Zhouhui Lian

A comparison of methods for non-rigid 3D shape retrieval

Non-rigid 3D shape retrieval has become an active and important research topic in content-based 3D object retrieval. The aim of this paper is to measure and compare the performance of state-of-the-art methods for non-rigid 3D shape retrieval. The paper develops a new benchmark consisting of 600 non-rigid 3D watertight meshes, which are equally classified into 30 categories, to carry out experiments for 11 different algorithms, whose retrieval accuracies are evaluated using six commonly utilized measures. Models and evaluation tools of the new benchmark are publicly available on our web site [1].

SHREC'11 track: shape retrieval on non-rigid 3D watertight meshes

Non-rigid 3D shape retrieval has become an important research topic in content-based 3D object retrieval. The aim of this track is to measure and compare the performance of non-rigid 3D shape retrieval methods implemented by different participants around the world. The track is based on a new non-rigid 3D shape benchmark, which contains 600 watertight triangle meshes that are equally classified into 30 categories. In this track, 25 runs have been submitted by 9 groups and their retrieval accuracies were evaluated using 6 commonly-utilized measures.

Visual Similarity Based 3D Shape Retrieval Using Bag-of-Features

This paper presents a novel 3D shape retrieval method, which uses Bag-of-Features and an efficient multi-view shape matching scheme. In our approach, a properly normalized object is first described by a set of depth-buffer views captured on the surrounding vertices of a given unit geodesic sphere. We then represent each view as a word histogram generated by the vector quantization of the view’s salient local features. The dissimilarity between two 3D models is measured by the minimum distance of their all (24) possible matching pairs. This paper also investigates several critical issues including the influence of the number of views, codebook, training data, and distance function. Experiments on four commonly-used benchmarks demonstrate that: 1) Our approach obtains superior performance in searching for rigid models. 2) The local feature and global feature based methods are somehow complementary. Moreover, a linear combination of them significantly outperforms the state-of-the-art in terms of retrieval accuracy.

Rectilinearity of 3D Meshes

In this paper, we propose and evaluate a novel shape measure describing the extent to which a 3D polygon mesh is rectilinear. The rectilinearity measure is based on the maximum ratio of the surface area to the sum of three orthogonal projected areas of the mesh. It has the following desirable properties: 1) the estimated rectilinearity is always a number from (0,1]; 2) the measure is invariant under scale, rotation, and translation; 3) the 3D objects can be either open or closed meshes, and we can also deal with degenerate meshes; 4) the measure is insensitive to noise, stable under small topology errors, and robust against face deletion and mesh simplification. Moreover, a genetic algorithm (GA) can be applied to compute the approximate rectilinearity efficiently. We find that the calculation of rectilinearity can be used to normalize the pose of 3D meshes, and in many cases it performs better than the principal component analysis (PCA) based method. By applying a simple selection criterion, the combination of these two methods results in a new pose normalization algorithm which not only provides a higher successful alignment rate but also corresponds better with intuition. Finally, we carry out several experiments showing that both the rectilinearity based pose normalization preprocessing and the combined signatures, which consist of the rectilinearity measure and other shape descriptors, can significantly improve the performance of 3D shape retrieval.

Shape Retrieval of Non-rigid 3D Human Models

Abstract3D models of humans are commonly used within computer graphics and vision, and so the ability to distinguish between body shapes is an important shape retrieval problem. We extend our recent paper which provided a benchmark for testing non-rigid 3D shape retrieval algorithms on 3D human models. This benchmark provided a far stricter challenge than previous shape benchmarks. We have added 145 new models for use as a separate training set, in order to standardise the training data used and provide a fairer comparison. We have also included experiments with the FAUST dataset of human scans. All participants of the previous benchmark study have taken part in the new tests reported here, many providing updated results using the new data. In addition, further participants have also taken part, and we provide extra analysis of the retrieval results. A total of 25 different shape retrieval methods are compared.

