sketchkit.vectorization package

Subpackages

• sketchkit.vectorization.DeepVecSIG24 package
  • Submodules
  • sketchkit.vectorization.DeepVecSIG24.DeepVecSIG24 module
    • DeepVecSIG24
      • DeepVecSIG24.device
      • DeepVecSIG24._D()
      • DeepVecSIG24._download_models()
      • DeepVecSIG24._load_checkpoint_ndc()
      • DeepVecSIG24._load_checkpoint_udf()
      • DeepVecSIG24._load_img()
      • DeepVecSIG24._load_model()
      • DeepVecSIG24._paths_to_Sketch()
      • DeepVecSIG24._pre_svg()
      • DeepVecSIG24._pre_udf()
      • DeepVecSIG24._predict_SVG()
      • DeepVecSIG24._predict_UDF()
      • DeepVecSIG24._simplify_SVG()
      • DeepVecSIG24._vis_stroke()
      • DeepVecSIG24.run()
    • safe_torch_load()
  • Module contents
    • DeepVecSIG24
      • DeepVecSIG24.device
      • DeepVecSIG24._D()
      • DeepVecSIG24._download_models()
      • DeepVecSIG24._load_checkpoint_ndc()
      • DeepVecSIG24._load_checkpoint_udf()
      • DeepVecSIG24._load_img()
      • DeepVecSIG24._load_model()
      • DeepVecSIG24._paths_to_Sketch()
      • DeepVecSIG24._pre_svg()
      • DeepVecSIG24._pre_udf()
      • DeepVecSIG24._predict_SVG()
      • DeepVecSIG24._predict_UDF()
      • DeepVecSIG24._simplify_SVG()
      • DeepVecSIG24._vis_stroke()
      • DeepVecSIG24.run()
• sketchkit.vectorization.LineDrawer package
  • Subpackages
    • sketchkit.vectorization.LineDrawer.CNNVE package
      • Subpackages
      • Submodules
      • sketchkit.vectorization.LineDrawer.CNNVE.CNNVE module
      • Module contents
  • Submodules
  • sketchkit.vectorization.LineDrawer.Line_Drawer module
    • LineDrawer
      • LineDrawer._convert_to_sketch()
      • LineDrawer.run()
  • Module contents
    • LineDrawer
      • LineDrawer._convert_to_sketch()
      • LineDrawer.run()

Submodules

sketchkit.vectorization.vectorizer module

class sketchkit.vectorization.vectorizer.Vectorizer(method: str = 'DeepVecSIG24', device: str = 'cuda')

Bases: object

A class for image vectorization.

This class provides functionality to convert a raster image to a vector image.

method

The vectorization method that is used.

Type:

str

device

The device that is used.

Type:

str

run(input: ndarray) → Sketch

Vectorize the input raster image.

Parameters:

input (numpy.ndarray) – input raster image in shape (H, W), with values in [0, 255].

Returns:

a Sketch instance.

Return type:

sketch (Sketch)

Module contents

class sketchkit.vectorization.DeepVecSIG24(device: str = 'cuda')

Bases: object

A class for image vectorization using the method of paper “Deep Sketch Vectorization via Implicit Surface Extraction” in SIGGRAPH 2024.

device

The device that is used.

Type:

str

_D(t)

_download_models()

Download the pretrained models

_load_checkpoint_ndc(filepath)

Loads model from a checkpoint we will need the distance threshold to accruately recover the UDF for the next NDC model

_load_checkpoint_udf(filepath)

Loads model from a checkpoint we will need the distance threshold to accruately recover the UDF for the next NDC model

_load_img(img_np, device, resize=False, resize_to=1024)

_load_model(device)

_paths_to_Sketch(paths)

_pre_svg(net, udf, gsize)

_pre_udf(net, img)

_predict_SVG(udf_topo_pre, model_ndc, args_udf, args_ndc, refine=True)

_predict_UDF(img, img_np, model_udf, usm_thr=0.5)

_simplify_SVG(path_to_svg, keypt_pre_dict, rdp_simplify=False, epsilon=0.4, skip_len=4)

_vis_stroke(strokes, canvas_size, save_path)

run(image_array: ndarray, image_folder: str = './', out_folder: str = 'svg') → Sketch

Vectorize the input raster image.

Parameters:

• image_array (numpy.ndarray) – input raster image in shape (H, W), with values in [0, 255].

• image_folder (str, optional) – the folder of the input raster image.

• out_folder (str, optional) – an output folder to store the output svg file.

Returns:

a Sketch instance.

Return type:

sketch (Sketch)

class sketchkit.vectorization.LineDrawer(method: str = 'CNNVE', device: str = 'cuda')

Bases: object

Native LineDrawer integration that mirrors the structure of other vectorizers.

_convert_to_sketch(merge_dic: dict, height: int, width: int) → Sketch

Convert the CNNVE output dictionary to a Sketch object.

run(img: ndarray) → Sketch

Vectorize the provided numpy image.

Parameters:

img (np.ndarray) – Input image as a 2D numpy array (grayscale).

Returns:

The vectorized sketch.

Return type:

Sketch

class sketchkit.vectorization.Vectorizer(method: str = 'DeepVecSIG24', device: str = 'cuda')

Bases: object

A class for image vectorization.

This class provides functionality to convert a raster image to a vector image.

method

The vectorization method that is used.

Type:

str

device

The device that is used.

Type:

str

run(input: ndarray) → Sketch

Vectorize the input raster image.

Parameters:

input (numpy.ndarray) – input raster image in shape (H, W), with values in [0, 255].

Returns:

a Sketch instance.

Return type:

sketch (Sketch)