• Corpus ID: 47889035

Flow-Centric Painterly Rendering

  title={Flow-Centric Painterly Rendering},
  author={Omar Hesham and David Mould},
We present a painterly rendering technique that emphasizes smooth line flows to describe important shapes in the image, as well as contributing in an essential part to the final stylistic artwork. Our method uses the smoothed edge tangent flow (ETF) [20] for stroke pathing, and provides an artist-friendly way to control the general look and feel of the image using familiar brush stroke properties and colour theme palettes. We achieve a highly stylized expressionistic look that can be applied to… 



Flow-Based Image Abstraction

A non-photorealistic rendering technique that automatically delivers a stylized abstraction of a photograph based on shape/color filtering guided by a vector field that describes the flow of salient features in the image.

Coherent line drawing

A novel method for constructing a smooth direction field that preserves the flow of the salient image features and the notion of flow-guided anisotropic filtering for detecting highly coherent lines while suppressing noise is introduced.

Shape‐simplifying Image Abstraction

Experimental results show that the proposed algorithm effectively produces highly abstract yet feature‐preserving illustrations from photographs, which outperforms the original mean curvature flow in conveying the directionality of features and shape boundaries.

Paint by numbers: abstract image representations

Computer graphics research has concentrated on creating photo-realistic images of synthetic objects. These images communicate surface shading and curvature, as well as the depth relationships of

Painterly rendering for animation

This work extends the still frame method to animation by solving two major specific problems of previous techniques, eliminating the “shower door” effect and providing for frame-to-frame coherence in animations so that the resulting frames do not randomly change every frame.

Interactive vector fields for painterly rendering

The aim is to enable casual users to create results evocative of expressionistic art by combining vortex dynamics and semi-Lagrangian fluid simulation to create stable, easily controlled vector fields.

Processing images and video for an impressionist effect

This method is the first to exploit temporal coherence in video clips to design an automatic filter with a hand-drawn animation quality, in this case, one that produces an Impressionist effect.

Painterly rendering with curved brush strokes of multiple sizes

This work presents a new method for creating an image with a handpainted appearance from a photograph, and a new approach to designing styles of illustration, and presents a framework for describing a wide range of visual styles.

Image and video based painterly animation

This work presents techniques for transforming images and videos into painterly animations depicting different artistic styles using image and video analysis and methods for modifying the properties of these brush strokes according to the input images, videos, or motions.

Video Painting Based on a Stabilized Time-Varying Flow Field

The method extracts smoothly aligned 3D vectors that describe the smallest variation of colors within a spatiotemporal video cube, and thus effectively preserves both spatial and temporal coherence in a relatively inexpensive manner.