Sketch-based 3D model retrieval by incorporating 2D-3D alignment

Sketch-based 3D model retrieval is very important for applications such as 3D modeling and recognition. In this paper, a sketch-based retrieval algorithm is proposed based on a 3D model feature named View Context and 2D relative shape context matching. To enhance the accuracy of 2D sketch-3D model correspondence as well as the retrieval performance, we propose to align a 3D model with a query 2D sketch before measuring their distance. First, we efficiently select some candidate views from a set of densely sampled views of the 3D model to align the sketch and the model based on their View Context similarities. Then, we compute the more accurate relative shape context distance between the sketch and every candidate view, and regard the minimum one as the sketch-model distance. To speed up retrieval, we precompute the View Context and relative shape context features of the sample views of all the 3D models in the database. Comparative and evaluative experiments based on hand-drawn and standard line drawing sketches demonstrate the effectiveness and robustness of our approach and it significantly outperforms several latest sketch-based retrieval algorithms.     

Fast Retrieval of Isolated Visual Shapes

Similarity-based retrieval from databases of isolated visual shapes has become an important information retrieval problem. The goal of the current work is to achieve high retrieval speed with reasonable retrieval effectiveness, and support for partial and occluded shape queries. In the proposed method, histograms of local shape parts are coded as index vectors. To increase retrieval accuracy, a rich set of parts at all scales of the shape is used; specifically, the parts are defined as connected sequences of regions in curvature scale space. To increase efficiency, structural indexing is used to compare the index vectors of the query and database shapes. In experimental evaluations, the method retrieved at least one similar shape in the top three retrieved items 99–100% of the time, depending on the database. Average retrieval times ranged from 0.7 ms on a 131-shape database to 7 ms on a 1310-shape database. The method is thus suitable for fast, approximate shape retrieval in comparison with more accurate but more costly structural matching.     

Non‐Rigid Puzzles

Shape correspondence is a fundamental problem in computer graphics and vision, with applications in various problems including animation, texture mapping, robotic vision, medical imaging, archaeology and many more. In settings where the shapes are allowed to undergo non‐rigid deformations and only partial views are available, the problem becomes very challenging. To this end, we present a non‐rigid multi‐part shape matching algorithm. We assume to be given a reference shape and its multiple parts undergoing a non‐rigid deformation. Each of these query parts can be additionally contaminated by clutter, may overlap with other parts, and there might be missing parts or redundant ones. Our method simultaneously solves for the segmentation of the reference model, and for a dense correspondence to (subsets of) the parts. Experimental results on synthetic as well as real scans demonstrate the effectiveness of our method in dealing with this challenging matching scenario.     

DeepSketch 3

Freehand sketches are a simple and powerful tool for communication. They are easily recognized across cultures and suitable for various applications. In this paper, we use deep convolutional neural networks (ConvNets), state-of-the-art in the field of sketch recognition, to address several applications of automatic sketch processing: complete and partial sketch recognition, sketch retrieval using query-by-example (QbE), and sketch-based image retrieval (SBIR) i.e the retrieval of images using a QbE paradigm but where the query is a sketch. We first focus on improving sketch recognition. For this purpose we compare different ConvNet architectures, training paradigms and data fusion schemes. This enabled us to outperform previous state-of-the-art in two large scale benchmarks for sketch classification. We achieved a mean average accuracy of 79.18% for the TU-Berlin sketch benchmark and 93.02% for the sketchy database. For partial sketch recognition, we were able to produce a system that achieves a mean average accuracy of 52.58% with only 40% of the strokes. We then conduct a comprehensive study of ConvNets features to enhance sketch retrieval and image retrieval, using a kNN similarity search paradigm in the ConvNet feature space. For the sketch retrieval tasks, we compare the performance obtained with features extracted from various depths (ConvNet layers) using one of the best performing model from the previous work. For the sketch-based image retrieval (SBIR), a sketch query is used to retrieve images of objects that belong to the same category, or even with a shape and pose close to the sketch query. The main challenge in the field of SBIR is to obtain efficient cross-domain features for sketch-image similarity measure. For this, besides comparing features extracted from different depth, we additionally compare different training approaches (some novel) for the ConvNets applied to sketches and images. Eventually, our best SBIR system achieves state-of-the-art results on the sketchy database (close to 40% recall at k = 1).

