Query Sketch Research Articles

Data compensation and feature fusion for sketch based person retrieval

Sketch re-identification (Re-ID) aims to retrieve pedestrian photo in the gallery dataset by a query sketch drawn by professionals. The sketch Re-ID task has not been adequately studied because collecting such sketches is difficult and expensive. In addition, the significant modality difference between sketches and images makes extracting the discriminative feature information difficult. To address above issues, we introduce a novel sketch-style pedestrian dataset named Pseudo-Sketch dataset. Our proposed dataset maximizes the utilization of the existing person dataset resources and is freely available, thus effectively reducing the expenses associated with the training and deployment phases. Furthermore, to mitigate the modality gap between sketches and visible images, a cross-modal feature fusion network is proposed that incorporates information from each modality. Experiment results show that the proposed Pseudo-Sketch dataset can effectively complement the real sketch dataset, and the proposed network obtains competitive results than SOTA methods. The dataset will be released later.

SketchCleanGAN: A generative network to enhance and correct query sketches for improving 3D CAD model retrieval systems

Given an input query, a search and retrieval system fetches relevant information from a dataset. In the Engineering domain, such a system is beneficial for tasks such as design reuse. A two-dimensional (2D) sketch is more conducive for an end user to give as a query than a three-dimensional (3D) object. Such query sketches, nevertheless, will inevitably contain defects like incomplete lines, mesh lines, overdrawn areas, missing areas, etc. Since a retrieval system’s results are only as good as the query, it is necessary to improve the query sketches.In this paper, the problem of transforming a defective CAD sketch into a defect-free sketch is addressed using Generative Adversarial Networks (GANs), which, to the best of our knowledge, has not been investigated before. We first create a dataset of 534 hand-drawn sketches by tracing the boundaries of images of CAD models. We then pair the corrected sketches with their corresponding defective sketches and use them for training a C-WGAN (Conditional Wasserstein Generative Adversarial Network), called SketchCleanGAN. We model the transformation from defective to defect-free sketch as a factorization of the defective input sketch and then translate it to the space of defect-free sketch. We propose a three-branch strategy to this problem. Ablation studies and comparisons with other state-of-the-art techniques demonstrate the efficacy of the proposed technique. Additionally, we also contribute to a dataset of around 58000 improved sketches using the proposed framework.

Zero-Shot Sketch-Based Remote-Sensing Image Retrieval Based on Multi-Level and Attention-Guided Tokenization

Effectively and efficiently retrieving images from remote-sensing databases is a critical challenge in the realm of remote-sensing big data. Utilizing hand-drawn sketches as retrieval inputs offers intuitive and user-friendly advantages, yet the potential of multi-level feature integration from sketches remains underexplored, leading to suboptimal retrieval performance. To address this gap, our study introduces a novel zero-shot, sketch-based retrieval method for remote-sensing images, leveraging multi-level feature extraction, self-attention-guided tokenization and filtering, and cross-modality attention update. This approach employs only vision information and does not require semantic knowledge concerning the sketch and image. It starts by employing multi-level self-attention guided feature extraction to tokenize the query sketches, as well as self-attention feature extraction to tokenize the candidate images. It then employs cross-attention mechanisms to establish token correspondence between these two modalities, facilitating the computation of sketch-to-image similarity. Our method significantly outperforms existing sketch-based remote-sensing image retrieval techniques, as evidenced by tests on multiple datasets. Notably, it also exhibits robust zero-shot learning capabilities in handling unseen categories and strong domain adaptation capabilities in handling unseen novel remote-sensing data. The method’s scalability can be further enhanced by the pre-calculation of retrieval tokens for all candidate images in a database. This research underscores the significant potential of multi-level, attention-guided tokenization in cross-modal remote-sensing image retrieval. For broader accessibility and research facilitation, we have made the code and dataset used in this study publicly available online.

Zero-Shot Sketch-Based Image Retrieval Using StyleGen and Stacked Siamese Neural Networks.

Sketch-based image retrieval (SBIR) refers to a sub-class of content-based image retrieval problems where the input queries are ambiguous sketches and the retrieval repository is a database of natural images. In the zero-shot setup of SBIR, the query sketches are drawn from classes that do not match any of those that were used in model building. The SBIR task is extremely challenging as it is a cross-domain retrieval problem, unlike content-based image retrieval problems because sketches and images have a huge domain gap. In this work, we propose an elegant retrieval methodology, StyleGen, for generating fake candidate images that match the domain of the repository images, thus reducing the domain gap for retrieval tasks. The retrieval methodology makes use of a two-stage neural network architecture known as the stacked Siamese network, which is known to provide outstanding retrieval performance without losing the generalizability of the approach. Experimental studies on the image sketch datasets TU-Berlin Extended and Sketchy Extended, evaluated using the mean average precision (mAP) metric, demonstrate a marked performance improvement compared to the current state-of-the-art approaches in the domain.

