A Deep Learning based VapourSynth filter for colorizing and restoring old images and video, based on the following projects: DeOldify , DDColor, Colorization, Deep Exemplar based Video Colorization, DeepRemaster, ColorMNet and CMNET2. The project Colorization includes 2 models: Real-Time User-Guided Image Colorization with Learned Deep Priors (Zhang, 2017) and Colorful Image Colorization (Zhang, 2016). These 2 models has been added as alternative models (named: siggraph17, eccv16) to DDColor.
The Vapoursynth filter version has the advantage of coloring the images directly in memory, without the need to use the filesystem to store the video frames.
For this filter is available a User Guide which provides useful tips and detailed explanations regarding the filter functions and usage. It is strongly recommended reading it before using the filter.
The filter (HAVC in short) can be considered the Swiss Army knife for coloring videos. It offers a wide range of options and coloring models and filters. It is able to combine the results provided by DeOldify and DDColor (Colorization), which are some of the best models available for coloring pictures, providing often a final colorized image that is better than the image obtained from the individual models. But the main strength of this filter is the addition of specialized filters to improve the quality of videos obtained by using these color models and the possibility to improve further the stability by using these models as input to Deep Exemplar based Video Colorization model (DeepEx in short), DeepRemaster, ColorMNet and the new CMNET2 model.
DeepEx, DeepRemaster, ColorMNet and CMNET2 are exemplar-based video colorization models, which allow to colorize a movie starting from one or more external-colored reference images. They allow to colorize a Video in sequence based on the colorization history, enforcing its coherency by using a temporal consistency loss.
The major addition of HAVC 5.8.0 is CMNET2, a new exemplar-based video colorization model developed as an evolution of ColorMNet. CMNET2 is now the default exemplar model in HAVC and provides significant improvements in color consistency and quality, especially on long videos with many reference frames. CMNET2 was developed by me as an extension of ColorMNet in order to reduce the main defects of ColorNet: faded and/or incorrect colors for frames distant from the main reference frame (solved by the perm_mem), temporal inconsistency of colors (solved by the sliding perm_mem window).
The key innovations of CMNET2 over ColorMNet are:
- Three-tier memory architecture (inspired by XMem++): a dedicated
perm_memstore keeps the reference frames permanently, never compressing or evicting them. This ensures that the colors of the reference frames are preserved with high fidelity throughout the entire video, removing one of the main limitations of the original ColorMNet (which stored only key points of reference frames, allowing colors to drift away from the reference). - Sliding window over permanent memory: long videos with hundreds or thousands of reference frames are handled by sliding the permanent-memory window forward as colorization progresses, keeping VRAM usage bounded without losing reference fidelity.
- Adaptive VRAM management: graduated response to memory pressure (slide 70% of permanent memory when VRAM is low, full reset only as a last resort), instead of the abrupt full memory reset of the original ColorMNet.
- Reference preloading: reference frames can be bulk-loaded into memory before colorization begins, decoupling the reference ingestion phase from the inference phase.
Compared to ColorMNet, the practical effect is more stable, consistent and faithful colors, especially in long videos: the colors stay close to the reference frames over hundreds of frames instead of slowly drifting away, and new reference frames can be added during the video without losing the previous ones.
The standalone CMNET2 project (and full technical documentation) is available at: github.com/dan64/cmnet2. The version integrated in HAVC 5.8.0 is exposed via the new public function HAVC_cmnet2() and is also used internally by HAVC_main() whenever the exemplar-based model is enabled.
NOTE for users coming from HAVC 5.6.7 or earlier: the function
HAVC_cmnet2()exists in earlier versions of HAVC, but in those versions it called the original ColorMNet model. Starting with HAVC 5.8.0,HAVC_cmnet2()calls the new CMNET2 model. Its parameter list has also changed (see the Exemplar-based Models section). Existing scripts based onHAVC_cmnet2()should be reviewed before upgrading.
To use the HAVC filter is necessary a GPU supporting CUDA, a NVIDIA RTX3060 is the minimum requirement to use this filter satisfactorily. The filter is distributed with the torch package provided with the Hybrid Windows Addons. To use it on Desktop (Windows) it is necessary install Hybrid and the related Addons. Hybrid is a Qt-based frontend for a lot video filters (including this one) which can convert most input formats to common audio & video formats and containers. Hybrid represents one of the most comprehensive solutions for implementing A.I. video filters and offers the most user-friendly approach to image colorization using the HAVC filter via VapourSynth. In the folder documentation is available a User Guide that provides detailed information on how to install Hybrid and use it to colorize videos. The Guide also provides tips on how to improve the final quality of colored movies.
