM	60.30 7	67.58 50	68.82 65	66.13 36	70.59 41	72.01 57	76.54 40	54.26 35	65.64 58	54.78 57	50.35 138	61.72 113	58.74 41	75.79 40	75.03 36	81.88 35	81.17 56
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
HPM-MVS++		76.01 12	80.47 14	70.81 11	76.60 10	74.96 39	80.18 20	58.36 3	81.96 12	63.50 12	78.80 16	82.53 13	64.40 8	78.74 11	78.84 5	81.81 37	87.46 20

HQP-MVS		70.88 36	75.02 36	66.05 37	71.69 34	74.47 44	77.51 36	53.17 41	72.89 42	54.88 52	70.03 30	70.48 56	57.26 51	76.02 38	75.01 37	81.78 38	86.21 25

TSAR-MVS + MP.		75.22 16	80.06 15	69.56 18	74.61 22	72.74 52	80.59 17	55.70 26	80.80 15	62.65 17	86.25 8	82.92 11	62.07 21	76.89 30	75.66 33	81.77 39	85.19 36
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
train_agg		73.89 23	78.25 24	68.80 25	75.25 21	72.27 55	79.75 22	56.05 23	74.87 34	58.97 33	81.83 13	79.76 23	61.05 27	77.39 27	76.01 31	81.71 40	85.61 33

CP-MVS		72.63 29	76.95 30	67.59 28	70.67 40	75.53 37	77.95 35	56.01 24	75.65 28	58.82 34	69.16 32	76.48 35	60.46 32	77.66 24	77.20 21	81.65 41	86.97 22

APD-MVS		75.80 13	80.90 13	69.86 17	75.42 19	78.48 18	81.43 16	57.44 13	80.45 16	59.32 32	85.28 10	80.82 20	63.96 9	76.89 30	76.08 30	81.58 42	88.30 14
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
CS-MVS		65.88 56	69.71 60	61.41 57	61.76 101	68.14 80	67.65 84	44.00 114	59.14 82	52.69 71	65.19 41	68.13 70	60.90 28	74.74 48	71.58 54	81.46 43	81.04 57

3Dnovator	60.86 6	66.99 54	70.32 54	63.11 51	66.63 58	74.52 42	71.56 58	45.76 84	67.37 56	55.00 51	54.31 120	68.19 69	58.49 45	73.97 52	73.63 48	81.22 44	80.23 60

3Dnovator+	62.63 4	69.51 38	72.62 41	65.88 39	68.21 52	76.47 33	73.50 53	52.74 45	70.85 48	58.65 35	55.97 108	69.95 57	61.11 26	76.80 32	75.09 35	81.09 45	83.23 47

SPE-MVS-test		65.18 63	68.70 66	61.07 59	61.92 98	68.06 87	67.09 95	45.18 92	58.47 87	52.02 78	65.76 38	66.44 88	59.24 38	72.71 59	70.05 68	80.98 46	79.40 66

ACM-MVS					76.60 10	76.13 35	80.06 21		73.64 39	60.95 26	65.55 39	77.63 32	56.51 61			80.91 47	85.93 29

CANet		68.77 42	73.01 39	63.83 47	68.30 50	75.19 38	73.73 52	47.90 72	63.86 60	54.84 56	67.51 36	74.36 44	57.62 47	74.22 51	73.57 49	80.56 48	82.36 49

ETV-MVS		63.23 83	66.08 93	59.91 75	63.13 83	68.13 81	67.62 85	44.62 99	53.39 112	46.23 109	58.74 97	58.19 127	57.45 49	73.60 53	71.38 57	80.39 49	79.13 67

MSP-MVS		77.82 6	83.46 6	71.24 10	75.26 20	80.22 8	82.95 4	57.85 9	85.90 4	64.79 5	88.54 3	83.43 9	66.24 3	78.21 18	78.56 7	80.34 50	89.39 7
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
TSAR-MVS + GP.		69.71 37	73.92 38	64.80 45	68.27 51	70.56 63	71.90 54	50.75 54	71.38 47	57.46 41	68.68 33	75.42 37	60.10 35	73.47 54	73.99 44	80.32 51	83.97 41

MVSMamba_PlusPlus		67.64 48	71.37 46	63.30 49	66.37 62	72.40 54	70.80 61	48.42 71	62.82 64	54.87 54	63.02 60	70.51 55	59.13 39	75.59 41	73.57 49	80.21 52	81.67 53

MVS_111021_HR		67.62 49	70.39 53	64.39 46	69.77 45	70.45 65	71.44 59	51.72 50	60.77 71	55.06 49	62.14 72	66.40 89	58.13 46	76.13 37	74.79 39	80.19 53	82.04 52

DeepPCF-MVS	66.49 1	74.25 22	80.97 12	66.41 34	67.75 54	78.87 15	75.61 44	54.16 36	84.86 7	58.22 38	77.94 18	81.01 19	62.52 17	78.34 14	77.38 17	80.16 54	88.40 13

EIA-MVS		61.53 98	63.79 111	58.89 84	63.82 80	67.61 96	65.35 117	42.15 158	49.98 133	45.66 113	57.47 104	56.62 134	56.59 60	70.91 77	69.15 75	79.78 55	74.80 129

MAR-MVS		68.04 46	70.74 51	64.90 44	71.68 35	76.33 34	74.63 48	50.48 58	63.81 61	55.52 45	54.88 115	69.90 58	57.39 50	75.42 44	74.79 39	79.71 56	80.03 61
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
MSLP-MVS++		68.17 45	70.72 52	65.19 41	69.41 46	70.64 62	74.99 46	45.76 84	70.20 51	60.17 29	56.42 106	73.01 47	61.14 25	72.80 58	70.54 63	79.70 57	81.42 55

DELS-MVS		65.87 57	70.30 55	60.71 69	64.05 77	72.68 53	70.90 60	45.43 88	57.49 95	49.05 91	64.43 46	68.66 65	55.11 77	74.31 50	73.02 51	79.70 57	81.51 54
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
AdaColmap		67.89 47	68.85 64	66.77 31	73.73 26	74.30 46	75.28 45	53.58 39	70.24 50	57.59 40	51.19 135	59.19 124	60.74 30	75.33 45	73.72 47	79.69 59	77.96 82

Effi-MVS+		63.28 82	65.96 94	60.17 72	64.26 73	68.06 87	68.78 80	45.71 86	54.08 107	46.64 104	55.92 109	63.13 103	55.94 67	70.38 84	71.43 55	79.68 60	78.70 71

Casviewmamba		66.44 55	70.12 57	62.15 54	66.40 61	71.79 58	71.67 56	47.32 74	64.01 59	51.09 82	64.00 52	69.72 60	57.04 54	72.83 57	69.10 77	79.37 61	79.41 65

casdiffmvs_mvg		65.26 62	69.48 63	60.33 71	62.99 93	69.34 68	69.80 75	45.27 90	63.38 63	51.11 81	65.12 43	69.75 59	53.51 94	71.74 65	68.86 81	79.33 62	78.19 78
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
PVSNet_Blended_VisFu		63.65 80	66.92 77	59.83 77	60.03 116	73.44 50	66.33 101	48.95 66	52.20 125	50.81 84	56.07 107	60.25 120	53.56 92	73.23 56	70.01 69	79.30 63	83.24 46

GeoE		62.43 88	64.79 104	59.68 78	64.15 76	67.17 104	68.80 79	44.42 103	55.65 101	47.38 96	51.54 132	62.51 104	54.04 89	69.99 91	68.07 90	79.28 64	78.57 72

EPP-MVSNet		59.39 112	65.45 99	52.32 144	60.96 109	67.70 94	58.42 157	44.75 97	49.71 135	27.23 211	59.03 94	62.20 110	43.34 165	70.71 78	69.13 76	79.25 65	79.63 64

