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.

SF-MVS		77.13 8	81.70 8	71.79 3	79.32 1	80.76 5	82.96 2	57.49 11	82.82 9	64.79 5	83.69 10	84.46 5	62.83 13	77.13 26	75.21 31	83.35 7	87.85 16

SED-MVS		79.21 1	84.74 2	72.75 1	78.66 2	81.96 2	82.94 4	58.16 4	86.82 2	67.66 1	88.29 4	86.15 3	66.42 2	80.41 4	78.65 6	82.65 16	90.92 2

DVP-MVS		78.77 2	84.89 1	71.62 4	78.04 3	82.05 1	81.64 10	57.96 7	87.53 1	66.64 2	88.77 1	86.31 1	63.16 10	79.99 7	78.56 7	82.31 22	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
APDe-MVS		77.58 6	82.93 6	71.35 6	77.86 4	80.55 6	83.38 1	57.61 10	85.57 5	61.11 21	86.10 7	82.98 8	64.76 4	78.29 15	76.78 22	83.40 6	90.20 5
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
DPE-MVS		78.11 4	83.84 4	71.42 5	77.82 5	81.32 4	82.92 5	57.81 9	84.04 8	63.19 12	88.63 2	86.00 4	64.52 5	78.71 11	77.63 15	82.26 23	90.57 3
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
SteuartSystems-ACMMP		75.23 13	79.60 15	70.13 13	76.81 6	78.92 12	81.74 8	57.99 6	75.30 29	59.83 26	75.69 18	78.45 24	60.48 29	80.58 2	79.77 2	83.94 3	88.52 10
Skip Steuart: Steuart Systems R&D Blog.
DVP-MVS++		78.76 3	84.44 3	72.14 2	76.63 7	81.93 3	82.92 5	58.10 5	85.86 4	66.53 3	87.86 5	86.16 2	66.45 1	80.46 3	78.53 9	82.19 27	90.29 4

HPM-MVS++		76.01 10	80.47 12	70.81 9	76.60 8	74.96 36	80.18 17	58.36 2	81.96 10	63.50 11	78.80 14	82.53 11	64.40 6	78.74 10	78.84 5	81.81 33	87.46 18

MCST-MVS		73.67 24	77.39 25	69.33 18	76.26 9	78.19 17	78.77 26	54.54 30	75.33 27	59.99 25	67.96 31	79.23 22	62.43 16	78.00 18	75.71 29	84.02 2	87.30 19

CNVR-MVS		75.62 12	79.91 14	70.61 10	75.76 10	78.82 14	81.66 9	57.12 13	79.77 16	63.04 13	70.69 24	81.15 16	62.99 11	80.23 5	79.54 3	83.11 8	89.16 8

NCCC		74.27 19	77.83 24	70.13 13	75.70 11	77.41 22	80.51 15	57.09 14	78.25 20	62.28 18	65.54 37	78.26 25	62.18 18	79.13 8	78.51 10	83.01 10	87.68 17

CSCG		74.68 16	79.22 16	69.40 17	75.69 12	80.01 9	79.12 24	52.83 41	79.34 17	63.99 9	70.49 25	82.02 12	60.35 32	77.48 24	77.22 19	84.38 1	87.97 15

DPM-MVS		72.80 26	75.90 29	69.19 20	75.51 13	77.68 20	81.62 11	54.83 26	75.96 25	62.06 19	63.96 49	76.58 30	58.55 40	76.66 32	76.77 23	82.60 18	83.68 40

TPM-MVS					75.48 14	76.70 29	79.31 21			62.34 17	64.71 42	77.88 27	56.94 53			81.88 31	83.68 40
Ray Leroy Khuboni and Hongjun Xu: Textureless Resilient Propagation Matching in Multiple View Stereosis (TPM-MVS). SATNAC 2025
SMA-MVS		77.32 7	82.51 7	71.26 7	75.43 15	80.19 8	82.22 7	58.26 3	84.83 7	64.36 7	78.19 15	83.46 6	63.61 8	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
APD-MVS		75.80 11	80.90 11	69.86 15	75.42 16	78.48 16	81.43 13	57.44 12	80.45 14	59.32 27	85.28 8	80.82 18	63.96 7	76.89 28	76.08 27	81.58 39	88.30 12
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
MSP-MVS		77.82 5	83.46 5	71.24 8	75.26 17	80.22 7	82.95 3	57.85 8	85.90 3	64.79 5	88.54 3	83.43 7	66.24 3	78.21 17	78.56 7	80.34 46	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
train_agg		73.89 21	78.25 22	68.80 23	75.25 18	72.27 51	79.75 18	56.05 20	74.87 32	58.97 28	81.83 11	79.76 21	61.05 25	77.39 25	76.01 28	81.71 36	85.61 29

TSAR-MVS + MP.		75.22 14	80.06 13	69.56 16	74.61 19	72.74 49	80.59 14	55.70 23	80.80 13	62.65 15	86.25 6	82.92 9	62.07 19	76.89 28	75.66 30	81.77 35	85.19 32
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
SD-MVS		74.43 17	78.87 18	69.26 19	74.39 20	73.70 45	79.06 25	55.24 25	81.04 12	62.71 14	80.18 12	82.61 10	61.70 21	75.43 40	73.92 43	82.44 21	85.22 31
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
ACMMP_NAP		76.15 9	81.17 9	70.30 11	74.09 21	79.47 10	81.59 12	57.09 14	81.38 11	63.89 10	79.02 13	80.48 19	62.24 17	80.05 6	79.12 4	82.94 11	88.64 9

HFP-MVS		74.87 15	78.86 20	70.21 12	73.99 22	77.91 18	80.36 16	56.63 16	78.41 19	64.27 8	74.54 20	77.75 28	62.96 12	78.70 12	77.82 13	83.02 9	86.91 21

AdaColmap		67.89 45	68.85 60	66.77 29	73.73 23	74.30 43	75.28 40	53.58 36	70.24 46	57.59 35	51.19 105	59.19 94	60.74 28	75.33 42	73.72 45	79.69 54	77.96 72

MP-MVS		74.31 18	78.87 18	68.99 21	73.49 24	78.56 15	79.25 23	56.51 17	75.33 27	60.69 23	75.30 19	79.12 23	61.81 20	77.78 21	77.93 12	82.18 29	88.06 14
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
TSAR-MVS + ACMM		72.56 28	79.07 17	64.96 40	73.24 25	73.16 48	78.50 27	48.80 66	79.34 17	55.32 41	85.04 9	81.49 15	58.57 39	75.06 43	73.75 44	75.35 108	85.61 29

CDPH-MVS		71.47 31	75.82 31	66.41 31	72.97 26	77.15 24	78.14 30	54.71 27	69.88 48	53.07 56	70.98 23	74.83 37	56.95 52	76.22 33	76.57 24	82.62 17	85.09 33

PGM-MVS		72.89 25	77.13 26	67.94 25	72.47 27	77.25 23	79.27 22	54.63 29	73.71 36	57.95 34	72.38 22	75.33 35	60.75 27	78.25 16	77.36 18	82.57 19	85.62 28

ACMMPR		73.79 23	78.41 21	68.40 24	72.35 28	77.79 19	79.32 20	56.38 18	77.67 23	58.30 32	74.16 21	76.66 29	61.40 22	78.32 14	77.80 14	82.68 15	86.51 22

