Partial Sketch Research Articles

A Collaborative, Interactive and Context-Aware Drawing Agent for Co-Creative Design.

Recent advances in text-conditioned generative models have provided us with neural networks capable of creating images of astonishing quality, be they realistic, abstract, or even creative. These models have in common that (more or less explicitly) they all aim to produce a high-quality one-off output given certain conditions, and in that they are not well suited for a creative collaboration framework. Drawing on theories from cognitive science that model how professional designers and artists think, we argue how this setting differs from the former and introduce CICADA: a Collaborative, Interactive Context-Aware Drawing Agent. CICADA uses a vector-based synthesis-by-optimisation method to take a partial sketch (such as might be provided by a user) and develop it towards a goal by adding and/or sensibly modifying traces. Given that this topic has been scarcely explored, we also introduce a way to evaluate desired characteristics of a model in this context by means of proposing a diversity measure. CICADA is shown to produce sketches of quality comparable to a human user's, enhanced diversity and most importantly to be able to cope with change by continuing the sketch minding the user's contributions in a flexible manner.

HiSEG: Human assisted instance segmentation

Instance segmentation is a form of image detection which has a range of applications, such as object refinement, medical image analysis, and image/video editing, all of which demand a high degree of accuracy. However, this precision is often beyond the reach of what even state-of-the-art, fully automated instance segmentation algorithms can deliver. The performance gap becomes particularly prohibitive for small and complex objects. Practitioners typically resort to fully manual annotation, which can be a laborious process. In order to overcome this problem, we propose a novel approach to enable more precise predictions and generate higher-quality segmentation masks for high-curvature, complex and small-scale objects. Our human-assisted segmentation method, HiSEG, augments the existing Strong Mask R-CNN network to incorporate human-specified partial boundaries. We also present a dataset of hand-drawn partial object boundaries, which we refer to as “human attention maps”. In addition, the Partial Sketch Object Boundaries (PSOB) dataset contains hand-drawn partial object boundaries which represent curvatures of an object’s ground truth mask with several pixels. Through extensive evaluation using the PSOB dataset, we show that HiSEG outperforms state-of-the art methods such as Mask R-CNN, Strong Mask R-CNN, Mask2Former, and Segment Anything, achieving respective increases of +42.0, +34.9, +29.9, and +13.4 points in APMask metrics for these four models. We hope that our novel approach will set a baseline for future human-aided deep learning models by combining fully automated and interactive instance segmentation architectures.

Prior semantic-embedding representation learning for on-the-fly FG-SBIR

In fine-grained sketch-based image retrieval (FG-SBIR) framework, sketch drawing is a time-consuming and skill-intensive process that greatly restricts its practical application. Our study aims to enhance the early-stage retrieval efficiency by utilizing partial sketches with a minimum number of strokes in the on-the-fly FG-SBIR framework. Nevertheless, partial sketches with few strokes usually lack global information and consist only of sparse local details. This lack of detail results in ambiguous semantic content and indistinct differences among images, which consequently impairs early-stage retrieval. To acquire an efficient representation for these sketches, we propose a multi-granularity feature representation model that utilizes prior knowledge embedding to deal with the sketch drawing process. In the first stage,we design a triplet network to learn the joint a coarse representation embedding space that is common between the complete sketch and the image. In the second stage, We enhanced the semantic representation of sketches by utilizing prior knowledge, which aids in supplementing missing fine-grained features. This was achieved by formalizing the prior knowledge and integrating it into the feature vector obtained in the initial stage, thereby acquiring the final representation of a subset of sketches. Experiments conducted on two public datasets indicate that our method outperforms the state-of-the-art baseline during the early retrieval phase. In practical applications, our approach has also achieved good results.