CPTT-MVS		68.76 43	73.01 39	63.81 48	65.42 66	73.66 49	76.39 42	52.08 46	72.61 44	50.33 85	60.73 84	72.65 49	59.43 37	73.32 55	72.12 52	79.19 66	85.99 28

viewdifsd2359ckpt09		65.38 60	68.69 67	61.53 56	62.15 95	71.64 59	71.84 55	47.45 73	58.95 83	51.79 79	61.73 77	65.71 94	57.08 53	72.17 61	70.82 59	78.87 67	79.79 62

casdiffseed414692147		63.90 77	66.17 92	61.24 58	64.92 68	69.27 69	70.00 74	46.18 81	58.66 85	51.43 80	55.30 112	62.51 104	56.20 65	70.93 76	68.62 85	78.73 68	77.90 83

Fast-Effi-MVS+		60.36 105	63.35 114	56.87 105	58.70 124	65.86 117	65.08 120	37.11 216	53.00 117	45.36 115	52.12 129	56.07 140	56.27 63	71.28 70	69.42 73	78.71 69	75.69 123

PCF-MVS	59.98 8	67.32 51	71.04 50	62.97 52	64.77 69	74.49 43	74.78 47	49.54 60	67.44 55	54.39 66	58.35 100	72.81 48	55.79 69	71.54 67	69.24 74	78.57 70	83.41 45
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
casdiffmvs		64.09 71	68.13 69	59.37 80	61.81 99	68.32 77	68.48 82	44.45 102	61.95 68	49.12 90	63.04 59	69.67 62	53.83 90	70.46 81	66.06 137	78.55 71	77.43 86
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
UniMVSNet_NR-MVSNet		56.94 139	61.14 122	52.05 146	60.02 117	65.21 127	57.44 162	52.93 43	49.37 139	24.31 227	54.62 119	50.54 162	39.04 187	68.69 111	68.84 82	78.53 72	70.72 148

hybridcas		64.37 66	68.25 68	59.84 76	63.43 82	68.95 71	70.14 72	43.11 149	62.73 66	49.21 88	62.50 69	69.22 63	54.64 82	70.95 75	66.48 129	78.51 73	76.90 101

sasdasda		65.62 58	72.06 42	58.11 87	63.94 78	71.05 60	64.49 126	43.18 144	74.08 35	47.35 97	64.17 49	71.97 50	51.17 118	71.87 63	70.74 60	78.51 73	80.56 58

canonicalmvs		65.62 58	72.06 42	58.11 87	63.94 78	71.05 60	64.49 126	43.18 144	74.08 35	47.35 97	64.17 49	71.97 50	51.17 118	71.87 63	70.74 60	78.51 73	80.56 58

IS_MVSNet		57.95 131	64.26 107	50.60 152	61.62 103	65.25 126	57.18 164	45.42 89	50.79 129	26.49 217	57.81 102	60.05 121	34.51 221	71.24 71	70.20 67	78.36 76	74.44 131

PHI-MVS		69.27 40	74.84 37	62.76 53	66.83 57	74.83 40	73.88 51	49.32 63	70.61 49	50.93 83	69.62 31	74.84 39	57.25 52	75.53 42	74.32 42	78.35 77	84.17 40

EG-PatchMatch MVS		56.98 137	58.24 161	55.50 117	64.66 70	68.62 74	61.48 138	43.63 131	38.44 237	41.44 135	38.05 228	46.18 206	43.95 161	71.71 66	70.61 62	77.87 78	74.08 135

E6new		64.03 73	66.63 84	60.99 60	63.04 88	68.16 78	70.80 61	44.14 105	57.66 93	54.63 58	60.32 86	66.05 90	55.49 70	70.14 89	67.09 106	77.85 79	76.94 96

E6		64.03 73	66.63 84	60.99 60	63.04 88	68.16 78	70.80 61	44.14 105	57.66 93	54.63 58	60.32 86	66.05 90	55.49 70	70.14 89	67.09 106	77.85 79	76.94 96

E4		64.06 72	66.79 81	60.87 64	63.03 90	68.11 82	70.61 64	44.00 114	58.24 90	54.56 60	61.00 83	66.64 85	55.22 73	69.80 93	66.69 119	77.81 81	77.07 95

E5new		64.00 75	66.77 82	60.77 67	63.02 91	68.11 82	70.42 69	43.97 116	58.41 88	54.52 61	61.10 80	66.52 86	54.97 80	69.61 95	66.52 125	77.74 82	77.09 93

E5		64.00 75	66.77 82	60.77 67	63.02 91	68.11 82	70.42 69	43.97 116	58.41 88	54.52 61	61.10 80	66.52 86	54.97 80	69.61 95	66.52 125	77.74 82	77.09 93

OpenMVS	57.13 9	62.81 85	65.75 96	59.39 79	66.47 60	69.52 67	64.26 129	43.07 150	61.34 70	50.19 86	47.29 156	64.41 98	54.60 83	70.18 88	68.62 85	77.73 84	78.89 70

E3new		64.18 69	67.01 74	60.89 62	63.07 85	68.08 85	70.57 65	43.95 118	59.33 78	54.87 54	61.94 76	66.76 84	55.16 75	69.60 97	66.42 132	77.70 85	76.92 98

E3		64.18 69	67.01 74	60.89 62	63.07 85	68.07 86	70.57 65	43.94 119	59.32 79	54.88 52	61.95 74	66.78 83	55.16 75	69.60 97	66.43 131	77.70 85	76.92 98

NR-MVSNet		55.35 154	59.46 149	50.56 153	61.33 105	62.97 146	57.91 160	51.80 48	48.62 153	20.59 234	51.99 130	44.73 221	34.10 224	68.58 114	68.64 84	77.66 87	70.67 152

QAPM		65.27 61	69.49 62	60.35 70	65.43 65	72.20 56	65.69 114	47.23 75	63.46 62	49.14 89	53.56 121	71.04 54	57.01 55	72.60 60	71.41 56	77.62 88	82.14 51

viewcassd2359sk11		64.22 67	67.08 71	60.87 64	63.08 84	68.05 89	70.51 67	43.92 121	59.80 74	55.05 50	62.49 70	66.89 81	55.09 78	69.39 101	66.19 136	77.60 89	76.77 106

IB-MVS	54.11 11	58.36 126	60.70 127	55.62 116	58.67 125	68.02 90	61.56 136	43.15 147	46.09 171	44.06 121	44.24 188	50.99 161	48.71 133	66.70 157	70.33 64	77.60 89	78.50 73
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
ACMH+	53.71 12	59.26 113	60.28 132	58.06 89	64.17 75	68.46 75	67.51 87	50.93 53	52.46 123	35.83 164	40.83 216	45.12 215	52.32 108	69.88 92	69.00 80	77.59 91	76.21 118

TranMVSNet+NR-MVSNet		55.87 147	60.14 137	50.88 151	59.46 122	63.82 140	57.93 159	52.98 42	48.94 145	20.52 235	52.87 124	47.33 189	36.81 208	69.12 107	69.03 79	77.56 92	69.89 154

E2		64.19 68	67.06 72	60.84 66	63.07 85	68.02 90	70.44 68	43.88 122	59.94 73	55.15 48	62.73 64	66.97 80	55.01 79	69.18 104	65.98 140	77.53 93	76.63 109

viewdifsd2359ckpt13		63.83 78	67.03 73	60.10 73	62.56 94	68.92 72	69.73 76	43.49 136	57.96 91	52.16 76	61.09 82	65.39 95	55.20 74	70.36 85	67.48 102	77.48 94	78.00 81

MSDG		58.46 123	58.97 154	57.85 96	66.27 64	66.23 114	67.72 83	42.33 154	53.43 111	43.68 122	43.39 198	45.35 211	49.75 128	68.66 113	67.77 95	77.38 95	67.96 171

Effi-MVS+-dtu		60.34 106	62.32 118	58.03 91	64.31 71	67.44 100	65.99 107	42.26 155	49.55 136	42.00 134	48.92 146	59.79 122	56.27 63	68.07 129	67.03 108	77.35 96	75.45 125

ET-MVSNet_ETH3D		58.38 125	61.57 120	54.67 123	42.15 237	65.26 124	65.70 112	43.82 123	48.84 146	42.34 129	59.76 91	47.76 182	56.68 59	67.02 153	68.60 87	77.33 97	73.73 138

