playground (low-res many-view)

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

Ground Truth (full)
Ground Truth (rig eval)
3Dnovator
3Dnovator - accuracy (80.89%)
3Dnovator - completeness (40.78%)
3Dnovator+
3Dnovator+ - accuracy (77.81%)
3Dnovator+ - completeness (42.55%)
A-TVSNet + Gipuma
A-TVSNet + Gipuma - accuracy (55.66%)
A-TVSNet + Gipuma - completeness (50.01%)
ACMH
ACMH - accuracy (66.11%)
ACMH - completeness (55.85%)
ACMH+
ACMH+ - accuracy (66.14%)
ACMH+ - completeness (60.23%)
ACMM
ACMM - accuracy (66.86%)
ACMM - completeness (60.58%)
ACMP
ACMP - accuracy (63.77%)
ACMP - completeness (61.58%)
BP-MVSNet
BP-MVSNet - accuracy (60.27%)
BP-MVSNet - completeness (41.09%)
CasMVSNet(base)
CasMVSNet(base) - accuracy (80.80%)
CasMVSNet(base) - completeness (24.20%)
CasMVSNet(SR_A)
CasMVSNet(SR_A) - accuracy (72.78%)
CasMVSNet(SR_A) - completeness (26.45%)
CasMVSNet(SR_B)
CasMVSNet(SR_B) - accuracy (72.78%)
CasMVSNet(SR_B) - completeness (26.45%)
CIDER
CIDER - accuracy (59.83%)
CIDER - completeness (42.26%)
CMPMVS
CMPMVS - accuracy (0.00%)
CMPMVS - completeness (0.00%)
COLMAP(base)
COLMAP(base) - accuracy (65.31%)
COLMAP(base) - completeness (60.04%)
COLMAP(SR)
COLMAP(SR) - accuracy (58.43%)
COLMAP(SR) - completeness (70.64%)
COLMAP_ROB
COLMAP_ROB - accuracy (82.45%)
COLMAP_ROB - completeness (34.10%)
DeepC-MVS
DeepC-MVS - accuracy (77.28%)
DeepC-MVS - completeness (58.50%)
DeepC-MVS_fast
DeepC-MVS_fast - accuracy (72.88%)
DeepC-MVS_fast - completeness (63.92%)
DeepPCF-MVS
DeepPCF-MVS - accuracy (69.44%)
DeepPCF-MVS - completeness (64.76%)
dnet
dnet - accuracy (0.00%)
dnet - completeness (0.00%)
DPSNet
DPSNet - accuracy (6.88%)
DPSNet - completeness (14.58%)
example
example - accuracy (14.17%)
example - completeness (17.85%)
GSE
GSE - accuracy (63.49%)
GSE - completeness (54.04%)
hgnet
hgnet - accuracy (6.88%)
hgnet - completeness (14.58%)
IB-MVS
IB-MVS - accuracy (68.03%)
IB-MVS - completeness (41.89%)
LPCS
LPCS - accuracy (68.83%)
LPCS - completeness (46.01%)
LTVRE_ROB
LTVRE_ROB - accuracy (80.16%)
LTVRE_ROB - completeness (47.61%)
MVE
MVE - accuracy (23.13%)
MVE - completeness (20.55%)
OpenMVS
OpenMVS - accuracy (76.73%)
OpenMVS - completeness (38.70%)
PCF-MVS
PCF-MVS - accuracy (62.44%)
PCF-MVS - completeness (66.49%)
PLC
PLC - accuracy (63.24%)
PLC - completeness (59.97%)
PMVS
PMVS - accuracy (50.77%)
PMVS - completeness (7.19%)
TAPA-MVS
TAPA-MVS - accuracy (64.86%)
TAPA-MVS - completeness (56.68%)
TAPA-MVS(SR)
TAPA-MVS(SR) - accuracy (73.02%)
TAPA-MVS(SR) - completeness (56.41%)
unsupervisedMVS_cas
unsupervisedMVS_cas - accuracy (47.49%)
unsupervisedMVS_cas - completeness (23.30%)

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