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 48	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 59	66.77 29	73.73 23	74.30 43	75.28 40	53.58 36	70.24 45	57.59 35	51.19 104	59.19 93	60.74 28	75.33 42	73.72 45	79.69 54	77.96 71

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 47	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 35	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 75	53.81 53	59.51 65	68.96 57	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 38	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 37	54.88 45	70.03 27	70.48 51	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 55	55.52 40	54.88 84	69.90 53	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	38.91 161	71.86 41	60.70 22	64.97 41	67.88 65	51.88 92	76.77 31	74.98 36	76.11 96	69.75 124
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 60	66.13 33	70.59 37	72.01 53	76.54 35	54.26 32	65.64 53	54.78 47	50.35 107	61.72 82	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 36	55.56 39	70.13 26	71.36 49	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 64	55.06 43	62.14 57	66.40 68	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 46	60.17 24	56.42 76	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 48	52.05 60	63.21 50	63.89 71	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 49	55.74 38	61.53 60	62.29 78	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 54	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 42	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 43	58.65 30	55.97 78	69.95 52	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 58	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 67	53.23 55	64.01 47	69.71 55	60.37 31	74.92 44	71.24 55	82.50 20	82.41 45

UA-Net		58.50 91	64.68 79	51.30 120	66.97 53	67.13 85	53.68 162	45.65 80	49.51 107	31.58 148	62.91 52	68.47 59	35.85 172	68.20 100	67.28 97	74.03 119	69.24 134

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 44	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 51	55.00 44	54.31 89	68.19 61	58.49 42	73.97 49	73.63 46	81.22 41	80.23 56

EPNet		65.14 60	69.54 56	60.00 58	66.61 56	67.67 77	67.53 64	55.32 24	62.67 60	46.22 81	67.74 32	65.93 69	48.07 111	72.17 57	72.12 49	76.28 92	78.47 67
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 71	59.39 62	66.47 57	69.52 61	64.26 98	43.07 130	61.34 63	50.19 66	47.29 125	64.41 70	54.60 65	70.18 78	68.62 80	77.73 70	78.89 63

ACMH	52.42 13	58.24 98	59.56 118	56.70 85	66.34 58	69.59 60	66.71 73	49.12 61	46.08 140	28.90 161	42.67 172	41.20 189	52.60 84	71.39 63	70.28 61	76.51 88	75.72 91
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
MSDG		58.46 93	58.97 124	57.85 77	66.27 59	66.23 94	67.72 61	42.33 134	53.43 82	43.68 93	43.39 163	45.35 166	49.75 100	68.66 91	67.77 89	77.38 76	67.96 139

QAPM		65.27 56	69.49 57	60.35 55	65.43 60	72.20 52	65.69 85	47.23 69	63.46 56	49.14 68	53.56 90	71.04 50	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 39	50.33 65	60.73 61	72.65 46	59.43 36	73.32 52	72.12 49	79.19 60	85.99 25

MS-PatchMatch		58.19 100	60.20 105	55.85 90	65.17 62	64.16 113	64.82 92	41.48 142	50.95 97	42.17 102	45.38 146	56.42 105	48.08 110	68.30 96	66.70 105	73.39 127	69.46 132

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 50	54.39 51	58.35 70	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		56.98 107	58.24 131	55.50 92	64.66 64	68.62 65	61.48 107	43.63 114	38.44 193	41.44 104	38.05 184	46.18 161	43.95 129	71.71 61	70.61 58	77.87 69	74.08 104

Effi-MVS+-dtu		60.34 78	62.32 88	58.03 72	64.31 65	67.44 81	65.99 80	42.26 135	49.55 105	42.00 103	48.92 115	59.79 91	56.27 57	68.07 104	67.03 98	77.35 77	75.45 94

FC-MVSNet-train		58.40 94	63.15 85	52.85 111	64.29 66	61.84 125	55.98 146	46.47 73	53.06 86	34.96 136	61.95 59	56.37 107	39.49 149	68.67 90	68.36 82	75.92 102	71.81 112

Effi-MVS+		63.28 63	65.96 70	60.17 57	64.26 67	68.06 71	68.78 59	45.71 79	54.08 78	46.64 78	55.92 79	63.13 75	55.94 60	70.38 76	71.43 52	79.68 55	78.70 64

LS3D		60.20 79	61.70 89	58.45 67	64.18 68	67.77 74	67.19 66	48.84 65	61.67 62	41.27 107	45.89 140	51.81 124	54.18 67	68.78 88	66.50 112	75.03 111	69.48 130

ACMH+	53.71 12	59.26 83	60.28 102	58.06 70	64.17 69	68.46 66	67.51 65	50.93 50	52.46 92	35.83 133	40.83 177	45.12 170	52.32 87	69.88 80	69.00 75	77.59 74	76.21 88

GeoE		62.43 69	64.79 78	59.68 61	64.15 70	67.17 84	68.80 58	44.42 96	55.65 74	47.38 72	51.54 101	62.51 76	54.04 69	69.99 79	68.07 84	79.28 58	78.57 65

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 70	49.05 70	64.43 43	68.66 58	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 45	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 45	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 83	58.89 65	63.82 74	67.61 78	65.35 88	42.15 138	49.98 102	45.66 84	57.47 74	56.62 103	56.59 55	70.91 70	69.15 71	79.78 50	74.80 98

Anonymous202405211			60.60 98		63.44 75	66.71 91	61.00 112	47.23 69	50.62 100		36.85 187	60.63 88	43.03 137	69.17 84	67.72 91	75.41 105	72.54 109

