Search

Pose transfer of human videos aims to generate a high fidelity video of a target person imitating actions of a source person. A few studies have made great progress either through image translation with deep latent features or neural rendering with explicit 3D features. However, both of them rely on large amounts of training data to generate realistic results, and the performance degrades on more accessible internet videos due to insufficient training frames. In this paper, we demonstrate that the dynamic details can be preserved even trained from short monocular videos. Overall, we propose a neural video rendering framework coupled with an image-translation-based dynamic details generation network (D2G-Net), which fully utilizes both the stability of explicit 3D features and the capacity of learning components. To be specific, a novel texture representation is presented to encode both the static and pose-varying appearance characteristics, which is then mapped to the image space and rendered as a detail-rich frame in the neural rendering stage. Moreover, we introduce a concise temporal loss in the training stage to suppress the detail flickering that is made more visible due to high-quality dynamic details generated by our method. Through extensive comparisons, we demonstrate that our neural human video renderer is capable of achieving both clearer dynamic details and more robust performance even on accessible short videos with only 2k - 4k frames., Video link: https://www.bilibili.com/video/BV1y64y1C7ge/

Face portrait line drawing is a unique style of art which is highly abstract and expressive. However, due to its high semantic constraints, many existing methods learn to generate portrait drawings using paired training data, which is costly and time-consuming to obtain. In this paper, we propose a novel method to automatically transform face photos to portrait drawings using unpaired training data with two new features; i.e., our method can (1) learn to generate high quality portrait drawings in multiple styles using a single network and (2) generate portrait drawings in a "new style" unseen in the training data. To achieve these benefits, we (1) propose a novel quality metric for portrait drawings which is learned from human perception, and (2) introduce a quality loss to guide the network toward generating better looking portrait drawings. We observe that existing unpaired translation methods such as CycleGAN tend to embed invisible reconstruction information indiscriminately in the whole drawings due to significant information imbalance between the photo and portrait drawing domains, which leads to important facial features missing. To address this problem, we propose a novel asymmetric cycle mapping that enforces the reconstruction information to be visible and only embedded in the selected facial regions. Along with localized discriminators for important facial regions, our method well preserves all important facial features in the generated drawings. Generator dissection further explains that our model learns to incorporate face semantic information during drawing generation. Extensive experiments including a user study show that our model outperforms state-of-the-art methods., Accepted by IEEE Transactions on Pattern Analysis and Machine Intelligence, https://doi.org/10.1109/TPAMI.2022.3147570, code: https://github.com/yiranran/QMUPD

Realistic speech-driven 3D facial animation is a challenging problem due to the complex relationship between speech and face. In this paper, we propose a deep architecture, called Geometry-guided Dense Perspective Network (GDPnet), to achieve speaker-independent realistic 3D facial animation. The encoder is designed with dense connections to strengthen feature propagation and encourage the re-use of audio features, and the decoder is integrated with an attention mechanism to adaptively recalibrate point-wise feature responses by explicitly modeling interdependencies between different neuron units. We also introduce a non-linear face reconstruction representation as a guidance of latent space to obtain more accurate deformation, which helps solve the geometry-related deformation and is good for generalization across subjects. Huber and HSIC (Hilbert-Schmidt Independence Criterion) constraints are adopted to promote the robustness of our model and to better exploit the non-linear and high-order correlations. Experimental results on the public dataset and real scanned dataset validate the superiority of our proposed GDPnet compared with state-of-the-art model. The code is available for research purposes at http://cic.tju.edu.cn/faculty/likun/projects/GDPnet.

Convolutional Neural Networks (CNNs) can reveal local variation details and multi-scale spatial context in images via low-to-high stages of feature expression; effective fusion of these raw features is key to Semantic Edge Detection (SED). The methods available in the field generally fuse features across stages in a position-aligned mode, which cannot satisfy the requirements of diverse semantic context in categorizing different pixels. In this paper, we propose a deep framework for SED, the core of which is a new multi-stage feature fusion structure, called All-HiS-In ACA (All-Higher-Stages-In Adaptive Context Aggregation). All-HiS-In ACA can adaptively select semantic context from all higher-stages for detailed features via a cross-stage self-attention paradigm, and thus can obtain fused features with high-resolution details for edge localization and rich semantics for edge categorization. In addition, we develop a non-parametric Inter-layer Complementary Enhancement (ICE) module to supplement clues at each stage with their counterparts in adjacent stages. The ICE-enhanced multi-stage features are then fed into the All-HiS-In ACA module. We also construct an Object-level Semantic Integration (OSI) module to further refine the fused features by enforcing the consistency of the features within the same object. Extensive experiments demonstrate the superior performance of the proposed method over state-of-the-art works.

