Alfredo Ferreira

A comparison of methods for sketch-based 3D shape retrieval

Sketch-based 3D shape retrieval has become an important research topic in content-based 3D object retrieval. To foster this research area, two Shape Retrieval Contest (SHREC) tracks on this topic have been organized by us in 2012 and 2013 based on a small-scale and large-scale benchmarks, respectively. Six and five (nine in total) distinct sketch-based 3D shape retrieval methods have competed each other in these two contests, respectively. To measure and compare the performance of the top participating and other existing promising sketch-based 3D shape retrieval methods and solicit the state-of-the-art approaches, we perform a more comprehensive comparison of fifteen best (four top participating algorithms and eleven additional state-of-the-art methods) retrieval methods by completing the evaluation of each method on both benchmarks. The benchmarks, results, and evaluation tools for the two tracks are publicly available on our websites [1,2].

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.

Content-based retrieval of technical drawings

This paper presents a new approach to classify, index and retrieve technical drawings by content. Our work uses spatial relationships, shape geometry and high-dimensional indexing mechanisms to retrieve complex drawings from CAD databases. This contrasts with conventional approaches which use mostly textual metadata. Creative designers and draftspeople often re-use data from previous projects, publications and libraries of ready-to-use components. Usually, retrieving these drawings is a slow, complex and error-prone endeavour. Unfortunately, the widespread use of CAD systems, while making it easier to create drawings, exacerbates this problem, insofar as the number of projects grows enormously, without providing adequate searching mechanisms to support retrieving these documents. We describe an approach that supports automatic indexation of technical drawing databases through drawing simplification, feature extraction and efficient algorithms to index large amounts of data. We describe in detail our classification process and present results from usability tests on our prototype.

Sketch-based retrieval of complex drawings using hierarchical topology and geometry

Due to the proliferation of drafting packages, there are a lot of vector drawings available for people to integrate into documents. Moreover, creative designers and drafts-people often reuse data from previous projects and libraries of ready-to-use components. Usually, retrieving these drawings is a slow, complex and error-prone endeavor. While text-driven attempts at classifying image data have been recently supplemented with query-by-image content, these work only for bitmap-type data and cannot handle vectorial information. Furthermore, they are not very good at retrieving partial information, which makes it difficult to search complex documents. Here we present a new approach to allow efficient retrieval of complex vector drawings by content using simple sketches as queries. Our work uses a new hierarchical topology description mechanism, which allows comparing complex drawings to simple queries. In particular, we produce a multilevel description of drawings, from the topology graph, using different levels of detail and subparts of the information. We also show that the graph spectrum is stable and reliable for use as a topology description. Finally, experimental tests show that our approach is good at retrieving complex drawings from two different application domains, CAD and clip-art figures.

Towards 3D modeling using sketches and retrieval

Retrieving 2D and 3D drawings by content is not an easy task. Automatic feature extraction, indexing and matching are some of the problems raised by these approaches. We have developed a generic method to classify, index and retrieve drawings using sketches, based on spatial relationships, shape geometry and high-dimensional indexing mechanisms. This approach has been applied with success to retrieving clip-art and complex technical drawings from large databases. In this paper we give a brief overview of our approach for content-based retrieval and describe two prototypes for retrieving 2D drawings. We also present a preliminary study that combines retrieval of 3D objects and expectation lists to define a new interaction paradigm based on suggestions. 3D objects are described using their face and edge graphs, which are then mapped into multidimensional descriptors through graph spectra. Preliminary results show that the combination of these two descriptors (faces and edges) provide a good novel method to describe and retrieve similar 3D objects. Finally, rather than developing a system to specify and display 3D queries and results, we integrated the retrieval system into a 3D modeling tool, through the use of expectation lists. This way, results from the query are presented as suggestions to the user, in what constitutes a new interaction paradigm, which is more flexible then present approaches.

Mid-air interactions above stereoscopic interactive tables

Stereoscopic tabletops offer unique visualization capabilities, enabling users to perceive virtual objects as if they were lying above the surface. While allowing virtual objects to coexist with user actions in the physical world, interaction with these virtual objects above the surface presents interesting challenges. In this paper, we aim to understand which approaches to 3D virtual object manipulations are suited to this scenario. To this end, we implemented five different techniques based on the literature. Four are mid-air techniques, while the remainder relies on multi-touch gestures, which act as a baseline. Our setup combines affordable non-intrusive tracking technologies with a multi-touch stereo tabletop, providing head and hands tracking, to improve both depth perception and seamless interactions above the table. We conducted a user evaluation to find out which technique appealed most to participants. Results suggest that mid-air interactions, combining direct manipulation with six degrees of freedom for the dominant hand, are both more satisfying and efficient than the alternatives tested.

Towards a serious game for portuguese learning

Language learning resources are constantly evolving alongside technology. One of such resources is REAP.PT, a system which aims to raise users proficiency in the Portuguese language in an interactive manner. Its current features include text-based exercises. This paper describes the evolution of REAP.PT aiming on locative prepositions used to describe the spatial position between objects. In this new REAP.PT, exercises take place in a 3D environment, and are complemented with gaming aspects to make them more appealing to students. The game scenario is an office, where each room contains different exercises. Completing exercises awards the student with points that unlock harder rooms. This provides the student with a challenge and a sense of progression. We believe that with these gaming aspects, students will have increased motivation to complete exercises.

Using sketches and retrieval to create LEGO models

In this paper we describe a system to create LEGO models using sketches. Although there are a few applications to create LEGO models, they are difficult to use, mainly due to the searching and manipulation mechanisms that they (do not) offer. Here, we propose a sketch based approach, where users can easily insert parts, by specifying their dimensions through sketches and the system suggests a list of possible parts. To help with the modeling and the manipulation we also developed a constraint based mechanism, which keeps parts connected, performs snapto- grid and detects collisions. Experimental tests with users revealed that our approach is easier and faster to use than a conventional application, such as LeoCAD.

Effects of speed and transitions on target-based travel techniques

Travel on Virtual Environments is the simple action where a user moves from a starting point A to a target point B. Choosing an incorrect type of technique could compromise the Virtual Reality experience and cause side effects such as spatial disorientation, fatigue and cybersickness. The design of effective travelling techniques demands to be as natural as possible, thus real walking techniques presents better results, despite their physical limitations. Approaches to surpass these limitations employ techniques that provide an indirect travel metaphor such as point-steering and target-based. In fact, target-based techniques evince a reduction in fatigue and cybersickness against the point-steering techniques, even though providing less control. In this paper we investigate further effects of speed and transition on target-based techniques on factors such as comfort and cybersickness using a Head-Mounted Display setup.

Collaboration Meets Interactive Surfaces: Walls, Tables, Tablets, and Phones (CMIS)

This workshop proposes to bring together researchers who are interested in improving collaborative experiences through the use of multi-sized interaction surfaces, ranging from large-scale walls, to tables, tablets and phones. The opportunities for innovation exist, but the tabletop community has not still completely addressed the problem of bringing effective collaboration activities using multiple interactive surfaces, especially in complex work domains. Of particular interest is the potential synergy that one can obtain by effectively combining different-sized surfaces.