Differentiable rasterizer for vector font generation and editing
AssigneeAdobe Inc.
InventorsZhaowen Wang, Zhifei Zhang, Xuan Li, Matthew Fisher, Hailin Jin
Life of this patent
Estimating the term…
Abstract
Systems and methods provide for generating glyph initiations using a generative font system. A glyph variant may be generated based on an input vector glyph. A plurality of line segments may be approximated using a differentiable rasterizer with the plurality of line segments representing the contours of the glyph variant. A bitmap of the glyph variant may then be generated based on the line segments. The image loss between the bitmap and a rasterized representation of a vector glyph may be calculated and provided to the generative font system. Based on the image loss, a refined glyph variant may be provided to a user.
Claims20
A method comprising:
- receiving an image representative of a vector glyph;
- generating, using a generative neural network, a glyph variant based on the vector glyph;
- providing the glyph variant to a differentiable rasterizer;
- approximating, using the differentiable rasterizer, a plurality of line segments for the glyph variant, wherein the plurality of line segments are representative of contours of the glyph variant;
- generating a bitmap of the glyph variant based on the plurality of line segments;
- calculating an image loss of the glyph variant based on a comparison of the bitmap of the glyph variant to a rasterized representation of the vector glyph;
- providing the image loss to the generative neural network;
- and
- generating a refined glyph variant using the generative neural network based on the provided image loss.
One or more non-transitory computer storage media storing computer-useable instructions that, when executed by a computing device, cause the computing device to perform operations comprising:
- receiving an image representative of a vector glyph;
- generating, using a generative neural network, a glyph variant based on the vector glyph;
- providing the glyph variant to a differentiable rasterizer comprising a polyline sampler and a contour renderer;
- approximating, using the polyline sampler, a plurality of line segments for the glyph variant, wherein the plurality of line segments are representative of contours of the glyph variant;
- generating, using the contour renderer, a bitmap of the glyph variant based on the plurality of line segments;
- calculating an image loss of the glyph variant based on a comparison of the bitmap of the glyph variant to a rasterized representation of the vector glyph;
- providing the image loss to the neural network;
- and
- generating a refined glyph variant using the generative neural network based on the provided image loss.
A computer system comprising:
- one or more hardware processors and memory configured to provide computer program instructions to the one or more hardware processors;
- a generative font system configured to use the one or more hardware processors, the generative font system comprising:
- means for generating, using a generative neural network, a glyph variant based on a vector glyph;
- means for generating a differentiable bitmap of the glyph variant based on contours of the glyph variant;
- means for calculating an image loss of the glyph variant based on a comparison of the bitmap of the glyph variant to a rasterized representation of the vector glyph;
- means for providing the image loss to the neural network;
- and
- means for generating a refined glyph variant using the generative neural network based on the provided image loss.
Dependencies are inferred from the claim text.