- PyTorch 2.1.1 or later
- VapourSynth R62 or later
- MiscFilters.dll Vapoursynth's Miscellaneous Filters
pip install vsdeoldify-x.x.x-py3-none-any.whl
with the version 5.8.0 of HAVC has been released a modified version of DDColor to manage the Scene Detection properties available in the input clip, this version can be installed with the command:
pip install vsddcolor-1.0.2-py3-none-any.whl.zip
with the version 4.5.0 of HAVC has been introduced the support to ColorMNet. All the necessary packages to use ColorMNet (and CMNET2) are included in Hybrid's torch add-on package. For a manual installation not using Hybrid, it is necessary to install all the packages reported in the project page of ColorMNet. To simplify the installation, in the release 4.5.0 of this filter is available as asset the spatial_correlation_sampler package compiled against CUDA 12.4, python 3.12 and torch. To install it is necessary to unzip the following archive (using the nearest torch version available in the host system):
spatial_correlation_sampler-0.5.0-py312-cp312-win_amd64_torch-x.x.x.whl.zip
in the Library packages folder: .\Lib\site-packages\
The models are not installed with the package, they must be downloaded from the Deoldify website at: completed-generator-weights.
The models to download are:
- ColorizeVideo_gen.pth
- ColorizeStable_gen.pth
- ColorizeArtistic_gen.pth
The model files have to be copied in the models directory usually located in:
.\Lib\site-packages\vsdeoldify\models
To use ColorMNet and CMNET2 it is also necessary to download the file DINOv2FeatureV6_LocalAtten_s2_154000.pth and save it in
.\Lib\site-packages\vsdeoldify\colormnet\weights
A single copy is sufficient: CMNET2 automatically locates and reuses the same file, so there is no need to duplicate it in the colormnet2\weights directory.
With the version 5.0 of HAVC has been added the model DeepRemaster, for using it is necessary to download the file remasternet.pth.tar (is not a tar, just a "pth" renamed as "pth.tar") and copy it in: ".\Lib\site-packages\vsdeoldify\remaster\model".
At the first usage it is possible that are automatically downloaded by torch the neural networks: resnet101 and resnet34, and starting with the release 4.5.0: resnet50, resnet18, dinov2_vits14_pretrain and the folder facebookresearch_dinov2_main
So don't be worried if at the first usage the filter will be very slow to start, at the initialization are loaded almost all the Fastai and PyTorch modules and the resnet networks.
It is possible specify the destination directory of networks used by torch, by using the function parameter torch_hub_dir, if this parameter is set to None, the files will be downloaded in the torch's cache dir, more details are available at: caching-logic.
The models used by DDColor can be installed with the command
python -m vsddcolor
The models for Deep-Exemplar based Video Colorization. can be installed by downloading the file colorization_checkpoint.zip available in: inference code.
The archive colorization_checkpoint.zip have to be unziped in: .\Lib\site-packages\vsdeoldify\deepex
# loading plugins
core.std.LoadPlugin(path="MiscFilters.dll")
import vsdeoldify as havc
# changing range from limited to full range for HAVC
clip = core.resize.Bicubic(clip, range_in_s="limited", range_s="full")
# setting color range to PC (full) range.
clip = core.std.SetFrameProps(clip=clip, _ColorRange=0)
# adjusting color space from YUV420P16 to RGB24
clip = core.resize.Bicubic(clip=clip, format=vs.RGB24, matrix_in_s="709", range_s="full")
# DeOldify with DDColor, Preset = "fast"
clip = havc.HAVC_main(clip=clip, Preset="fast")
# DeOldify only model
clip = havc.HAVC_colorizer(clip, method=0)
# DDColor only model
clip = havc.HAVC_colorizer(clip, method=1)
# To apply video color stabilization filters to colored clip
clip = havc.HAVC_stabilizer(clip, dark=True, smooth=True, stab=True)
# Simplest way to use Presets
clip = havc.HAVC_main(clip=clip, Preset="fast", ColorFix="violet/red", ColorTune="medium", ColorMap="none")
# CMNET2 model (default exemplar model in 5.8.0) using HAVC as input for the reference frames
clip = havc.HAVC_main(clip=clip, EnableDeepEx=True, ScThreshold=0.1)
# changing range from full to limited range for HAVC
clip = core.resize.Bicubic(clip, range_in_s="full", range_s="limited")See __init__.py for the description of the parameters.