Cartoon is a common form of art in our daily life and automatic generation of cartoon images from photos is highly desirable. However, state-of-the-art single-style methods can only generate one style of cartoon images from photos and existing multi-style image style transfer methods still struggle to produce high-quality cartoon images due to their highly simplified and abstract nature. In this article, we propose a novel multi-style generative adversarial network (GAN) architecture, called MS-CartoonGAN, which can transform photos into multiple cartoon styles. MS-CartoonGAN uses only unpaired photos and cartoon images of multiple styles for training. To achieve this, we propose to use (1) a hierarchical semantic loss with sparse regularization to retain semantic content and recover flat shading in different abstract levels, (2) a new edge-promoting adversarial loss for producing fine edges, and (3) a style loss to enhance the difference between output cartoon styles and make training process more stable. We also develop a multi-domain architecture, where the generator consists of a shared encoder and multiple decoders for different cartoon styles, along with multiple discriminators for individual styles. By observing that cartoon images drawn by different artists have their unique styles while sharing some common characteristics, our shared network architecture exploits the common characteristics of cartoon styles, achieving better cartoonization and being more efficient than single-style cartoonization. We show that our multi-domain architecture can theoretically guarantee to output desired multiple cartoon styles. Through extensive experiments including a user study, we demonstrate the superiority of the proposed method, outperforming state-of-the-art single-style and multi-style image style transfer methods.

Spatially localized deformation components are very useful for shape analysis and synthesis in 3D geometry processing. Several methods have recently been developed, with an aim to extract intuitive and interpretable deformation components. However, these techniques suffer from fundamental limitations especially for meshes with noise or large-scale nonlinear deformations, and may not always be able to identify important deformation components. In this paper we propose a mesh-based variational autoencoder architecture that is able to cope with meshes with irregular connectivity and nonlinear deformations, assuming that the analyzed dataset contains meshes with the same vertex connectivity, which is common for deformation analysis. To help localize deformations, we introduce sparse regularization in this framework, along with spectral graph convolutional operations. Through modifying the regularization formulation and allowing dynamic change of sparsity ranges, we improve the visual quality and reconstruction ability of the extracted deformation components. Our system also provides a nonlinear approach to reconstruction of meshes using the extracted basis, which is more effective than the current linear combination approach. As an important application of localized deformation components and a novel approach on its own, we further develop a neural shape editing method, achieving shape editing and deformation component extraction in a unified framework, and ensuring plausibility of the edited shapes. Extensive experiments show that our method outperforms state-of-the-art methods in both qualitative and quantitative evaluations. We also demonstrate the effectiveness of our method for neural shape editing.

Image colorization is a classic and important topic in computer graphics, where the aim is to add color to a monochromatic input image to produce a colorful result. In this survey, we present the history of colorization research in chronological order and summarize popular algorithms in this field. Early works on colorization mostly focused on developing techniques to improve the colorization quality. In the last few years, researchers have considered more possibilities such as combining colorization with NLP (natural language processing) and focused more on industrial applications. To better control the color, various types of color control are designed, such as providing reference images or color-scribbles. We have created a taxonomy of the colorization methods according to the input type, divided into grayscale, sketch-based and hybrid. The pros and cons are discussed for each algorithm, and they are compared according to their main characteristics. Finally, we discuss how deep learning, and in particular Generative Adversarial Networks (GANs), has changed this field.

