Sketch-based shape retrieval

Eitz, Mathias; Richter, R. L.; Boubekeur, Tamy; Hildebrand, Kristian; Alexa, Marc

doi:10.1145/2185520.2335382

Cited by 87 publications

(79 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This approach is robust to intra-class variations and is consistent within the models of the same class of shapes, but its performance highly depends on the training datasets. Eitz et al [4] just uses the silhouette length, projected area and smoothness of depth distribution over the shape as the features to learn a perceptual classifier. Although it shows capable results for simple shapes, it fails easily when the shape is complex.…”

Section: Related Workmentioning

confidence: 99%

“…In the experiments, 3D shape collection of the Princeton Shape Benchmark (PSB) [26], and relevant sketch data collected by [4] are used. The PSB defines a split into training and test dataset, which both have 907 shapes with different classification.…”

Section: The Training Datamentioning

confidence: 99%

“…The PSB defines a split into training and test dataset, which both have 907 shapes with different classification. Then for each shape, a set of sketches belonging to the same category are collected by [4]. Each sketch consists of hand-drawn silhouettes and closed boundary curves, which meets our requirements.…”

Section: The Training Datamentioning

confidence: 99%

“…Automatically selecting the best views for a given 3D shape is one of the B Shuang Liang shuangliang@tongji.edu.cn 1 Tongji University, Shanghai, China 2 Microsoft Research, Beijing, China most important preprocessing tasks in 3D graphics. It has been applied in many 3D graphics applications, including virtual reality, shape retrieval [4,9,25], computer-aided design (CAD) [18], 3D multimedia [32], and so on. The problem of best view selection is to seek a few viewpoints that follow human visual preference.…”

Section: Introductionmentioning

confidence: 99%

“…In addition, hand-drawn sketches are used to model this concept. Thanks to the rapid development of sketch-based shape retrieval technology, lots of large-scale 3D shape datasets providing relevant sketches are available from different sources [4,14,15]. As illustrated in Fig.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Learning best views of 3D shapes from sketch contour

et al. 2015

View full text Add to dashboard Cite

In this paper, we introduce a novel learningbased approach to automatically select the best views of 3D shapes using a new prior. We think that a viewpoint of the 3D shape is reasonable if a human usually draws the shape from it. Hand-drawn sketches collected from relevant datasets are used to model this concept. We reveal the connection between sketches and viewpoints by taking context information of their contours into account. Furthermore, a learning framework is proposed to generalize this connection which aims to learn an automatic best view selector for different kinds of 3D shapes. Experiments on the Princeton Shape Benchmark dataset are conducted to demonstrate the superiority of our approach. The results show that compared with other stateof-the-art methods, our approach is not only robust but also efficient when applied to shape retrieval tasks.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: The Training Datamentioning

confidence: 99%

Section: The Training Datamentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Learning best views of 3D shapes from sketch contour

et al. 2015

View full text Add to dashboard Cite

show abstract

Sketch‐based shape‐constrained fireworks simulation in head‐mounted virtual reality

Cui

Cai

Tang

et al. 2020

Computer Animation & Virtual

View full text Add to dashboard Cite

In this paper we present a novel shape‐constrained fireworks simulation method with rich textures in an HMD (Helmet Mounted Display) virtual environment using sketched feature lines as input. Our approach first retrieves an object from a three‐dimensional (3D) model database using a sketch‐based 3D shape retrieval algorithm. Then, in order to approximate models with complex structures, we introduce a novel point sampling algorithm based on Gaussian curvatures, which stores not only the positions of the selected vertices but also the texture (UV) coordinates information for texture display. In addition, we introduce a multilevel explosion process so that the fireworks can dynamically form specific, visually pleasing shapes. Through our experiments, we demonstrate that our approach can produce better results than state‐of‐the‐art approaches.

show abstract

Deep Shape Matching

Radenović

Tolias

Chum

2018

Lecture Notes in Computer Science

View full text Add to dashboard Cite

We cast shape matching as metric learning with convolutional networks. We break the end-to-end process of image representation into two parts. Firstly, well established efficient methods are chosen to turn the images into edge maps. Secondly, the network is trained with edge maps of landmark images, which are automatically obtained by a structure-from-motion pipeline. The learned representation is evaluated on a range of different tasks, providing improvements on challenging cases of domain generalization, generic sketch-based image retrieval or its fine-grained counterpart. In contrast to other methods that learn a different model per task, object category, or domain, we use the same network throughout all our experiments, achieving state-of-the-art results in multiple benchmarks.

show abstract

Sketch-based shape retrieval

Cited by 87 publications

References 0 publications

Learning best views of 3D shapes from sketch contour

Learning best views of 3D shapes from sketch contour

Sketch‐based shape‐constrained fireworks simulation in head‐mounted virtual reality

Deep Shape Matching

Contact Info

Product

Resources

About