Sketch2Photo: Synthesizing photo-realistic images from sketches via global contexts

Sketch-to-image synthesis aims to generate realistic images that match the input sketches or edge maps exactly. Most known sketch-to-image synthesis methods use various generative adversarial networks (GANs) that are trained with numerous pairs of sketches and real images. Because of the convolution locality, the low-level layers of the generators in these GANs lack global perception ability, causing feature maps derived from them easily to overlook global cues. Since the global receptive field is crucial for acquiring the non-local structures and features of sketches, the absence of global contexts will impact the generation of high-quality images. Some recent models turn to self-attention to construct global dependencies. However, they are not viable for large feature maps for the quadratic computational complexity concerning the size of feature maps. To address these problems, in this work, we propose Sketch2Photo — a new image synthesis approach that can capture global contexts as well as local features to generate photo-realistic images from weak or partial sketches or edge maps. We employ fast Fourier convolution (FFC) residual blocks to create global receptive fields in the bottom layers of the network and incorporate Swin Transformer block (STB) units to obtain long-range global contexts for large-size feature maps efficiently. We also present an improved spatial attention pooling (ISAP) module to relax the strict alignment requirements between incomplete sketches and generated images. Quantitative and qualitative experiments on multiple public datasets demonstrate the superiority of the proposed approach over many other sketch-to-image synthesis methods. The project code is available at https://github.com/hengliusky/Skecth2Photo.

Multi-granularity Association Learning for On-the-fly Fine-grained Sketch-based Image Retrieval

Fine-grained sketch-based image retrieval (FG-SBIR) addresses the problem of retrieving a specific photo from a given query sketch. However, its widespread applicability is limited because it is difficult for most people to draw a complete sketch, and the drawing process is often time consuming. In this study, we aim to retrieve the target photo from an partial sketch with the least number of strokes possible; the method is referred to as on-the-fly FG-SBIR (Bhunia et al., 2020), in which the retrieval begins after each stroke of the drawing. We consider that a significant correlation exists between these incomplete sketches in the sketch-drawing episodes of each photo. We propose a multi-granularity-association-learning method that further optimizes the embedding space of all incomplete sketches to learn an efficient joint-embedding space. Specifically, based on the integrity of the sketch, a complete sketch episode can be divided into several stages, each of which corresponds to a simple linear-mapping layer. Furthermore, our framework guides the vector space representation of the current sketch to approximate that with its later sketches. In this manner, the retrieval performance of a sketch with fewer strokes can approach that of a sketch with more strokes. We conducted experiments that included more realistic challenges, and our method achieved superior early-retrieval efficiency over the state-of-the-art methods and alternative baselines on two publicly available fine-grained sketch-retrieval datasets.

Introducing postqualitative inquiry in sport and exercise psychology

ABSTRACTIn recent years, qualitative research has gained popularity and legitimacy in sport and exercise psychology. However, this scientific discipline has not yet paid attention to postqualitative inquiry (PQI), despite the possibilities it offers for producing different knowledge and producing knowledge differently. The present article is the first attempt to rectify this lack of attention by offering a brief and partial sketch of PQI in the context of sport and exercise psychology. To start with, three of the basic propositions that enable PQI are described. These are: adopt a posthumanist view of ontology and the subject; engage with poststructuralism (necessarily) and new materialism (possibly); and think with concepts. Potential reasons for turning to PQI are then highlighted. Following from this, some perils and horizons for PQI are identified and discussed. The article concludes by presenting several reflections and recommendations to facilitate a progressive introduction of PQI in sport and exercise psychology.

Detailed Visualization of Aromaticity Using Isotropic Magnetic Shielding.

For many years, Clar's aromatic sextet theory has served as a qualitative method for assessing the aromatic character of polycyclic aromatic hydrocarbons. A new approach, based on the calculation of isotropic magnetic shielding (IMS) contour plots, is shown to provide a feature-rich picture of aromaticity that is both quantitative yet still easily interpreted. Chemists are visual creatures who are adept at discerning reactivity and chemical behavior from molecular structures. To quote Roald Hoffmann, "People like pictures. Chemists live off them." Thus, the detailed image analysis we present simultaneously provides quantitative assessment of electronic structure, which is still easy-to-understand through visual inspection, embedded in an aesthetically appealing and intuitive picture that draws the reader in. We provide novel computed IMS contour plots for a representative selection of aromatic molecules. Where Clar's static drawings capture only a partial sketch of the electronic properties of a molecule, IMS contour plots present a detailed, global landscape of a molecule that sums all possible resonance structures. This novel analysis allows us to correct certain drawbacks of Clar's analysis with respect to polycyclic aromatics and quantitatively assess the bonding and electronic structure of acene hydrocarbons.

