SketchINR: A First Look into Sketches as Implicit Neural Representations

TL;DR

SketchINR introduces an implicit neural model for vector sketches that achieves high compression, fidelity, and speed, enabling scalable and human-like sketch reproduction.

Contribution

It is the first to model sketches as implicit neural functions, providing a compact, high-fidelity, and scalable representation that outperforms existing methods.

Findings

Achieves 60x data compression over raster sketches

Supports rendering 100x faster than previous learned vector models

Emulates human sketch reproduction with varying abstraction levels

Abstract

We propose SketchINR, to advance the representation of vector sketches with implicit neural models. A variable length vector sketch is compressed into a latent space of fixed dimension that implicitly encodes the underlying shape as a function of time and strokes. The learned function predicts the $xy$ point coordinates in a sketch at each time and stroke. Despite its simplicity, SketchINR outperforms existing representations at multiple tasks: (i) Encoding an entire sketch dataset into a fixed size latent vector, SketchINR gives $60\times$ and $10\times$ data compression over raster and vector sketches, respectively. (ii) SketchINR's auto-decoder provides a much higher-fidelity representation than other learned vector sketch representations, and is uniquely able to scale to complex vector sketches such as FS-COCO. (iii) SketchINR supports parallelisation that can decode/render $\sim$$100\times$ faster than other learned vector representations such as SketchRNN. (iv) SketchINR, for the first time, emulates the human ability to reproduce a sketch with varying abstraction in terms of number and complexity of strokes. As a first look at implicit sketches, SketchINR's compact high-fidelity representation will support future work in modelling long and complex sketches.