Continuous semantic description of 3D meshes

León, Vladimir; Bonneel, Nicolas; Lavoué, Guillaume; Vandeborre, Jean-Philippe

doi:10.1016/j.cag.2015.07.018

Cited by 7 publications

(4 citation statements)

References 57 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The system can infer relationships implied in the text and yield common model placement patterns based on conditional probabilities. 14,15 Stanford University extended the 2D relational dataset to the 3D space by combining scene images with 3D space, semantics, and cameras to build a spatial semantic framework structure layer by layer through scene analysis in 2019. In 2020, the MIT SPARK Lab proposed the concept of dynamic 3D scene maps based on research from Stanford University.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

A semantic‐driven generation of 3D Chinese opera performance scenes

Liang

Dong

Liu

et al. 2022

Computer Animation & Virtual

View full text Add to dashboard Cite

The emergence of digital opera has enriched the stage performance of Chinese opera and expanded its dissemination means. However, the modern spread of traditional Chinese opera still faces hindrances. Digital opera performances require the generation of virtual scenes of the stages and characters. However, traditional virtual scene generation requires workers to build 3D models using modeling software and incorporate them into the performance scene. This article proposes a semantic-based generation method for Chinese opera performance scenes. First, we analyze the scene description scripts to understand the elements in Chinese opera virtual scenes. The prior probability is subsequently used to learn the model placement rules in the opera scene model. A digital scene suitable for Chinese opera performance is then generated. The final resultsshow that the method can generate natural and receptive opera digital performance scenes. This article's research ideas and achievements are conducive to the promotion of development of Chinese digital opera technology. They possess substantial significance to the inheritance and development of traditional Chinese opera art.

show abstract

Section: Related Workmentioning

confidence: 99%

“…In 2014, Stanford University proposed a scene generation system supporting partially interactable scene manipulation and active learning. The system can infer relationships implied in the text and yield common model placement patterns based on conditional probabilities 14,15 …”

Section: Related Workmentioning

confidence: 99%

A semantic‐driven generation of 3D Chinese opera performance scenes

Liang

Dong

Liu

et al. 2022

Computer Animation & Virtual

View full text Add to dashboard Cite

show abstract

“…As preprocessing, we manually charted the SMPL and the chimp meshes into L = 32 semantically-corresponding parts to guide the mapping. Then, for each vertex p of each mesh S, we extracted an adapted version of the continuous semantic descriptor d(p) proposed by Léon et al [25]:…”

Section: Annotation Through 3d Shape Re-mappingmentioning

confidence: 99%

Transferring Dense Pose to Proximal Animal Classes

Sanakoyeu¹,

Khalidov²,

McCarthy³

et al. 2020

Preprint

View full text Add to dashboard Cite

We consider the problem of dense pose labelling in animal classes. We show that, for proximal to humans classes such as chimpanzees (left), we can obtain excellent performance by learning an integrated recognition architecture from existing data sources, including DensePose for humans as well as detection and segmentation information from other COCO classes (right). The key is to establish a common reference (middle), which we obtain via alignment of the reference models of the animals. This enables training a model for the target class without having to label a single example image for it.

show abstract

“…In particular, the proposed decomposition provides an automatic pre-processing for applications such as structuring a 3D shape (e.g. like [3] whose semantic descriptors relies on a decomposition of the shape), or similarity detection in a 3D shape, as required by Guy et al [4].…”

mentioning

confidence: 99%

A salience measure for 3D shape decomposition and sub-parts classification

et al. 2018

View full text Add to dashboard Cite

Open Archive Toulouse Archive OuverteOATAO is an open access repository that collects the work of Toulouse researchers and makes it freely available over the web where possible a A B S T R A C T This paper introduces a measure of significance on a curve skeleton of a 3D piecewise linear shape mesh, allowing the computation of both the shape's parts and their saliency. We begin by reformulating three existing pruning measures into a non-linear PCA along the skeleton. From this PCA, we then derive a volume-based salience measure, the 3D WEDF, that determines the relative importance to the global shape of the shape part associated to a point of the skeleton. First, we provide robust algorithms for computing the 3D WEDF on a curve skeleton, independent on the number of skeleton branches. Then, we cluster the WEDF values to partition the curve skeleton, and coherently map the decomposition to the associated surface mesh. Thus, we develop an unsupervised hierarchical decomposition of the mesh faces into visually meaningful shape regions that are or-dered according to their degree of perceptual salience. The shape analysis tools introduced in this paper are important for many applications including shape comparison, editing, and compression.

show abstract

Continuous semantic description of 3D meshes

Cited by 7 publications

References 57 publications

A semantic‐driven generation of 3D Chinese opera performance scenes

A semantic‐driven generation of 3D Chinese opera performance scenes

Transferring Dense Pose to Proximal Animal Classes

A salience measure for 3D shape decomposition and sub-parts classification

Contact Info

Product

Resources

About