Universal Perceptual Grouping

TL;DR

This paper introduces a universal sketch grouping model capable of segmenting sketches across diverse categories, supported by a large annotated dataset and novel training losses, outperforming existing methods and aiding sketch analysis tasks.

Contribution

The paper presents the largest sketch grouping dataset and a novel deep model with generative and discriminative losses for universal sketch grouping.

Findings

Model outperforms state-of-the-art groupers.

Effective in sketch synthesis and retrieval tasks.

Generalizes well to unseen categories.

Abstract

In this work we aim to develop a universal sketch grouper. That is, a grouper that can be applied to sketches of any category in any domain to group constituent strokes/segments into semantically meaningful object parts. The first obstacle to this goal is the lack of large-scale datasets with grouping annotation. To overcome this, we contribute the largest sketch perceptual grouping (SPG) dataset to date, consisting of 20,000 unique sketches evenly distributed over 25 object categories. Furthermore, we propose a novel deep universal perceptual grouping model. The model is learned with both generative and discriminative losses. The generative losses improve the generalisation ability of the model to unseen object categories and datasets. The discriminative losses include a local grouping loss and a novel global grouping loss to enforce global grouping consistency. We show that the proposed model significantly outperforms the state-of-the-art groupers. Further, we show that our grouper is useful for a number of sketch analysis tasks including sketch synthesis and fine-grained sketch-based image retrieval (FG-SBIR).