DI_MVS_pp		61.88 92	65.17 101	58.06 89	60.05 115	65.26 124	66.03 105	44.22 104	55.75 100	46.73 102	54.64 118	68.12 71	54.13 88	69.13 106	66.66 120	77.18 98	76.61 110

v1144		58.88 116	60.16 136	57.39 98	58.03 131	67.26 102	67.14 93	44.46 101	45.17 177	44.33 120	47.81 153	49.92 167	53.20 102	67.77 135	66.62 123	77.15 99	76.58 111

v1192		58.51 120	59.66 143	57.17 100	57.82 133	67.72 93	66.21 103	44.83 96	44.15 186	43.49 123	46.68 158	47.94 179	53.55 93	67.39 143	66.51 127	77.13 100	77.20 90

UniMVSNet (Re)		55.15 159	60.39 131	49.03 167	55.31 163	64.59 132	55.77 179	50.63 55	48.66 152	20.95 233	51.47 133	50.40 163	34.41 223	67.81 134	67.89 92	77.11 101	71.88 142

viewmacassd2359aftdt		63.43 81	66.95 76	59.32 81	61.27 107	67.48 99	70.15 71	40.54 176	57.82 92	52.27 75	60.49 85	66.81 82	54.58 84	70.67 79	67.39 104	77.08 102	78.02 80

viewmanbaseed2359cas		63.67 79	67.42 70	59.30 82	61.34 104	67.42 101	70.01 73	40.50 179	59.53 76	52.60 72	62.56 68	67.34 79	54.44 85	70.33 86	66.93 112	76.91 103	77.82 85

v10		59.17 115	60.60 128	57.50 97	57.95 132	66.73 108	67.09 95	44.11 107	46.85 165	45.42 114	48.18 152	51.07 158	53.63 91	67.84 133	66.59 124	76.79 104	76.92 98

MVS_Test		62.40 89	66.23 90	57.94 92	59.77 120	64.77 131	66.50 100	41.76 161	57.26 97	49.33 87	62.68 65	67.47 78	53.50 96	68.57 115	66.25 133	76.77 105	76.58 111

FA-MVS(training)		60.00 108	63.14 116	56.33 109	59.50 121	64.30 136	65.15 119	38.75 200	56.20 99	45.77 111	53.08 122	56.45 135	52.10 111	69.04 109	67.67 98	76.69 106	75.27 128

v144192		58.23 129	59.40 150	56.87 105	57.56 135	66.89 106	65.70 112	45.01 94	44.06 187	42.88 125	46.61 160	48.09 178	53.49 97	66.94 154	65.90 143	76.61 107	77.29 88

v2v482		58.69 119	60.12 139	57.03 102	57.16 153	66.05 116	67.17 92	43.52 134	46.33 169	45.19 116	49.46 142	51.02 159	52.51 106	67.30 146	66.03 139	76.61 107	74.62 130

ACMH	52.42 13	58.24 128	59.56 148	56.70 107	66.34 63	69.59 66	66.71 98	49.12 65	46.08 172	28.90 199	42.67 210	41.20 234	52.60 105	71.39 68	70.28 65	76.51 109	75.72 122
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
PVSNet_BlendedMVS		61.63 96	64.82 102	57.91 94	57.21 149	67.55 97	63.47 133	46.08 82	54.72 104	52.46 73	58.59 98	60.73 116	51.82 114	70.46 81	65.20 154	76.44 110	76.50 115

PVSNet_Blended		61.63 96	64.82 102	57.91 94	57.21 149	67.55 97	63.47 133	46.08 82	54.72 104	52.46 73	58.59 98	60.73 116	51.82 114	70.46 81	65.20 154	76.44 110	76.50 115

v1921920		57.89 132	59.02 153	56.58 108	57.55 136	66.66 112	64.72 123	44.70 98	43.55 191	42.73 126	46.17 168	46.93 197	53.51 94	66.78 156	65.75 145	76.29 112	77.28 89

EPNet		65.14 65	69.54 61	60.00 74	66.61 59	67.67 95	67.53 86	55.32 27	62.67 67	46.22 110	67.74 35	65.93 92	48.07 141	72.17 61	72.12 52	76.28 113	78.47 74
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
v8		58.88 116	60.57 130	56.92 103	57.35 143	65.69 119	66.69 99	42.64 152	47.89 160	45.77 111	49.04 143	52.98 151	52.77 104	67.51 141	65.57 146	76.26 114	75.30 127

DCV-MVSNet		59.49 109	64.00 110	54.23 126	61.81 99	64.33 135	61.42 139	43.77 124	52.85 120	38.94 152	55.62 111	62.15 111	43.24 168	69.39 101	67.66 99	76.22 115	75.97 120

v1240		57.55 134	58.63 157	56.29 110	57.30 146	66.48 113	63.77 131	44.56 100	42.77 202	42.48 128	45.64 174	46.28 204	53.46 98	66.32 163	65.80 144	76.16 116	77.13 92

CLD-MVS		67.02 52	71.57 45	61.71 55	71.01 39	74.81 41	71.62 57	38.91 194	71.86 46	60.70 27	64.97 44	67.88 73	51.88 113	76.77 33	74.98 38	76.11 117	69.75 155
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
test2506		55.82 149	59.57 147	51.46 148	60.39 113	64.55 133	58.69 155	48.87 67	53.91 108	26.99 212	48.97 144	41.72 233	37.71 198	70.96 73	69.49 71	76.08 118	67.37 176

ECVR-MVS		56.44 144	60.74 126	51.42 149	60.39 113	64.55 133	58.69 155	48.87 67	53.91 108	26.76 214	45.55 176	53.43 149	37.71 198	70.96 73	69.49 71	76.08 118	67.32 178

v7n		55.67 150	57.46 169	53.59 132	56.06 158	65.29 123	61.06 142	43.26 143	40.17 221	37.99 156	40.79 217	45.27 214	47.09 145	67.67 138	66.21 134	76.08 118	76.82 102

OMC-MVS		65.16 64	71.35 48	57.94 92	52.95 182	68.82 73	69.00 78	38.28 203	79.89 17	55.20 47	62.76 63	68.31 67	56.14 66	71.30 69	68.70 83	76.06 121	79.67 63

DU-MVS		55.41 153	59.59 144	50.54 154	54.60 170	62.97 146	57.44 162	51.80 48	48.62 153	24.31 227	51.99 130	47.00 194	39.04 187	68.11 127	67.75 96	76.03 122	70.72 148

FC-MVSNet-train		58.40 124	63.15 115	52.85 140	64.29 72	61.84 156	55.98 178	46.47 79	53.06 115	34.96 168	61.95 74	56.37 138	39.49 185	68.67 112	68.36 88	75.92 123	71.81 143

Anonymous20231211		57.71 133	60.79 125	54.13 128	61.68 102	65.81 118	60.81 144	43.70 129	51.97 126	39.67 147	34.82 236	63.59 100	43.31 166	68.55 116	66.63 122	75.59 124	74.13 134

MVSTER		57.19 135	61.11 123	52.62 142	50.82 202	58.79 186	61.55 137	37.86 213	48.81 148	41.31 137	57.43 105	52.10 154	48.60 135	68.19 126	66.75 117	75.56 125	75.68 124

Anonymous202405211			60.60 128		63.44 81	66.71 111	61.00 143	47.23 75	50.62 131		36.85 231	60.63 119	43.03 169	69.17 105	67.72 97	75.41 126	72.54 140

thisisatest0530		56.68 141	59.68 142	53.19 136	52.97 181	60.96 166	59.41 150	40.51 177	48.26 156	41.06 140	52.67 125	46.30 203	49.78 126	67.66 139	67.83 93	75.39 127	74.07 136

Fast-Effi-MVS+-dtu		56.30 145	59.29 151	52.82 141	58.64 126	64.89 128	65.56 115	32.89 244	45.80 174	35.04 167	45.89 171	54.14 145	49.41 129	67.16 149	66.45 130	75.37 128	70.69 150