Zero-shot sketch-based image retrieval via adaptive relation-aware metric learning

Retrieving natural images with the query sketches under the zero-shot scenario is known as zero-shot sketch-based image retrieval (ZS-SBIR). Most of the best-performing methods adapt the triplet loss to learn projections that map natural images and sketches to a latent embedding space. They nevertheless neglect the modality gap between the hand-drawn sketches and the photos and consider no difference between any two incorrect classes, which limits their performance in real use cases. Towards this end, we put forward a simple and effective model, which adopts relation-aware metric learning to suppress the modality gap between the sketches and the photos. We also propose an adaptive margin that utilizes each anchor in embedding space to improve clustering ability in metric learning. Extensive experiments on the Sketchy and TU-Berlin datasets show the dominant position of our proposed model over SOTA competitors.

Retrieval-Specific View Learning for Sketch-to-Shape Retrieval

Sketch-based 3D shape retrieval (SBSR) can be approached by learning domain-invariant descriptors or ranking metrics from sketches and 2D view images of 3D shapes rendered through numerous viewpoints. However, determining the most appropriate viewpoints that convey discriminative geometric features to benefit the task of SBSR became an essential yet not fully explored area. Existing works extract 3D features from multi-view images observed through pre-defined viewpoints to match 2D sketches. Those methods, however, fail to dynamically select viewpoints by considering the SBSR task. In this work, we introduce a fully differentiable viewpoint learning paradigm driven by the downstream SBSR task, which supports the task-aware and sketch-dependent dynamic viewpoint determination process. We naturally integrate this task-specific and sketch-dependent viewpoint learning process into a meta-learning framework to develop a novel Dynamic Viewer (DV) module for SBSR. DV module comprises a Meta View Learner (MVL) block and a View Generator (VG) block. Specifically, as the first part of the DV module, the MVL block learns to initiate the necessary network parameters of the VG block. Then, the VG block that serves as the second part learns the best viewpoints to render 2D images. To learn the optimal viewpoints for SBSR, we further introduce a view mining loss that aims to maximize the similarity of feature-level information among rendered 2D views and the query sketch. Further, we adopt a variational autoencoder (VAE) to retrieve 3D shapes by setting the newly rendered images and query sketch as inputs. As evidenced by the comprehensive experimental results conducted on popular SBSR datasets, the proposed framework has been demonstrated to outperform recent methods in both category-level sketch-based and fine-grained SBSR.

SketchANIMAR: Sketch-based 3D animal fine-grained retrieval

The retrieval of 3D objects has gained significant importance in recent years due to its broad range of applications in computer vision, computer graphics, virtual reality, and augmented reality. However, the retrieval of 3D objects presents significant challenges due to the intricate nature of 3D models, which can vary in shape, size, and texture, and have numerous polygons and vertices. To this end, we introduce a novel SHREC challenge track that focuses on retrieving relevant 3D animal models from a dataset using sketch queries and expedites accessing 3D models through available sketches. Furthermore, a new dataset named ANIMAR was constructed in this study, comprising a collection of 711 unique 3D animal models and 140 corresponding sketch queries. Our contest requires participants to retrieve 3D models based on complex and detailed sketches. We receive satisfactory results from eight teams and 204 runs. Although further improvement is necessary, the proposed task has the potential to incentivize additional research in the domain of 3D object retrieval, potentially yielding benefits for a wide range of applications. We also provide insights into potential areas of future research, such as improving techniques for feature extraction and matching and creating more diverse datasets to evaluate retrieval performance.

TextANIMAR: Text-based 3D animal fine-grained retrieval

3D object retrieval is an important yet challenging task that has drawn more and more attention in recent years. While existing approaches have made strides in addressing this issue, they are often limited to restricted settings such as image and sketch queries, which are often unfriendly interactions for common users. In order to overcome these limitations, this paper presents a novel SHREC challenge track focusing on text-based fine-grained retrieval of 3D animal models. Unlike previous SHREC challenge tracks, the proposed task is considerably more challenging, requiring participants to develop innovative approaches to tackle the problem of text-based retrieval. Despite the increased difficulty, we believe this task can potentially drive useful applications in practice and facilitate more intuitive interactions with 3D objects. Five groups participated in our competition, submitting a total of 114 runs. While the results obtained in our competition are satisfactory, we note that the challenges presented by this task are far from fully solved. As such, we provide insights into potential areas for future research and improvements. We believe we can help push the boundaries of 3D object retrieval and facilitate more user-friendly interactions via vision-language technologies.

