The princeton shape benchmark

Shilane, Philip; Min, Patrick; Kazhdan, Michael; Funkhouser, Thomas

doi:10.1109/smi.2004.1314504

Cited by 1,055 publications

(853 citation statements)

References 21 publications

Supporting

Mentioning

833

Contrasting

Unclassified

Order By: Relevance

“…In order to keep the results comparable to experiments given in [9] we conducted our experiments only on the test set of the PSB at the finest granularity. To show the superiority of the Wigner D-matrices over the Spherical Harmonics we also give the results for the best corresponding SH-feature (see [8]).…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Using Irreducible Group Representations for Invariant 3D Shape Description

Reisert

Burkhardt

2006

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. Invariant feature representations for 3D objects are one of the basic needs in 3D object retrieval and classification. One tool to obtain rotation invariance are Spherical Harmonics, which are an orthogonal basis for the functions defined on the 2-sphere. We show that the irreducible representations of the 3D rotation group, which acts on the Spherical Harmonic representation, can give more information about the considered object than the Spherical Harmonic expansion itself. We embed our new feature extraction methods in the group integration framework and show experiments for 3D-surface data (Princeton Shape Benchmark).

show abstract

Section: Methodsmentioning

confidence: 99%

“…The Princeton Shape Benchmark (PSB) [9] offers a possibility to evaluate 3D-feature extraction techniques. It consists of approx.…”

Section: Introductionmentioning

confidence: 99%

Using Irreducible Group Representations for Invariant 3D Shape Description

Reisert

Burkhardt

2006

Lecture Notes in Computer Science

View full text Add to dashboard Cite

show abstract

“…Eight of the models will be familiar to graphics researchers (armadillo, dragon, etc.) and the other eight are selected from separate categories in the Princeton Shape Benchmark [Shilane et al 2004]. All but one of the objects are recognizable shapes even for people who have never seen them before.…”

Section: Collecting Human Preferencesmentioning

confidence: 99%

Perceptual models of viewpoint preference

et al. 2011

View full text Add to dashboard Cite

The question of what are good views of a 3D object has been addressed by numerous researchers in perception, computer vision, and computer graphics. This has led to a large variety of measures for the goodness of views as well as some special-case viewpoint selection algorithms. In this article, we leverage the results of a large user study to optimize the parameters of a general model for viewpoint goodness, such that the fitted model can predict people's preferred views for a broad range of objects. Our model is represented as a combination of attributes known to be important for view selection, such as projected model area and silhouette length. Moreover, this framework can easily incorporate new attributes in the future, based on the data from our existing study. We demonstrate our combined goodness measure in a number of applications, such as automatically selecting a good set of representative views, optimizing camera orbits to pass through good views and avoid bad views, and trackball controls that gently guide the viewer towards better views.

show abstract

“…However, having many unbiased classes of models does help the learning process to better understand the essence of orientation identification among different kinds of models, thus boosting generalizability. We construct a training set of standing man-made models using the Princeton Shape Benchmark (PSB) [Shilane et al 2004], a publicly available database of polygonal models. For training purposes, we select from it a representative sample of models covering the major classes of man-made models present in PSB.…”

Section: Trainingmentioning

confidence: 99%

Upright orientation of man-made objects

Cohen–Or

Dror

et al. 2008

ACM SIGGRAPH 2008 Papers

View full text Add to dashboard Cite

Humans usually associate an upright orientation with objects, placing them in a way that they are most commonly seen in our surroundings. While it is an open challenge to recover the functionality of a shape from its geometry alone, this paper shows that it is often possible to infer its upright orientation by analyzing its geometry. Our key idea is to reduce the two-dimensional (spherical) orientation space to a small set of orientation candidates using functionality-related geometric properties of the object, and then determine the best orientation using an assessment function of several functional geometric attributes defined with respect to each candidate. Specifically we focus on obtaining the upright orientation for man-made objects that typically stand on some flat surface (ground, floor, table, etc.), which include the vast majority of objects in our everyday surroundings. For these types of models orientation candidates can be defined according to static equilibrium. For each candidate, we introduce a set of discriminative attributes linking shape to function. We learn an assessment function of these attributes from a training set using a combination of Random Forest classifier and Support Vector Machine classifier. Experiments demonstrate that our method generalizes well and achieves about 90% prediction accuracy for both a 10-fold cross-validation over the training set and a validation with an independent test set.

show abstract

The princeton shape benchmark

Cited by 1,055 publications

References 21 publications

Using Irreducible Group Representations for Invariant 3D Shape Description

Using Irreducible Group Representations for Invariant 3D Shape Description

Perceptual models of viewpoint preference

Upright orientation of man-made objects

Contact Info

Product

Resources

About