TSAR-MVS + ACMM		72.56 30	79.07 19	64.96 43	73.24 28	73.16 51	78.50 31	48.80 70	79.34 19	55.32 46	85.04 11	81.49 17	58.57 42	75.06 46	73.75 46	75.35 129	85.61 33

tttt0517		56.53 143	59.59 144	52.95 139	52.66 184	60.99 165	59.21 152	40.51 177	47.89 160	40.40 143	52.50 128	46.04 207	49.78 126	67.75 136	67.83 93	75.15 130	74.17 133

test1111		55.24 155	59.98 140	49.71 158	59.80 119	64.10 138	56.48 172	49.34 62	52.27 124	21.56 232	44.49 186	51.96 155	35.93 216	70.59 80	69.07 78	75.13 131	67.40 174

MGCFI-Net		61.46 99	69.72 59	51.83 147	61.00 108	66.16 115	56.50 171	40.73 174	73.98 37	35.18 165	64.23 48	71.42 52	42.45 171	69.22 103	64.01 169	75.09 132	79.03 69

LS3D		60.20 107	61.70 119	58.45 86	64.18 74	67.77 92	67.19 90	48.84 69	61.67 69	41.27 138	45.89 171	51.81 156	54.18 87	68.78 110	66.50 128	75.03 133	69.48 162

baseline2		55.89 146	57.82 164	53.64 130	57.36 142	61.09 164	59.75 148	40.45 180	47.38 163	41.26 139	51.23 134	46.90 198	48.11 139	65.63 174	64.38 166	74.90 134	68.16 170

HyFIR lowres test		56.87 140	58.60 158	54.84 120	56.62 157	69.27 69	64.77 122	42.21 156	45.66 175	37.50 159	33.08 240	57.47 132	53.33 99	65.46 176	67.94 91	74.60 135	71.35 145

PLC	52.09 14	59.21 114	62.47 117	55.41 118	53.24 180	64.84 129	64.47 128	40.41 182	65.92 57	44.53 119	46.19 167	55.69 141	55.33 72	68.24 123	65.30 151	74.50 136	71.09 146
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
GA-MVS		55.67 150	58.33 159	52.58 143	55.23 167	63.09 145	61.08 141	40.15 185	42.95 197	37.02 162	52.61 126	47.68 183	47.51 143	65.92 170	65.35 148	74.49 137	70.68 151

MVS_111021_LR		63.05 84	66.43 88	59.10 83	61.33 105	63.77 141	65.87 111	43.58 132	60.20 72	53.70 68	62.09 73	62.38 106	55.84 68	70.24 87	68.08 89	74.30 138	78.28 77

anonymousdsp		52.84 169	57.78 165	47.06 189	40.24 248	58.95 185	53.70 198	33.54 240	36.51 245	32.69 181	43.88 191	45.40 210	47.97 142	67.17 148	70.28 65	74.22 139	82.29 50

CANet_DTU		58.88 116	64.68 105	52.12 145	55.77 161	66.75 107	63.92 130	37.04 217	53.32 113	37.45 160	59.81 90	61.81 112	44.43 159	68.25 121	67.47 103	74.12 140	75.33 126

viewdifsd2359ckpt07		61.71 94	65.49 98	57.31 99	62.12 96	65.52 121	68.53 81	38.21 205	56.37 98	48.07 95	61.11 79	65.85 93	52.82 103	68.34 118	64.46 165	74.08 141	76.80 103

blended_shiyan8		49.21 204	52.59 208	45.27 203	41.67 239	58.47 189	52.41 208	38.16 206	38.60 231	28.53 204	40.26 220	47.07 192	36.78 209	59.62 204	57.26 213	74.06 142	66.88 184

blended_shiyan6		49.22 203	52.60 207	45.26 204	41.68 238	58.46 191	52.42 207	38.16 206	38.60 231	28.50 205	40.28 219	47.09 191	36.76 210	59.62 204	57.25 214	74.06 142	66.92 181

UA-Net		58.50 121	64.68 105	51.30 150	66.97 56	67.13 105	53.68 200	45.65 87	49.51 138	31.58 186	62.91 61	68.47 66	35.85 217	68.20 125	67.28 105	74.03 144	69.24 166

blend_shiyan4		50.41 190	53.51 192	46.79 193	44.79 228	58.47 189	52.51 206	36.99 218	41.74 210	34.13 171	42.68 207	49.24 170	38.37 190	58.53 218	56.69 219	73.96 145	67.20 179

usedtu_dtu_shiyan1		51.41 182	55.78 175	46.30 197	47.91 214	59.47 177	52.99 205	42.13 159	48.17 157	24.88 223	40.95 215	48.18 177	35.95 215	64.48 182	64.49 163	73.94 146	64.75 206

WR-MVS		48.78 212	55.06 183	41.45 226	55.50 162	60.40 169	43.77 247	49.99 59	41.92 208	8.10 265	45.24 180	45.56 209	17.47 253	61.57 195	64.60 160	73.85 147	66.14 195

v148		55.58 152	57.61 168	53.20 135	54.59 172	61.86 155	61.18 140	38.70 201	44.30 185	42.25 130	47.53 154	50.24 165	48.73 132	65.15 178	62.61 189	73.79 148	71.61 144

wanda-best-256-512		49.05 208	52.38 212	45.17 207	41.54 240	58.31 196	52.24 210	38.00 208	38.58 233	28.56 202	40.23 221	47.00 194	36.88 206	59.28 207	56.77 215	73.78 149	66.45 187

FE-blended-shiyan7		49.05 208	52.38 212	45.17 207	41.54 240	58.31 196	52.24 210	38.00 208	38.58 233	28.56 202	40.23 221	47.00 194	36.88 206	59.28 207	56.77 215	73.78 149	66.45 187

usedtu_blend_shiyan5		50.12 194	53.15 199	46.58 194	41.54 240	58.31 196	53.69 199	38.00 208	38.58 233	34.13 171	42.68 207	49.24 170	38.37 190	59.28 207	56.77 215	73.78 149	67.20 179

FE-MVSNET3		49.99 197	53.11 200	46.34 196	41.54 240	58.31 196	52.24 210	38.00 208	38.58 233	34.13 171	42.68 207	49.24 170	38.37 190	59.28 207	56.77 215	73.78 149	66.92 181

viewdifsd2359ckpt11		59.45 110	63.57 112	54.65 124	57.17 151	62.71 151	64.67 124	38.99 191	52.96 118	42.12 132	58.97 95	62.23 108	51.18 116	67.35 144	63.98 170	73.75 153	76.80 103

viewmsd2359difaftdt		59.45 110	63.57 112	54.65 124	57.17 151	62.71 151	64.67 124	38.99 191	52.96 118	42.12 132	58.97 95	62.22 109	51.18 116	67.35 144	63.98 170	73.75 153	76.80 103

PEN-MVS		49.21 204	54.32 187	43.24 220	54.33 173	59.26 181	47.04 232	51.37 52	41.67 211	9.97 259	46.22 166	41.80 232	22.97 248	60.52 198	64.03 168	73.73 155	66.75 185

GBi-Net		55.20 156	60.25 133	49.31 161	52.42 185	61.44 158	57.03 165	44.04 110	49.18 142	30.47 188	48.28 148	58.19 127	38.22 193	68.05 130	66.96 109	73.69 156	69.65 156

test1		55.20 156	60.25 133	49.31 161	52.42 185	61.44 158	57.03 165	44.04 110	49.18 142	30.47 188	48.28 148	58.19 127	38.22 193	68.05 130	66.96 109	73.69 156	69.65 156

FMVSNet2		55.04 160	59.95 141	49.31 161	52.42 185	61.44 158	57.03 165	44.08 109	49.55 136	30.40 191	46.89 157	58.84 125	38.22 193	67.07 152	66.21 134	73.69 156	69.65 156

