CVLGIVSep 24, 2019

Interactive Sketch & Fill: Multiclass Sketch-to-Image Translation

arXiv:1909.11081v2149 citations
Originality Incremental advance
AI Analysis

This work addresses the challenge of making image creation accessible to non-experts, though it is incremental in improving user interaction for sketch-based generation.

The authors tackled the problem of enabling novice users to create images of simple objects through an interactive sketch-to-image translation method, achieving a system that provides real-time feedback and plausible completions as users draw.

We propose an interactive GAN-based sketch-to-image translation method that helps novice users create images of simple objects. As the user starts to draw a sketch of a desired object type, the network interactively recommends plausible completions, and shows a corresponding synthesized image to the user. This enables a feedback loop, where the user can edit their sketch based on the network's recommendations, visualizing both the completed shape and final rendered image while they draw. In order to use a single trained model across a wide array of object classes, we introduce a gating-based approach for class conditioning, which allows us to generate distinct classes without feature mixing, from a single generator network. Video available at our website: https://arnabgho.github.io/iSketchNFill/.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes