Combined analysis of the metabolome and transcriptome reveals the metabolic characteristics and candidate genes involved in alkaloid metabolism in Heuchera micrantha Douglas ex Lindl.

BACKGROUND: Alkaloids, important secondary metabolites produced by plants, play a crucial role in responding to environmental stress. Heuchera micrantha, a well-known plant used in landscaping, has the ability to purify air, and absorb toxic and radioactive substances, showing strong environmental adaptability. However, there is still limited understanding of the accumulation characteristics and metabolic mechanism of alkaloids in H. micrantha. RESULTS: In this study, four distinct varieties of H. micrantha were used to investigate the accumulation and metabolic traits of alkaloids in its leaves. We conducted a combined analysis of the plant's metabolome and transcriptome. Our analysis identified 44 alkaloids metabolites in the leaves of the four H. micrantha varieties, with 26 showing different levels of accumulation among the groups. The HT and JQ varieties exhibited higher accumulation of differential alkaloid metabolites compared to YH and HY. We annotated the differential alkaloid metabolites to 22 metabolic pathways, including several alkaloid metabolism. Transcriptome data revealed 5064 differentially expressed genes involved in these metabolic pathways. Multivariate analysis showed that four key metabolites (N-hydroxytryptamine, L-tyramine, tryptamine, and 2-phenylethylamine) and three candidate genes (Cluster-15488.116815, Cluster-15488.146268, and Cluster-15488.173297) that merit further investigation. CONCLUSIONS: This study provided preliminarily insight into the molecular mechanism of the biosynthesis of alkaloids in H. micrantha. However, further analysis is required to elucidate the specific regulatory mechanisms of the candidate gene involved in the synthesis of key alkaloid metabolites. In summary, our findings provide important information about how alkaloid metabolites build up and the metabolic pathways involved in H. micrantha varieties. This gives us a good starting point for future research on the regulation mechanism, and development, and utilization of alkaloids in H. micrantha.

Patient tissue-derived FGFR4-variant and wild-type colorectal cancer organoid development and anticancer drug sensitivity testing.

Objectives: FGFR4-variant and wild-type colorectal cancer (CRC) organoids were developed to investigate the effects of FGFR4-targeted drugs, including FGFR4-IN and erdafitinib, on CRC and their possible molecular mechanism. Methods: Clinical CRC tissues were collected, seven CRC organoids were developed, and whole exome sequencing (WES) was performed. CRC organoids were cultured and organoid drug sensitivity studies were conducted. Finally, an FGFR4-variant (no wild-type) CRC patient-derived orthotopic xenograft mouse model was developed. Western blot measured ERK/AKT/STAT3 pathway-related protein levels. Results: WES results revealed the presence of FGFR4-variants in 5 of the 7 CRC organoids. The structural organization and integrity of organoids were significantly altered under the influence of targeted drugs (FGFR4-IN-1 and erdafitinib). The effects of FGFR4 targeted drugs were not selective for FGFR4 genotypes. FGFR4-IN-1 and erdafitinib significantly reduced the growth, diameter, and Adenosine Triphosphate (ATP) activity of organoids. Furthermore, chemotherapeutic drugs, including 5-fluorouracil and cisplatin, inhibited FGFR4-variant and wild-type CRC organoid activity. Moreover, the tumor volume of mice was significantly reduced at week 6, and p-ERK1/2, p-AKT, and p-STAT3 levels were down-regulated following FGFR4-IN-1 and erdafitinib treatment. Conclusions: FGFR4-targeted and chemotherapeutic drugs inhibited the activity of FGFR4-variant and wild-type CRC organoids, and targeted drugs were more effective than chemotherapeutic drugs at the same concentration. Additionally, FGFR4 inhibitors hindered tumorigenesis in FGFR4-variant CRC organoids through ERK1/2, AKT, and STAT3 pathways. However, no wild-type control was tested in this experiment, which need further confirmation in the next study.

GP-Recon: Online Monocular Neural 3D Reconstruction with Geometric Prior.

High-fidelity online 3D scene reconstruction from monocular videos continues to be challenging, especially for coherent and fine-grained geometry reconstruction. The previous learning-based online 3D reconstruction approaches with neural implicit representations have shown a promising ability for coherent scene reconstruction, but often fail to consistently reconstruct fine-grained geometric details during online reconstruction. This paper presents a new on-the-fly monocular 3D reconstruction approach, named GP-Recon, to perform high-fidelity online neural 3D reconstruction with fine-grained geometric details. We incorporate geometric prior (GP) into a scene's neural geometry learning to better capture its geometric details and, more importantly, propose an online volume rendering optimization to reconstruct and maintain geometric details during the online reconstruction task. The extensive comparisons with state-of-the-art approaches show that our GP-Recon consistently generates more accurate and complete reconstruction results with much better fine-grained details, both quantitatively and qualitatively.

Sketch2Human: Deep Human Generation with Disentangled Geometry and Appearance Constraints.

Geometry- and appearance-controlled full-body human image generation is an interesting but challenging task. Existing solutions are either unconditional or dependent on coarse conditions (e.g., pose, text), thus lacking explicit geometry and appearance control of body and garment. Sketching offers such editing ability and has been adopted in various sketch-based face generation and editing solutions. However, directly adapting sketch-based face generation to full-body generation often fails to produce high-fidelity and diverse results due to the high complexity and diversity in the pose, body shape, and garment shape and texture. Recent geometrically controllable diffusion-based methods mainly rely on prompts to generate appearance. It is hard to balance the realism and the faithfulness of their results to the sketch when the input is coarse. This work presents Sketch2Human, the first system for controllable full-body human image generation guided by a semantic sketch (for geometry control) and a reference image (for appearance control). Our solution is based on the latent space of StyleGAN-Human with inverted geometry and appearance latent codes as input. Specifically, we present a sketch encoder trained with a large synthetic dataset sampled from StyleGAN-Human's latent space and directly supervised by sketches rather than real images. Considering the entangled information of partial geometry and texture in StyleGAN-Human and the absence of disentangled datasets, we design a novel training scheme that creates geometry-preserved and appearance-transferred training data to tune a generator to achieve disentangled geometry and appearance control. Although our method is trained with synthetic data, it can also handle hand-drawn sketches. Qualitative and quantitative evaluations demonstrate the superior performance of our method to state-of-the-art methods.

Dual-Responsive MXene-Functionalized Wool Yarn Artificial Muscles.

Fiber-based artificial muscles are promising for smart textiles capable of sensing, interacting, and adapting to environmental stimuli. However, the application of current artificial muscle-based textiles in wearable and engineering fields has largely remained a constraint due to the limited deformation, restrictive stimulation, and uncomfortable. Here, dual-responsive yarn muscles with high contractile actuation force are fabricated by incorporating a very small fraction (<1 wt.%) of Ti3C2Tx MXene/cellulose nanofibers (CNF) composites into self-plied and twisted wool yarns. They can lift and lower a load exceeding 3400 times their own weight when stimulated by moisture and photothermal. Furthermore, the yarn muscles are coiled homochirally or heterochirally to produce spring-like muscles, which generated over 550% elongation or 83% contraction under the photothermal stimulation. The actuation mechanism, involving photothermal/moisture-mechanical energy conversion, is clarified by a combination of experiments and finite element simulations. Specifically, MXene/CNF composites serve as both photothermal and hygroscopic agents to accelerate water evaporation under near-infrared (NIR) light and moisture absorption from ambient air. Due to their low-cost facile fabrication, large scalable dimensions, and robust strength coupled with dual responsiveness, these soft actuators are attractive for intelligent textiles and devices such as self-adaptive textiles, soft robotics, and wearable information encryption.

Phase State Regulates Photochemical HONO Production from NaNO3/Dicarboxylic Acid Mixtures.