NOTES:
- In the DDColor version included with HAVC the parameter input_size has changed name in render_factor because were changed the range of values of this parameter to be equivalent to render_factor in DeOldify, the relationship between these 2 parameters is the following:
input_size = render_factor * 16
-
In the modified version of DDColor 1.0.1 was added the boolean parameter scenechange, if this parameter is set to True, will be colored only the frames tagged as scene change.
-
In the folder samples there are some clips and reference images that can be used to test the filter. The clips sample_colored_sync.mp4 and sample_colored_async.mp4 are useful to test the new video restore functionality added in HAVC 5.0 (described in the User Guide). The clip sample_colored_sync.mp4 is fully in sync with the clip sample_bw.mp4 and any of the exemplar-based models can be used to colorize it, while the clip sample_colored_async.mp4 is not in sync and only DeepRemaster is able to properly colorize the movie.
The filter was developed having in mind to use it mainly to colorize movies. Both DeOldify and DDcolor are good models for coloring pictures (see the Comparison of Models). But when are used for coloring movies they are introducing artifacts that usually are not noticeable in the images. Especially in dark scenes both DeOldify and DDcolor are not able to understand what it is the dark area and what color to give it, they often decide to color these dark areas with blue, then in the next frame this area could become red and then in the next frame return to blue, introducing a flashing psychedelic effect when all the frames are put in a movie. To try to solve this problem has been developed pre- and post- process filters. It is possible to see them in the Hybrid screenshot below.
The main filters introduced are:
Chroma Smoothing: This filter allows to reduce the vibrancy of colors assigned by DeOldify/DDcolor by using the parameters de-saturation and de-vibrancy (the effect on vibrancy will be visible only if the option chroma resize is enabled, otherwise this parameter has effect on the luminosity). The area impacted by the filter is defined by the thresholds dark/white. All the pixels with luma below the dark threshold will be impacted by the filter, while the pixels above the white threshold will be left untouched. All the pixels in the middle will be gradually impacted depending on the luma value.
Chroma Stabilization: This filter will try to stabilize the frames' colors. As explained previously since the frames are colored individually, the colors can change significantly from one frame to the next, introducing a disturbing psychedelic flashing effect. This filter try to reduce this by averaging the chroma component of the frames. The average is performed using a number of frames specified in the Frames parameter. Are implemented 2 averaging methods:
- Arithmetic average: the current frame is averaged using equal weights on the past and future frames
- Weighted average: the current frame is averaged using a weighed mean of the past and future frames, where the weight decrease with the time (far frames have lower weight respect to the nearest frames).
As explained previously the stabilization is performed by averaging the past/future frames. Since the non matched areas of past/future frames are gray because is missing in the past/future the color information, the filter will apply a color restore procedure that fills the gray areas with the pixels of current frames (eventually de-saturated with the parameter "sat"). The image restored in this way is blended with the non restored image using the parameter "weight". The gray areas are selected by the threshold parameter "tht". All the pixels in the HSV color space with "S" < "tht" will be considered gray. If is detected a scene change (controlled by the parameter "tht_scen"), the color restore is not applied.
DDColor Tweaks: This filter is available only for DDColor and has been added because has been observed that the DDcolor's inference is quite poor on dark/bright scenes depending on the luma value. This filter will force the luma of input image to don't be below the threshold defined by the parameter luma_min. Moreover this filter allows to apply a dynamic gamma correction. The gamma adjustment will be applied when the average luma is below the parameter gamma_luma_min. A gamma value > 2.0 improves the DDColor stability on bright scenes, while a gamma < 1 improves the DDColor stability on dark scenes.
B&W tune: Starting with HAVC version 5.5.0, a new post-processing filter called B&W Tune was introduced, which can automatically correct most color allocation errors. The color adjustment capability has been further improved with the version 5.6.0 where the Retinex filter and LUTs have been included to improve the overall output color quality. Unfortunately, forcing color stability has the side effect of producing washed-out colors with a slight pink cast (similar to skin tone). This new post-processing filter can automatically correct this problem and restore image colors to a more natural color. With the version 5.6.0, HAVC has evolved beyond basic colorization, it now delivers vivid, natural colors while ensuring consistent color stability throughout films.