ETV-MVS		63.23 64	66.08 69	59.91 59	63.13 76	68.13 70	67.62 63	44.62 92	53.39 83	46.23 80	58.74 67	58.19 96	57.45 46	73.60 50	71.38 54	80.39 45	79.13 61

casdiffmvs_mvg		65.26 57	69.48 58	60.33 56	62.99 77	69.34 62	69.80 55	45.27 83	63.38 57	51.11 62	65.12 40	69.75 54	53.51 74	71.74 60	68.86 76	79.33 56	78.19 70
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		49.07 168	52.56 168	45.00 168	61.99 78	59.78 144	53.55 164	41.63 140	31.62 209	12.08 205	29.56 205	53.28 118	29.57 187	66.27 135	64.49 139	71.19 156	62.92 173

CS-MVS-test		65.18 58	68.70 61	61.07 53	61.92 79	68.06 71	67.09 70	45.18 85	58.47 69	52.02 61	65.76 36	66.44 67	59.24 37	72.71 55	70.05 64	80.98 43	79.40 60

DCV-MVSNet		59.49 81	64.00 82	54.23 97	61.81 80	64.33 111	61.42 108	43.77 108	52.85 89	38.94 121	55.62 81	62.15 80	43.24 136	69.39 83	67.66 93	76.22 94	75.97 89

casdiffmvs		64.09 61	68.13 62	59.37 63	61.81 80	68.32 68	68.48 60	44.45 95	61.95 61	49.12 69	63.04 51	69.67 56	53.83 70	70.46 73	66.06 117	78.55 63	77.43 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
CS-MVS		65.88 52	69.71 55	61.41 52	61.76 82	68.14 69	67.65 62	44.00 105	59.14 68	52.69 57	65.19 38	68.13 62	60.90 26	74.74 45	71.58 51	81.46 40	81.04 53

Anonymous20231211		57.71 103	60.79 95	54.13 99	61.68 83	65.81 97	60.81 113	43.70 112	51.97 95	39.67 116	34.82 192	63.59 72	43.31 134	68.55 94	66.63 108	75.59 103	74.13 103

IS_MVSNet		57.95 101	64.26 81	50.60 122	61.62 84	65.25 103	57.18 133	45.42 82	50.79 98	26.49 175	57.81 72	60.05 90	34.51 176	71.24 66	70.20 63	78.36 67	74.44 100

NR-MVSNet		55.35 124	59.46 119	50.56 123	61.33 85	62.97 119	57.91 129	51.80 45	48.62 122	20.59 189	51.99 99	44.73 176	34.10 179	68.58 92	68.64 79	77.66 71	70.67 121

MVS_111021_LR		63.05 65	66.43 66	59.10 64	61.33 85	63.77 116	65.87 82	43.58 115	60.20 65	53.70 54	62.09 58	62.38 77	55.84 61	70.24 77	68.08 83	74.30 116	78.28 69

EPP-MVSNet		59.39 82	65.45 73	52.32 115	60.96 87	67.70 76	58.42 126	44.75 90	49.71 104	27.23 169	59.03 66	62.20 79	43.34 133	70.71 71	69.13 72	79.25 59	79.63 59

TransMVSNet (Re)		51.92 150	55.38 148	47.88 154	60.95 88	59.90 143	53.95 159	45.14 86	39.47 187	24.85 179	43.87 158	46.51 157	29.15 188	67.55 114	65.23 130	73.26 132	65.16 164

gm-plane-assit		44.74 188	45.95 196	43.33 176	60.88 89	46.79 202	36.97 211	32.24 201	24.15 216	11.79 206	29.26 206	32.97 211	46.64 116	65.09 149	62.95 152	71.45 153	60.42 184

baseline1		54.48 133	58.69 125	49.57 129	60.63 90	58.29 159	55.70 148	44.95 88	49.20 110	29.62 157	54.77 85	54.75 112	35.29 173	67.15 122	64.08 141	71.21 155	62.58 177

test2506		55.82 119	59.57 117	51.46 118	60.39 91	64.55 109	58.69 124	48.87 63	53.91 79	26.99 170	48.97 113	41.72 188	37.71 159	70.96 68	69.49 67	76.08 97	67.37 144

ECVR-MVS		56.44 114	60.74 96	51.42 119	60.39 91	64.55 109	58.69 124	48.87 63	53.91 79	26.76 172	45.55 145	53.43 117	37.71 159	70.96 68	69.49 67	76.08 97	67.32 146

DI_MVS_plusplus_trai		61.88 71	65.17 75	58.06 70	60.05 93	65.26 101	66.03 79	44.22 97	55.75 73	46.73 76	54.64 87	68.12 63	54.13 68	69.13 85	66.66 106	77.18 79	76.61 81

PVSNet_Blended_VisFu		63.65 62	66.92 63	59.83 60	60.03 94	73.44 47	66.33 76	48.95 62	52.20 94	50.81 64	56.07 77	60.25 89	53.56 72	73.23 53	70.01 65	79.30 57	83.24 43

UniMVSNet_NR-MVSNet		56.94 109	61.14 92	52.05 117	60.02 95	65.21 104	57.44 131	52.93 40	49.37 108	24.31 182	54.62 88	50.54 130	39.04 151	68.69 89	68.84 77	78.53 64	70.72 117

IterMVS-LS		58.30 97	61.39 91	54.71 95	59.92 96	58.40 156	59.42 118	43.64 113	48.71 119	40.25 114	57.53 73	58.55 95	52.15 89	65.42 147	65.34 127	72.85 134	75.77 90
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
test1111		55.24 125	59.98 110	49.71 128	59.80 97	64.10 114	56.48 140	49.34 59	52.27 93	21.56 187	44.49 153	51.96 123	35.93 171	70.59 72	69.07 73	75.13 110	67.40 142

MVS_Test		62.40 70	66.23 68	57.94 73	59.77 98	64.77 107	66.50 75	41.76 139	57.26 71	49.33 67	62.68 54	67.47 66	53.50 76	68.57 93	66.25 114	76.77 84	76.58 82