     

Contextual Part Analogies in 3D Objects

In this paper we address the problem of finding analogies between parts of 3D objects. By partitioning an object into meaningful parts and finding analogous parts in other objects, not necessarily of the same type, many analysis and modeling tasks could be enhanced. For instance, partial match queries can be formulated, annotation of parts in objects can be utilized, and modeling-by-parts applications could be supported. We define a similarity measure between two parts based not only on their local signatures and geometry, but also on their context within the shape to which they belong. In our approach, all objects are hierarchically segmented (e.g. using the shape diameter function), and each part is given a local signature. However, to find corresponding parts in other objects we use a context enhanced part-in-whole matching. Our matching function is based on bi-partite graph matching and is computed using a flow algorithm which takes into account both local geometrical features and the partitioning hierarchy. We present results on finding part analogies among numerous objects from shape repositories, and demonstrate sub-part queries using an implementation of a simple search and retrieval application. We also demonstrate a simple annotation tool that carries textual tags of object parts from one model to many others using analogies, laying a basis for semantic text based search.     

Autocorrelation Descriptor for Efficient Co‐Alignment of 3D Shape Collections

Co‐aligning a collection of shapes to a consistent pose is a common problem in shape analysis with applications in shape matching, retrieval and visualization. We observe that resolving among some orientations is easier than others, for example, a common mistake for bicycles is to align front‐to‐back, while even the simplest algorithm would not erroneously pick orthogonal alignment. The key idea of our work is to analyse rotational autocorrelations of shapes to facilitate shape co‐alignment. In particular, we use such an autocorrelation measure of individual shapes to decide which shape pairs might have well‐matching orientations; and, if so, which configurations are likely to produce better alignments. This significantly prunes the number of alignments to be examined, and leads to an efficient, scalable algorithm that performs comparably to state‐of‐the‐art techniques on benchmark data sets, but requires significantly fewer computations, resulting in 2–16× speed improvement in our tests.     

Thesaurus-based 3D Object Retrieval with Part-in-Whole Matching

Research in content-based 3D retrieval has already started, and several approaches have been proposed which use in different manner a similarity assessment to match the shape of the query against the shape of the objects in the database. However, the success of these solutions are far from the success obtained by their textual counterparts. A major drawback of most existing 3D retrieval solutions is their inability to support partial queries, that is, a query which does not need to be formulated by specifying a whole query shape, but just a part of it, for example a detail of its overall shape, just like documents are retrieved by specifying words and not whole texts. Recently, researchers have focused their investigation on 3D retrieval which is solved by partial shape matching. However, at the extent of our knowledge, there is still no 3D search engine that provides an indexing of the 3D models based on all the interesting subparts of the models. In this paper we present a novel approach to 3D shape retrieval that uses a collection-aware shape decomposition combined with a shape thesaurus and inverted indexes to describe and retrieve 3D models using part-in-whole matching. The proposed method clusters similar segments obtained trough a multilevel decomposition of models, constructing from such partition the shape thesaurus. Then, to retrieve a model containing a sub-part similar to a given query, instead of looking on a large set of subparts or executing partial matching between the query and all models in the collection, we just perform a fast global matching between the query and the few entries in the thesaurus. With this technique we overcame the time complexity problems associated with partial queries in large collections.     

Discriminative Sketch‐based 3D Model Retrieval via Robust Shape Matching

We propose a sketch‐based 3D shape retrieval system that is substantially more discriminative and robust than existing systems, especially for complex models. The power of our system comes from a combination of a contour‐based 2D shape representation and a robust sampling‐based shape matching scheme. They are defined over discriminative local features and applicable for partial sketches; robust to noise and distortions in hand drawings; and consistent when strokes are added progressively. Our robust shape matching, however, requires dense sampling and registration and incurs a high computational cost. We thus devise critical acceleration methods to achieve interactive performance: precomputing kNN graphs that record transformations between neighboring contour images and enable fast online shape alignment; pruning sampling and shape registration strategically and hierarchically; and parallelizing shape matching on multi‐core platforms or GPUs. We demonstrate the effectiveness of our system through various experiments, comparisons, and user studies.     