Unfortunately when are applied to movies the color models are subject to assign unstable colors to the frames especially on the red/violet chroma range. This problem is more visible on DDColor than on DeOldify. To mitigate this issue was necessary to implement some kind of chroma adjustment. This adjustment allows to de-saturate all the colors included in a given color range. The color range must be specified in the HSV color space. This color space is useful because all the chroma is represented by only the parameter "Hue". In this color space the colors are specified in degree (from 0 to 360), as shown in the DDeoldify Hue Wheel. It is possible to apply this adjustment on all filters described previously. Depending on the filter the adjustment can be enabled using the following syntax:
chroma_range = "hue_start:hue_end" or "hue_wheel_name"
for example this assignment:
chroma_range = "290:330,rose"
specify the range of hue colors: 290-360, because "rose" is hue wheel name that correspond to the range:330-360.
It is possible to specify more ranges by using the comma "," separator.
When the de-saturation information is not already available in the filter's parameters, it necessary to use the following syntax:
chroma_adjustment = "chroma_range|sat,weight"
in this case it is necessary to specify also the de-saturation parameter "sat" and the blending parameter "weight".
for example with this assignment:
chroma_range = "300:340|0.4,0.2"
the hue colors in the range 300-340 will be de-saturated by the amount 0.4 and the final frame will be blended by applying a 20% de-saturation of 0.4 an all the pixels (if weight=0, no blending is applied).
To simplify the usage of this filter has been added the Preset ColorFix which allows to fix a given range of chroma combination. The strength of the filter is controlled by the the Preset ColorTune.
Using an approach similar to Chroma Adjustment has been introduced the possibility to remap a given gange of colors in another chroma range. This remapping is controlled by the Preset ColorMap. For example the preset "blue->brown" allows to remap all the chroma combinations of blue in the color brown. It is not expected that this filter can be applied on a full movie, but it could be useful to remap the color on some portion of a movie.
In the HAVC User Guide are provided useful tips on how to use both the Chroma Adjustment and Color Mapping features provided by this filter.
As explained previously, this filter is able to combine the results provided by DeOldify and DDColor, to perform this combination has been implemented 8 methods:
-
DeOldify only coloring model.
-
DDColor only color model.
-
Simple Merge: the frames are combined using a weighted merge, where the parameter merge_weight represent the weight assigned to the frames provided by the DDcolor model.
-
Constrained Chroma Merge: given that the colors provided by DeOldify's Video model are more conservative and stable than the colors obtained with DDcolor. The frames are combined by assigning a limit to the amount of difference in chroma values between DeOldify and DDcolor. This limit is defined by the parameter threshold. The limit is applied to the frame converted to "YUV". For example when threshold=0.1, the chroma values "U","V" of DDcolor frame will be constrained to have an absolute percentage difference respect to "U","V" provided by DeOldify not higher than 10%. If merge_weight is < 1.0, the chroma limited DDColor frames will be will be merged again with the frames of DeOldify using the Simple Merge.
- Luma Masked Merge: the behaviour is similar to the method Adaptive Luma Merge. With this method the frames are combined using a masked merge. The pixels of DDColor's frame with luma < luma_limit will be filled with the (de-saturated) pixels of DeOldify, while the pixels above the white_limit threshold will be left untouched. All the pixels in the middle will be gradually replaced depending on the luma value. If the parameter merge_weight is < 1.0, the resulting masked frames will be merged again with the non de-saturated frames of DeOldify using the Simple Merge.
-
Adaptive Luma Merge: given that the DDcolor performance is quite bad on dark scenes, with this method the images are combined by decreasing the weight assigned to DDcolor frames when the luma is below the luma_threshold. For example with: luma_threshold = 0.6 and alpha = 1, the weight assigned to DDcolor frames will start to decrease linearly when the luma < 60% till min_weight. For alpha=2, the weight begins to decrease quadratically.