OPM-MVS		69.33 37	71.05 46	67.32 27	72.34 29	75.70 33	79.57 19	56.34 19	55.21 76	53.81 53	59.51 66	68.96 58	59.67 34	77.61 23	76.44 25	82.19 27	83.88 38
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
X-MVS		71.18 32	75.66 32	65.96 35	71.71 30	76.96 25	77.26 33	55.88 22	72.75 39	54.48 48	64.39 44	74.47 38	54.19 66	77.84 20	77.37 17	82.21 26	85.85 26

HQP-MVS		70.88 33	75.02 33	66.05 34	71.69 31	74.47 41	77.51 32	53.17 38	72.89 38	54.88 45	70.03 27	70.48 52	57.26 48	76.02 35	75.01 35	81.78 34	86.21 23

MAR-MVS		68.04 44	70.74 48	64.90 41	71.68 32	76.33 31	74.63 44	50.48 55	63.81 56	55.52 40	54.88 85	69.90 54	57.39 47	75.42 41	74.79 37	79.71 51	80.03 57
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
mPP-MVS					71.67 33							74.36 41

SR-MVS					71.46 34			54.67 28				81.54 14

CLD-MVS		67.02 49	71.57 43	61.71 51	71.01 35	74.81 38	71.62 51	38.91 162	71.86 42	60.70 22	64.97 41	67.88 66	51.88 92	76.77 31	74.98 36	76.11 96	69.75 125
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
CP-MVS		72.63 27	76.95 27	67.59 26	70.67 36	75.53 34	77.95 31	56.01 21	75.65 26	58.82 29	69.16 29	76.48 31	60.46 30	77.66 22	77.20 20	81.65 37	86.97 20

ACMM	60.30 7	67.58 47	68.82 61	66.13 33	70.59 37	72.01 53	76.54 35	54.26 32	65.64 54	54.78 47	50.35 108	61.72 83	58.74 38	75.79 38	75.03 33	81.88 31	81.17 52
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
XVS					70.49 38	76.96 25	74.36 45			54.48 48		74.47 38				82.24 24

X-MVStestdata					70.49 38	76.96 25	74.36 45			54.48 48		74.47 38				82.24 24

ACMMP		71.57 30	75.84 30	66.59 30	70.30 40	76.85 28	78.46 28	53.95 34	73.52 37	55.56 39	70.13 26	71.36 50	58.55 40	77.00 27	76.23 26	82.71 14	85.81 27
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
MVS_111021_HR		67.62 46	70.39 50	64.39 43	69.77 41	70.45 59	71.44 53	51.72 47	60.77 65	55.06 43	62.14 58	66.40 69	58.13 43	76.13 34	74.79 37	80.19 48	82.04 49

MSLP-MVS++		68.17 43	70.72 49	65.19 38	69.41 42	70.64 56	74.99 41	45.76 77	70.20 47	60.17 24	56.42 77	73.01 44	61.14 23	72.80 54	70.54 59	79.70 52	81.42 51

LGP-MVS_train		68.87 39	72.03 42	65.18 39	69.33 43	74.03 44	76.67 34	53.88 35	68.46 49	52.05 60	63.21 51	63.89 72	56.31 56	75.99 36	74.43 39	82.83 13	84.18 35

ACMP	61.42 5	68.72 42	71.37 44	65.64 37	69.06 44	74.45 42	75.88 38	53.30 37	68.10 50	55.74 38	61.53 61	62.29 79	56.97 51	74.70 46	74.23 41	82.88 12	84.31 34
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
DeepC-MVS_fast	65.08 3	72.00 29	76.11 28	67.21 28	68.93 45	77.46 21	76.54 35	54.35 31	74.92 31	58.64 31	65.18 39	74.04 43	62.62 14	77.92 19	77.02 21	82.16 30	86.21 23
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
CANet		68.77 40	73.01 37	63.83 45	68.30 46	75.19 35	73.73 48	47.90 67	63.86 55	54.84 46	67.51 33	74.36 41	57.62 44	74.22 48	73.57 47	80.56 44	82.36 46

TSAR-MVS + GP.		69.71 34	73.92 36	64.80 42	68.27 47	70.56 57	71.90 50	50.75 51	71.38 43	57.46 36	68.68 30	75.42 34	60.10 33	73.47 51	73.99 42	80.32 47	83.97 37

3Dnovator+	62.63 4	69.51 35	72.62 39	65.88 36	68.21 48	76.47 30	73.50 49	52.74 42	70.85 44	58.65 30	55.97 79	69.95 53	61.11 24	76.80 30	75.09 32	81.09 42	83.23 44

MVS_0304		69.49 36	73.96 35	64.28 44	67.92 49	76.13 32	74.90 42	47.60 68	63.29 59	54.09 52	67.44 34	76.35 32	59.53 35	75.81 37	75.03 33	81.62 38	83.70 39

DeepC-MVS	66.32 2	73.85 22	78.10 23	68.90 22	67.92 49	79.31 11	78.16 29	59.28 1	78.24 21	61.13 20	67.36 35	76.10 33	63.40 9	79.11 9	78.41 11	83.52 5	88.16 13
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
DeepPCF-MVS	66.49 1	74.25 20	80.97 10	66.41 31	67.75 51	78.87 13	75.61 39	54.16 33	84.86 6	58.22 33	77.94 16	81.01 17	62.52 15	78.34 13	77.38 16	80.16 49	88.40 11

EC-MVSNet		67.01 50	70.27 53	63.21 47	67.21 52	70.47 58	69.01 56	46.96 71	59.16 68	53.23 55	64.01 48	69.71 56	60.37 31	74.92 44	71.24 55	82.50 20	82.41 45

UA-Net		58.50 92	64.68 80	51.30 121	66.97 53	67.13 85	53.68 163	45.65 80	49.51 108	31.58 149	62.91 53	68.47 60	35.85 173	68.20 101	67.28 97	74.03 120	69.24 135

PHI-MVS		69.27 38	74.84 34	62.76 50	66.83 54	74.83 37	73.88 47	49.32 60	70.61 45	50.93 63	69.62 28	74.84 36	57.25 49	75.53 39	74.32 40	78.35 68	84.17 36

3Dnovator	60.86 6	66.99 51	70.32 51	63.11 48	66.63 55	74.52 39	71.56 52	45.76 77	67.37 52	55.00 44	54.31 90	68.19 62	58.49 42	73.97 49	73.63 46	81.22 41	80.23 56

EPNet		65.14 60	69.54 57	60.00 58	66.61 56	67.67 77	67.53 64	55.32 24	62.67 61	46.22 81	67.74 32	65.93 70	48.07 111	72.17 57	72.12 49	76.28 92	78.47 68
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
OpenMVS	57.13 9	62.81 66	65.75 72	59.39 62	66.47 57	69.52 61	64.26 98	43.07 130	61.34 64	50.19 66	47.29 126	64.41 71	54.60 65	70.18 78	68.62 80	77.73 70	78.89 64

ACMH	52.42 13	58.24 99	59.56 119	56.70 85	66.34 58	69.59 60	66.71 73	49.12 61	46.08 141	28.90 162	42.67 173	41.20 190	52.60 84	71.39 63	70.28 61	76.51 88	75.72 92
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
MSDG		58.46 94	58.97 125	57.85 77	66.27 59	66.23 94	67.72 61	42.33 134	53.43 83	43.68 93	43.39 164	45.35 167	49.75 100	68.66 92	67.77 89	77.38 76	67.96 140

QAPM		65.27 56	69.49 58	60.35 55	65.43 60	72.20 52	65.69 85	47.23 69	63.46 57	49.14 68	53.56 91	71.04 51	57.01 50	72.60 56	71.41 53	77.62 72	82.14 48