Detailed Visualization of Aromaticity Using Isotropic Magnetic Shielding

AbstractFor many years, Clar's aromatic sextet theory has served as a qualitative method for assessing the aromatic character of polycyclic aromatic hydrocarbons. A new approach, based on the calculation of isotropic magnetic shielding (IMS) contour plots, is shown to provide a feature‐rich picture of aromaticity that is both quantitative yet still easily interpreted. Chemists are visual creatures who are adept at discerning reactivity and chemical behavior from molecular structures. To quote Roald Hoffmann, “People like pictures. Chemists live off them.” Thus, the detailed image analysis we present simultaneously provides quantitative assessment of electronic structure, which is still easy‐to‐understand through visual inspection, embedded in an aesthetically appealing and intuitive picture that draws the reader in. We provide novel computed IMS contour plots for a representative selection of aromatic molecules. Where Clar's static drawings capture only a partial sketch of the electronic properties of a molecule, IMS contour plots present a detailed, global landscape of a molecule that sums all possible resonance structures. This novel analysis allows us to correct certain drawbacks of Clar's analysis with respect to polycyclic aromatics and quantitatively assess the bonding and electronic structure of acene hydrocarbons.

DOXASTICISM: BELIEF AND THE INFORMATION-RESPONSIVENESS OF MIND

ABSTRACTThis paper concerns a problem that has received insufficient analysis in the philosophical literature so far: the conditions under which an information-bearing state – say a perception or recollection – yields belief. The paper distinguishes between belief and a psychological property easily conflated with belief, illustrates the tendency of philosophers to overlook this distinction, and offers a positive conception of the mind's information-responsiveness that requires far less belief-formation – and far less formation of other propositional attitudes – than has been commonly supposed to be produced by perception and other experiences. This conception is clarified by a partial sketch of the natural economy of mind. The paper then considers two important questions the conception raises. Does it force us to abandon the venerable belief-desire conception of intentional action, and does it require expanding the domain of intellectual responsibility and thereby our conception of epistemic virtue?

Robust flow-guided neural prediction for sketch-based freeform surface modeling

Sketching provides an intuitive user interface for communicating free form shapes. While human observers can easily envision the shapes they intend to communicate, replicating this process algorithmically requires resolving numerous ambiguities. Existing sketch-based modeling methods resolve these ambiguities by either relying on expensive user annotations or by restricting the modeled shapes to specific narrow categories. We present an approach for modeling generic freeform 3D surfaces from sparse, expressive 2D sketches that overcomes both limitations by incorporating convolution neural networks (CNN) into the sketch processing workflow. Given a 2D sketch of a 3D surface, we use CNNs to infer the depth and normal maps representing the surface. To combat ambiguity we introduce an intermediate CNN layer that models the dense curvature direction, or flow, field of the surface, and produce an additional output confidence map along with depth and normal. The flow field guides our subsequent surface reconstruction for improved regularity; the confidence map trained unsupervised measures ambiguity and provides a robust estimator for data fitting. To reduce ambiguities in input sketches users can refine their input by providing optional depth values at sparse points and curvature hints for strokes. Our CNN is trained on a large dataset generated by rendering sketches of various 3D shapes using non-photo-realistic line rendering (NPR) method that mimics human sketching of free-form shapes. We use the CNN model to process both single- and multi-view sketches. Using our multi-view framework users progressively complete the shape by sketching in different views, generating complete closed shapes. For each new view, the modeling is assisted by partial sketches and depth cues provided by surfaces generated in earlier views. The partial surfaces are fused into a complete shape using predicted confidence levels as weights. We validate our approach, compare it with previous methods and alternative structures, and evaluate its performance with various modeling tasks. The results demonstrate our method is a new approach for efficiently modeling freeform shapes with succinct but expressive 2D sketches.

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).