Most previous EEG-based emotion recognition methods studied hand-crafted EEG features extracted from different electrodes. In this paper, we study the relation among different EEG electrodes and propose a deep learning method to automatically extract the spatial features that characterize the functional relation between EEG signals at different electrodes. Our proposed deep model is called ATtention-based LSTM with Domain Discriminator (ATDD-LSTM) that can characterize nonlinear relations among EEG signals of different electrodes. To achieve state-of-the-art emotion recognition performance, the architecture of ATDD-LSTM has two distinguishing characteristics: (1) By applying the attention mechanism to the feature vectors produced by LSTM, ATDD-LSTM automatically selects suitable EEG channels for emotion recognition, which makes the learned model concentrate on the emotion related channels in response to a given emotion; (2) To minimize the significant feature distribution shift between different sessions and/or subjects, ATDD-LSTM uses a domain discriminator to modify the data representation space and generate domain-invariant features. We evaluate the proposed ATDD-LSTM model on three public EEG emotional databases (DEAP, SEED and CMEED) for emotion recognition. The experimental results demonstrate that our ATDD-LSTM model achieves superior performance on subject-dependent (for the same subject), subject-independent (for different subjects) and cross-session (for the same subject) evaluation.

Atherosclerosis (AS) is a primary cause of cardiovascular diseases. This study investigated the mechanism of methyltransferase-like 3 (METTL3) in AS plaques via modulating the phenotypic transformation of vascular smooth muscle cells (VSMCs).AS mouse models and MOVAS cell models were established through high-fat diet and the treatment of ox-LDL, respectively. METTL3 expression in AS models was detected via RT-qPCR and Western blot. The AS plaques, lipid deposition, and collagen fibers were examined via histological staining. The levels of Ly-6c, α-SMA, and OPN were examined via Western blot. The blood lipid indexes in mouse aortic tissues were determined using kits. The proliferation and migration of MOVAS cells were detected via CCK-8 and Transwell assays. The mMETTL3 was highly expressed in AS. Silencing METTL3 alleviated AS progression and stabilized AS plaques in mice, and limited the phenotypic transformation of VSMCs induced by ox-LDL. Silencing METTL3 inhibited mMETTL3-mediated m

As a popular concept proposed in the field of psychology, affordance has been regarded as one of the important abilities that enable humans to understand and interact with the environment. Briefly, it captures the possibilities and effects of the actions of an agent applied to a specific object or, more generally, a part of the environment. This paper provides a short review of the recent developments of deep robotic affordance learning (DRAL), which aims to develop data-driven methods that use the concept of affordance to aid in robotic tasks. We first classify these papers from a reinforcement learning (RL) perspective, and draw connections between RL and affordances. The technical details of each category are discussed and their limitations identified. We further summarise them and identify future challenges from the aspects of observations, actions, affordance representation, data-collection and real-world deployment. A final remark is given at the end to propose a promising future direction of the RL-based affordance definition to include the predictions of arbitrary action consequences., This paper is under review

Three new aaptamines (1–3) together with two known derivatives (4–5) were isolated from the South China Sea sponge Aaptos suberitoides. The structures of all compounds were unambiguously elucidated by spectroscopic analyses as well as the comparison with literature data. All the compounds were evaluated for their cytotoxic activities against five human cancer cell lines including H1299, H520, SCG7901, CNE-2 and SW680 cells. As a result, compounds 3–5 showed moderate cytotoxicities against H1299 and H520 cells with IC50 values ranging from 12.9 to 20.6 μg/mL. Besides, compounds 3–5 also showed potent inhibitory activities toward cyclin-dependent kinase-2 (CDK2) with IC50 values of 14.3, 3.0 and 6.0 μg/mL, respectively. In addition, compounds 3–5 significantly induced G1 arrests of H1299 cells at low concentrations. Drug affinity responsive target stability (DARTS) experiments were carried out and further demonstrated that compound 3 could effectively bind with CDK2 protein and protect it from the degradation by pronase.

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.