Learning Part Boundaries from 3D Point Clouds

We present a method that detects boundaries of parts in 3D shapes represented as point clouds. Our method is based on a graph convolutional network architecture that outputs a probability for a point to lie in an area that separates two or more parts in a 3D shape. Our boundary detector is quite generic: it can be trained to localize boundaries of semantic parts or geometric primitives commonly used in 3D modeling. Our experiments demonstrate that our method can extract more accurate boundaries that are closer to ground-truth ones compared to alternatives. We also demonstrate an application of our network to fine-grained semantic shape segmentation, where we also show improvements in terms of part labeling performance.     

Interactive Image‐Guided Modeling of Extruded Shapes

A recent trend in interactive modeling of 3D shapes from a single image is designing minimal interfaces, and accompanying algorithms, for modeling a specific class of objects. Expanding upon the range of shapes that existing minimal interfaces can model, we present an interactive image‐guided tool for modeling shapes made up of extruded parts. An extruded part is represented by extruding a closed planar curve, called base, in the direction orthogonal to the base. To model each extruded part, the user only needs to sketch the projected base shape in the image. The main technical contribution is a novel optimization‐based approach for recovering the 3D normal of the base of an extruded object by exploring both geometric regularity of the sketched curve and image contents. We developed a convenient interface for modeling multi‐part shapes and a method for optimizing the relative placement of the parts. Our tool is validated using synthetic data and tested on real‐world images.     

Similar-shape retrieval in shape data management

Addresses the problem of similar-shape retrieval, where shapes or images in a shape database that satisfy specified shape-similarity constraints with respect to the query shape or image must be retrieved from the database. In its simplest form, the similar-shape retrieval problem can be stated as, “retrieve or select all shapes or images that are visually similar to the query shape or the query image's shape”. We focus on databases of 2D shapes-or equivalently, databases of images of flat or almost flat objects. (We use the terms “object” and “shape” interchangeably). Two common types of 2D objects are rigid objects, which have a single rigid component called a link, and articulated objects, which have two or more rigid components joined by movable (rotating or sliding) joints. An ideal similar-shape retrieval technique must be general enough to handle images of articulated as well as rigid objects. It must be flexible enough to handle simple query images, which have isolated shapes, and complex query images, which have partially visible, overlapping or touching objects. We discuss the central issues in similar-shape retrieval and explain how these issues are resolved in a shape retrieval scheme called FIBSSR (Feature Index-Based Similar-Shape Retrieval). This new similar-shape retrieval system effectively models real-world applications     

基于图像辅助的三维模型形状检索

随着3D建模技术的快速发展,互联网上可用的3D模型库出现了爆炸式增长,越来越多的3D模型可以方便地通过网络下载使用.这直接促使了3D形状检索技术的发展,即给出特定的搜索信息,要求系统搜索出符合要求的、相似的3D模型.文章提出了一种新的3D形状检索方法,以3D模型作为输入,系统将会从模型数据库中自动检索出与输入形状最相似的模型.对于给定的输入模型以及数据库中的每一个模型,首先由计算机生成多幅在不同视角下的2D草图;然后,应用Gabor滤波器对每一幅2D草图提取图像上的局部特征,并对特征进行量化,从而得到代表该图像特征的直方图,这样对于每一个3D模型将得到多个代表该模型的直方图;最终,通过对比两个模型之间直方图的相似性,可以得到它们的相似性值,从而检索出与输入模型最相似的模型.文章所提出的方法通过采取2D图像分析方法提取能反映3D模型的特征并计算出模型之间的相似性值.经过测试,在一些公开的数据集上得到了较好的效果.     

Utilizing shape retrieval in sketch synthesis

This article describes SR-Sketch, a sketch creation tool that can act both as a front-end visual query module to visual information retrieval systems and as an aid tool for fast image composition. The system allows the user to draw shapes on the computer screen using the mouse cursor. At any time during this process the user can query a shape database for similar shapes and then select the ones s/he thinks are more relevant. The system can then automatically align and replace user-drawn objects with the chosen database shapes in the user sketch. For any match between a sketch shape and a database shape, the application can provide a visual explanation of how and why two shapes are considered similar. Evaluation results show that the system achieves favorable results with respect to noise tolerance, speed and reliability. SR-Sketch is freely available for download and experimentation.