CPTT-MVS		68.76 41	73.01 37	63.81 46	65.42 61	73.66 46	76.39 37	52.08 43	72.61 40	50.33 65	60.73 62	72.65 46	59.43 36	73.32 52	72.12 49	79.19 60	85.99 25

MS-PatchMatch		58.19 101	60.20 106	55.85 90	65.17 62	64.16 114	64.82 92	41.48 142	50.95 98	42.17 102	45.38 147	56.42 106	48.08 110	68.30 97	66.70 105	73.39 128	69.46 133

PCF-MVS	59.98 8	67.32 48	71.04 47	62.97 49	64.77 63	74.49 40	74.78 43	49.54 57	67.44 51	54.39 51	58.35 71	72.81 45	55.79 62	71.54 62	69.24 70	78.57 62	83.41 42
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
EG-PatchMatch MVS		56.98 108	58.24 132	55.50 92	64.66 64	68.62 65	61.48 107	43.63 114	38.44 194	41.44 104	38.05 185	46.18 162	43.95 129	71.71 61	70.61 58	77.87 69	74.08 105

Effi-MVS+-dtu		60.34 79	62.32 89	58.03 72	64.31 65	67.44 81	65.99 80	42.26 135	49.55 106	42.00 103	48.92 116	59.79 92	56.27 57	68.07 105	67.03 98	77.35 77	75.45 95

FC-MVSNet-train		58.40 95	63.15 86	52.85 111	64.29 66	61.84 126	55.98 147	46.47 73	53.06 87	34.96 137	61.95 60	56.37 108	39.49 150	68.67 91	68.36 82	75.92 102	71.81 113

Effi-MVS+		63.28 63	65.96 71	60.17 57	64.26 67	68.06 71	68.78 59	45.71 79	54.08 79	46.64 78	55.92 80	63.13 76	55.94 60	70.38 76	71.43 52	79.68 55	78.70 65

LS3D		60.20 80	61.70 90	58.45 67	64.18 68	67.77 74	67.19 66	48.84 65	61.67 63	41.27 107	45.89 141	51.81 125	54.18 67	68.78 89	66.50 112	75.03 112	69.48 131

ACMH+	53.71 12	59.26 84	60.28 103	58.06 70	64.17 69	68.46 66	67.51 65	50.93 50	52.46 93	35.83 133	40.83 178	45.12 171	52.32 87	69.88 80	69.00 75	77.59 74	76.21 89

GeoE		62.43 69	64.79 79	59.68 61	64.15 70	67.17 84	68.80 58	44.42 96	55.65 75	47.38 72	51.54 102	62.51 77	54.04 69	69.99 79	68.07 84	79.28 58	78.57 66

DELS-MVS		65.87 53	70.30 52	60.71 54	64.05 71	72.68 50	70.90 54	45.43 81	57.49 71	49.05 70	64.43 43	68.66 59	55.11 64	74.31 47	73.02 48	79.70 52	81.51 50
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
sasdasda		65.62 54	72.06 40	58.11 68	63.94 72	71.05 54	64.49 95	43.18 126	74.08 33	47.35 73	64.17 46	71.97 47	51.17 95	71.87 58	70.74 56	78.51 65	80.56 54

canonicalmvs		65.62 54	72.06 40	58.11 68	63.94 72	71.05 54	64.49 95	43.18 126	74.08 33	47.35 73	64.17 46	71.97 47	51.17 95	71.87 58	70.74 56	78.51 65	80.56 54

EIA-MVS		61.53 75	63.79 84	58.89 65	63.82 74	67.61 78	65.35 88	42.15 138	49.98 103	45.66 84	57.47 75	56.62 104	56.59 55	70.91 70	69.15 71	79.78 50	74.80 99

Anonymous202405211			60.60 99		63.44 75	66.71 91	61.00 112	47.23 69	50.62 101		36.85 188	60.63 89	43.03 137	69.17 85	67.72 91	75.41 105	72.54 110

ETV-MVS		63.23 64	66.08 70	59.91 59	63.13 76	68.13 70	67.62 63	44.62 92	53.39 84	46.23 80	58.74 68	58.19 97	57.45 46	73.60 50	71.38 54	80.39 45	79.13 61

casdiffmvs_mvg		65.26 57	69.48 59	60.33 56	62.99 77	69.34 62	69.80 55	45.27 83	63.38 58	51.11 62	65.12 40	69.75 55	53.51 74	71.74 60	68.86 76	79.33 56	78.19 71
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
gg-mvs-nofinetune		49.07 169	52.56 169	45.00 169	61.99 78	59.78 145	53.55 165	41.63 140	31.62 210	12.08 206	29.56 206	53.28 119	29.57 188	66.27 136	64.49 139	71.19 157	62.92 174

CS-MVS-test		65.18 58	68.70 62	61.07 53	61.92 79	68.06 71	67.09 70	45.18 85	58.47 70	52.02 61	65.76 36	66.44 68	59.24 37	72.71 55	70.05 64	80.98 43	79.40 60

DCV-MVSNet		59.49 82	64.00 83	54.23 97	61.81 80	64.33 112	61.42 108	43.77 108	52.85 90	38.94 121	55.62 82	62.15 81	43.24 136	69.39 83	67.66 93	76.22 94	75.97 90

casdiffmvs		64.09 61	68.13 63	59.37 63	61.81 80	68.32 68	68.48 60	44.45 95	61.95 62	49.12 69	63.04 52	69.67 57	53.83 70	70.46 73	66.06 117	78.55 63	77.43 74
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
CS-MVS		65.88 52	69.71 56	61.41 52	61.76 82	68.14 69	67.65 62	44.00 105	59.14 69	52.69 57	65.19 38	68.13 63	60.90 26	74.74 45	71.58 51	81.46 40	81.04 53

Anonymous20231211		57.71 104	60.79 96	54.13 99	61.68 83	65.81 98	60.81 113	43.70 112	51.97 96	39.67 116	34.82 193	63.59 73	43.31 134	68.55 95	66.63 108	75.59 103	74.13 104

IS_MVSNet		57.95 102	64.26 82	50.60 123	61.62 84	65.25 104	57.18 133	45.42 82	50.79 99	26.49 176	57.81 73	60.05 91	34.51 177	71.24 66	70.20 63	78.36 67	74.44 101

NR-MVSNet		55.35 125	59.46 120	50.56 124	61.33 85	62.97 120	57.91 129	51.80 45	48.62 123	20.59 190	51.99 100	44.73 177	34.10 180	68.58 93	68.64 79	77.66 71	70.67 122

MVS_111021_LR		63.05 65	66.43 67	59.10 64	61.33 85	63.77 117	65.87 82	43.58 115	60.20 66	53.70 54	62.09 59	62.38 78	55.84 61	70.24 77	68.08 83	74.30 117	78.28 70

MGCFI-Net		61.46 76	69.72 55	51.83 118	61.00 87	66.16 95	56.50 140	40.73 149	73.98 35	35.18 134	64.23 45	71.42 49	42.45 139	69.22 84	64.01 143	75.09 111	79.03 63

EPP-MVSNet		59.39 83	65.45 74	52.32 115	60.96 88	67.70 76	58.42 126	44.75 90	49.71 105	27.23 170	59.03 67	62.20 80	43.34 133	70.71 71	69.13 72	79.25 59	79.63 59

