CustomCut: On‐demand Extraction of Customized 3D Parts with 2D Sketches

Abstract

Several applications in shape modeling and exploration require identification and extraction of a 3D shape part matching a 2D sketch. We present CustomCut, an on‐demand part extraction algorithm. Given a sketched query, CustomCut automatically retrieves partially matching shapes from a database, identifies the region optimally matching the query in each shape, and extracts this region to produce a customized part that can be used in various modeling applications. In contrast to earlier work on sketch‐based retrieval of predefined parts, our approach can extract arbitrary parts from input shapes and does not rely on a prior segmentation into semantic components. The method is based on a novel data structure for fast retrieval of partial matches: the randomized compound k‐NN graph built on multi‐view shape projections. We also employ a coarse‐to‐fine strategy to progressively refine part boundaries down to the level of individual faces. Experimental results indicate that our approach provides an intuitive and easy means to extract customized parts from a shape database, and significantly expands the design space for the user. We demonstrate several applications of our method to shape design and exploration.

3D Shape Reconstruction from Sketches via Multi-view Convolutional Networks

“…Sketch-based 3D shape retrieval: Sketch-based retrieval methods typically transform features of the input sketch and 3D shapes into a common space where comparisons can be made. Early work was based on hand-engineered descriptors [38], [39], [40], [41], [42], [43], [44], [45], [46], while more recently, ConvNets have been proposed to learn powerful representations for sketch-based retrieval [47], [48]. Unfortunately, these methods only allow retrieval of existing 3D shapes or parts.…”

Fast character modeling with sketch-based PDE surfaces

“…Through learning structural groups from a large database of scenes, Xu et al developed a framework to automatically obtain semantically valid and well-arranged scenes of 3D models from a freehand sketch drawing which infers multiple scene objects [38]. Based on a novel data structure for fast retrieval of partial matches, Guo et al investigated an on-demand part extraction algorithm called CustomCut [14]. For a user's input sketch query, it searches a database to find partially matching shapes, and identifies and extracts the region optimally matching the query in each shape to produce a customized part.…”

Learning Part Generation and Assembly for Sketching Man‐Made Objects

“…In user‐end modelling systems, such as Maya and 3ds Max, objects can be designed by part‐based modelling and assembly, which is difficult to master and time‐consuming to operate for amateurs. Since man‐made objects are essentially constructed by part assembly, early works assemble the shape structure from part candidates [SFCH12], or utilize strokes to retrieve the 3D counterparts for subsequent shape assembly [FWX*13, XXM*13, GLX*16]. Nishida et al.…”