Discriminative Sketch‐based 3D Model Retrieval via Robust Shape Matching

75 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Multi-view Convolutional Neural Networks for 3D Shape Recognition (2015, background): “However, it is hard to convey stylistic and geometric variations using only textual descriptions, thus sketchbased shape retrieval [38, 31, 12] has been proposed as an alternative for users to retrieve shapes with an approximate sketch of the desired 3D shape in mind.”
Deep Learning for Free-Hand Sketch: A Survey (2020, background): “As aforementioned in this survey, the coarse-grained sketch-based cross-modal retrieval systems adopt category-level validation criterion, which will determine a returned sample as a true match if this returned sample has the identical class label to the query.”
Query-driven iterated neighborhood graph search for large scale indexing (2012, methodology): “To match two 2D contours, we estimate an affine transformation between them using RANSAC and use the registration error as the distance, which is described in [34].”
Sketch-based shape retrieval (2012, methodology): “Instead, sketch-based retrieval has been proposed [Löffler 2000; Funkhouser et al. 2003; Chen et al. 2003; Yoon et al. 2010; Shao et al. 2011], where users sketch the desired model as seen from one or more viewpoints.”