TransMVSNet (Re)		51.92 151	55.38 149	47.88 155	60.95 89	59.90 144	53.95 160	45.14 86	39.47 188	24.85 180	43.87 159	46.51 158	29.15 189	67.55 115	65.23 130	73.26 133	65.16 165

gm-plane-assit		44.74 189	45.95 197	43.33 177	60.88 90	46.79 203	36.97 212	32.24 202	24.15 217	11.79 207	29.26 207	32.97 212	46.64 116	65.09 150	62.95 153	71.45 154	60.42 185

baseline1		54.48 134	58.69 126	49.57 130	60.63 91	58.29 160	55.70 149	44.95 88	49.20 111	29.62 158	54.77 86	54.75 113	35.29 174	67.15 123	64.08 141	71.21 156	62.58 178

test2506		55.82 120	59.57 118	51.46 119	60.39 92	64.55 110	58.69 124	48.87 63	53.91 80	26.99 171	48.97 114	41.72 189	37.71 160	70.96 68	69.49 67	76.08 97	67.37 145

ECVR-MVS		56.44 115	60.74 97	51.42 120	60.39 92	64.55 110	58.69 124	48.87 63	53.91 80	26.76 173	45.55 146	53.43 118	37.71 160	70.96 68	69.49 67	76.08 97	67.32 147

DI_MVS_plusplus_trai		61.88 71	65.17 76	58.06 70	60.05 94	65.26 102	66.03 79	44.22 97	55.75 74	46.73 76	54.64 88	68.12 64	54.13 68	69.13 86	66.66 106	77.18 79	76.61 82

PVSNet_Blended_VisFu		63.65 62	66.92 64	59.83 60	60.03 95	73.44 47	66.33 76	48.95 62	52.20 95	50.81 64	56.07 78	60.25 90	53.56 72	73.23 53	70.01 65	79.30 57	83.24 43

UniMVSNet_NR-MVSNet		56.94 110	61.14 93	52.05 117	60.02 96	65.21 105	57.44 131	52.93 40	49.37 109	24.31 183	54.62 89	50.54 131	39.04 152	68.69 90	68.84 77	78.53 64	70.72 118

IterMVS-LS		58.30 98	61.39 92	54.71 95	59.92 97	58.40 157	59.42 118	43.64 113	48.71 120	40.25 114	57.53 74	58.55 96	52.15 89	65.42 148	65.34 127	72.85 135	75.77 91
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
test1111		55.24 126	59.98 111	49.71 129	59.80 98	64.10 115	56.48 141	49.34 59	52.27 94	21.56 188	44.49 154	51.96 124	35.93 172	70.59 72	69.07 73	75.13 110	67.40 143

MVS_Test		62.40 70	66.23 69	57.94 73	59.77 99	64.77 108	66.50 75	41.76 139	57.26 72	49.33 67	62.68 55	67.47 67	53.50 76	68.57 94	66.25 114	76.77 84	76.58 83

FA-MVS(training)		60.00 81	63.14 87	56.33 87	59.50 100	64.30 113	65.15 90	38.75 167	56.20 73	45.77 82	53.08 92	56.45 105	52.10 90	69.04 88	67.67 92	76.69 85	75.27 98

TranMVSNet+NR-MVSNet		55.87 118	60.14 108	50.88 122	59.46 101	63.82 116	57.93 128	52.98 39	48.94 115	20.52 191	52.87 94	47.33 149	36.81 168	69.12 87	69.03 74	77.56 75	69.89 124

Fast-Effi-MVS+		60.36 78	63.35 85	56.87 83	58.70 102	65.86 97	65.08 91	37.11 176	53.00 89	45.36 86	52.12 99	56.07 110	56.27 57	71.28 65	69.42 69	78.71 61	75.69 93

IB-MVS	54.11 11	58.36 97	60.70 98	55.62 91	58.67 103	68.02 73	61.56 105	43.15 128	46.09 140	44.06 92	44.24 156	50.99 130	48.71 105	66.70 129	70.33 60	77.60 73	78.50 67
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
Fast-Effi-MVS+-dtu		56.30 116	59.29 122	52.82 112	58.64 104	64.89 106	65.56 86	32.89 199	45.80 143	35.04 136	45.89 141	54.14 115	49.41 101	67.16 122	66.45 113	75.37 107	70.69 120

CNLPA		62.78 67	66.31 68	58.65 66	58.47 105	68.41 67	65.98 81	41.22 145	78.02 22	56.04 37	46.65 129	59.50 93	57.50 45	69.67 81	65.27 129	72.70 141	76.67 81

tpm cat1		53.30 139	53.41 162	53.17 108	58.16 106	59.15 151	63.73 101	38.27 171	50.73 100	46.98 75	45.57 145	44.00 183	49.20 102	55.90 196	54.02 195	62.65 187	64.50 169

v1144		58.88 87	60.16 107	57.39 79	58.03 107	67.26 82	67.14 68	44.46 94	45.17 146	44.33 91	47.81 123	49.92 136	53.20 82	67.77 111	66.62 109	77.15 80	76.58 83

v10		59.17 86	60.60 99	57.50 78	57.95 108	66.73 88	67.09 70	44.11 98	46.85 134	45.42 85	48.18 122	51.07 127	53.63 71	67.84 109	66.59 110	76.79 83	76.92 79

v1192		58.51 91	59.66 114	57.17 80	57.82 109	67.72 75	66.21 78	44.83 89	44.15 154	43.49 94	46.68 128	47.94 140	53.55 73	67.39 118	66.51 111	77.13 81	77.20 77

v144192		58.23 100	59.40 121	56.87 83	57.56 110	66.89 86	65.70 83	45.01 87	44.06 155	42.88 96	46.61 130	48.09 139	53.49 77	66.94 127	65.90 121	76.61 86	77.29 75

v1921920		57.89 103	59.02 124	56.58 86	57.55 111	66.66 92	64.72 94	44.70 91	43.55 159	42.73 97	46.17 138	46.93 153	53.51 74	66.78 128	65.75 123	76.29 91	77.28 76

Vis-MVSNet (Re-imp)		50.37 159	57.73 138	41.80 184	57.53 112	54.35 174	45.70 193	45.24 84	49.80 104	13.43 204	58.23 72	56.42 106	20.11 205	62.96 156	63.36 149	68.76 166	58.96 190

CostFormer		56.57 113	59.13 123	53.60 102	57.52 113	61.12 133	66.94 72	35.95 181	53.44 82	44.68 89	55.87 81	54.44 114	48.21 108	60.37 169	58.33 176	68.27 168	70.33 123

thres400		52.38 145	55.51 147	48.74 141	57.49 114	60.10 143	55.45 152	43.54 116	42.90 166	26.72 174	43.34 166	45.03 175	36.61 169	66.20 138	64.53 138	72.66 142	66.43 151

thres600view7		51.91 152	55.14 151	48.14 151	57.43 115	60.18 141	54.60 158	43.73 110	42.61 170	25.20 179	43.10 169	44.47 180	35.19 175	66.36 133	63.28 150	72.66 142	66.01 158

thres200		52.39 144	55.37 150	48.90 139	57.39 116	60.18 141	55.60 150	43.73 110	42.93 165	27.41 168	43.35 165	45.09 172	36.61 169	66.36 133	63.92 145	72.66 142	65.78 160

baseline2		55.89 117	57.82 135	53.64 101	57.36 117	61.09 134	59.75 117	40.45 153	47.38 132	41.26 108	51.23 104	46.90 154	48.11 109	65.63 145	64.38 140	74.90 113	68.16 139

v8		58.88 87	60.57 101	56.92 82	57.35 118	65.69 99	66.69 74	42.64 132	47.89 129	45.77 82	49.04 113	52.98 120	52.77 83	67.51 116	65.57 124	76.26 93	75.30 97

thres100view900		52.04 149	54.81 155	48.80 140	57.31 119	59.33 148	55.30 154	42.92 131	42.85 167	27.81 166	43.00 170	45.06 173	36.99 166	64.74 151	63.51 147	72.47 145	65.21 164

tfpn200view9		52.53 142	55.51 147	49.06 137	57.31 119	60.24 140	55.42 153	43.77 108	42.85 167	27.81 166	43.00 170	45.06 173	37.32 164	66.38 132	64.54 137	72.71 140	66.54 150

v1240		57.55 105	58.63 128	56.29 88	57.30 121	66.48 93	63.77 100	44.56 93	42.77 169	42.48 99	45.64 144	46.28 160	53.46 78	66.32 135	65.80 122	76.16 95	77.13 78

dmvs_re		52.07 147	55.11 152	48.54 146	57.27 122	51.93 183	57.73 130	43.13 129	43.65 157	26.57 175	44.52 153	50.00 135	36.53 171	66.58 131	62.15 160	69.97 162	66.91 148