FA-MVS(training)		60.00 80	63.14 86	56.33 87	59.50 99	64.30 112	65.15 90	38.75 166	56.20 72	45.77 82	53.08 91	56.45 104	52.10 90	69.04 87	67.67 92	76.69 85	75.27 97

TranMVSNet+NR-MVSNet		55.87 117	60.14 107	50.88 121	59.46 100	63.82 115	57.93 128	52.98 39	48.94 114	20.52 190	52.87 93	47.33 148	36.81 167	69.12 86	69.03 74	77.56 75	69.89 123

Fast-Effi-MVS+		60.36 77	63.35 84	56.87 83	58.70 101	65.86 96	65.08 91	37.11 175	53.00 88	45.36 86	52.12 98	56.07 109	56.27 57	71.28 65	69.42 69	78.71 61	75.69 92

IB-MVS	54.11 11	58.36 96	60.70 97	55.62 91	58.67 102	68.02 73	61.56 105	43.15 128	46.09 139	44.06 92	44.24 155	50.99 129	48.71 105	66.70 128	70.33 60	77.60 73	78.50 66
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		56.30 115	59.29 121	52.82 112	58.64 103	64.89 105	65.56 86	32.89 198	45.80 142	35.04 135	45.89 140	54.14 114	49.41 101	67.16 121	66.45 113	75.37 107	70.69 119

CNLPA		62.78 67	66.31 67	58.65 66	58.47 104	68.41 67	65.98 81	41.22 145	78.02 22	56.04 37	46.65 128	59.50 92	57.50 45	69.67 81	65.27 129	72.70 140	76.67 80

tpm cat1		53.30 138	53.41 161	53.17 108	58.16 105	59.15 150	63.73 101	38.27 170	50.73 99	46.98 75	45.57 144	44.00 182	49.20 102	55.90 195	54.02 194	62.65 186	64.50 168

v1144		58.88 86	60.16 106	57.39 79	58.03 106	67.26 82	67.14 68	44.46 94	45.17 145	44.33 91	47.81 122	49.92 135	53.20 82	67.77 110	66.62 109	77.15 80	76.58 82

v10		59.17 85	60.60 98	57.50 78	57.95 107	66.73 88	67.09 70	44.11 98	46.85 133	45.42 85	48.18 121	51.07 126	53.63 71	67.84 108	66.59 110	76.79 83	76.92 78

v1192		58.51 90	59.66 113	57.17 80	57.82 108	67.72 75	66.21 78	44.83 89	44.15 153	43.49 94	46.68 127	47.94 139	53.55 73	67.39 117	66.51 111	77.13 81	77.20 76

v144192		58.23 99	59.40 120	56.87 83	57.56 109	66.89 86	65.70 83	45.01 87	44.06 154	42.88 96	46.61 129	48.09 138	53.49 77	66.94 126	65.90 121	76.61 86	77.29 74

v1921920		57.89 102	59.02 123	56.58 86	57.55 110	66.66 92	64.72 94	44.70 91	43.55 158	42.73 97	46.17 137	46.93 152	53.51 74	66.78 127	65.75 123	76.29 91	77.28 75

Vis-MVSNet (Re-imp)		50.37 158	57.73 137	41.80 183	57.53 111	54.35 173	45.70 192	45.24 84	49.80 103	13.43 203	58.23 71	56.42 105	20.11 204	62.96 155	63.36 148	68.76 165	58.96 189

CostFormer		56.57 112	59.13 122	53.60 102	57.52 112	61.12 132	66.94 72	35.95 180	53.44 81	44.68 89	55.87 80	54.44 113	48.21 108	60.37 168	58.33 175	68.27 167	70.33 122

thres400		52.38 144	55.51 146	48.74 140	57.49 113	60.10 142	55.45 151	43.54 116	42.90 165	26.72 173	43.34 165	45.03 174	36.61 168	66.20 137	64.53 138	72.66 141	66.43 150

thres600view7		51.91 151	55.14 150	48.14 150	57.43 114	60.18 140	54.60 157	43.73 110	42.61 169	25.20 178	43.10 168	44.47 179	35.19 174	66.36 132	63.28 149	72.66 141	66.01 157

thres200		52.39 143	55.37 149	48.90 138	57.39 115	60.18 140	55.60 149	43.73 110	42.93 164	27.41 167	43.35 164	45.09 171	36.61 168	66.36 132	63.92 144	72.66 141	65.78 159

baseline2		55.89 116	57.82 134	53.64 101	57.36 116	61.09 133	59.75 117	40.45 152	47.38 131	41.26 108	51.23 103	46.90 153	48.11 109	65.63 144	64.38 140	74.90 112	68.16 138

v8		58.88 86	60.57 100	56.92 82	57.35 117	65.69 98	66.69 74	42.64 132	47.89 128	45.77 82	49.04 112	52.98 119	52.77 83	67.51 115	65.57 124	76.26 93	75.30 96

thres100view900		52.04 148	54.81 154	48.80 139	57.31 118	59.33 147	55.30 153	42.92 131	42.85 166	27.81 165	43.00 169	45.06 172	36.99 165	64.74 150	63.51 146	72.47 144	65.21 163

tfpn200view9		52.53 141	55.51 146	49.06 136	57.31 118	60.24 139	55.42 152	43.77 108	42.85 166	27.81 165	43.00 169	45.06 172	37.32 163	66.38 131	64.54 137	72.71 139	66.54 149

v1240		57.55 104	58.63 127	56.29 88	57.30 120	66.48 93	63.77 100	44.56 93	42.77 168	42.48 99	45.64 143	46.28 159	53.46 78	66.32 134	65.80 122	76.16 95	77.13 77

dmvs_re		52.07 146	55.11 151	48.54 145	57.27 121	51.93 182	57.73 130	43.13 129	43.65 156	26.57 174	44.52 152	50.00 134	36.53 170	66.58 130	62.15 159	69.97 161	66.91 147