FMVSNet1		54.08 164	58.68 156	48.71 171	50.90 201	61.35 161	56.73 169	43.94 119	45.91 173	29.32 198	42.72 206	56.26 139	37.70 200	68.05 130	66.96 109	73.69 156	69.50 161

dtuplus		60.38 104	64.02 109	56.13 111	58.12 130	63.10 144	66.05 104	41.59 164	54.56 106	46.60 105	59.27 93	64.90 96	50.72 123	66.90 155	63.35 179	73.68 160	76.05 119

viewmambaseed2359dif		60.40 103	64.15 108	56.03 112	57.79 134	63.53 143	65.91 110	41.64 162	54.98 103	46.47 106	60.16 89	64.71 97	50.76 122	66.25 165	62.83 185	73.61 161	76.57 113

diffmvs_AUTHOR		61.79 93	66.80 80	55.95 113	56.69 155	63.92 139	67.27 89	41.28 168	59.32 79	46.43 107	63.31 56	68.30 68	50.56 124	68.30 119	66.06 137	73.48 162	78.36 75

gbinet_0.2-2-1-0.02		48.89 210	52.69 204	44.45 213	39.54 251	59.33 179	52.39 209	38.76 199	35.41 246	26.17 219	39.15 225	47.39 188	36.41 214	60.29 202	57.58 211	73.45 163	69.65 156

viewmamba		62.28 91	66.90 78	56.89 104	58.53 127	64.79 130	67.28 88	43.17 146	59.60 75	48.15 94	63.20 58	67.57 77	50.82 121	69.05 108	66.77 116	73.41 164	77.32 87

MS-PatchMatch		58.19 130	60.20 135	55.85 115	65.17 67	64.16 137	64.82 121	41.48 166	50.95 128	42.17 131	45.38 177	56.42 136	48.08 140	68.30 119	66.70 118	73.39 165	69.46 164

TAPA-MVS	54.74 10	60.85 101	66.61 86	54.12 129	47.38 216	65.33 122	65.35 117	36.51 221	75.16 32	48.82 92	54.70 117	63.51 101	53.31 100	68.36 117	64.97 159	73.37 166	74.27 132
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
thisisatest0515		53.85 165	56.84 172	50.37 155	50.25 205	58.17 202	55.99 177	39.90 187	41.88 209	38.16 155	45.91 170	45.30 212	44.58 158	66.15 168	66.89 113	73.36 167	73.57 139

FMVSNet3		54.78 161	59.58 146	49.17 164	52.37 188	61.31 162	56.72 170	44.04 110	49.18 142	30.47 188	48.28 148	58.19 127	38.09 196	65.48 175	65.20 154	73.31 168	69.45 165

WR-MVS_H		47.65 219	53.67 190	40.63 232	51.45 193	59.74 176	44.71 245	49.37 61	40.69 217	7.61 267	46.04 169	44.34 226	17.32 254	57.79 223	61.18 195	73.30 169	65.86 197

TransMVSNet (Re)		51.92 180	55.38 179	47.88 184	60.95 110	59.90 174	53.95 195	45.14 93	39.47 225	24.85 224	43.87 192	46.51 202	29.15 233	67.55 140	65.23 153	73.26 170	65.16 204

diffmvs		61.64 95	66.55 87	55.90 114	56.63 156	63.71 142	67.13 94	41.27 169	59.49 77	46.70 103	63.93 54	68.01 72	50.46 125	67.30 146	65.51 147	73.24 171	77.87 84
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
onestephybrid01		62.35 90	66.85 79	57.10 101	59.33 123	65.58 120	67.18 91	43.71 128	57.48 96	48.34 93	62.61 66	67.84 74	50.93 120	69.40 100	66.88 115	73.15 172	78.12 79

FE-MVSNET2		45.69 231	49.95 229	40.72 231	40.11 249	56.16 213	46.59 233	41.89 160	36.97 244	13.66 249	29.00 252	37.59 250	28.96 236	63.26 184	63.93 173	73.13 173	62.72 219

IterMVS-LS		58.30 127	61.39 121	54.71 122	59.92 118	58.40 193	59.42 149	43.64 130	48.71 150	40.25 145	57.53 103	58.55 126	52.15 110	65.42 177	65.34 149	72.85 174	75.77 121
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
Baseline_NR-MVSNet		53.50 166	57.89 163	48.37 178	54.60 170	59.25 182	56.10 174	51.84 47	49.32 140	17.92 242	45.38 177	47.68 183	36.93 205	68.11 127	65.95 141	72.84 175	69.57 160

Vis-MVSNet		58.48 122	65.70 97	50.06 157	53.40 179	67.20 103	60.24 147	43.32 141	48.83 147	30.23 192	62.38 71	61.61 114	40.35 180	71.03 72	69.77 70	72.82 176	79.11 68
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
UniMVSNet_ETH3D		52.62 170	55.98 174	48.70 172	51.04 199	60.71 168	56.87 168	46.74 78	42.52 204	26.96 213	42.50 211	45.95 208	37.87 197	66.22 166	65.15 157	72.74 177	68.78 169

V42		56.97 138	60.14 137	53.28 134	48.16 211	62.78 149	66.30 102	37.93 212	47.44 162	42.68 127	48.19 151	52.59 153	51.90 112	67.46 142	65.94 142	72.72 178	76.55 114

tfpn200view9		52.53 171	55.51 177	49.06 166	57.31 144	60.24 170	55.42 185	43.77 124	42.85 200	27.81 207	43.00 204	45.06 217	37.32 202	66.38 160	64.54 161	72.71 179	66.54 186

CNLPA		62.78 86	66.31 89	58.65 85	58.47 128	68.41 76	65.98 108	41.22 170	78.02 24	56.04 42	46.65 159	59.50 123	57.50 48	69.67 94	65.27 152	72.70 180	76.67 108

thres600view7		51.91 181	55.14 181	48.14 180	57.43 140	60.18 171	54.60 190	43.73 126	42.61 203	25.20 222	43.10 203	44.47 224	35.19 219	66.36 161	63.28 180	72.66 181	66.01 196

thres400		52.38 174	55.51 177	48.74 170	57.49 139	60.10 173	55.45 184	43.54 133	42.90 199	26.72 215	43.34 200	45.03 219	36.61 211	66.20 167	64.53 162	72.66 181	66.43 189

thres200		52.39 173	55.37 180	48.90 168	57.39 141	60.18 171	55.60 181	43.73 126	42.93 198	27.41 209	43.35 199	45.09 216	36.61 211	66.36 161	63.92 174	72.66 181	65.78 198

hybridnocas07		61.04 100	66.19 91	55.03 119	55.86 160	62.77 150	66.02 106	39.98 186	58.77 84	47.07 99	63.48 55	67.60 76	48.61 134	68.22 124	65.32 150	72.62 184	77.17 91

thres100view900		52.04 178	54.81 185	48.80 169	57.31 144	59.33 179	55.30 186	42.92 151	42.85 200	27.81 207	43.00 204	45.06 217	36.99 204	64.74 180	63.51 176	72.47 185	65.21 203

hybrid		60.72 102	65.86 95	54.73 121	55.25 166	62.37 153	65.92 109	39.45 189	58.64 86	46.85 101	62.81 62	67.76 75	48.44 136	67.71 137	65.01 158	72.46 186	76.72 107

TSAR-MVS + COLMAP		62.65 87	69.90 58	54.19 127	46.31 221	66.73 108	65.49 116	41.36 167	76.57 26	46.31 108	76.80 19	56.68 133	53.27 101	69.50 99	66.65 121	72.40 187	76.36 117

pmmvs4		54.66 162	56.07 173	53.00 138	54.63 169	57.08 211	60.43 146	44.10 108	51.69 127	40.55 142	46.55 163	44.79 220	45.95 151	62.54 189	63.66 175	72.36 188	66.20 193

DTE-MVSNet		48.03 218	53.28 196	41.91 224	54.64 168	57.50 209	44.63 246	51.66 51	41.02 215	7.97 266	46.26 165	40.90 235	20.24 251	60.45 199	62.89 184	72.33 189	63.97 211

UGNet		57.03 136	65.25 100	47.44 187	46.54 220	66.73 108	56.30 173	43.28 142	50.06 132	32.99 178	62.57 67	63.26 102	33.31 226	68.25 121	67.58 100	72.20 190	78.29 76
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
COLMAP_ROB	46.52 15	51.99 179	54.86 184	48.63 173	49.13 209	61.73 157	60.53 145	36.57 220	53.14 114	32.95 179	37.10 229	38.68 245	40.49 179	65.72 172	63.08 181	72.11 191	64.60 208
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
CP-MVSNet		48.37 213	53.53 191	42.34 222	51.35 195	58.01 205	46.56 234	50.54 56	41.62 212	10.61 255	46.53 164	40.68 238	23.18 246	58.71 216	61.83 192	71.81 192	67.36 177