CHOSEN 1792x2688		55.85 119	58.01 133	53.33 104	57.26 123	62.82 122	63.29 104	41.55 141	46.65 136	38.34 122	34.55 194	53.50 116	52.43 86	67.10 124	67.56 95	67.13 172	73.92 107

PVSNet_BlendedMVS		61.63 73	64.82 77	57.91 75	57.21 124	67.55 79	63.47 102	46.08 75	54.72 77	52.46 58	58.59 69	60.73 86	51.82 93	70.46 73	65.20 131	76.44 89	76.50 86

PVSNet_Blended		61.63 73	64.82 77	57.91 75	57.21 124	67.55 79	63.47 102	46.08 75	54.72 77	52.46 58	58.59 69	60.73 86	51.82 93	70.46 73	65.20 131	76.44 89	76.50 86

v2v482		58.69 90	60.12 110	57.03 81	57.16 126	66.05 96	67.17 67	43.52 117	46.33 138	45.19 87	49.46 112	51.02 128	52.51 85	67.30 119	66.03 118	76.61 86	74.62 100

tfpnnormal		50.16 161	52.19 173	47.78 157	56.86 127	58.37 158	54.15 159	44.01 104	38.35 196	25.94 177	36.10 189	37.89 203	34.50 178	65.93 140	63.42 148	71.26 155	65.28 163

diffmvs		61.64 72	66.55 66	55.90 89	56.63 128	63.71 118	67.13 69	41.27 144	59.49 67	46.70 77	63.93 50	68.01 65	50.46 97	67.30 119	65.51 125	73.24 134	77.87 73
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
HyFIR lowres test		56.87 111	58.60 129	54.84 94	56.62 129	69.27 63	64.77 93	42.21 136	45.66 144	37.50 128	33.08 197	57.47 102	53.33 79	65.46 147	67.94 85	74.60 114	71.35 115

v7n		55.67 121	57.46 140	53.59 103	56.06 130	65.29 101	61.06 111	43.26 125	40.17 185	37.99 125	40.79 179	45.27 170	47.09 115	67.67 113	66.21 115	76.08 97	76.82 80

dps		50.42 158	51.20 179	49.51 131	55.88 131	56.07 170	53.73 161	38.89 163	43.66 156	40.36 113	45.66 143	37.63 205	45.23 124	59.05 172	56.18 180	62.94 186	60.16 186

CANet_DTU		58.88 87	64.68 80	52.12 116	55.77 132	66.75 87	63.92 99	37.04 177	53.32 85	37.45 129	59.81 64	61.81 82	44.43 128	68.25 98	67.47 96	74.12 119	75.33 96

WR-MVS		48.78 171	55.06 153	41.45 185	55.50 133	60.40 139	43.77 201	49.99 56	41.92 173	8.10 217	45.24 150	45.56 165	17.47 206	61.57 164	64.60 136	73.85 121	66.14 157

UniMVSNet (Re)		55.15 130	60.39 102	49.03 138	55.31 134	64.59 109	55.77 148	50.63 52	48.66 122	20.95 189	51.47 103	50.40 132	34.41 179	67.81 110	67.89 86	77.11 82	71.88 112

test-LLR		49.28 165	50.29 183	48.10 152	55.26 135	47.16 198	49.52 174	43.48 120	39.22 189	31.98 145	43.65 162	47.93 141	41.29 145	56.80 187	55.36 186	67.08 173	61.94 179

test0.0.03 1		43.15 194	46.95 196	38.72 193	55.26 135	50.56 187	42.48 204	43.48 120	38.16 198	15.11 200	35.07 192	44.69 178	16.47 208	55.95 195	54.34 194	59.54 194	49.87 208

GA-MVS		55.67 121	58.33 130	52.58 114	55.23 137	63.09 119	61.08 110	40.15 158	42.95 164	37.02 131	52.61 96	47.68 144	47.51 113	65.92 141	65.35 126	74.49 116	70.68 121

DTE-MVSNet		48.03 177	53.28 164	41.91 183	54.64 138	57.50 166	44.63 200	51.66 48	41.02 179	7.97 218	46.26 135	40.90 191	20.24 204	60.45 168	62.89 154	72.33 148	63.97 170

pmmvs4		54.66 133	56.07 144	53.00 109	54.63 139	57.08 168	60.43 115	44.10 99	51.69 97	40.55 111	46.55 133	44.79 176	45.95 121	62.54 158	63.66 146	72.36 147	66.20 155

DU-MVS		55.41 124	59.59 115	50.54 125	54.60 140	62.97 120	57.44 131	51.80 45	48.62 123	24.31 183	51.99 100	47.00 152	39.04 152	68.11 103	67.75 90	76.03 101	70.72 118

Baseline_NR-MVSNet		53.50 137	57.89 134	48.37 149	54.60 140	59.25 150	56.10 143	51.84 44	49.32 110	17.92 198	45.38 147	47.68 144	36.93 167	68.11 103	65.95 119	72.84 136	69.57 129

v148		55.58 123	57.61 139	53.20 106	54.59 142	61.86 125	61.18 109	38.70 168	44.30 153	42.25 101	47.53 124	50.24 134	48.73 104	65.15 149	62.61 158	73.79 122	71.61 114

PEN-MVS		49.21 167	54.32 157	43.24 179	54.33 143	59.26 149	47.04 187	51.37 49	41.67 175	9.97 212	46.22 136	41.80 188	22.97 202	60.52 167	64.03 142	73.73 123	66.75 149

pm-mvs1		51.02 155	55.55 146	45.73 164	54.16 144	58.52 155	50.92 170	42.56 133	40.32 183	25.67 178	43.66 161	50.34 133	30.06 187	65.85 142	63.97 144	70.99 158	66.21 154

EPNet_dtu		52.05 148	58.26 131	44.81 170	54.10 145	50.09 190	52.01 168	40.82 148	53.03 88	27.41 168	54.90 84	57.96 101	26.72 194	62.97 155	62.70 157	67.78 170	66.19 156
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
tpm		48.82 170	51.27 178	45.96 163	54.10 145	47.35 197	56.05 144	30.23 203	46.70 135	43.21 95	52.54 97	47.55 147	37.28 165	54.11 201	50.50 204	54.90 204	60.12 187

CDS-MVSNet		52.42 143	57.06 142	47.02 160	53.92 147	58.30 159	55.50 151	46.47 73	42.52 171	29.38 160	49.50 111	52.85 121	28.49 192	66.70 129	66.89 102	68.34 167	62.63 177
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
test20.03		40.38 203	44.20 203	35.92 201	53.73 148	49.05 191	38.54 210	43.49 119	32.55 207	9.54 213	27.88 209	39.12 199	12.24 213	56.28 192	54.69 191	57.96 199	49.83 209