Field observations of daytime HONO source strengths have not been well explained by laboratory measurements and model predictions up until now. More efforts are urgently needed to fill the knowledge gaps concerning how environmental factors, especially relative humidity (RH), affect particulate nitrate photolysis. In this work, two critical attributes for atmospheric particles, i.e., phase state and bulk-phase acidity, both influenced by ambient RH, were focused to illuminate the key regulators for reactive nitrogen production from typical internally mixed systems, i.e., NaNO3 and dicarboxylic acid (DCA) mixtures. The dissolution of only few oxalic acid (OA) crystals resulted in a remarkable 50-fold increase in HONO production compared to pure nitrate photolysis at 85% RH. Furthermore, the HONO production rates (PHONO) increased by about 1 order of magnitude as RH rose from <5% to 95%, initially exhibiting an almost linear dependence on the amount of surface absorbed water and subsequently showing a substantial increase in PHONO once nitrate deliquescence occurred at approximately 75% RH. NaNO3/malonic acid (MA) and NaNO3/succinic acid (SA) mixtures exhibited similar phase state effects on the photochemical HONO production. These results offer a new perspective on how aerosol physicochemical properties influence particulate nitrate photolysis in the atmosphere.

Region-Aware Color Smudging.

Color smudge operations from digital painting software enable users to create natural shading effects in high-fidelity paintings by interactively mixing colors. To precisely control results in traditional painting software, users tend to organize flat-filled color regions in multiple layers and smudge them to generate different color gradients. However, the requirement to carefully deal with regions makes the smudging process time-consuming and laborious, especially for non-professional users. This motivates us to investigate how to infer user-desired smudging effects when users smudge over regions in a single layer. To investigate improving color smudge performance, we first conduct a formative study. Following the findings of this study, we design SmartSmudge, a novel smudge tool that offers users dynamical smudge brushes and real-time region selection for easily generating natural and efficient shading effects. We demonstrate the efficiency and effectiveness of the proposed tool via a user study and quantitative analysis.

Significantly Accelerated Photosensitized Formation of Atmospheric Sulfate at the Air-Water Interface of Microdroplets.

The multiphase oxidation of sulfur dioxide (SO2) to form sulfate is a complex and important process in the atmosphere. While the conventional photosensitized reaction mainly explored in the bulk medium is reported to be one of the drivers to trigger atmospheric sulfate production, how this scheme functionalizes at the air-water interface (AWI) of aerosol remains an open question. Herein, employing an advanced size-controllable microdroplet-printing device, surface-enhanced Raman scattering (SERS) analysis, nanosecond transient adsorption spectrometer, and molecular level theoretical calculations, we revealed the previously overlooked interfacial role in photosensitized oxidation of SO2 in humic-like substance (HULIS) aerosol, where a 3-4 orders of magnitude increase in sulfate formation rate was speculated in cloud and aerosol relevant-sized particles relative to the conventional bulk-phase medium. The rapid formation of a battery of reactive oxygen species (ROS) comes from the accelerated electron transfer process at the AWI, where the excited triplet state of HULIS (3HULIS*) of the incomplete solvent cage can readily capture electrons from HSO3- in a way that is more efficient than that in the bulk medium fully blocked by water molecules. This phenomenon could be explained by the significantly reduced desolvation energy barrier required for reagents residing in the AWI region with an open solvent shell.

Quantification and Characterization of Fine Plastic Particles as Considerable Components in Atmospheric Fine Particles.

The negative effects of air pollution, especially fine particulate matter (PM2.5, particles with an aerodynamic diameter of ≤2.5 µm), on human health, climate, and ecosystems are causing significant concern. Nevertheless, little is known about the contributions of emerging pollutants such as plastic particles to PM2.5 due to the lack of continuous measurements and characterization methods for atmospheric plastic particles. Here, we investigated the levels of fine plastic particles (FPPs) in PM2.5 collected in urban Shanghai at a 2 h resolution by using a novel versatile aerosol concentration enrichment system that concentrates ambient aerosols up to 10-fold. The FPPs were analyzed offline using the combination of spectroscopic and microscopic techniques that distinguished FPPs from other carbon-containing particles. The average FPP concentrations of 5.6 µg/m3 were observed, and the ratio of FPPs to PM2.5 was 13.2% in this study. The FPP sources were closely related to anthropogenic activities, which pose a potential threat to ecosystems and human health. Given the dramatic increase in plastic production over the past 70 years, this study calls for better quantification and control of FPP pollution in the atmosphere.

Text2Face: Text-based Face Generation with Geometry and Appearance Control.

Recent years have witnessed the emergence of various techniques proposed for text-based human face generation and manipulation. Such methods, targeting bridging the semantic gap between text and visual contents, provide users with a deft hand to turn ideas into visuals via text interface and enable more diversified multimedia applications. However, due to the flexibility of linguistic expressiveness, the mapping from sentences to desired facial images is clearly many-to-many, causing ambiguities during text-to-face generation. To alleviate these ambiguities, we introduce a local-to-global framework with two graph neural networks (one for geometry and the other for appearance) embedded to model the inter-dependency among facial parts. This is based upon our key observation that the geometry and appearance attributes among different facial components are not mutually independent, i.e., the combinations of part-level facial features are not arbitrary and thus do not conform to a uniform distribution. By learning from the dataset distribution and enabling recommendations given partial descriptions of human faces, these networks are highly suitable for our text-to-face task. Our method is capable of generating high-quality attribute-conditioned facial images from text. Extensive experiments have confirmed the superiority and usability of our method over the prior art.

Sketch2Stress: Sketching With Structural Stress Awareness.

In the process of product design and digital fabrication, the structural analysis of a designed prototype is a fundamental and essential step. However, such a step is usually invisible or inaccessible to designers at the early sketching phase. This limits the user's ability to consider a shape's physical properties and structural soundness. To bridge this gap, we introduce a novel approach Sketch2Stress that allows users to perform structural analysis of desired objects at the sketching stage. This method takes as input a 2D freehand sketch and one or multiple locations of user-assigned external forces. With the specially-designed two-branch generative-adversarial framework, it automatically predicts a normal map and a corresponding structural stress map distributed over the user-sketched underlying object. In this way, our method empowers designers to easily examine the stress sustained everywhere and identify potential problematic regions of their sketched object. Furthermore, combined with the predicted normal map, users are able to conduct a region- wise structural analysis efficiently by aggregating the stress effects of multiple forces in the same direction. Finally, we demonstrate the effectiveness and practicality of our system with extensive experiments and user studies.

Sketch Beautification: Learning Part Beautification and Structure Refinement for Sketches of Man-made Objects.

We present a novel freehand sketch beautification method, which takes as input a freely drawn sketch of a man-made object and automatically beautifies it both geometrically and structurally. Beautifying a sketch is challenging because of its highly abstract and heavily diverse drawing manner. Existing methods are usually confined to their limited training samples and thus cannot beautify freely drawn sketches with both geometric and structural variations. To address this challenge, we adopt a divide-and-combine strategy. Specifically, we first parse an input sketch into semantic components, beautify individual components by a learned part beautification module based on part-level implicit manifolds, and then reassemble the beautified components through a structure beautification module. With this strategy, our method can go beyond the training samples and handle novel freehand sketches. We demonstrate the effectiveness of our system with extensive experiments and a perceptual study.

Uncovering nutritional metabolites and candidate genes involved in flavonoid metabolism in Houttuynia cordata through combined metabolomic and transcriptomic analyses.

