electro (low-res many-view)

electro (low-res many-view) - Tolerance 5cm

Ground Truth (full)
Ground Truth (rig eval)
3Dnovator
3Dnovator - accuracy (91.15%)
3Dnovator - completeness (64.91%)
3Dnovator+
3Dnovator+ - accuracy (89.56%)
3Dnovator+ - completeness (65.67%)
A-TVSNet + Gipuma
A-TVSNet + Gipuma - accuracy (68.78%)
A-TVSNet + Gipuma - completeness (67.86%)
ACMH
ACMH - accuracy (75.63%)
ACMH - completeness (68.46%)
ACMH+
ACMH+ - accuracy (77.67%)
ACMH+ - completeness (73.36%)
ACMM
ACMM - accuracy (83.04%)
ACMM - completeness (72.53%)
ACMP
ACMP - accuracy (77.96%)
ACMP - completeness (75.34%)
BP-MVSNet
BP-MVSNet - accuracy (68.36%)
BP-MVSNet - completeness (72.63%)
CasMVSNet(base)
CasMVSNet(base) - accuracy (84.35%)
CasMVSNet(base) - completeness (54.66%)
CasMVSNet(SR_A)
CasMVSNet(SR_A) - accuracy (83.69%)
CasMVSNet(SR_A) - completeness (27.33%)
CasMVSNet(SR_B)
CasMVSNet(SR_B) - accuracy (83.69%)
CasMVSNet(SR_B) - completeness (57.58%)
CIDER
CIDER - accuracy (69.05%)
CIDER - completeness (64.08%)
CMPMVS
CMPMVS - accuracy (0.00%)
CMPMVS - completeness (0.00%)
COLMAP(base)
COLMAP(base) - accuracy (77.81%)
COLMAP(base) - completeness (68.30%)
COLMAP(SR)
COLMAP(SR) - accuracy (73.67%)
COLMAP(SR) - completeness (72.54%)
COLMAP_ROB
COLMAP_ROB - accuracy (88.13%)
COLMAP_ROB - completeness (58.44%)
DeepC-MVS
DeepC-MVS - accuracy (84.49%)
DeepC-MVS - completeness (74.89%)
DeepC-MVS_fast
DeepC-MVS_fast - accuracy (86.15%)
DeepC-MVS_fast - completeness (74.06%)
DeepPCF-MVS
DeepPCF-MVS - accuracy (84.10%)
DeepPCF-MVS - completeness (77.01%)
dnet
dnet - accuracy (0.00%)
dnet - completeness (0.00%)
DPSNet
DPSNet - accuracy (18.34%)
DPSNet - completeness (14.06%)
example
example - accuracy (12.09%)
example - completeness (14.08%)
GSE
GSE - accuracy (79.08%)
GSE - completeness (68.47%)
hgnet
hgnet - accuracy (18.34%)
hgnet - completeness (14.06%)
IB-MVS
IB-MVS - accuracy (82.10%)
IB-MVS - completeness (72.44%)
LPCS
LPCS - accuracy (83.89%)
LPCS - completeness (58.18%)
LTVRE_ROB
LTVRE_ROB - accuracy (87.74%)
LTVRE_ROB - completeness (57.68%)
MVE
MVE - accuracy (25.73%)
MVE - completeness (28.76%)
OpenMVS
OpenMVS - accuracy (87.60%)
OpenMVS - completeness (63.31%)
PCF-MVS
PCF-MVS - accuracy (72.45%)
PCF-MVS - completeness (75.68%)
PLC
PLC - accuracy (75.04%)
PLC - completeness (70.68%)
PMVS
PMVS - accuracy (51.35%)
PMVS - completeness (21.30%)
TAPA-MVS
TAPA-MVS - accuracy (88.26%)
TAPA-MVS - completeness (66.60%)
TAPA-MVS(SR)
TAPA-MVS(SR) - accuracy (81.86%)
TAPA-MVS(SR) - completeness (69.51%)
unsupervisedMVS_cas
unsupervisedMVS_cas - accuracy (42.31%)
unsupervisedMVS_cas - completeness (44.79%)

Attributes:
RGB

Attribute Weights

RGB:

Intensity:

Elevation:

Classification:

Return Number:

Source ID:

RGB

Gamma: 1.00

Brightness: 0.00

Contrast: 0.00

Elevation

: 0.00 to 1.00

Transition

transition:

Intensity

Range: 0 to 300

Gamma: 1.00

Brightness: 0.00

Contrast: 0.00

:1,000,000
:1.00
:60
:1.00
Point Sizing Adaptive
Squares

Eye-Dome-Lighting

:1.4

:1.0

Background

Gradient

Black

White

Navigation

: 0.4

Potree is a viewer for large point cloud / LIDAR data sets, developed at the Vienna University of Technology. (github)
Author: Markus Schütz
License: FreeBSD (2-clause BSD)

Libraries:
- three.js
- Jquery
- laszip
- Plas.io (laslaz)
- OpenLayers3
- proj4js
- tween
- i18next
Donators:
- rapidlasso
- georepublic
- sitn
- Veesus
- sigeom sa
Credits:

loading 1 / 10

Fixed
Attenuated
Adaptive

Squares
Circles
Interpolation

RGB
RGB and Elevation
Elevation
Level of Detail