A content based image retrieval system for a biological specimen collection

Digital photography and decreasing cost of storing data in digital form has led to an explosion of large digital image repositories. Since the number of images in image databases can be large (millions in some cases) it is important to develop automated tools to search them. In this paper, we present a content based image retrieval system for a database of parasite specimen images. Unlike most content based image retrieval systems, where the database consists of objects that vary widely in shape and size, the objects in our database are fairly uniform. These objects are characterized by flexible body shapes, but with fairly rigid ends. We define such shapes to be FleBoRE (Flexible Body Rigid Extremities) objects, and present a shape model for this class of objects. We have defined similarity functions to compute the degree of likeness between two FleBoRE objects and developed automated methods to extract them from specimen images. The system has been tested with a collection of parasite images from the Harold W. Manter Laboratory for Parasitology. Empirical and expert-based evaluations show that query by shape approach is effective in retrieving specimens of the same class.     

Learning Part Generation and Assembly for Sketching Man‐Made Objects

Modeling 3D objects on existing software usually requires a heavy amount of interactions, especially for users who lack basic knowledge of 3D geometry. Sketch‐based modeling is a solution to ease the modelling procedure and thus has been researched for decades. However, modelling a man‐made shape with complex structures remains challenging. Existing methods adopt advanced deep learning techniques to map holistic sketches to 3D shapes. They are still bottlenecked to deal with complicated topologies. In this paper, we decouple the task of sketch2shape into a part generation module and a part assembling module, where deep learning methods are leveraged for the implementation of both modules. By changing the focus from holistic shapes to individual parts, it eases the learning process of the shape generator and guarantees high‐quality outputs. With the learned automated part assembler, users only need a little manual tuning to obtain a desired layout. Extensive experiments and user studies demonstrate the usefulness of our proposed system.     

Query-by-Gesture: An Alternative Content-Based Image Retrieval Query Scheme

Current research on content-based image retrieval (CBIR) is centered on designing efficient query schemes in order to provide a user with effective mechanisms for image database search. Among representative CBIR query schemes, query-by-sketch has been one of the attractive query tools that are highly adaptive to user's subjectivity. However, query-by-sketch has a few limitations. That is, most sketch tools demand expertise in image processing or computer vision of the user to provide good enough sketches that can be used as query. Furthermore, sketching the exact shape of an object using a mouse can be a burden on the user. To overcome some of the limitations associated with query-by-sketch, we propose a new query method for CBIR, query-by-gesture, that does not require sketches, thereby minimizing user interaction. In our system, the user does not need to use a mouse to make a sketch. Instead, the user draws the shape of the object that heshe intends to search in front of a camera by hand. In addition, our query-by-gesture technique uses relevance feedback to interactively improve retrieval performance and allow progressive refinement of query results according to the user's specification. The efficacy of our proposed method is validated using images from the Corel-Photo CD.     

Super-vector coding features extracted from both depth buffer and view-normal-angle images for part-based 3D shape retrieval

We have witnessed 3D shape models abundant in many application fields including 3D CAD/CAM, augmented/mixed reality (AR/MR), and entertainment. Creating 3D shape models from scratch is still very expensive. Efficient and accurate methods for shape retrieval is essential for 3D shape models to be reused. To retrieve similar 3D shape models, one must provide an arbitrary 3D shape as a query. Most of the research on 3D shape retrieval has been conducted with a “whole” shape as a query (aka whole-to-whole shape retrieval), while a “part” shape (aka part-to-whole shape retrieval) is more practically requested as a query especially by mechanical engineering with 3D CAD/CAM applications. A “part” shape is naturally constructed by a 3D range scanner as an input device. In this paper, we focus on the efficient method for part-to-whole shape retrieval where the “part” shape is assumed to be given by a 3D range scanner. Specifically, we propose a Super-Vector coding feature with SURF local features extracted from the View-Normal-Angle image, or the image synthesized by taking account of the angle between the view vector and the surface normal vector, together with the depth-buffered image, for part-to-whole shape retrieval. In addition, we propose a weighted whole-to-whole re-ranking method taking advantage of global information based on the result of part-to-whole shape retrieval. Through experiments we demonstrate that our proposed method outperforms the previous methods with or without re-ranking.