Vis-MVSNet		58.48 93	65.70 73	50.06 128	53.40 149	67.20 83	60.24 116	43.32 123	48.83 117	30.23 155	62.38 57	61.61 84	40.35 148	71.03 67	69.77 66	72.82 137	79.11 62
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
PLC	52.09 14	59.21 85	62.47 88	55.41 93	53.24 150	64.84 107	64.47 97	40.41 155	65.92 53	44.53 90	46.19 137	55.69 111	55.33 63	68.24 100	65.30 128	74.50 115	71.09 116
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
thisisatest0530		56.68 112	59.68 113	53.19 107	52.97 151	60.96 136	59.41 119	40.51 151	48.26 126	41.06 109	52.67 95	46.30 159	49.78 98	67.66 114	67.83 87	75.39 106	74.07 106

OMC-MVS		65.16 59	71.35 45	57.94 73	52.95 152	68.82 64	69.00 57	38.28 170	79.89 15	55.20 42	62.76 54	68.31 61	56.14 59	71.30 64	68.70 78	76.06 100	79.67 58

tpmrst		48.08 175	49.88 187	45.98 162	52.71 153	48.11 195	53.62 164	33.70 194	48.70 121	39.74 115	48.96 115	46.23 161	40.29 149	50.14 210	49.28 206	55.80 201	57.71 193

tttt0517		56.53 114	59.59 115	52.95 110	52.66 154	60.99 135	59.21 121	40.51 151	47.89 129	40.40 112	52.50 98	46.04 163	49.78 98	67.75 112	67.83 87	75.15 109	74.17 103

GBi-Net		55.20 127	60.25 104	49.31 132	52.42 155	61.44 128	57.03 134	44.04 101	49.18 112	30.47 151	48.28 118	58.19 97	38.22 155	68.05 106	66.96 99	73.69 124	69.65 126

test1		55.20 127	60.25 104	49.31 132	52.42 155	61.44 128	57.03 134	44.04 101	49.18 112	30.47 151	48.28 118	58.19 97	38.22 155	68.05 106	66.96 99	73.69 124	69.65 126

FMVSNet2		55.04 131	59.95 112	49.31 132	52.42 155	61.44 128	57.03 134	44.08 100	49.55 106	30.40 154	46.89 127	58.84 95	38.22 155	67.07 125	66.21 115	73.69 124	69.65 126

FMVSNet3		54.78 132	59.58 117	49.17 135	52.37 158	61.31 132	56.72 139	44.04 101	49.18 112	30.47 151	48.28 118	58.19 97	38.09 158	65.48 146	65.20 131	73.31 131	69.45 134

testgi		38.71 205	43.64 205	32.95 205	52.30 159	48.63 194	35.59 215	35.05 184	31.58 211	9.03 216	30.29 202	40.75 193	11.19 219	55.30 197	53.47 200	54.53 206	45.48 212

Anonymous20231206		42.28 195	45.89 198	38.07 195	51.96 160	48.98 192	43.66 202	38.81 166	38.74 193	14.32 203	26.74 210	40.90 191	20.94 203	56.64 190	54.67 192	58.71 195	54.59 197

pmmvs6		48.35 173	51.64 175	44.51 172	51.92 161	57.94 164	49.44 176	42.17 137	34.45 203	24.62 182	28.87 208	46.90 154	29.07 191	64.60 152	63.08 151	69.83 163	65.68 161

PatchmatchNet		49.92 163	51.29 177	48.32 150	51.83 162	51.86 184	53.38 166	37.63 175	47.90 128	40.83 110	48.54 117	45.30 168	45.19 125	56.86 186	53.99 197	61.08 192	54.57 198
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
WR-MVS_H		47.65 178	53.67 160	40.63 188	51.45 163	59.74 146	44.71 199	49.37 58	40.69 181	7.61 219	46.04 139	44.34 182	17.32 207	57.79 183	61.18 164	73.30 132	65.86 159

LTVRE_ROB	44.17 16	47.06 183	50.15 186	43.44 176	51.39 164	58.42 156	42.90 203	43.51 118	22.27 219	14.85 202	41.94 177	34.57 209	45.43 122	62.28 161	62.77 156	62.56 189	68.83 137
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
CP-MVSNet		48.37 172	53.53 161	42.34 181	51.35 165	58.01 163	46.56 188	50.54 53	41.62 176	10.61 208	46.53 134	40.68 194	23.18 200	58.71 177	61.83 161	71.81 151	67.36 146

PS-CasMVS		48.18 174	53.25 165	42.27 182	51.26 166	57.94 164	46.51 189	50.52 54	41.30 177	10.56 209	45.35 149	40.34 196	23.04 201	58.66 178	61.79 162	71.74 153	67.38 144

our_test_3					51.15 167	57.31 167	55.12 155

SCA		50.99 156	53.22 166	48.40 148	51.07 168	56.78 169	50.25 172	39.05 161	48.31 125	41.38 105	49.54 110	46.70 157	46.00 120	58.31 179	56.28 179	62.65 187	56.60 195

UniMVSNet_ETH3D		52.62 141	55.98 145	48.70 143	51.04 169	60.71 138	56.87 137	46.74 72	42.52 171	26.96 172	42.50 174	45.95 164	37.87 159	66.22 137	65.15 134	72.74 138	68.78 138

IterMVS-SCA-FT		52.18 146	57.75 137	45.68 165	51.01 170	62.06 124	55.10 156	34.75 185	44.85 147	32.86 143	51.13 106	51.22 126	48.74 103	62.47 159	61.51 163	51.61 211	71.02 117

FMVSNet1		54.08 135	58.68 127	48.71 142	50.90 171	61.35 131	56.73 138	43.94 106	45.91 142	29.32 161	42.72 172	56.26 109	37.70 162	68.05 106	66.96 99	73.69 124	69.50 130

pmmvs-eth3d		51.33 153	52.25 172	50.26 127	50.82 172	54.65 173	56.03 145	43.45 122	43.51 160	37.20 130	39.20 182	39.04 200	42.28 140	61.85 163	62.78 155	71.78 152	64.72 167

MVSTER		57.19 106	61.11 94	52.62 113	50.82 172	58.79 153	61.55 106	37.86 173	48.81 118	41.31 106	57.43 76	52.10 123	48.60 106	68.19 102	66.75 104	75.56 104	75.68 94

ambc			45.54 201		50.66 174	52.63 181	40.99 207		38.36 195	24.67 181	22.62 215	13.94 225	29.14 190	65.71 144	58.06 177	58.60 197	67.43 142

thisisatest0515		53.85 136	56.84 143	50.37 126	50.25 175	58.17 161	55.99 146	39.90 159	41.88 174	38.16 124	45.91 140	45.30 168	44.58 127	66.15 139	66.89 102	73.36 130	73.57 109

baseline		55.19 129	60.88 95	48.55 145	49.87 176	58.10 162	58.70 123	34.75 185	52.82 91	39.48 120	60.18 63	60.86 85	45.41 123	61.05 165	60.74 168	63.10 185	72.41 111

MDTV_nov1_ep13		50.32 160	52.43 171	47.86 156	49.87 176	54.70 172	58.10 127	34.29 189	45.59 145	37.71 126	47.44 125	47.42 148	41.86 142	58.07 182	55.21 188	65.34 179	58.56 191