SketchCADGAN: A generative approach for completing partially drawn query sketches of engineering shapes to enhance retrieval system performance

Retrieval systems are commonly used to find relevant data in large datasets. In engineering, these systems are useful for locating specific engineering shapes in a large dataset of engineering components. When end users want to search for a shape, they prefer a two-dimensional (2D) sketch over a three-dimensional (3D) object. However, users lacking domain knowledge may struggle to generate a complete query sketch and provide a partially completed sketch instead. Retrieving relevant information from partially drawn sketches is difficult because they may have missing edges, partially drawn circles, holes, ovals, etc. Most retrieval systems compare the similarity between the query and items in the database, so incomplete sketches may be ineffective in finding the relevant information.To address this problem with incomplete sketches, we propose a new generative adversarial network called SketchCADGAN. This network uses a two-stage cascaded architecture, with the first network attempting to predict a CAD model image from an incomplete sketch and the second network using the CAD model image to predict a completed sketch. Both networks are trained together adversarially. Our approach is proven more effective than other advanced techniques through qualitative and quantitative comparisons. Furthermore, we present the results of the retrieval system using both partially drawn and completed sketches, and demonstrate that incorporating completed sketches from the suggested cascaded GAN architecture results in improved retrieval performance.

Scene-Level Sketch-Based Image Retrieval with Minimal Pairwise Supervision

The sketch-based image retrieval (SBIR) task has long been researched at the instance level, where both query sketches and candidate images are assumed to contain only one dominant object. This strong assumption constrains its application, especially with the increasingly popular intelligent terminals and human-computer interaction technology. In this work, a more general scene-level SBIR task is explored, where sketches and images can both contain multiple object instances. The new general task is extremely challenging due to several factors: (i) scene-level SBIR inherently shares sketch-specific difficulties with instance-level SBIR (e.g., sparsity, abstractness, and diversity), (ii) the cross-modal similarity is measured between two partially aligned domains (i.e., not all objects in images are drawn in scene sketches), and (iii) besides instance-level visual similarity, a more complex multi-dimensional scene-level feature matching problem is imposed (including appearance, semantics, layout, etc.). Addressing these challenges, a novel Conditional Graph Autoencoder model is proposed to deal with scene-level sketch-images retrieval. More importantly, the model can be trained with only pairwise supervision, which distinguishes our study from others in that elaborate instance-level annotations (for example, bounding boxes) are no longer required. Extensive experiments confirm the ability of our model to robustly retrieve multiple related objects at the scene level and exhibit superior performance beyond strong competitors.

A novel sketch based face recognition in unconstrained video for criminal investigation

Face recognition in video surveillance helps to identify an individual by comparing facial features of given photograph or sketch with a video for criminal investigations. Generally, face sketch is used by the police when suspect’s photo is not available. Manual matching of facial sketch with suspect’s image in a long video is tedious and time-consuming task. To overcome these drawbacks, this paper proposes an accurate face recognition technique to recognize a person based on his sketch in an unconstrained video surveillance. In the proposed method, surveillance video and sketch of suspect is taken as an input. Firstly, input video is converted into frames and summarized using the proposed quality indexed three step cross search algorithm. Next, faces are detected by proposed modified Viola-Jones algorithm. Then, necessary features are selected using the proposed salp-cat optimization algorithm. Finally, these features are fused with scale-invariant feature transform (SIFT) features and Euclidean distance is computed between feature vectors of sketch and each face in a video. Face from the video having lowest Euclidean distance with query sketch is considered as suspect’s face. The proposed method’s performance is analyzed on Chokepoint dataset and the system works efficiently with 89.02% of precision, 91.25% of recall and 90.13% of F-measure.

Fine-Grained Video Retrieval With Scene Sketches.