Le Fils and the Limits of Philosophical Ethics

Le Fils and the Limits of Philosophical Ethics Damian Cox (bio) Introduction This paper is a study in contrasts. In the first part, I describe one prominent set of approaches to representing the ethical: those of analytic philosophy and the experimental moral psychology inspired by it. I argue that what is missing in this approach is a perspicuous representation of the ethical. The term “perspicuous representation” is drawn from the work of Wittgenstein, where it means a way of representing phenomena that reveals the inner connections between their parts or aspects and makes apparent their meaning for us. Arriving at perspicuous representations is fundamental to Wittgenstein’s interpretative/philosophical methodology. In Philosophical Investigations he says, “The concept of a perspicuous representation is of fundamental significance for us. It earmarks the form of account we give, the way we look at things” (122). I use the term in a slightly broader way than this. I take it to indicate a kind of achievement: the Wittgensteinian achievement of elucidating the inner connections between aspects of a thing, but also a representation that captures some of its richness, complexity and ambiguity. The opposite of a perspicuous representation is a partial sketch that oversimplifies the phenomenon represented and gives unwarranted prominence to certain aspects of it over other equally, if not more, important aspects. I argue that what is missing in much contemporary philosophical ethics is a perspicuous representation of how ethics is experienced and the many and varied ways it enters into human affairs. This occurs in large part because of an unwarranted emphasis in contemporary philosophical ethics on moral judgment at the expense of moral experience. A perspicuous representation of the ethical must make lived ethical experience central; it must do justice to the complex phenomenology of ethical experience. Analytic philosophers and experimental moral psychologists tend to study the ethical in vitro; a perspicuous representation of the ethical needs it captured in vivo. In the second part, I contrast the analytic approach with that of film-philosophy. I examine the philosophical-ethical potential of cinema through Le Fils (2002), a film by Jean-Pierre and Luc Dardenne. I argue [End Page 84] that this film demonstrates the perspicuous representation of the ethical in a paradigmatic way. Analyzing the Ethical In order to study ethics philosophically or experimentally, one has to identify an object of study, an object amenable to analysis and experimental investigation. Moral judgment seems to be such a thing, and indeed, a preponderance of work in analytic ethics and experimental moral psychology is devoted to understanding the nature of moral judgment. To study moral judgment, it is necessary to examine exemplars of moral judgment. Two main kinds of moral judgment are studied: judgments of principle and judgments of cases. For example, Jeremy Stangroom runs a highly successful website of philosophy experiments, one of which investigates moral judgment by asking web-users to respond to propositions such as: Question 1: Torture, as a matter of principle, is always morally wrong. (59% of roughly 200,000 respondents say that it is; 41% say that it isn’t.) Question 2: The morality of an action is determined by whether, compared to the other available options, it maximizes the sum total of happiness of all the people affected by it. (57% of roughly 200,000 respondents disagree with this; 43% agree.) (“Should You Strangle”) Strangroom runs another experiment that deals with a wide range of simple cases, asking for moral judgment at every turn. Questions include: Question 1: You pass someone in the street who is in severe need and you are able to help them at little cost to yourself. Are you morally obliged to do so? (67% of 5000 respondents say that you are.) Question 8: You can save the lives of a thousand patients by cancelling one hundred operations that would have saved the lives of a hundred different patients. (58% of 5000 respondents say that it is permissible to do so.) Question 13: You see a charity advertisement in a newspaper about a person in severe need in India. There is no state welfare available to this person, but you can help them at little cost to yourself. You have...

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

AbstractWe 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.

Sketching reality

In this article, we introduce sketching reality , the process of converting a freehand sketch into a realistic-looking model. We apply this concept to architectural designs. As the sketch is being drawn, our system periodically interprets its 2.5D-geometry by identifying new junctions, edges, and faces, and then analyzing the extracted topology. The user can add detailed geometry and textures through sketches as well. This is possible through the use of databases that match partial sketches to models of detailed geometry and textures. The final product is a realistic texture-mapped 2.5D-model of the building. We show a variety of buildings that have been created using this system.

Philosophical Scrutiny of Evidence of Risks: From Bioethics to Bioevidence

We argue that a responsible analysis of today's evidence-based risk assessments and risk debates in biology demands a critical or metascientific scrutiny of the uncertainties, assumptions, and threats of error along the manifold steps in risk analysis. Without an accompanying methodological critique, neither sensitivity to social and ethical values, nor conceptual clarification alone, suffices. In this view, restricting the invitation for philosophical involvement to those wearing a “bioethicist” label precludes the vitally important role philosophers of science may be able to play as bioevidentialists. The goal of this paper is to give a brief and partial sketch of how a metascientific scrutiny of risk evidence might work.

