Salient local visual features for shape-based 3D model retrieval

By Ryutarou Ohbuchi, Kunio Osada, Takahiko Furuya, Tomohisa Banno. Shape Modeling International Conference, 2008

303 citations recorded by the source corpus.

Subfields: Aerospace Engineering, Computational Mechanics, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/35d4c914ca7b001bb97e1ce1d940e55f21a47e66

How researchers see this paper

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

In Aerospace Engineering

In Computational Mechanics

In Computer Vision and Pattern Recognition

Citations in the corpus

Learning 3D Part Detection from Sparsely Labeled Data (2014, background): “3D PART DETECTION AS STRUCTURED PREDICTION We focus our attention on labeling 3D models belonging to the same category (in practical applications, the category can be discerned from associated text descriptions or metadata, or reliably determined from automated techniques [19]).”
Rotational Projection Statistics for 3D Local Surface Description and Object Recognition (2013, methodology): “Note that, some existing view-based methods can be found in the literature, such as (Yamauchi et al., 2006), (Ohbuchi et al., 2008) and (Atmosukarto and Shapiro, 2010).”
Completing 3D object shape from one depth image (2015, methodology): “[28] propose an approach for retrieval based on SIFT applied to depth images, which is used by Goldfeder et al.”
3-D Object Retrieval and Recognition With Hypergraph Analysis (2012, methodology): “2) The “Bag of visual features” (BoVF) method [60]: In BoVF, local SIFT features are extracted from all views of a 3-D object and they are quantized into visual words based on a pretrained visual vocabulary.”
3D deep shape descriptor (2015, background): “The development of an effective and efficient 3D shape descriptor poses several technical challenges, including, in particular, the high data complexity of 3D models and their representations, the structural variations, noise, and incompleteness present in 3D models [47, 24, 15, 49, 43, 36, 27, 23, ”
Data-driven grasping with partial sensor data (2009, methodology): “The key innovation of [27] was to describe a 3D model using a single bag-of-features, encoding features drawn from many views of the model in the same histogram.”