0.4-1-1-0.1		50.59 187	53.51 192	47.17 188	46.63 219	58.96 184	54.24 192	36.39 222	43.20 194	33.94 175	44.77 183	49.55 168	40.04 184	57.50 225	56.17 222	71.80 193	64.43 210

pmmvs-eth3d		51.33 183	52.25 214	50.26 156	50.82 202	54.65 217	56.03 176	43.45 140	43.51 192	37.20 161	39.20 224	39.04 244	42.28 172	61.85 194	62.78 186	71.78 194	64.72 207

PS-CasMVS		48.18 215	53.25 197	42.27 223	51.26 196	57.94 207	46.51 235	50.52 57	41.30 213	10.56 256	45.35 179	40.34 240	23.04 247	58.66 217	61.79 193	71.74 195	67.38 175

gm-plane-assit		44.74 233	45.95 241	43.33 218	60.88 111	46.79 249	36.97 260	32.24 247	24.15 263	11.79 254	29.26 251	32.97 257	46.64 146	65.09 179	62.95 183	71.45 196	60.42 230

0.3-1-1-0.015		50.11 195	52.80 202	46.98 191	46.15 223	58.39 194	53.96 194	35.90 225	42.52 204	34.13 171	43.69 194	49.24 170	40.30 181	56.60 233	55.53 228	71.41 197	63.65 214

tfpnnormal		50.16 193	52.19 215	47.78 186	56.86 154	58.37 195	54.15 193	44.01 113	38.35 239	25.94 220	36.10 232	37.89 247	34.50 222	65.93 169	63.42 177	71.26 198	65.28 202

baseline1		54.48 163	58.69 155	49.57 159	60.63 112	58.29 201	55.70 180	44.95 95	49.20 141	29.62 195	54.77 116	54.75 143	35.29 218	67.15 150	64.08 167	71.21 199	62.58 223

gg-mvs-nofinetune		49.07 207	52.56 209	45.00 209	61.99 97	59.78 175	53.55 202	41.63 163	31.62 255	12.08 253	29.56 250	53.28 150	29.57 232	66.27 164	64.49 163	71.19 200	62.92 218

0.4-1-1-0.2		49.99 197	52.69 204	46.83 192	45.99 224	58.16 203	53.71 197	35.75 226	42.13 207	34.14 170	44.08 189	49.28 169	40.24 183	56.44 235	55.24 231	71.18 201	63.49 216

pm-mvs1		51.02 185	55.55 176	45.73 200	54.16 174	58.52 188	50.92 215	42.56 153	40.32 219	25.67 221	43.66 195	50.34 164	30.06 231	65.85 171	63.97 172	70.99 202	66.21 192

TDRefinement		49.31 200	52.44 210	45.67 202	30.44 263	59.42 178	59.24 151	39.78 188	48.76 149	31.20 187	35.73 233	29.90 263	42.81 170	64.24 183	62.59 190	70.55 203	66.43 189

IterMVS		53.45 167	57.12 170	49.17 164	49.23 208	60.93 167	59.05 153	34.63 232	44.53 180	33.22 176	51.09 137	51.01 160	48.38 137	62.43 191	60.79 198	70.54 204	69.05 167
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
USDC		51.11 184	53.71 189	48.08 182	44.76 229	55.99 215	53.01 204	40.90 171	52.49 122	36.14 163	44.67 184	33.66 256	43.27 167	63.23 185	61.10 196	70.39 205	64.82 205

dmvs_re		52.07 176	55.11 182	48.54 175	57.27 147	51.93 227	57.73 161	43.13 148	43.65 189	26.57 216	44.52 185	50.00 166	36.53 213	66.58 159	62.15 191	69.97 206	66.91 183

pmmvs6		48.35 214	51.64 217	44.51 212	51.92 191	57.94 207	49.44 221	42.17 157	34.45 248	24.62 226	28.87 254	46.90 198	29.07 235	64.60 181	63.08 181	69.83 207	65.68 199

SixPastTwentyTwo		47.55 221	50.25 227	44.41 214	47.30 217	54.31 219	47.81 227	40.36 183	33.76 249	19.93 237	43.75 193	32.77 258	42.07 173	59.82 203	60.94 197	68.98 208	66.37 191

pmmvs5		47.07 224	51.02 223	42.46 221	45.18 227	51.47 229	48.23 226	33.09 243	38.17 240	28.62 201	46.60 161	43.48 228	30.74 229	58.28 220	58.63 207	68.92 209	60.48 229

Vis-MVSNet (Re-imp)		50.37 191	57.73 167	41.80 225	57.53 137	54.35 218	45.70 239	45.24 91	49.80 134	13.43 250	58.23 101	56.42 136	20.11 252	62.96 187	63.36 178	68.76 210	58.96 235

CDS-MVSNet		52.42 172	57.06 171	47.02 190	53.92 177	58.30 200	55.50 183	46.47 79	42.52 204	29.38 197	49.50 141	52.85 152	28.49 237	66.70 157	66.89 113	68.34 211	62.63 222
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
CostFormer		56.57 142	59.13 152	53.60 131	57.52 138	61.12 163	66.94 97	35.95 224	53.44 110	44.68 118	55.87 110	54.44 144	48.21 138	60.37 200	58.33 208	68.27 212	70.33 153

PMMVS		49.20 206	54.28 188	43.28 219	34.13 257	45.70 252	48.98 222	26.09 258	46.31 170	34.92 169	55.22 113	53.47 148	47.48 144	59.43 206	59.04 206	68.05 213	60.77 228

EPNet_dtu		52.05 177	58.26 160	44.81 210	54.10 175	50.09 234	52.01 213	40.82 173	53.03 116	27.41 209	54.90 114	57.96 131	26.72 239	62.97 186	62.70 188	67.78 214	66.19 194
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
TinyColmap		47.08 223	47.56 239	46.52 195	42.35 236	53.44 221	51.77 214	40.70 175	43.44 193	31.92 184	29.78 249	23.72 269	45.04 157	61.99 193	59.54 204	67.35 215	61.03 227

CHOSEN 1792x2688		55.85 148	58.01 162	53.33 133	57.26 148	62.82 148	63.29 135	41.55 165	46.65 167	38.34 153	34.55 237	53.50 147	52.43 107	67.10 151	67.56 101	67.13 216	73.92 137

test-LLR		49.28 201	50.29 225	48.10 181	55.26 164	47.16 244	49.52 219	43.48 138	39.22 226	31.98 182	43.65 196	47.93 180	41.29 177	56.80 229	55.36 229	67.08 217	61.94 224

TESTMET0.1,1		46.09 229	50.29 225	41.18 228	36.91 255	47.16 244	49.52 219	20.32 264	39.22 226	31.98 182	43.65 196	47.93 180	41.29 177	56.80 229	55.36 229	67.08 217	61.94 224

test-mter		45.30 232	50.37 224	39.38 235	33.65 259	46.99 246	47.59 228	18.59 265	38.75 229	28.00 206	43.28 201	46.82 200	41.50 176	57.28 226	55.78 225	66.93 219	63.70 213

FE-MVSNET		39.75 248	44.50 247	34.21 249	32.01 262	48.77 238	37.71 259	38.94 193	30.91 257	6.25 270	26.24 258	32.10 260	23.68 244	57.28 226	59.53 205	66.68 220	56.64 240

PatchMatch-RL		50.11 195	51.56 218	48.43 176	46.23 222	51.94 226	50.21 218	38.62 202	46.62 168	37.51 158	42.43 212	39.38 242	52.24 109	60.98 197	59.56 203	65.76 221	60.01 233

CR-MVSNet		50.47 188	52.61 206	47.98 183	49.03 210	52.94 222	48.27 224	38.86 196	44.41 181	39.59 148	44.34 187	44.65 223	46.63 147	58.97 213	60.31 200	65.48 222	62.66 220

RPMNet		46.41 226	48.72 234	43.72 215	47.77 215	52.94 222	46.02 238	33.92 236	44.41 181	31.82 185	36.89 230	37.42 251	37.41 201	53.88 246	54.02 239	65.37 223	61.47 226