CHOSEN 1792x2688		55.85 118	58.01 132	53.33 104	57.26 122	62.82 121	63.29 104	41.55 141	46.65 135	38.34 122	34.55 193	53.50 115	52.43 86	67.10 123	67.56 95	67.13 171	73.92 106

PVSNet_BlendedMVS		61.63 73	64.82 76	57.91 75	57.21 123	67.55 79	63.47 102	46.08 75	54.72 76	52.46 58	58.59 68	60.73 85	51.82 93	70.46 73	65.20 131	76.44 89	76.50 85

PVSNet_Blended		61.63 73	64.82 76	57.91 75	57.21 123	67.55 79	63.47 102	46.08 75	54.72 76	52.46 58	58.59 68	60.73 85	51.82 93	70.46 73	65.20 131	76.44 89	76.50 85

v2v482		58.69 89	60.12 109	57.03 81	57.16 125	66.05 95	67.17 67	43.52 117	46.33 137	45.19 87	49.46 111	51.02 127	52.51 85	67.30 118	66.03 118	76.61 86	74.62 99

tfpnnormal		50.16 160	52.19 172	47.78 156	56.86 126	58.37 157	54.15 158	44.01 104	38.35 195	25.94 176	36.10 188	37.89 202	34.50 177	65.93 139	63.42 147	71.26 154	65.28 162

diffmvs		61.64 72	66.55 65	55.90 89	56.63 127	63.71 117	67.13 69	41.27 144	59.49 66	46.70 77	63.93 49	68.01 64	50.46 97	67.30 118	65.51 125	73.24 133	77.87 72
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		56.87 110	58.60 128	54.84 94	56.62 128	69.27 63	64.77 93	42.21 136	45.66 143	37.50 128	33.08 196	57.47 101	53.33 79	65.46 146	67.94 85	74.60 113	71.35 114

v7n		55.67 120	57.46 139	53.59 103	56.06 129	65.29 100	61.06 111	43.26 125	40.17 184	37.99 125	40.79 178	45.27 169	47.09 115	67.67 112	66.21 115	76.08 97	76.82 79

dps		50.42 157	51.20 178	49.51 130	55.88 130	56.07 169	53.73 160	38.89 162	43.66 155	40.36 113	45.66 142	37.63 204	45.23 124	59.05 171	56.18 179	62.94 185	60.16 185

CANet_DTU		58.88 86	64.68 79	52.12 116	55.77 131	66.75 87	63.92 99	37.04 176	53.32 84	37.45 129	59.81 63	61.81 81	44.43 128	68.25 97	67.47 96	74.12 118	75.33 95

WR-MVS		48.78 170	55.06 152	41.45 184	55.50 132	60.40 138	43.77 200	49.99 56	41.92 172	8.10 216	45.24 149	45.56 164	17.47 205	61.57 163	64.60 136	73.85 120	66.14 156

UniMVSNet (Re)		55.15 129	60.39 101	49.03 137	55.31 133	64.59 108	55.77 147	50.63 52	48.66 121	20.95 188	51.47 102	50.40 131	34.41 178	67.81 109	67.89 86	77.11 82	71.88 111

test-LLR		49.28 164	50.29 182	48.10 151	55.26 134	47.16 197	49.52 173	43.48 120	39.22 188	31.98 144	43.65 161	47.93 140	41.29 144	56.80 186	55.36 185	67.08 172	61.94 178

test0.0.03 1		43.15 193	46.95 195	38.72 192	55.26 134	50.56 186	42.48 203	43.48 120	38.16 197	15.11 199	35.07 191	44.69 177	16.47 207	55.95 194	54.34 193	59.54 193	49.87 207

GA-MVS		55.67 120	58.33 129	52.58 114	55.23 136	63.09 118	61.08 110	40.15 157	42.95 163	37.02 131	52.61 95	47.68 143	47.51 113	65.92 140	65.35 126	74.49 115	70.68 120

DTE-MVSNet		48.03 176	53.28 163	41.91 182	54.64 137	57.50 165	44.63 199	51.66 48	41.02 178	7.97 217	46.26 134	40.90 190	20.24 203	60.45 167	62.89 153	72.33 147	63.97 169

pmmvs4		54.66 132	56.07 143	53.00 109	54.63 138	57.08 167	60.43 115	44.10 99	51.69 96	40.55 111	46.55 132	44.79 175	45.95 121	62.54 157	63.66 145	72.36 146	66.20 154

DU-MVS		55.41 123	59.59 114	50.54 124	54.60 139	62.97 119	57.44 131	51.80 45	48.62 122	24.31 182	51.99 99	47.00 151	39.04 151	68.11 102	67.75 90	76.03 101	70.72 117

Baseline_NR-MVSNet		53.50 136	57.89 133	48.37 148	54.60 139	59.25 149	56.10 142	51.84 44	49.32 109	17.92 197	45.38 146	47.68 143	36.93 166	68.11 102	65.95 119	72.84 135	69.57 128

v148		55.58 122	57.61 138	53.20 106	54.59 141	61.86 124	61.18 109	38.70 167	44.30 152	42.25 101	47.53 123	50.24 133	48.73 104	65.15 148	62.61 157	73.79 121	71.61 113

PEN-MVS		49.21 166	54.32 156	43.24 178	54.33 142	59.26 148	47.04 186	51.37 49	41.67 174	9.97 211	46.22 135	41.80 187	22.97 201	60.52 166	64.03 142	73.73 122	66.75 148

pm-mvs1		51.02 154	55.55 145	45.73 163	54.16 143	58.52 154	50.92 169	42.56 133	40.32 182	25.67 177	43.66 160	50.34 132	30.06 186	65.85 141	63.97 143	70.99 157	66.21 153