Benefiting from the intuitiveness and naturalness of sketch interaction, sketch-based video retrieval (SBVR) has received considerable attention in the video retrieval research area. However, most existing SBVR research still lacks the capability of accurate video retrieval with fine-grained scene content. To address this problem, in this paper we investigate a new task, which focuses on retrieving the target video by utilizing a fine-grained storyboard sketch depicting the scene layout and major foreground instances' visual characteristics (e.g., appearance, size, pose, etc.) of video; we call such a task "fine-grained scene-level SBVR". The most challenging issue in this task is how to perform scene-level cross-modal alignment between sketch and video. Our solution consists of two parts. First, we construct a scene-level sketch-video dataset called SketchVideo, in which sketch-video pairs are provided and each pair contains a clip-level storyboard sketch and several keyframe sketches (corresponding to video frames). Second, we propose a novel deep learning architecture called Sketch Query Graph Convolutional Network (SQ-GCN). In SQ-GCN, we first adaptively sample the video frames to improve video encoding efficiency, and then construct appearance and category graphs to jointly model visual and semantic alignment between sketch and video. Experiments show that our fine-grained scene-level SBVR framework with SQ-GCN architecture outperforms the state-of-the-art fine-grained retrieval methods. The SketchVideo dataset and SQ-GCN code are available in the project webpage https://iscas-mmsketch.github.io/FG-SL-SBVR/.

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.

SketchCleanNet — A deep learning approach to the enhancement and correction of query sketches for a 3D CAD model retrieval system

Search and retrieval remains a major research topic in several domains, including computer graphics, computer vision, engineering design, etc. A search engine requires primarily an input search query and a database of items to search from. In engineering, which is the primary context of this paper, the database consists of 3D CAD models, such as washers, pistons, connecting rods, etc. A query from a user is typically in the form of a sketch, which attempts to capture the details of a 3D model. However, sketches have certain typical defects such as gaps, over-drawn portions (multi-strokes), etc. Since the retrieved results are only as good as the input query, sketches need cleaning-up and enhancement for better retrieval results.In this paper, a deep learning approach is proposed to improve or clean the query sketches. Initially, sketches from various categories are analysed in order to understand the many possible defects that may occur. A dataset of cleaned-up or enhanced query sketches is then created based on an understanding of these defects. Consequently, an end-to-end training of a deep neural network is carried out in order to provide a mapping between the defective and the clean sketches. This network takes the defective query sketch as the input and generates a clean or an enhanced query sketch. Qualitative and quantitative comparisons of the proposed approach with other state-of-the-art techniques show that the proposed approach is effective. The results of the search engine are reported using both the defective and enhanced query sketches, and it is shown that using the enhanced query sketches from the developed approach yields improved search results.

Cohesion Intensive Hash Code Book Coconstruction for Efficiently Localizing Sketch Depicted Scenes

We investigate the problem of efficiently localizing sketch depicted scenes in a remote sensing image dataset. We pose the problem as that of remote sensing image retrieval with sketch queries and explore the use of hashing techniques to achieve efficient retrieval. Given two training datasets of sketches and remote sensing images that have a common set of class labels, we develop a hashing strategy that coconstructs two hash code books for the sketches and the remote sensing images separately. The hash code book coconstruction strategy encourages hash codes for the sketches and remote sensing images from different classes to be far away from one another and those from the same class to be close. This property is maintained by two cohesion intensive cues: 1) an interclass pairwise disperse cue (InterPDC) and 2) an intraclass pairwise balance cue (IntraPBC). We use the two coconstructed hash code books for training two linear mapping models that generate hash codes for sketches and remote sensing images separately. Sorting the Hamming distance between the sketch hash codes and the remote sensing image hash codes renders efficient remote sensing image retrieval with sketch queries. This enables localizing the sketch depicted scenes in the remote sensing image dataset. In addition, our method can also be used for fast localizing sketch depicted scenes in a remote sensing image of large size. Extensive experiments on public datasets validate the effectiveness and efficiency of our method.

SceneSketcher-v2: Fine-Grained Scene-Level Sketch-Based Image Retrieval Using Adaptive GCNs.

Sketch-based image retrieval (SBIR) is a long-standing research topic in computer vision. Existing methods mainly focus on category-level or instance-level image retrieval. This paper investigates the fine-grained scene-level SBIR problem where a free-hand sketch depicting a scene is used to retrieve desired images. This problem is useful yet challenging mainly because of two entangled facts: 1) achieving an effective representation of the input query data and scene-level images is difficult as it requires to model the information across multiple modalities such as object layout, relative size and visual appearances, and 2) there is a great domain gap between the query sketch input and target images. We present SceneSketcher-v2, a Graph Convolutional Network (GCN) based architecture to address these challenges. SceneSketcher-v2 employs a carefully designed graph convolution network to fuse the multi-modality information in the query sketch and target images and uses a triplet training process and end-to-end training manner to alleviate the domain gap. Extensive experiments demonstrate SceneSketcher-v2 outperforms state-of-the-art scene-level SBIR models with a significant margin.

Augmented Multimodality Fusion for Generalized Zero-Shot Sketch-Based Visual Retrieval.