Content-based image indexing and searching using Daubechies' wavelets

This paper describes WBIIS (Wavelet-Based Image Indexing and Searching), a new image indexing and retrieval algorithm with partial sketch image searching capability for large image databases. The algorithm characterizes the color variations over the spatial extent of the image in a manner that provides semantically meaningful image comparisons. The indexing algorithm applies a Daubechies' wavelet transform for each of the three opponent color components. The wavelet coefficients in the lowest few frequency bands, and their variances, are stored as feature vectors. To speed up retrieval, a two-step procedure is used that first does a crude selection based on the variances, and then refines the search by performing a feature vector match between the selected images and the query. For better accuracy in searching, two-level multiresolution matching may also be used. Masks are used for partial-sketch queries. This technique performs much better in capturing coherence of image, object granularity, local color/texture, and bias avoidance than traditional color layout algorithms. WBIIS is much faster and more accurate than traditional algorithms. When tested on a database of more than 10 000 general-purpose images, the best 100 matches were found in 3.3 seconds.

Aurora, Nemesis and Clio

This essay offers some preliminary and general considerations of big picture historiography of science, attempting an introductory specification of the topic by means of narratological analysis. It takes no strong, substantive position eitherpro or contrabig pictures themselves, preferring an approach which is more diagnostic and heuristic in nature. After considering what may be meant by a term such as ‘big picture’ and its cognates, it interrogates the kind of desire which could lie behind the wish expressed by the conference title ‘Getting the Big Picture’: namely, that a big picture may be worth getting. It proceeds by way of a limited enquiry into what seems to be felt as a relative absence of big picture works in contemporary historiography, criticizing one very general historicocultural thesis which accounts for such an absence, advancing instead evolving features of the professional history of science community over the last thirty years as reasons for this relative absence. Concludingly, it turns the issues raised thus far on their head, in some measure at least. In trying for a more precise specification of the contemporary historiographical formation, we will discover eventually a situation not so much of relative absence of big pictures, rather one where there exists both frame and title for the picture, together with some distinguished painters' names; but where the canvas is only minimally marked, a partial and shadowy sketch, stylistically disjoined. Although this sounds paradoxical, a concrete paradox is not intended. The existence of frame and title enclosing mainly empty canvas indicates only the limitations of the pictorial metaphor for describing complex and developing sets of historiographical practice. What is instanced concludingly is less a theoretical paradox than an intelligible sequence and form of development which issues in a potential problem of practice.

The Vienna stela of Meryre

The fragmentary stela of Meryre, presently in Vienna (no. 5814), is one of very few objects known from this Eighteenth Dynasty individual. This article presents two partial sketches of the stela found in a collection of the sketches and rubbings of the nineteenth-century traveller Paul Durand which is presently in Montreal. One allows us partially to reconstruct the missing fragment of the stela, and records of dates in the collection permit some educated guesses about the early modern history of the stela.

Some Comments on the Stevens Linear and Quadratic Programming Versions of von Thünen's Theory of Agricultural Land Usage

This paper examines the Stevens linear and quadratic programming formulations of von Thünen's analysis of agricultural land usage (Stevens, 1968). The first section contains a description of the Walras—Wald version of general economic equilibrium, plus a working definition of the expressions: general equilibrium sketch, paticularised general equilibrium sketch, and partial equilibrium sketch. [The author's distinction between a sketch and a model is explained in Macmillan (1978).] In section 2, von Thünen's assumptions, Stevens's (first) revised version of those assumptions, and Stevens's linear programming model are described. In section 3, the relationship between the Stevens linear programming model and the Walras—Wald model is examined. The fourth section contains a description of Stevens's approach to the relaxation of von Thünen's assumption of infinite demand elasticity, and a comparison of that approach with the so-called partial equilibrium approach to the same problem. It is claimed that this comparison is of some general, methodological interest. Section 5 contains the paper's conclusions.

SYSTEM ECONOMIC RESPONSE TO WATER QUANTITY AND QUALITY ‐ FUNDAMENTAL CONSIDERATIONS1

ABSTRACTThe relationship between water quantity, water quality, and system economic response to permutations of these variables on any given water use, and the allocation of water among competing uses is outlined by means of a conceptual model. The effect of the quantity‐quality variable mix on a given use is called the “intensive effect,” and the allocation mix on the total system is the “extensive effect.” The elements of the model are best described by the partial sketch of the flow diagram, outlined below in terms of symbols.