3D indoor scenes are widely used in computer graphics, with applications ranging from interior design to gaming to virtual and augmented reality. They also contain rich information, including room layout, as well as furniture type, geometry, and placement. High-quality 3D indoor scenes are highly demanded while it requires expertise and is time-consuming to design high-quality 3D indoor scenes manually. Existing research only addresses partial problems: some works learn to generate room layout, and other works focus on generating detailed structure and geometry of individual furniture objects. However, these partial steps are related and should be addressed together for optimal synthesis. We propose SCENEHGN, a hierarchical graph network for 3D indoor scenes that takes into account the full hierarchy from the room level to the object level, then finally to the object part level. Therefore for the first time, our method is able to directly generate plausible 3D room content, including furniture objects with fine-grained geometry, and their layout. To address the challenge, we introduce functional regions as intermediate proxies between the room and object levels to make learning more manageable. To ensure plausibility, our graph-based representation incorporates both vertical edges connecting child nodes with parent nodes from different levels, and horizontal edges encoding relationships between nodes at the same level. Extensive experiments demonstrate that our method produces superior generation results, even when comparing results of partial steps with alternative methods that can only achieve these. We also demonstrate that our method is effective for various applications such as part-level room editing, room interpolation, and room generation by arbitrary room boundaries., Comment: 21 pages, 21 figures, Project: http://geometrylearning.com/scenehgn/

Recent facial image synthesis methods have been mainly based on conditional generative models. Sketch-based conditions can effectively describe the geometry of faces, including the contours of facial components, hair structures, as well as salient edges (e.g., wrinkles) on face surfaces but lack effective control of appearance, which is influenced by color, material, lighting condition, etc. To have more control of generated results, one possible approach is to apply existing disentangling works to disentangle face images into geometry and appearance representations. However, existing disentangling methods are not optimized for human face editing, and cannot achieve fine control of facial details such as wrinkles. To address this issue, we propose DeepFaceEditing, a structured disentanglement framework specifically designed for face images to support face generation and editing with disentangled control of geometry and appearance. We adopt a local-to-global approach to incorporate the face domain knowledge: local component images are decomposed into geometry and appearance representations, which are fused consistently using a global fusion module to improve generation quality. We exploit sketches to assist in extracting a better geometry representation, which also supports intuitive geometry editing via sketching. The resulting method can either extract the geometry and appearance representations from face images, or directly extract the geometry representation from face sketches. Such representations allow users to easily edit and synthesize face images, with decoupled control of their geometry and appearance. Both qualitative and quantitative evaluations show the superior detail and appearance control abilities of our method compared to state-of-the-art methods.

Although scholars have sought to theorize tourism from important philosophical turns (e.g., epistemological/antirational/postmodern/practice), one influential turn (viz. linguistic) has not received much attention. This study attempts to fill this gap by retheorizing tourism from the linguistic turn. We introduced major theories of meaning (a core part of the linguistic turn) from the philosophy literature, on the basis of which we constructed a new semantic space of “tourism” where multiple semantic dimensions (defined by particular types of meaning theories) coexist and possess different semantic veins (determined by a subtheory of meaning) consisting of numerous semantic dots (i.e., actual understandings of tourism). This prescriptive space captures the image of tourism in a semantic mirror, encompassing tourism ontologies in a semantic/linguistic realm. This space also offers solutions to four problems in prior tourism theorization. By innovatively linking tourism and philosophy of language, this study has expanded the options in addressing the question “What is tourism?”

In geometry processing, symmetry is a universal type of high-level structural information of 3D models and benefits many geometry processing tasks including shape segmentation, alignment, matching, and completion. Thus it is an important problem to analyze various symmetry forms of 3D shapes. Planar reflective symmetry is the most fundamental one. Traditional methods based on spatial sampling can be time-consuming and may not be able to identify all the symmetry planes. In this article, we present a novel learning framework to automatically discover global planar reflective symmetry of a 3D shape. Our framework trains an unsupervised 3D convolutional neural network to extract global model features and then outputs possible global symmetry parameters, where input shapes are represented using voxels. We introduce a dedicated symmetry distance loss along with a regularization loss to avoid generating duplicated symmetry planes. Our network can also identify generalized cylinders by predicting their rotation axes. We further provide a method to remove invalid and duplicated planes and axes. We demonstrate that our method is able to produce reliable and accurate results. Our neural network based method is hundreds of times faster than the state-of-the-art methods, which are based on sampling. Our method is also robust even with noisy or incomplete input surfaces.