Zero-shot sketch-based image retrieval (ZS-SBIR) has attracted great attention recently, due to the potential application of sketch-based retrieval under zero-shot scenarios, where the categories of query sketches and gallery photos are not observed in the training stage. However, it is still under insufficient exploration for the general and practical scenario when the query sketches and gallery photos contain both seen and unseen categories. Such a problem is defined as generalized zero-shot sketch-based image retrieval (GZS-SBIR), which is the focus of this work. To this end, we propose a novel Augmented Multi-modality Fusion (AMF) framework to generalize seen concepts to unobserved ones efficiently. Specifically, a novel knowledge discovery module named cross-domain augmentation is designed in both visual and semantic space to mimic novel knowledge unseen from the training stage, which is the key to handling the GZS-SBIR challenge. Moreover, a triplet domain alignment module is proposed to couple the cross-domain distribution between photo and sketch in visual space. To enhance the robustness of our model, we explore embedding propagation to refine both visual and semantic features by removing undesired noise. Eventually, visual-semantic fusion representations are concatenated for further domain discrimination and task-specific recognition, which tend to trigger the cross-domain alignment in both visual and semantic feature space. Experimental evaluations are conducted on popular ZS-SBIR benchmarks as well as a new evaluation protocol designed for GZS-SBIR from DomainNet dataset with more diverse sub-domains, and the promising results demonstrate the superiority of the proposed solution over other baselines. The source code is available at https://github.com/scottjingtt/AMF_GZS_SBIR.git.

REBOR: A new sketch-based 3d object retrieval framework using retina inspired features

With the rapid development of data science and modeling engineering, the capacity of cyberspace has significantly expanded which enables the online storage of increasing number of 3D models. Hence, the development of effective and efficient approaches to search 3D models is becoming increasingly important and urgent. In this paper, we propose a new sketch-based 3D retrieval framework named REBOR under the inspiration of retina which is not only consistent with human perception sensitivity but also simplifies the requirement of retrieval query by enabling hand-drawn sketch. The feature extraction process incorporates human visual system by simulating the ganglion perceptive mechanism in retina. Support Vector Machine is used to classify the query sketches and is further optimized by means of an global optimization algorithm so as to acquire optimal results automatically. Experiments are done on the database generated by ourselves with 15 categories of 3D objects, and the results indicate the effectiveness of REBOR in terms of retrieval accuracy.

Toward Fine-Grained Sketch-Based 3D Shape Retrieval.

In this paper we study, for the first time, the problem of fine-grained sketch-based 3D shape retrieval. We advocate the use of sketches as a fine-grained input modality to retrieve 3D shapes at instance-level - e.g., given a sketch of a chair, we set out to retrieve a specific chair from a gallery of all chairs. Fine-grained sketch-based 3D shape retrieval (FG-SBSR) has not been possible till now due to a lack of datasets that exhibit one-to-one sketch-3D correspondences. The first key contribution of this paper is two new datasets, consisting a total of 4,680 sketch-3D pairings from two object categories. Even with the datasets, FG-SBSR is still highly challenging because (i) the inherent domain gap between 2D sketch and 3D shape is large, and (ii) retrieval needs to be conducted at the instance level instead of the coarse category level matching as in traditional SBSR. Thus, the second contribution of the paper is the first cross-modal deep embedding model for FG-SBSR, which specifically tackles the unique challenges presented by this new problem. Core to the deep embedding model is a novel cross-modal view attention module which automatically computes the optimal combination of 2D projections of a 3D shape given a query sketch.

Sketch Fewer to Recognize More by Learning a Co-Regularized Sparse Representation

Categorizing free-hand human sketches has profound implications in applications such as human computer interaction and image retrieval. The task is non-trivial due to the iconic nature of sketches, signified by large variances in both appearance and structure when compared with photographs. Despite recent advances made by deep learning methods, the requirement of a large training set is commonly imposed making them impractical for real-world applications where training sketches are cumbersome to obtain - sketches have to be hand-drawn one by one other than crawled freely on the Internet. In this work, we aim to delve further into the data scarcity problem of sketch-related research, by proposing a few-shot sketch classification framework. The model is based on a co-regularized embedding algorithm where common/shareable parts of learned human sketches are exploited, thereby can embed query sketch into a co-regularized sparse representation space for few-shot classification. A new dataset of 8,000 part-level annotated sketches of 100 categories is also proposed to facilitate future research. Experiment shows that our approach can achieve an 5-way one-shot classification accuracy of 85%, and 20-way one-shot at 51%.