The perennial herb Houttuynia cordata has long been cultivated and used as medicinal and edible plant in Asia. Nowadays, increasing attention is attracted due to its numerous health benefits. Flavonoids are the main chemical constituents exerting pharmacological activities. In the present study, we investigated both metabolome and transcriptome of two H. cordata accessions (6# and 7#) with distinct flavonoids contents. In total 397 metabolites, i.e., 220 flavonoids, 92 amino acids and derivatives, 20 vitamins, and 65 saccharides were abundant in aboveground part. Cyanidin-3-O-rutinoside and quercetin-3-O-galactoside were the most abundant flavonoids, which can be categorized into seven classes, namely anthocyanidins, chalcones, flavanols, flavanones, flavanonols, flavones, and flavonols. Flavonols was the most abundant group. Contents of 112 flavonoids differed significantly between the two accessions, with catechin-(7,8-bc)-4α-(3,4-dihydroxyphenyl)-dihydro-2-(3H)-one, cinchonain Id, and cinchonain Ic being the dominant flavonoid metabolites among them. Pinocembrin-7-O-neohesperidoside, pinocembrin-7-O-rutinoside, and kaempferol-3-O-galactoside-4'-O-glucoside were uniquely abundant in accession 7. Transcriptome data revealed a total of 110 different expressed genes related to flavonoid metabolism, with more highly expressed genes observed in 7#. We annotated a total of 19 differential flavonoid metabolites and 34 differentially expressed genes that are associated with the flavonoid metabolic network. Based on the transcriptome and qPCR data a total of 8 key candidate genes involved in flavonoid metabolism were identified. The ANS gene were found to play an important role in the synthesis of cyanidin-3-O-glucoside, while the CHI, F3'H and FLS genes were mainly responsible for controlling the levels of flavanones, flavones, and flavonols, respectively. Collectively, the present study provides important insights into the molecular mechanism underlying flavonoid metabolism in H. cordata.

SketchMetaFace: A Learning-based Sketching Interface for High-fidelity 3D Character Face Modeling.

Modeling 3D avatars benefits various application scenarios such as AR/VR, gaming, and filming. Character faces contribute significant diversity and vividity as a vital component of avatars. However, building 3D character face models usually requires a heavy workload with commercial tools, even for experienced artists. Various existing sketch-based tools fail to support amateurs in modeling diverse facial shapes and rich geometric details. In this paper, we present SketchMetaFace - a sketching system targeting amateur users to model high-fidelity 3D faces in minutes. We carefully design both the user interface and the underlying algorithm. First, curvature-aware strokes are adopted to better support the controllability of carving facial details. Second, considering the key problem of mapping a 2D sketch map to a 3D model, we develop a novel learning-based method termed "Implicit and Depth Guided Mesh Modeling" (IDGMM). It fuses the advantages of mesh, implicit, and depth representations to achieve high-quality results with high efficiency. In addition, to further support usability, we present a coarse-to-fine 2D sketching interface design and a data-driven stroke suggestion tool. User studies demonstrate the superiority of our system over existing modeling tools in terms of the ease to use and visual quality of results. Experimental analyses also show that IDGMM reaches a better trade-off between accuracy and efficiency.

Coaxial radiography guided puncture technique for percutaneous transforaminal endoscopic lumbar discectomy: A randomized control trial.

