A Sketch-Based Image Retrieval (SBIR) algorithm compares a linedrawing sketch with images. The comparison is made difficult by image background clutter. A query sketch includes an object of interest only, while database images would also contain background clutters. In addition, variability of hand-drawn sketches, due to “stroke noise” such as disconnected and/or wobbly lines, also makes the co...

Sketch-and-extrude is a common and intuitive modeling process in computer aided design. This paper studies the problem of learning shape given form point clouds by “inverse” sketch-and-extrude. We present ExtrudeNet, an unsupervised end-to-end network for discovering sketch extrude from clouds. Behind ExtrudeNet are two new technical components: 1) effective representation extrude, which can mo...

Current feature-based methods for sketch recognition systems rely on human-selected features. Certain machine learning techniques have been found to be good nonlinear features extractors. In this paper, we apply a manifold learning method, kernel Isomap, with a new algorithm for multi-stroke sketch recognition, which significantly outperforms the standard featurebased techniques. INTRODUCTION S...

A technique for the classification and ‘understanding’ of ‘child-like’ sketches is explained. Using a live pen-based input device, sketches of animals are classified using our system: SIVA (Sketch Understanding Via Agents). We separate the task into three sub-problems: Sketch segmentation, segment matching and a contextual conflict-resolution system. A successful sketch segmentation method invo...

With the increased complexity in state of the art models created using common digital content creation applications, such as AutoCAD, Maya or XSI, the need to have more than one person work on a single model is common. Ideally people would work on the same model at the same time, from several workstations possibly at distant locations. Using a mesh based modelling approach requires synchronizin...

Humans show high-level of abstraction capabilities in games that require quickly communicating object information. They decompose the message content into multiple parts and communicate them an interpretable protocol. Toward equipping machines with such capabilities, we propose Primitive-based Sketch Abstraction task where goal is to represent sketches using a fixed set drawing primitives under...

The problem of matching a forensic sketch to a gallery of mugshot images is addressed in this paper. Previous research in sketch matching offered solutions to matching highly accurate sketches that were drawn while looking at the subject. We refer to these as viewed sketches. Forensic sketches differ from viewed sketches in that they are drawn by a police sketch artist using the description pro...

We explore the possibility of deeper linguistic research based on corpus and computational linguistic tools in this paper. In particular, we adopt Chinese Word Sketch, the application of Word Sketch Engine to Chinese GigaWord Corpus, for linguistic research. We apply Chinese Sketch Engine results to deeper linguistic account such as selectional restriction and event type selection. The study is...