MDTV_nov1_ep13_2view		47.62 220	49.72 231	45.18 206	48.05 212	53.70 220	54.90 189	33.80 238	39.90 224	29.79 194	38.85 226	41.89 231	39.17 186	58.99 212	55.55 227	65.34 224	59.17 234

MDTV_nov1_ep13		50.32 192	52.43 211	47.86 185	49.87 206	54.70 216	58.10 158	34.29 234	45.59 176	37.71 157	47.44 155	47.42 187	41.86 174	58.07 222	55.21 232	65.34 224	58.56 236

MVS-HIRNet		42.24 240	41.15 254	43.51 216	44.06 233	40.74 257	35.77 263	35.35 227	35.38 247	38.34 153	25.63 259	38.55 246	43.48 164	50.77 252	47.03 256	64.07 226	49.98 253

MDA-MVSNet-bldmvs		41.36 241	43.15 252	39.27 236	28.74 265	52.68 224	44.95 244	40.84 172	32.89 251	18.13 241	31.61 244	22.09 270	38.97 189	50.45 255	56.11 223	64.01 227	56.23 242

CVMVSNet		46.38 228	52.01 216	39.81 234	42.40 235	50.26 232	46.15 236	37.68 214	40.03 223	15.09 246	46.56 162	47.56 185	33.72 225	56.50 234	55.65 226	63.80 228	67.53 172

PatchT		48.08 216	51.03 222	44.64 211	42.96 234	50.12 233	40.36 255	35.09 228	43.17 195	39.59 148	42.00 213	39.96 241	46.63 147	58.97 213	60.31 200	63.21 229	62.66 220

baseline		55.19 158	60.88 124	48.55 174	49.87 206	58.10 204	58.70 154	34.75 230	52.82 121	39.48 151	60.18 88	60.86 115	45.41 153	61.05 196	60.74 199	63.10 230	72.41 141

dps		50.42 189	51.20 221	49.51 160	55.88 159	56.07 214	53.73 196	38.89 195	43.66 188	40.36 144	45.66 173	37.63 249	45.23 154	59.05 211	56.18 221	62.94 231	60.16 231

dtuonlycased		45.76 230	49.64 232	41.23 227	39.65 250	57.99 206	55.53 182	26.40 257	40.07 222	17.92 242	28.95 253	49.18 174	45.13 156	53.73 247	52.03 246	62.75 232	65.55 200

SCA		50.99 186	53.22 198	48.40 177	51.07 198	56.78 212	50.25 217	39.05 190	48.31 155	41.38 136	49.54 140	46.70 201	46.00 150	58.31 219	56.28 220	62.65 233	56.60 241

tpm cat1		53.30 168	53.41 194	53.17 137	58.16 129	59.15 183	63.73 132	38.27 204	50.73 130	46.98 100	45.57 175	44.00 227	49.20 130	55.90 240	54.02 239	62.65 233	64.50 209

LTVRE_ROB	44.17 16	47.06 225	50.15 228	43.44 217	51.39 194	58.42 192	42.90 249	43.51 135	22.27 266	14.85 247	41.94 214	34.57 254	45.43 152	62.28 192	62.77 187	62.56 235	68.83 168
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
PM-MVS		44.55 235	48.13 237	40.37 233	32.85 261	46.82 248	46.11 237	29.28 250	40.48 218	29.99 193	39.98 223	34.39 255	41.80 175	56.08 238	53.88 243	62.19 236	65.31 201

usedtu_dtu_shiyan2		36.29 253	39.77 256	32.23 251	19.53 271	48.11 240	41.99 253	36.59 219	23.95 264	12.80 251	22.03 263	32.26 259	20.73 250	50.69 254	50.64 249	61.72 237	50.72 249

EU-MVSNet		40.63 245	45.65 244	34.78 248	39.11 253	46.94 247	40.02 256	34.03 235	33.50 250	10.37 257	35.57 234	37.80 248	23.65 245	51.90 249	50.21 251	61.49 238	63.62 215

PatchmatchNet		49.92 199	51.29 219	48.32 179	51.83 192	51.86 228	53.38 203	37.63 215	47.90 159	40.83 141	48.54 147	45.30 212	45.19 155	56.86 228	53.99 241	61.08 239	54.57 244
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
CMPMVS	37.70 17	49.24 202	52.71 203	45.19 205	45.97 225	51.23 230	47.44 230	29.31 249	43.04 196	44.69 117	34.45 238	48.35 176	43.64 162	62.59 188	59.82 202	60.08 240	69.48 162
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
test0.0.03 1		43.15 238	46.95 240	38.72 237	55.26 164	50.56 231	42.48 250	43.48 138	38.16 241	15.11 245	35.07 235	44.69 222	16.47 255	55.95 239	54.34 238	59.54 241	49.87 255

Anonymous20231206		42.28 239	45.89 242	38.07 239	51.96 190	48.98 236	43.66 248	38.81 198	38.74 230	14.32 248	26.74 256	40.90 235	20.94 249	56.64 232	54.67 236	58.71 242	54.59 243

TAMVS		44.02 236	49.18 233	37.99 240	47.03 218	45.97 251	45.04 242	28.47 252	39.11 228	20.23 236	43.22 202	48.52 175	28.49 237	58.15 221	57.95 210	58.71 242	51.36 247

ambc			45.54 245		50.66 204	52.63 225	40.99 254		38.36 238	24.67 225	22.62 262	13.94 273	29.14 234	65.71 173	58.06 209	58.60 244	67.43 173

pmmvs3		35.10 255	38.47 257	31.17 253	26.37 269	40.47 258	34.51 265	18.09 266	24.75 262	16.88 244	23.05 261	26.69 265	32.69 227	50.73 253	51.60 247	58.46 245	51.98 246

test20.03		40.38 247	44.20 248	35.92 245	53.73 178	49.05 235	38.54 257	43.49 136	32.55 252	9.54 260	27.88 255	39.12 243	12.24 261	56.28 236	54.69 235	57.96 246	49.83 256

MIMVSNet		43.79 237	48.53 235	38.27 238	41.46 244	48.97 237	50.81 216	32.88 245	44.55 179	22.07 230	32.05 241	47.15 190	24.76 242	58.73 215	56.09 224	57.63 247	52.14 245

tpmrst		48.08 216	49.88 230	45.98 198	52.71 183	48.11 240	53.62 201	33.70 239	48.70 151	39.74 146	48.96 145	46.23 205	40.29 182	50.14 256	49.28 252	55.80 248	57.71 238

dtuonly		47.41 222	53.02 201	40.88 230	39.20 252	46.62 250	54.26 191	25.80 259	44.41 181	26.35 218	45.20 181	53.69 146	44.32 160	60.37 200	57.56 212	55.34 249	63.26 217

FPMVS		38.36 251	40.41 255	35.97 244	38.92 254	39.85 260	45.50 240	25.79 260	41.13 214	18.70 239	30.10 247	24.56 267	31.86 228	49.42 258	46.80 257	55.04 250	51.03 248

FMVSNet5		40.96 242	45.81 243	35.29 247	34.30 256	44.55 255	47.28 231	28.84 251	40.76 216	21.62 231	29.85 248	42.44 229	24.77 241	57.53 224	55.00 233	54.93 251	50.56 251

tpm		48.82 211	51.27 220	45.96 199	54.10 175	47.35 243	56.05 175	30.23 248	46.70 166	43.21 124	52.54 127	47.55 186	37.28 203	54.11 245	50.50 250	54.90 252	60.12 232

PMVS	27.84 18	33.81 256	35.28 261	32.09 252	34.13 257	24.81 269	32.51 266	26.48 256	26.41 260	19.37 238	23.76 260	24.02 268	25.18 240	50.78 251	47.24 255	54.89 253	49.95 254
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
testgi		38.71 250	43.64 250	32.95 250	52.30 189	48.63 239	35.59 264	35.05 229	31.58 256	9.03 264	30.29 246	40.75 237	11.19 267	55.30 241	53.47 244	54.53 254	45.48 259

GG-mvs-BLEND		36.62 252	53.39 195	17.06 262	0.01 281	58.61 187	48.63 223	0.01 275	47.13 164	0.02 281	43.98 190	60.64 118	0.03 277	54.92 244	51.47 248	53.64 255	56.99 239