-
Chroma Retention Merge: Given that the colors provided by deoldify() are more conservative and stable than the colors obtained with ddcolor(). This function try to restore the colors of gray pixels provide by deoldify() by using the colors provided by ddcolor(). The gray pixels are identified by the parameter "tht". Once are identified the gray pixels are substituted with the desaturated colors in deoldify(), the level of desaturation is identified by the parameter "sat". It is performed a "gradient" substitution, i.e. the gray pixels are gradually substituted depending on the level of gray gradient. The steepness of gradient curve is controlled by the parameter "alpha". Optionally is possible to resize the frame before the filter application to speed up the filter by setting True the parameter ?chroma_resize?.
-
ChromaBound Adaptive: Adaptive version of Constrained-Chroma. In this version the chroma tolerance is adaptive, i.e., it is applied an approach that will allow more color variation in textured/complex regions and less in smooth areas. The texture strength is computed via Laplacian and chroma tolerance is controlled by the following parameters:
- base_tol: int = 20, Base chroma tolerance (smooth areas)
- max_extra: int = 24, Extra tolerance for textured areas
The merging methods 2-7 are leveraging on the fact that usually the DeOldify Video model provides frames which are more stable, this feature is exploited to stabilize also DDColor. The methods 3, 4 and 7 are similar to Simple Merge, but before the merge with DeOldify the DDColor frame is limited in the chroma changes (method 3) or limited based on the luma (method 4). The method 5 is a Simple Merge where the weight decrease with luma and the method 7 is an hybrid model that combines the approach of methods 4 and 5.
Taking inspiration from the article published on Habr: Mode on: Comparing the two best colorization AI's. It was decided to use it to get the refence images and the images obtained using the ColTran model, to extend the analysis with the models implemented in the HAVC filter.
The added models are:
D+D: DeOldify (with model Video & render_factor = 24) + DDColor (with model Artistic and render_factor = 24)
DD: DDColor (with model Artistic and and render_factor = 24 equivalent to input_size = 384)
DS: DeOldify (with model Stable & render_factor =24)
DV: DeOldify (with model Video & render_factor = 24)
T241: ColTran + TensorFlow 2.4.1 model as shown in Habr
The models were compared by measuring the perceptual color distance (dE) of each colorized image from a ground-truth reference using the CIEDE2000 method, which takes into account the non-uniformities of human color perception.
The combined model D+D (DeOldify + DDColor) was the best overall performer, winning 10 out of 23 tests in the first set and confirming that DeOldify and DDColor are able to compensate each other's weaknesses. The DD model (DDColor alone) was the second best, but with occasional poor outputs that the merge with DeOldify is able to correct. T241 (ColTran) was the worst performer.
In a second test set focused on combinations of DeOldify Artistic and Stable with different DDColor variants, all the combined models performed similarly well, confirming the positive impact of merging the two model families regardless of the specific variants used.
The full per-image CIEDE2000 results, the comparison methodology and the detailed analysis of both test sets are available in documentation/MODEL_COMPARISON.md.
As stated previously to stabilize further the colorized videos it is possible to use the frames colored by HAVC as reference frames (exemplar) as input to the supported exemplar-based models: CMNET2, ColorMNet, Deep Exemplar based Video Colorization and DeepRemaster.
In Hybrid the Exemplar Models have their own panel, as shown in the following picture:
The available exemplar models are selected via the field Model with the following values:
- 0 : CMNET2 (default) — new in 5.8.0, recommended
- 1 : Deep-Exemplar
- 2 : DeepRemaster
- 3 : ColorMNet (original)
For CMNET2 and ColorMNet there are 2 implementations defined, by the field Mode:
- 'remote' (has not memory frames limitation but it uses a remote process for the inference)
- 'local' (the inference is performed inside the Vapoursynth local thread but has memory limitation)
The field Preset controls the render method and speed, allowed values are:
- 'Auto' (default — automatically assigns the optimal render size)
- 'Fast' (faster but colors are more washed out)
- 'Medium' (colors are a little washed out)
- 'Slow' (slower but colors are a little more vivid)
- 'Slower' (colors are more accurate, usually very slow)
The 'Auto' and 'Slower' presets are new in 5.8.0.
The field SC thresh define the sensitivity for the scene detection (suggested value 0.1, see Miscellaneous Filters), while the field SC min freq allows to specify the minimum number of reference frames that have to be generated.
The flag Vivid has different meanings depending on the Exemplar Model used:
- CMNET2: the saturation will be increased by about 15%.