EPNet_dtu		52.05 147	58.26 130	44.81 169	54.10 144	50.09 189	52.01 167	40.82 148	53.03 87	27.41 167	54.90 83	57.96 100	26.72 193	62.97 154	62.70 156	67.78 169	66.19 155
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
tpm		48.82 169	51.27 177	45.96 162	54.10 144	47.35 196	56.05 143	30.23 202	46.70 134	43.21 95	52.54 96	47.55 146	37.28 164	54.11 200	50.50 203	54.90 203	60.12 186

CDS-MVSNet		52.42 142	57.06 141	47.02 159	53.92 146	58.30 158	55.50 150	46.47 73	42.52 170	29.38 159	49.50 110	52.85 120	28.49 191	66.70 128	66.89 102	68.34 166	62.63 176
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
test20.03		40.38 202	44.20 202	35.92 200	53.73 147	49.05 190	38.54 209	43.49 119	32.55 206	9.54 212	27.88 208	39.12 198	12.24 212	56.28 191	54.69 190	57.96 198	49.83 208

Vis-MVSNet		58.48 92	65.70 72	50.06 127	53.40 148	67.20 83	60.24 116	43.32 123	48.83 116	30.23 154	62.38 56	61.61 83	40.35 147	71.03 67	69.77 66	72.82 136	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 84	62.47 87	55.41 93	53.24 149	64.84 106	64.47 97	40.41 154	65.92 52	44.53 90	46.19 136	55.69 110	55.33 63	68.24 99	65.30 128	74.50 114	71.09 115
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
thisisatest0530		56.68 111	59.68 112	53.19 107	52.97 150	60.96 135	59.41 119	40.51 150	48.26 125	41.06 109	52.67 94	46.30 158	49.78 98	67.66 113	67.83 87	75.39 106	74.07 105

OMC-MVS		65.16 59	71.35 45	57.94 73	52.95 151	68.82 64	69.00 57	38.28 169	79.89 15	55.20 42	62.76 53	68.31 60	56.14 59	71.30 64	68.70 78	76.06 100	79.67 58

tpmrst		48.08 174	49.88 186	45.98 161	52.71 152	48.11 194	53.62 163	33.70 193	48.70 120	39.74 115	48.96 114	46.23 160	40.29 148	50.14 209	49.28 205	55.80 200	57.71 192

tttt0517		56.53 113	59.59 114	52.95 110	52.66 153	60.99 134	59.21 121	40.51 150	47.89 128	40.40 112	52.50 97	46.04 162	49.78 98	67.75 111	67.83 87	75.15 109	74.17 102

GBi-Net		55.20 126	60.25 103	49.31 131	52.42 154	61.44 127	57.03 134	44.04 101	49.18 111	30.47 150	48.28 117	58.19 96	38.22 154	68.05 105	66.96 99	73.69 123	69.65 125

test1		55.20 126	60.25 103	49.31 131	52.42 154	61.44 127	57.03 134	44.04 101	49.18 111	30.47 150	48.28 117	58.19 96	38.22 154	68.05 105	66.96 99	73.69 123	69.65 125

FMVSNet2		55.04 130	59.95 111	49.31 131	52.42 154	61.44 127	57.03 134	44.08 100	49.55 105	30.40 153	46.89 126	58.84 94	38.22 154	67.07 124	66.21 115	73.69 123	69.65 125

FMVSNet3		54.78 131	59.58 116	49.17 134	52.37 157	61.31 131	56.72 139	44.04 101	49.18 111	30.47 150	48.28 117	58.19 96	38.09 157	65.48 145	65.20 131	73.31 130	69.45 133

testgi		38.71 204	43.64 204	32.95 204	52.30 158	48.63 193	35.59 214	35.05 183	31.58 210	9.03 215	30.29 201	40.75 192	11.19 218	55.30 196	53.47 199	54.53 205	45.48 211

Anonymous20231206		42.28 194	45.89 197	38.07 194	51.96 159	48.98 191	43.66 201	38.81 165	38.74 192	14.32 202	26.74 209	40.90 190	20.94 202	56.64 189	54.67 191	58.71 194	54.59 196

pmmvs6		48.35 172	51.64 174	44.51 171	51.92 160	57.94 163	49.44 175	42.17 137	34.45 202	24.62 181	28.87 207	46.90 153	29.07 190	64.60 151	63.08 150	69.83 162	65.68 160

PatchmatchNet		49.92 162	51.29 176	48.32 149	51.83 161	51.86 183	53.38 165	37.63 174	47.90 127	40.83 110	48.54 116	45.30 167	45.19 125	56.86 185	53.99 196	61.08 191	54.57 197
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
WR-MVS_H		47.65 177	53.67 159	40.63 187	51.45 162	59.74 145	44.71 198	49.37 58	40.69 180	7.61 218	46.04 138	44.34 181	17.32 206	57.79 182	61.18 163	73.30 131	65.86 158

LTVRE_ROB	44.17 16	47.06 182	50.15 185	43.44 175	51.39 163	58.42 155	42.90 202	43.51 118	22.27 218	14.85 201	41.94 176	34.57 208	45.43 122	62.28 160	62.77 155	62.56 188	68.83 136
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		48.37 171	53.53 160	42.34 180	51.35 164	58.01 162	46.56 187	50.54 53	41.62 175	10.61 207	46.53 133	40.68 193	23.18 199	58.71 176	61.83 160	71.81 150	67.36 145

PS-CasMVS		48.18 173	53.25 164	42.27 181	51.26 165	57.94 163	46.51 188	50.52 54	41.30 176	10.56 208	45.35 148	40.34 195	23.04 200	58.66 177	61.79 161	71.74 152	67.38 143

our_test_3					51.15 166	57.31 166	55.12 154

SCA		50.99 155	53.22 165	48.40 147	51.07 167	56.78 168	50.25 171	39.05 160	48.31 124	41.38 105	49.54 109	46.70 156	46.00 120	58.31 178	56.28 178	62.65 186	56.60 194