MIMVSNet1		35.51 254	41.41 253	28.63 255	27.53 267	43.36 256	38.09 258	33.82 237	32.01 253	6.77 268	21.63 264	35.43 253	11.97 263	55.05 243	53.99 241	53.59 256	48.36 258

EPMVS		44.66 234	47.86 238	40.92 229	47.97 213	44.70 254	47.58 229	33.27 241	48.11 158	29.58 196	49.65 139	44.38 225	34.65 220	51.71 250	47.90 254	52.49 257	48.57 257

RPSCF		46.41 226	54.42 186	37.06 242	25.70 270	45.14 253	45.39 241	20.81 263	62.79 65	35.10 166	44.92 182	55.60 142	43.56 163	56.12 237	52.45 245	51.80 258	63.91 212

IterMVS-SCA-FT		52.18 175	57.75 166	45.68 201	51.01 200	62.06 154	55.10 188	34.75 230	44.85 178	32.86 180	51.13 136	51.22 157	48.74 131	62.47 190	61.51 194	51.61 259	71.02 147

pmnet_mix02		40.48 246	43.80 249	36.61 243	45.79 226	40.45 259	42.12 251	33.18 242	40.30 220	24.11 229	38.76 227	37.11 252	24.30 243	52.97 248	46.66 258	50.17 260	50.33 252

FC-MVSNet-test		39.65 249	48.35 236	29.49 254	44.43 230	39.28 263	30.23 267	40.44 181	43.59 190	3.12 274	53.00 123	42.03 230	10.02 269	55.09 242	54.77 234	48.66 261	50.71 250

CHOSEN 280x420		40.80 243	45.05 246	35.84 246	32.95 260	29.57 267	44.98 243	23.71 262	37.54 242	18.42 240	31.36 245	47.07 192	46.41 149	56.71 231	54.65 237	48.55 262	58.47 237

ADS-MVSNet		40.67 244	43.38 251	37.50 241	44.36 231	39.79 261	42.09 252	32.67 246	44.34 184	28.87 200	40.76 218	40.37 239	30.22 230	48.34 261	45.87 259	46.81 263	44.21 261

new-patchmatchnet		33.24 257	37.20 258	28.62 256	44.32 232	38.26 264	29.68 268	36.05 223	31.97 254	6.33 269	26.59 257	27.33 264	11.12 268	50.08 257	41.05 263	44.23 264	45.15 260

Gipuma		25.87 260	26.91 263	24.66 258	28.98 264	20.17 270	20.46 269	34.62 233	29.55 258	9.10 262	4.91 275	5.31 278	15.76 258	49.37 259	49.10 253	39.03 265	29.95 266
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
PatchmatchNet1												31.00 261	16.29 257	46.93 263	41.22 261	38.25 266	37.14 263
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
N_pmnet		32.67 258	36.85 259	27.79 257	40.55 247	32.13 265	35.80 262	26.79 255	37.24 243	9.10 262	32.02 242	30.94 262	16.30 256	47.22 262	41.21 262	38.21 267	37.21 262

new_pmnet		23.19 261	28.17 262	17.37 260	17.03 272	24.92 268	19.66 270	16.16 268	27.05 259	4.42 271	20.77 265	19.20 272	12.19 262	37.71 264	36.38 264	34.77 268	31.17 265

WB-MVS		29.70 259	35.40 260	23.05 259	40.96 246	39.59 262	18.79 271	40.20 184	25.26 261	1.88 277	33.33 239	21.97 271	3.36 271	48.69 260	44.60 260	33.11 269	34.39 264

E-PMN		15.09 263	13.19 267	17.30 261	27.80 266	12.62 273	7.81 275	27.54 253	14.62 270	3.19 272	6.89 272	2.52 283	15.09 259	15.93 268	20.22 267	22.38 270	19.53 269

EMVS		14.49 264	12.45 268	16.87 263	27.02 268	12.56 274	8.13 274	27.19 254	15.05 269	3.14 273	6.69 273	2.67 282	15.08 260	14.60 270	18.05 268	20.67 271	17.56 272

test_method		12.44 266	14.66 266	9.85 266	1.30 277	3.32 277	13.00 273	3.21 269	22.42 265	10.22 258	14.13 266	25.64 266	11.43 266	19.75 267	11.61 270	19.96 272	5.79 274

PMMVS2		15.84 262	19.68 264	11.35 264	15.74 273	16.95 271	13.31 272	17.64 267	16.08 268	0.36 278	13.12 268	11.47 274	1.69 274	28.82 265	27.24 266	19.38 273	24.09 268

MVE	12.28 19	13.53 265	15.72 265	10.96 265	7.39 274	15.71 272	6.05 276	23.73 261	10.29 272	3.01 275	5.77 274	3.41 281	11.91 264	20.11 266	29.79 265	13.67 274	24.98 267
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
tmp_tt				5.40 267	3.97 276	2.35 278	3.26 278	0.44 272	17.56 267	12.09 252	11.48 270	7.14 276	1.98 273	15.68 269	15.49 269	10.69 275

DeepMVS_CX						6.95 275	5.98 277	2.25 270	11.73 271	2.07 276	11.85 269	5.43 277	11.75 265	11.40 271		8.10 276	18.38 270

VLMVS_CLIP		6.73 267	10.38 269	2.46 268	3.99 275	4.43 276	1.10 279	0.52 271	9.66 273	0.13 279	13.65 267	7.20 275	6.06 270	10.97 272	8.87 271	2.96 277	17.92 271

VLMVS		1.68 269	2.72 271	0.47 270	0.61 278	0.83 280	0.31 281	0.04 274	3.10 275	0.10 280	2.87 276	3.58 280	1.27 275	1.63 274	1.33 273	0.51 278	5.67 275

MVS_clip		2.93 268	4.95 270	0.58 269	0.38 279	0.87 279	0.22 282	0.07 273	4.80 274	0.01 282	7.77 271	4.35 279	2.40 272	4.36 273	3.82 272	0.40 279	8.69 273

MVS_baseline		0.92 270	1.62 272	0.10 271	0.03 280	0.03 281	0.01 283	0.00 276	1.26 276	0.00 283	2.32 277	1.37 284	0.57 276	0.42 275	0.44 274	0.00 280	5.51 276

uanet_test		0.00 273	0.00 275	0.00 272	0.00 282	0.00 282	0.00 285	0.00 276	0.00 279	0.00 283	0.00 280	0.00 285	0.00 280	0.00 277	0.00 277	0.00 280	0.00 279

sosnet-low-res		0.00 273	0.00 275	0.00 272	0.00 282	0.00 282	0.00 285	0.00 276	0.00 279	0.00 283	0.00 280	0.00 285	0.00 280	0.00 277	0.00 277	0.00 280	0.00 279

sosnet		0.00 273	0.00 275	0.00 272	0.00 282	0.00 282	0.00 285	0.00 276	0.00 279	0.00 283	0.00 280	0.00 285	0.00 280	0.00 277	0.00 277	0.00 280	0.00 279

testmvs		0.01 271	0.02 273	0.00 272	0.00 282	0.00 282	0.01 283	0.00 276	0.01 277	0.00 283	0.03 279	0.00 285	0.01 278	0.01 276	0.01 275	0.00 280	0.06 278

test123		0.01 271	0.02 273	0.00 272	0.00 282	0.00 282	0.00 285	0.00 276	0.01 277	0.00 283	0.04 278	0.00 285	0.01 278	0.00 277	0.01 275	0.00 280	0.07 277

PatchmatchNet2					41.42 245	31.97 266	36.73 261
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
PatchmatchNet3										9.17 261	31.94 243
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
RE-MVS-def										33.01 177

9.14												81.81 15

SR-MVS					71.46 37			54.67 31				81.54 16

our_test_3					51.15 197	57.31 210	55.12 187

MTAPA										65.14 4		80.20 22

MTMP										62.63 18		78.04 29

Patchmatch-RL test							1.04 280

mPP-MVS					71.67 36							74.36 44

NP-MVS									72.00 45

Patchmtry						47.61 242	48.27 224	38.86 196		39.59 148

High-resolution multi-view benchmark