- Deep-Exemplar: the saturation will be increased by about 25%.
- DeepRemaster: the saturation will be increased by about 20% and Hue by +10.
- ColorMNet: the frames memory is reset at every reference frame update.
The field Method allows to specify the type of reference frames (RF) provided in input to the Exemplar-based Models, allowed values are:
- 0 = HAVC same as video (default)
- 1 = HAVC + RF same as video
- 2 = HAVC + RF different from video
- 3 = external RF same as video
- 4 = external RF different from video
- 5 = external ClipRef same as video
- 6 = external ClipRef different from video
It is possible to specify the directory containing the external reference frames by using the field Ref FrameDir. The frames must be named using the following format: ref_nnnnnn.[png|jpg]. For the methods 5 and 6 it is possible to pass a video clip as source for reference images.
Unfortunately the exemplar-based methods other than CMNET2 have the problem that they are unable to properly colorize the new "features" (new elements not available in the reference frame) so that often these new elements are colored with implausible colors (see for an example: New "features" are not properly colored). To try to fix this problem has been introduced the possibility to merge the frames propagated by the exemplar model with the frames colored with DDColor and/or DeOldify. The merge is controlled by the field Ref merge, allowed values are:
- 0 = no merge
- 1 = reference frames are merged with low weight
- 2 = reference frames are merged with medium weight
- 3 = reference frames are merged with high weight
When the field Ref merge is set to a value greater than 0, the field SC min freq is set =1, to allows the merge for every frame (more details are provided in HAVC User Guide). Note that Ref merge is intended for the exemplar models that suffer from the "new features" problem; with CMNET2 it is not disabled but is not useful, so the recommended value is 0.
Finally the flag Reference frames only can be used to export the reference frames generated with the method HAVC and defined by the parameters SC thresh, SC min freq fields.
When CMNET2 is used as exemplar model, the parameter DeepExMaxMemFrames controls the size of the sliding permanent-memory window: it defines how many reference frames are held in the model's permanent memory at any given time. As colorization progresses, the window slides forward automatically, evicting the oldest references and loading new ones. This allows CMNET2 to handle long videos with hundreds of reference frames while keeping VRAM usage bounded.
Suggested values for CMNET2:
- min = 10, max = 500
- if = 0 (default), the window size is automatically set to 50
For ColorMNet and DeepRemaster, DeepExMaxMemFrames keeps its previous meaning (max number of encoded frames / max number of reference frames in memory). Note that the suggested ranges have been revised in 5.8.0; please refer to the docstring of HAVC_main() and to the User Guide for the up-to-date values.
As stated previously the simplest way to colorize images with the HAVC filter it to use Hybrid. To simplify the usage has been introduced standard Presets that automatically apply all the filter's settings. A set of parameters that are able to provide a satisfactory colorization are the following:
- Speed: slower
- Color map: red->brown
- Color tweaks: retinex/red
- Denoise: medium
- Stabilize: balanced
- B&W tune: light
- B&W mode: CLAHE (luma)
- Interpolation: 3
then enable the Exemplar Models check box and set
- Method: HAVC
- Model: CMNET2
- SC thresh: 0.10
- SC SSIM thresh: 0.0
- SC min freq: 0
- normalize: checked
- Mode: remote
- Frames: 0
- Preset: Auto
- Vivid: checked
- Ref merge: high
In the following picture are shown the suggested parameters:
The suggested settings are appropriate for a medium powered GPU (RTX4070 or above). In the HAVC User Guide are provided more settings depending on the available hardware.
In Summary HAVC is able to provide often a final colorized image that is better than the image obtained from the individual models, and can be considered an improvement respect to the current Models. With the introduction of CMNET2 in version 5.8.0, the temporal consistency and color fidelity over long videos have been further improved, making HAVC an even more solid choice for video colorization. It is highly recommended to read the HAVC User Guide which provides useful tips on how to improve the colored movies.
As a final consideration I would like to point out that the test results showed that the images coloring technology is mature enough to be used concretely both for coloring images and, thanks to Hybrid, videos.
I would like to thank Selur, author of Hybrid, for his wise advices and for having developed a gorgeous interface for this filter. Despite the large number of parameters and the complexity of managing them appropriately, the interface developed by Selur makes its use easy even for non-experts users.