BACKGROUND: The coaxial radiography-guided puncture technique (CR-PT) is a novel technique for endoscopic lumbar discectomy. As the X-ray beam and the puncturing needle are maintained in a parallel and coaxial direction, the X-ray beam can be used to guide the trajectory angle, facilitating the choice of the puncture site and providing real-time guidance. This puncture technique offers numerous advantages over the conventional anterior-posterior and lateral radiography-guided puncture technique (AP-PT), especially in cases of herniated lumbar discs with a hypertrophied transverse process or articular process, high iliac crest, and narrowed intervertebral foramen. AIM: To confirm whether CR-PT is a superior approach to percutaneous transforaminal endoscopic lumbar discectomy compared to AP-PT. METHODS: In this parallel, controlled, randomized clinical trial, herniated lumbar disc patients appointed to receive percutaneous endoscopic lumbar discectomy treatment were recruited from the Pain Management Department of the Affiliated Hospital of Xuzhou Medical University and Nantong Hospital of Traditional Chinese Medicine. Sixty-five participants were enrolled and divided into either a CR-PT group or an AP-PT group. The CR-PT group underwent CR-PT, and the AP-PT group underwent AP-PT. The number of fluoroscopies during puncturing, puncture duration (min), surgery duration (min), VAS score during puncturing, and puncture success rate were recorded. RESULTS: Sixty-five participants were included, with 31 participants in the CR-PT group and 34 in the AP-PT group. One participant in the AP-PT group dropped out due to unsuccessful puncturing. The number of fluoroscopies [median (P25, P75)] was 12 (11, 14) in the CR-PT group vs 16 (12, 23) in the AP-PT group, while the puncture duration (mean ± SD) was 20.42 ± 5.78 vs 25.06 ± 5.46, respectively. The VAS score was 3 (2, 4) in the CR-PT group vs 3 (3, 4) in the AP-PT group. Further subgroup analysis was performed, considering only the participants with L5/S1 segment herniation: 9 patients underwent CR-PT, and 9 underwent AP-PT. The number of fluoroscopies was 11.56 ± 0.88 vs 25.22 ± 5.33; the puncture duration was 13.89 ± 1.45 vs 28.89 ± 3.76; the surgery duration was 105 (99.5, 120) vs 149 (125, 157.5); and the VAS score was 2.11 ± 0.93 vs 3.89 ± 0.6, respectively. All the above outcomes demonstrated statistical significance (P < 0.05), favoring the CR-PT treatment. CONCLUSION: CR-PT is a novel and effective technique. As opposed to conventional AP-PT, this technique significantly improves puncture accuracy, shortens puncture time and operation time, and reduces pain intensity during puncturing.

Ferroelectric Modulation in Flexible Lead-Free Perovskite Schottky Direct-Current Nanogenerator for Capsule-Like Magnetic Suspension Sensor.

The tribovoltaic nanogenerator (TVNG), a promising semiconductor energy technology, displays outstanding advantages such as low matching impedance and continuous direct-current output. However, the lack of controllable and stable performance modulation strategies is still a major bottleneck that impedes further practical applications of TVNG. Herein, by leveraging the ferroelectricity-enhanced mechanism and the control of interfacial energy band bending, a lead-free perovskite-based (3,3-difluorocyclobutylammonium)2 CuCl4 ((DF-CBA)2 CuCl4 )/Al Schottky junction TVNG is constructed. The multiaxial ferroelectricity of (DF-CBA)2 CuCl4 enables an excellent surface charge modulating capacity, realizing a high work function regulation of ≈0.7 eV and over 15-fold current regulation (from 6 to 93 µA) via an electrical poling control. The controllable electrical poling leads to elevated work function difference between the Al electrode and (DF-CBA)2 CuCl4 compared to traditional semiconductors and halide perovskites, which creates a stronger built-in electric field at the Schottky interface to enhance the electrical output. This TVNG device exhibits outstanding flexibility and long-term stability (>20 000 cycles) that can endure extreme mechanical deformations, and can also be used in a capsule-like magnetic suspension device capable of detecting vibration and weights of different objects as well as harvesting energy from human motions and water waves.

PlanNet: A Generative Model for Component-Based Plan Synthesis.

We propose a novel generative model named as PlanNet for component-based plan synthesis. The proposed model consists of three modules, a wave function collapse algorithm to create large-scale wireframe patterns as the embryonic forms of floor plans, and two deep neural networks to outline the plausible boundary from each squared pattern, and meanwhile estimate the potential semantic labels for the components. In this manner, we use PlanNet to generate a large-scale component-based plan dataset with 10 K examples. Given an input boundary, our method retrieves dataset plan examples with similar configurations to the input, and then transfers the space layout from a user-selected plan example to the input. Benefiting from our interactive workflow, users can recursively subdivide individual components of the plans to enrich the plan contents, thus designing more complex plans for larger scenes. Moreover, our method also adopts a random selection algorithm to make the variations on semantic labels of the plan components, aiming at enriching the 3D scenes that the output plans are suited for. To demonstrate the quality and versatility of our generative model, we conduct intensive experiments, including the analysis of plan examples and their evaluations, plan synthesis with both hard and soft boundary constraints, and 3D scenes designed with the plan subdivision on different scales. We also compare our results with the state-of-the-art floor plan synthesis methods to validate the feasibility and efficacy of the proposed generative model.