IterMVS		53.45 138	57.12 141	49.17 135	49.23 178	60.93 137	59.05 122	34.63 187	44.53 149	33.22 139	51.09 107	51.01 129	48.38 107	62.43 160	60.79 167	70.54 160	69.05 136
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
COLMAP_ROB	46.52 15	51.99 150	54.86 154	48.63 144	49.13 179	61.73 127	60.53 114	36.57 178	53.14 86	32.95 142	37.10 186	38.68 201	40.49 147	65.72 143	63.08 151	72.11 150	64.60 168
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
CR-MVSNet		50.47 157	52.61 168	47.98 154	49.03 180	52.94 178	48.27 179	38.86 164	44.41 150	39.59 117	44.34 155	44.65 179	46.63 117	58.97 174	60.31 169	65.48 177	62.66 175

V42		56.97 109	60.14 108	53.28 105	48.16 181	62.78 123	66.30 77	37.93 172	47.44 131	42.68 98	48.19 121	52.59 122	51.90 91	67.46 117	65.94 120	72.72 139	76.55 85

MDTV_nov1_ep13_2view		47.62 179	49.72 188	45.18 168	48.05 182	53.70 176	54.90 157	33.80 193	39.90 187	29.79 157	38.85 183	41.89 187	39.17 151	58.99 173	55.55 185	65.34 179	59.17 189

EPMVS		44.66 190	47.86 194	40.92 187	47.97 183	44.70 207	47.58 184	33.27 196	48.11 127	29.58 159	49.65 109	44.38 181	34.65 176	51.71 205	47.90 208	52.49 209	48.57 210

RPMNet		46.41 184	48.72 190	43.72 174	47.77 184	52.94 178	46.02 192	33.92 191	44.41 150	31.82 148	36.89 187	37.42 206	37.41 163	53.88 202	54.02 195	65.37 178	61.47 181

TAPA-MVS	54.74 10	60.85 77	66.61 65	54.12 100	47.38 185	65.33 100	65.35 88	36.51 179	75.16 30	48.82 71	54.70 87	63.51 74	53.31 80	68.36 96	64.97 135	73.37 129	74.27 102
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
SixPastTwentyTwo		47.55 180	50.25 185	44.41 173	47.30 186	54.31 175	47.81 182	40.36 156	33.76 204	19.93 193	43.75 160	32.77 213	42.07 141	59.82 170	60.94 166	68.98 164	66.37 153

TAMVS		44.02 192	49.18 189	37.99 196	47.03 187	45.97 204	45.04 196	28.47 207	39.11 191	20.23 192	43.22 168	48.52 137	28.49 192	58.15 181	57.95 178	58.71 195	51.36 201

UGNet		57.03 107	65.25 75	47.44 158	46.54 188	66.73 88	56.30 142	43.28 124	50.06 102	32.99 141	62.57 56	63.26 75	33.31 182	68.25 98	67.58 94	72.20 149	78.29 69
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
TSAR-MVS + COLMAP		62.65 68	69.90 54	54.19 98	46.31 189	66.73 88	65.49 87	41.36 143	76.57 24	46.31 79	76.80 17	56.68 103	53.27 81	69.50 82	66.65 107	72.40 146	76.36 88

PatchMatch-RL		50.11 162	51.56 176	48.43 147	46.23 190	51.94 182	50.21 173	38.62 169	46.62 137	37.51 127	42.43 175	39.38 198	52.24 88	60.98 166	59.56 172	65.76 176	60.01 188

CMPMVS	37.70 17	49.24 166	52.71 167	45.19 167	45.97 191	51.23 186	47.44 185	29.31 204	43.04 163	44.69 88	34.45 195	48.35 138	43.64 130	62.59 157	59.82 171	60.08 193	69.48 131
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
pmnet_mix02		40.48 202	43.80 204	36.61 199	45.79 192	40.45 212	42.12 205	33.18 197	40.30 184	24.11 185	38.76 184	37.11 207	24.30 198	52.97 203	46.66 212	50.17 212	50.33 205

pmmvs5		47.07 182	51.02 181	42.46 180	45.18 193	51.47 185	48.23 181	33.09 198	38.17 197	28.62 164	46.60 131	43.48 184	30.74 185	58.28 180	58.63 175	68.92 165	60.48 184

USDC		51.11 154	53.71 159	48.08 153	44.76 194	55.99 171	53.01 167	40.90 146	52.49 92	36.14 132	44.67 152	33.66 211	43.27 135	63.23 154	61.10 165	70.39 161	64.82 166

FC-MVSNet-test		39.65 204	48.35 192	29.49 208	44.43 195	39.28 216	30.23 218	40.44 154	43.59 158	3.12 225	53.00 93	42.03 186	10.02 221	55.09 198	54.77 190	48.66 213	50.71 203

ADS-MVSNet		40.67 200	43.38 206	37.50 197	44.36 196	39.79 214	42.09 206	32.67 201	44.34 152	28.87 163	40.76 180	40.37 195	30.22 186	48.34 215	45.87 213	46.81 215	44.21 214

new-patchmatchnet		33.24 211	37.20 212	28.62 210	44.32 197	38.26 217	29.68 219	36.05 180	31.97 209	6.33 221	26.59 211	27.33 216	11.12 220	50.08 211	41.05 216	44.23 216	45.15 213

MVS-HIRNet		42.24 196	41.15 209	43.51 175	44.06 198	40.74 210	35.77 214	35.35 182	35.38 202	38.34 122	25.63 212	38.55 202	43.48 132	50.77 207	47.03 210	64.07 181	49.98 206

PatchT		48.08 175	51.03 180	44.64 171	42.96 199	50.12 189	40.36 208	35.09 183	43.17 162	39.59 117	42.00 176	39.96 197	46.63 117	58.97 174	60.31 169	63.21 184	62.66 175

CVMVSNet		46.38 186	52.01 174	39.81 190	42.40 200	50.26 188	46.15 190	37.68 174	40.03 186	15.09 201	46.56 132	47.56 146	33.72 181	56.50 191	55.65 184	63.80 183	67.53 141

TinyColmap		47.08 181	47.56 195	46.52 161	42.35 201	53.44 177	51.77 169	40.70 150	43.44 161	31.92 147	29.78 205	23.72 221	45.04 126	61.99 162	59.54 173	67.35 171	61.03 182

ET-MVSNet_ETH3D		58.38 96	61.57 91	54.67 96	42.15 202	65.26 102	65.70 83	43.82 107	48.84 116	42.34 100	59.76 65	47.76 143	56.68 54	67.02 126	68.60 81	77.33 78	73.73 108

MIMVSNet		43.79 193	48.53 191	38.27 194	41.46 203	48.97 193	50.81 171	32.88 200	44.55 148	22.07 186	32.05 198	47.15 150	24.76 197	58.73 176	56.09 182	57.63 200	52.14 199

WB-MVS		29.70 213	35.40 214	23.05 213	40.96 204	39.59 215	18.79 222	40.20 157	25.26 215	1.88 228	33.33 196	21.97 223	3.36 222	48.69 214	44.60 214	33.11 220	34.39 216

N_pmnet		32.67 212	36.85 213	27.79 211	40.55 205	32.13 218	35.80 213	26.79 210	37.24 200	9.10 214	32.02 199	30.94 214	16.30 209	47.22 216	41.21 215	38.21 218	37.21 215

anonymousdsp		52.84 140	57.78 136	47.06 159	40.24 206	58.95 152	53.70 162	33.54 195	36.51 201	32.69 144	43.88 158	45.40 166	47.97 112	67.17 121	70.28 61	74.22 118	82.29 47

EU-MVSNet		40.63 201	45.65 200	34.78 204	39.11 207	46.94 201	40.02 209	34.03 190	33.50 205	10.37 210	35.57 191	37.80 204	23.65 199	51.90 204	50.21 205	61.49 191	63.62 173