UniMVSNet_ETH3D		52.62 140	55.98 144	48.70 142	51.04 168	60.71 137	56.87 137	46.74 72	42.52 170	26.96 171	42.50 173	45.95 163	37.87 158	66.22 136	65.15 134	72.74 137	68.78 137

IterMVS-SCA-FT		52.18 145	57.75 136	45.68 164	51.01 169	62.06 123	55.10 155	34.75 184	44.85 146	32.86 142	51.13 105	51.22 125	48.74 103	62.47 158	61.51 162	51.61 210	71.02 116

FMVSNet1		54.08 134	58.68 126	48.71 141	50.90 170	61.35 130	56.73 138	43.94 106	45.91 141	29.32 160	42.72 171	56.26 108	37.70 161	68.05 105	66.96 99	73.69 123	69.50 129

pmmvs-eth3d		51.33 152	52.25 171	50.26 126	50.82 171	54.65 172	56.03 144	43.45 122	43.51 159	37.20 130	39.20 181	39.04 199	42.28 139	61.85 162	62.78 154	71.78 151	64.72 166

MVSTER		57.19 105	61.11 93	52.62 113	50.82 171	58.79 152	61.55 106	37.86 172	48.81 117	41.31 106	57.43 75	52.10 122	48.60 106	68.19 101	66.75 104	75.56 104	75.68 93

ambc			45.54 200		50.66 173	52.63 180	40.99 206		38.36 194	24.67 180	22.62 214	13.94 224	29.14 189	65.71 143	58.06 176	58.60 196	67.43 141

thisisatest0515		53.85 135	56.84 142	50.37 125	50.25 174	58.17 160	55.99 145	39.90 158	41.88 173	38.16 124	45.91 139	45.30 167	44.58 127	66.15 138	66.89 102	73.36 129	73.57 108

baseline		55.19 128	60.88 94	48.55 144	49.87 175	58.10 161	58.70 123	34.75 184	52.82 90	39.48 120	60.18 62	60.86 84	45.41 123	61.05 164	60.74 167	63.10 184	72.41 110

MDTV_nov1_ep13		50.32 159	52.43 170	47.86 155	49.87 175	54.70 171	58.10 127	34.29 188	45.59 144	37.71 126	47.44 124	47.42 147	41.86 141	58.07 181	55.21 187	65.34 178	58.56 190

IterMVS		53.45 137	57.12 140	49.17 134	49.23 177	60.93 136	59.05 122	34.63 186	44.53 148	33.22 138	51.09 106	51.01 128	48.38 107	62.43 159	60.79 166	70.54 159	69.05 135
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
COLMAP_ROB	46.52 15	51.99 149	54.86 153	48.63 143	49.13 178	61.73 126	60.53 114	36.57 177	53.14 85	32.95 141	37.10 185	38.68 200	40.49 146	65.72 142	63.08 150	72.11 149	64.60 167
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
CR-MVSNet		50.47 156	52.61 167	47.98 153	49.03 179	52.94 177	48.27 178	38.86 163	44.41 149	39.59 117	44.34 154	44.65 178	46.63 117	58.97 173	60.31 168	65.48 176	62.66 174

V42		56.97 108	60.14 107	53.28 105	48.16 180	62.78 122	66.30 77	37.93 171	47.44 130	42.68 98	48.19 120	52.59 121	51.90 91	67.46 116	65.94 120	72.72 138	76.55 84

MDTV_nov1_ep13_2view		47.62 178	49.72 187	45.18 167	48.05 181	53.70 175	54.90 156	33.80 192	39.90 186	29.79 156	38.85 182	41.89 186	39.17 150	58.99 172	55.55 184	65.34 178	59.17 188

EPMVS		44.66 189	47.86 193	40.92 186	47.97 182	44.70 206	47.58 183	33.27 195	48.11 126	29.58 158	49.65 108	44.38 180	34.65 175	51.71 204	47.90 207	52.49 208	48.57 209

RPMNet		46.41 183	48.72 189	43.72 173	47.77 183	52.94 177	46.02 191	33.92 190	44.41 149	31.82 147	36.89 186	37.42 205	37.41 162	53.88 201	54.02 194	65.37 177	61.47 180

TAPA-MVS	54.74 10	60.85 76	66.61 64	54.12 100	47.38 184	65.33 99	65.35 88	36.51 178	75.16 30	48.82 71	54.70 86	63.51 73	53.31 80	68.36 95	64.97 135	73.37 128	74.27 101
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
SixPastTwentyTwo		47.55 179	50.25 184	44.41 172	47.30 185	54.31 174	47.81 181	40.36 155	33.76 203	19.93 192	43.75 159	32.77 212	42.07 140	59.82 169	60.94 165	68.98 163	66.37 152

TAMVS		44.02 191	49.18 188	37.99 195	47.03 186	45.97 203	45.04 195	28.47 206	39.11 190	20.23 191	43.22 167	48.52 136	28.49 191	58.15 180	57.95 177	58.71 194	51.36 200

UGNet		57.03 106	65.25 74	47.44 157	46.54 187	66.73 88	56.30 141	43.28 124	50.06 101	32.99 140	62.57 55	63.26 74	33.31 181	68.25 97	67.58 94	72.20 148	78.29 68
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	46.31 188	66.73 88	65.49 87	41.36 143	76.57 24	46.31 79	76.80 17	56.68 102	53.27 81	69.50 82	66.65 107	72.40 145	76.36 87

PatchMatch-RL		50.11 161	51.56 175	48.43 146	46.23 189	51.94 181	50.21 172	38.62 168	46.62 136	37.51 127	42.43 174	39.38 197	52.24 88	60.98 165	59.56 171	65.76 175	60.01 187