CM-BOF: visual similarity-based 3D shape retrieval using Clock Matching and Bag-of-Features

Content-based 3D object retrieval has become an active topic in many research communities. In this paper, we propose a novel visual similarity-based 3D shape retrieval method (CM-BOF) using Clock Matching and Bag-of-Features. Specifically, pose normalization is first applied to each object to generate its canonical pose, and then the normalized object is represented by a set of depth-buffer images captured on the vertices of a given geodesic sphere. Afterwards, each image is described as a word histogram obtained by the vector quantization of the image’s salient local features. Finally, an efficient multi-view shape matching scheme (i.e., Clock Matching) is employed to measure the dissimilarity between two models. When applying the CM-BOF method in non-rigid 3D shape retrieval, multidimensional scaling (MDS) should be utilized before pose normalization to calculate the canonical form for each object. This paper also investigates several critical issues for the CM-BOF method, including the influence of the number of views, codebook, training data, and distance function. Experimental results on five commonly used benchmarks demonstrate that: (1) In contrast to the traditional Bag-of-Features, the time-consuming clustering is not necessary for the codebook construction of the CM-BOF approach; (2) Our methods are superior or comparable to the state of the art in applications of both rigid and non-rigid 3D shape retrieval.

Non-rigid 3D shape retrieval using Multidimensional Scaling and Bag-of-Features

Matching non-rigid shapes is a challenging research field in content-based 3D object retrieval. In this paper, we present an image-based method to effectively address this problem. Multidimensional Scaling (MDS) and Principal Component Analysis (PCA) are first applied to each object to calculate its canonical form, which is afterward represented by 66 depth-buffer images captured on the vertices of an unit geodesic sphere. Then, each image is described as a word histogram obtained by the vector quantization of the images salient local features. Finally, a multi-view shape matching scheme is carried out to measure the dissimilarity between two models. Experimental results on the McGill Articulated Shape Benchmark database demonstrate that, our method obtains better retrieval performance compared to the state-of-the-art.

Shape retrieval of non-rigid 3D human models

We have created a new benchmarking dataset for testing non-rigid 3D shape retrieval algorithms, one that is much more challenging than existing datasets. Our dataset features exclusively human models, in a variety of body shapes and poses. 3D models of humans are commonly used within computer graphics and vision, and so the ability to distinguish between body shapes is an important shape retrieval problem. In this track nine groups have submitted the results of a total of 22 different methods which have been tested on our new dataset.

Feature-Preserved 3D Canonical Form

Measuring the dissimilarity between non-rigid objects is a challenging problem in 3D shape retrieval. One potential solution is to construct the models’ 3D canonical forms (i.e., isometry-invariant representations in 3D Euclidean space) on which any rigid shape matching algorithm can be applied. However, existing methods, which are typically based on embedding procedures, result in greatly distorted canonical forms, and thus could not provide satisfactory performance to distinguish non-rigid models.In this paper, we present a feature-preserved canonical form for non-rigid 3D watertight meshes. The basic idea is to naturally deform original models against corresponding initial canonical forms calculated by Multidimensional Scaling (MDS). Specifically, objects are first segmented into near-rigid subparts, and then, through properly-designed rotations and translations, original subparts are transformed into poses that correspond well with their positions and directions on MDS canonical forms. Final results are obtained by solving nonlinear minimization problems for optimal alignments and smoothing boundaries between subparts. Experiments on two non-rigid 3D shape benchmarks not only clearly verify the advantages of our algorithm against existing approaches, but also demonstrate that, with the help of the proposed canonical form, we can obtain significantly better retrieval accuracy compared to the state of the art.

Automatic generation of large-scale handwriting fonts via style learning

Generating personal handwriting fonts with large amounts of characters is a boring and time-consuming task. Take Chinese fonts as an example, the official standard GB18030-2000 for commercial font products contains 27533 simplified Chinese characters. Consistently and correctly writing out such huge amounts of characters is usually an impossible mission for ordinary people. To solve this problem, we propose a handy system to automatically synthesize personal handwritings for all characters (e.g., Chinese) in the font library by learning style from a small number (as few as 1%) of carefully-selected samples written by an ordinary person. Experiments including Turing tests with 69 participants demonstrate that the proposed system generates high-quality synthesis results which are indistinguishable from original handwritings. Using our system, for the first time the practical handwriting font library in a users personal style with arbitrarily large numbers of Chinese characters can be generated automatically.