FPMVS		38.36 206	40.41 210	35.97 200	38.92 208	39.85 213	45.50 194	25.79 213	41.13 178	18.70 195	30.10 203	24.56 219	31.86 184	49.42 212	46.80 211	55.04 202	51.03 202

TESTMET0.1,1		46.09 187	50.29 183	41.18 186	36.91 209	47.16 198	49.52 174	20.32 217	39.22 189	31.98 145	43.65 162	47.93 141	41.29 145	56.80 187	55.36 186	67.08 173	61.94 179

FMVSNet5		40.96 198	45.81 199	35.29 203	34.30 210	44.55 208	47.28 186	28.84 206	40.76 180	21.62 187	29.85 204	42.44 185	24.77 196	57.53 184	55.00 189	54.93 203	50.56 204

PMMVS		49.20 168	54.28 158	43.28 178	34.13 211	45.70 205	48.98 177	26.09 212	46.31 139	34.92 138	55.22 83	53.47 117	47.48 114	59.43 171	59.04 174	68.05 169	60.77 183

PMVS	27.84 18	33.81 210	35.28 215	32.09 206	34.13 211	24.81 221	32.51 217	26.48 211	26.41 214	19.37 194	23.76 213	24.02 220	25.18 195	50.78 206	47.24 209	54.89 205	49.95 207
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
test-mter		45.30 188	50.37 182	39.38 191	33.65 213	46.99 200	47.59 183	18.59 218	38.75 192	28.00 165	43.28 167	46.82 156	41.50 144	57.28 185	55.78 183	66.93 175	63.70 172

CHOSEN 280x420		40.80 199	45.05 202	35.84 202	32.95 214	29.57 219	44.98 197	23.71 215	37.54 199	18.42 196	31.36 201	47.07 151	46.41 119	56.71 189	54.65 193	48.55 214	58.47 192

PM-MVS		44.55 191	48.13 193	40.37 189	32.85 215	46.82 202	46.11 191	29.28 205	40.48 182	29.99 156	39.98 181	34.39 210	41.80 143	56.08 194	53.88 199	62.19 190	65.31 162

TDRefinement		49.31 164	52.44 170	45.67 166	30.44 216	59.42 147	59.24 120	39.78 160	48.76 119	31.20 150	35.73 190	29.90 215	42.81 138	64.24 153	62.59 159	70.55 159	66.43 151

Gipuma		25.87 214	26.91 217	24.66 212	28.98 217	20.17 222	20.46 220	34.62 188	29.55 212	9.10 214	4.91 225	5.31 229	15.76 210	49.37 213	49.10 207	39.03 217	29.95 218
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
MDA-MVSNet-bldmvs		41.36 197	43.15 207	39.27 192	28.74 218	52.68 180	44.95 198	40.84 147	32.89 206	18.13 197	31.61 200	22.09 222	38.97 154	50.45 209	56.11 181	64.01 182	56.23 196

E-PMN		15.09 217	13.19 221	17.30 215	27.80 219	12.62 225	7.81 226	27.54 208	14.62 223	3.19 223	6.89 222	2.52 232	15.09 211	15.93 221	20.22 220	22.38 221	19.53 221

MIMVSNet1		35.51 208	41.41 208	28.63 209	27.53 220	43.36 209	38.09 211	33.82 192	32.01 208	6.77 220	21.63 216	35.43 208	11.97 215	55.05 199	53.99 197	53.59 208	48.36 211

EMVS		14.49 218	12.45 222	16.87 217	27.02 221	12.56 226	8.13 225	27.19 209	15.05 222	3.14 224	6.69 223	2.67 231	15.08 212	14.60 223	18.05 221	20.67 222	17.56 223

pmmvs3		35.10 209	38.47 211	31.17 207	26.37 222	40.47 211	34.51 216	18.09 219	24.75 216	16.88 199	23.05 214	26.69 217	32.69 183	50.73 208	51.60 202	58.46 198	51.98 200

RPSCF		46.41 184	54.42 156	37.06 198	25.70 223	45.14 206	45.39 195	20.81 216	62.79 60	35.10 135	44.92 151	55.60 112	43.56 131	56.12 193	52.45 201	51.80 210	63.91 171

new_pmnet		23.19 215	28.17 216	17.37 214	17.03 224	24.92 220	19.66 221	16.16 221	27.05 213	4.42 222	20.77 217	19.20 224	12.19 214	37.71 217	36.38 217	34.77 219	31.17 217

PMMVS2		15.84 216	19.68 218	11.35 218	15.74 225	16.95 223	13.31 223	17.64 220	16.08 221	0.36 229	13.12 219	11.47 226	1.69 224	28.82 218	27.24 219	19.38 224	24.09 220

MVE	12.28 19	13.53 219	15.72 219	10.96 219	7.39 226	15.71 224	6.05 227	23.73 214	10.29 225	3.01 226	5.77 224	3.41 230	11.91 216	20.11 219	29.79 218	13.67 225	24.98 219
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
tmp_tt				5.40 221	3.97 227	2.35 229	3.26 229	0.44 224	17.56 220	12.09 205	11.48 221	7.14 227	1.98 223	15.68 222	15.49 222	10.69 226

test_method		12.44 220	14.66 220	9.85 220	1.30 228	3.32 228	13.00 224	3.21 222	22.42 218	10.22 211	14.13 218	25.64 218	11.43 218	19.75 220	11.61 223	19.96 223	5.79 224

GG-mvs-BLEND		36.62 207	53.39 163	17.06 216	0.01 229	58.61 154	48.63 178	0.01 225	47.13 133	0.02 230	43.98 157	60.64 88	0.03 225	54.92 200	51.47 203	53.64 207	56.99 194

uanet_test		0.00 223	0.00 225	0.00 222	0.00 230	0.00 230	0.00 232	0.00 226	0.00 228	0.00 231	0.00 228	0.00 233	0.00 228	0.00 226	0.00 226	0.00 228	0.00 227

sosnet-low-res		0.00 223	0.00 225	0.00 222	0.00 230	0.00 230	0.00 232	0.00 226	0.00 228	0.00 231	0.00 228	0.00 233	0.00 228	0.00 226	0.00 226	0.00 228	0.00 227

sosnet		0.00 223	0.00 225	0.00 222	0.00 230	0.00 230	0.00 232	0.00 226	0.00 228	0.00 231	0.00 228	0.00 233	0.00 228	0.00 226	0.00 226	0.00 228	0.00 227

testmvs		0.01 221	0.02 223	0.00 222	0.00 230	0.00 230	0.01 231	0.00 226	0.01 226	0.00 231	0.03 227	0.00 233	0.01 226	0.01 225	0.01 224	0.00 228	0.06 226

test123		0.01 221	0.02 223	0.00 222	0.00 230	0.00 230	0.00 232	0.00 226	0.01 226	0.00 231	0.04 226	0.00 233	0.01 226	0.00 226	0.01 224	0.00 228	0.07 225

RE-MVS-def										33.01 140

9.14												81.81 13

MTAPA										65.14 4		80.20 20

MTMP										62.63 16		78.04 26

Patchmatch-RL test							1.04 230

NP-MVS									72.00 41

Patchmtry						47.61 196	48.27 179	38.86 164		39.59 117

DeepMVS_CX						6.95 227	5.98 228	2.25 223	11.73 224	2.07 227	11.85 220	5.43 228	11.75 217	11.40 224		8.10 227	18.38 222

High-resolution multi-view benchmark