CMPMVS	37.70 17	49.24 165	52.71 166	45.19 166	45.97 190	51.23 185	47.44 184	29.31 203	43.04 162	44.69 88	34.45 194	48.35 137	43.64 130	62.59 156	59.82 170	60.08 192	69.48 130
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
pmnet_mix02		40.48 201	43.80 203	36.61 198	45.79 191	40.45 211	42.12 204	33.18 196	40.30 183	24.11 184	38.76 183	37.11 206	24.30 197	52.97 202	46.66 211	50.17 211	50.33 204

pmmvs5		47.07 181	51.02 180	42.46 179	45.18 192	51.47 184	48.23 180	33.09 197	38.17 196	28.62 163	46.60 130	43.48 183	30.74 184	58.28 179	58.63 174	68.92 164	60.48 183

USDC		51.11 153	53.71 158	48.08 152	44.76 193	55.99 170	53.01 166	40.90 146	52.49 91	36.14 132	44.67 151	33.66 210	43.27 135	63.23 153	61.10 164	70.39 160	64.82 165

FC-MVSNet-test		39.65 203	48.35 191	29.49 207	44.43 194	39.28 215	30.23 217	40.44 153	43.59 157	3.12 224	53.00 92	42.03 185	10.02 220	55.09 197	54.77 189	48.66 212	50.71 202

ADS-MVSNet		40.67 199	43.38 205	37.50 196	44.36 195	39.79 213	42.09 205	32.67 200	44.34 151	28.87 162	40.76 179	40.37 194	30.22 185	48.34 214	45.87 212	46.81 214	44.21 213

new-patchmatchnet		33.24 210	37.20 211	28.62 209	44.32 196	38.26 216	29.68 218	36.05 179	31.97 208	6.33 220	26.59 210	27.33 215	11.12 219	50.08 210	41.05 215	44.23 215	45.15 212

MVS-HIRNet		42.24 195	41.15 208	43.51 174	44.06 197	40.74 209	35.77 213	35.35 181	35.38 201	38.34 122	25.63 211	38.55 201	43.48 132	50.77 206	47.03 209	64.07 180	49.98 205

PatchT		48.08 174	51.03 179	44.64 170	42.96 198	50.12 188	40.36 207	35.09 182	43.17 161	39.59 117	42.00 175	39.96 196	46.63 117	58.97 173	60.31 168	63.21 183	62.66 174

CVMVSNet		46.38 185	52.01 173	39.81 189	42.40 199	50.26 187	46.15 189	37.68 173	40.03 185	15.09 200	46.56 131	47.56 145	33.72 180	56.50 190	55.65 183	63.80 182	67.53 140

TinyColmap		47.08 180	47.56 194	46.52 160	42.35 200	53.44 176	51.77 168	40.70 149	43.44 160	31.92 146	29.78 204	23.72 220	45.04 126	61.99 161	59.54 172	67.35 170	61.03 181

ET-MVSNet_ETH3D		58.38 95	61.57 90	54.67 96	42.15 201	65.26 101	65.70 83	43.82 107	48.84 115	42.34 100	59.76 64	47.76 142	56.68 54	67.02 125	68.60 81	77.33 78	73.73 107

MIMVSNet		43.79 192	48.53 190	38.27 193	41.46 202	48.97 192	50.81 170	32.88 199	44.55 147	22.07 185	32.05 197	47.15 149	24.76 196	58.73 175	56.09 181	57.63 199	52.14 198

WB-MVS		29.70 212	35.40 213	23.05 212	40.96 203	39.59 214	18.79 221	40.20 156	25.26 214	1.88 227	33.33 195	21.97 222	3.36 221	48.69 213	44.60 213	33.11 219	34.39 215

N_pmnet		32.67 211	36.85 212	27.79 210	40.55 204	32.13 217	35.80 212	26.79 209	37.24 199	9.10 213	32.02 198	30.94 213	16.30 208	47.22 215	41.21 214	38.21 217	37.21 214

anonymousdsp		52.84 139	57.78 135	47.06 158	40.24 205	58.95 151	53.70 161	33.54 194	36.51 200	32.69 143	43.88 157	45.40 165	47.97 112	67.17 120	70.28 61	74.22 117	82.29 47

EU-MVSNet		40.63 200	45.65 199	34.78 203	39.11 206	46.94 200	40.02 208	34.03 189	33.50 204	10.37 209	35.57 190	37.80 203	23.65 198	51.90 203	50.21 204	61.49 190	63.62 172

FPMVS		38.36 205	40.41 209	35.97 199	38.92 207	39.85 212	45.50 193	25.79 212	41.13 177	18.70 194	30.10 202	24.56 218	31.86 183	49.42 211	46.80 210	55.04 201	51.03 201

TESTMET0.1,1		46.09 186	50.29 182	41.18 185	36.91 208	47.16 197	49.52 173	20.32 216	39.22 188	31.98 144	43.65 161	47.93 140	41.29 144	56.80 186	55.36 185	67.08 172	61.94 178

FMVSNet5		40.96 197	45.81 198	35.29 202	34.30 209	44.55 207	47.28 185	28.84 205	40.76 179	21.62 186	29.85 203	42.44 184	24.77 195	57.53 183	55.00 188	54.93 202	50.56 203

PMMVS		49.20 167	54.28 157	43.28 177	34.13 210	45.70 204	48.98 176	26.09 211	46.31 138	34.92 137	55.22 82	53.47 116	47.48 114	59.43 170	59.04 173	68.05 168	60.77 182

PMVS	27.84 18	33.81 209	35.28 214	32.09 205	34.13 210	24.81 220	32.51 216	26.48 210	26.41 213	19.37 193	23.76 212	24.02 219	25.18 194	50.78 205	47.24 208	54.89 204	49.95 206
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
test-mter		45.30 187	50.37 181	39.38 190	33.65 212	46.99 199	47.59 182	18.59 217	38.75 191	28.00 164	43.28 166	46.82 155	41.50 143	57.28 184	55.78 182	66.93 174	63.70 171