MobileSky: Real-Time Sky Replacement for Mobile AR.

We present MobileSky, the first automatic method for real-time high-quality sky replacement for mobile AR applications. The primary challenge of this task is how to extract sky regions in camera feed both quickly and accurately. While the problem of sky replacement is not new, previous methods mainly concern extraction quality rather than efficiency, limiting their application to our task. We aim to provide higher quality, both spatially and temporally consistent sky mask maps for all camera frames in real time. To this end, we develop a novel framework that combines a new deep semantic network called FSNet with novel post-processing refinement steps. By leveraging IMU data, we also propose new sky-aware constraints such as temporal consistency, position consistency, and color consistency to help refine the weakly classified part of the segmentation output. Experiments show that our method achieves an average of around 30 FPS on off-the-shelf smartphones and outperforms the state-of-the-art sky replacement methods in terms of execution speed and quality. In the meantime, our mask maps appear to be visually more stable across frames. Our fast sky replacement method enables several applications, such as AR advertising, art making, generating fantasy celestial objects, visually learning about weather phenomena, and advanced video-based visual effects. To facilitate future research, we also create a new video dataset containing annotated sky regions with IMU data.

Magic Furniture: Design Paradigm of Multi-function Assembly.

Assembly-based furniture with movable parts enables shape and structure reconfiguration, thus supporting multiple functions. Although a few attempts have been made for facilitating the creation of multi-function objects, designing such a multi-function assembly with the existing solutions often requires high imagination of designers. We develop the Magic Furniture system for users to easily create such designs simply given multiple cross-category objects. Our system automatically leverages the given objects as references to generate a 3D model with movable boards driven by back-and-forth movement mechanisms. By controlling the states of these mechanisms, a designed multi-function furniture object can be reconfigured to approximate the shapes and functions of the given objects. To ensure the designed furniture easy to transform between different functions, we perform an optimization algorithm to choose a proper number of movable boards and determine their shapes and sizes, following a set of design guidelines. We demonstrate the effectiveness of our system through various multi-function furniture designed with different sets of reference inputs and various movement constraints. We also evaluate the design results through several experiments including comparative and user studies.

ReenactArtFace: Artistic Face Image Reenactment.

Large-scale datasets and deep generative models have enabled impressive progress in human face reenactment. Existing solutions for face reenactment have focused on processing real face images through facial landmarks by generative models. Different from real human faces, artistic human faces (e.g., those in paintings, cartoons, etc.) often involve exaggerated shapes and various textures. Therefore, directly applying existing solutions to artistic faces often fails to preserve the characteristics of the original artistic faces (e.g., face identity and decorative lines along face contours) due to the domain gap between real and artistic faces. To address these issues, we present ReenactArtFace, the first effective solution for transferring the poses and expressions from human videos to various artistic face images. We achieve artistic face reenactment in a coarse-to-fine manner. First, we perform 3D artistic face reconstruction, which reconstructs a textured 3D artistic face through a 3D morphable model (3DMM) and a 2D parsing map from an input artistic image. The 3DMM can not only rig the expressions better than facial landmarks but also render images under different poses/expressions as coarse reenactment results robustly. However, these coarse results suffer from self-occlusions and lack contour lines. Second, we thus perform artistic face refinement by using a personalized conditional adversarial generative model (cGAN) fine-tuned on the input artistic image and the coarse reenactment results. For high-quality refinement, we propose a contour loss to supervise the cGAN to faithfully synthesize contour lines. Quantitative and qualitative experiments demonstrate that our method achieves better results than the existing solutions.