CHOSEN 280x420		40.80 198	45.05 201	35.84 201	32.95 213	29.57 218	44.98 196	23.71 214	37.54 198	18.42 195	31.36 200	47.07 150	46.41 119	56.71 188	54.65 192	48.55 213	58.47 191

PM-MVS		44.55 190	48.13 192	40.37 188	32.85 214	46.82 201	46.11 190	29.28 204	40.48 181	29.99 155	39.98 180	34.39 209	41.80 142	56.08 193	53.88 198	62.19 189	65.31 161

TDRefinement		49.31 163	52.44 169	45.67 165	30.44 215	59.42 146	59.24 120	39.78 159	48.76 118	31.20 149	35.73 189	29.90 214	42.81 138	64.24 152	62.59 158	70.55 158	66.43 150

Gipuma		25.87 213	26.91 216	24.66 211	28.98 216	20.17 221	20.46 219	34.62 187	29.55 211	9.10 213	4.91 224	5.31 228	15.76 209	49.37 212	49.10 206	39.03 216	29.95 217
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
MDA-MVSNet-bldmvs		41.36 196	43.15 206	39.27 191	28.74 217	52.68 179	44.95 197	40.84 147	32.89 205	18.13 196	31.61 199	22.09 221	38.97 153	50.45 208	56.11 180	64.01 181	56.23 195

E-PMN		15.09 216	13.19 220	17.30 214	27.80 218	12.62 224	7.81 225	27.54 207	14.62 222	3.19 222	6.89 221	2.52 231	15.09 210	15.93 220	20.22 219	22.38 220	19.53 220

MIMVSNet1		35.51 207	41.41 207	28.63 208	27.53 219	43.36 208	38.09 210	33.82 191	32.01 207	6.77 219	21.63 215	35.43 207	11.97 214	55.05 198	53.99 196	53.59 207	48.36 210

EMVS		14.49 217	12.45 221	16.87 216	27.02 220	12.56 225	8.13 224	27.19 208	15.05 221	3.14 223	6.69 222	2.67 230	15.08 211	14.60 222	18.05 220	20.67 221	17.56 222

pmmvs3		35.10 208	38.47 210	31.17 206	26.37 221	40.47 210	34.51 215	18.09 218	24.75 215	16.88 198	23.05 213	26.69 216	32.69 182	50.73 207	51.60 201	58.46 197	51.98 199

RPSCF		46.41 183	54.42 155	37.06 197	25.70 222	45.14 205	45.39 194	20.81 215	62.79 59	35.10 134	44.92 150	55.60 111	43.56 131	56.12 192	52.45 200	51.80 209	63.91 170

new_pmnet		23.19 214	28.17 215	17.37 213	17.03 223	24.92 219	19.66 220	16.16 220	27.05 212	4.42 221	20.77 216	19.20 223	12.19 213	37.71 216	36.38 216	34.77 218	31.17 216

PMMVS2		15.84 215	19.68 217	11.35 217	15.74 224	16.95 222	13.31 222	17.64 219	16.08 220	0.36 228	13.12 218	11.47 225	1.69 223	28.82 217	27.24 218	19.38 223	24.09 219

MVE	12.28 19	13.53 218	15.72 218	10.96 218	7.39 225	15.71 223	6.05 226	23.73 213	10.29 224	3.01 225	5.77 223	3.41 229	11.91 215	20.11 218	29.79 217	13.67 224	24.98 218
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
tmp_tt				5.40 220	3.97 226	2.35 228	3.26 228	0.44 223	17.56 219	12.09 204	11.48 220	7.14 226	1.98 222	15.68 221	15.49 221	10.69 225

test_method		12.44 219	14.66 219	9.85 219	1.30 227	3.32 227	13.00 223	3.21 221	22.42 217	10.22 210	14.13 217	25.64 217	11.43 217	19.75 219	11.61 222	19.96 222	5.79 223

GG-mvs-BLEND		36.62 206	53.39 162	17.06 215	0.01 228	58.61 153	48.63 177	0.01 224	47.13 132	0.02 229	43.98 156	60.64 87	0.03 224	54.92 199	51.47 202	53.64 206	56.99 193

uanet_test		0.00 222	0.00 224	0.00 221	0.00 229	0.00 229	0.00 231	0.00 225	0.00 227	0.00 230	0.00 227	0.00 232	0.00 227	0.00 225	0.00 225	0.00 227	0.00 226

sosnet-low-res		0.00 222	0.00 224	0.00 221	0.00 229	0.00 229	0.00 231	0.00 225	0.00 227	0.00 230	0.00 227	0.00 232	0.00 227	0.00 225	0.00 225	0.00 227	0.00 226

sosnet		0.00 222	0.00 224	0.00 221	0.00 229	0.00 229	0.00 231	0.00 225	0.00 227	0.00 230	0.00 227	0.00 232	0.00 227	0.00 225	0.00 225	0.00 227	0.00 226

testmvs		0.01 220	0.02 222	0.00 221	0.00 229	0.00 229	0.01 230	0.00 225	0.01 225	0.00 230	0.03 226	0.00 232	0.01 225	0.01 224	0.01 223	0.00 227	0.06 225

test123		0.01 220	0.02 222	0.00 221	0.00 229	0.00 229	0.00 231	0.00 225	0.01 225	0.00 230	0.04 225	0.00 232	0.01 225	0.00 225	0.01 223	0.00 227	0.07 224

RE-MVS-def										33.01 139

9.14												81.81 13

MTAPA										65.14 4		80.20 20

MTMP										62.63 16		78.04 26

Patchmatch-RL test							1.04 229

NP-MVS									72.00 40

Patchmtry						47.61 195	48.27 178	38.86 163		39.59 117

DeepMVS_CX						6.95 226	5.98 227	2.25 222	11.73 223	2.07 226	11.85 219	5.43 227	11.75 216	11.40 223		8.10 226	18.38 221

High-resolution multi-view benchmark