Search

A modified Transformer model is introduced for estimating the mass of pseudoscalar glueball in lattice QCD. The model takes as input a sequence of floating-point numbers with lengths ranging from 30 to 35 and produces a two-dimensional vector output. It integrates floating-point embeddings and positional encoding, and is trained using binary cross-entropy loss. The paper provides a detailed description of the model's components and training methods, and compares the performance of the traditional least squares method, the previously used deep neural network, and the modified Transformer in mass estimation. The results show that the modified Transformer model achieves greater accuracy in mass estimation than the traditional least squares method. Additionally, compared to the deep neural network, this model utilizes positional encoding and can handle input sequences of varying lengths, offering enhanced adaptability.

Large Language Models (LLMs) have shown great potential in intelligent visualization systems, especially for domain-specific applications. Integrating LLMs into visualization systems presents challenges, and we categorize these challenges into three alignments: domain problems with LLMs, visualization with LLMs, and interaction with LLMs. To achieve these alignments, we propose a framework and outline a workflow to guide the application of fine-tuned LLMs to enhance visual interactions for domain-specific tasks. These alignment challenges are critical in education because of the need for an intelligent visualization system to support beginners' self-regulated learning. Therefore, we apply the framework to education and introduce Tailor-Mind, an interactive visualization system designed to facilitate self-regulated learning for artificial intelligence beginners. Drawing on insights from a preliminary study, we identify self-regulated learning tasks and fine-tuning objectives to guide visualization design and tuning data construction. Our focus on aligning visualization with fine-tuned LLM makes Tailor-Mind more like a personalized tutor. Tailor-Mind also supports interactive recommendations to help beginners better achieve their learning goals. Model performance evaluations and user studies confirm that Tailor-Mind improves the self-regulated learning experience, effectively validating the proposed framework.

The interaction between axion-like particles (ALPs) and photons induces ALP-photon oscillations in astrophysical magnetic fields, leading to spectral distortions in the $\gamma$-ray spectrum of blazars. The primary uncertainty of this phenomenon may originate from the magnetic field within the jet of the blazar. While many studies have explored the effects of ALP-photon oscillations using typical values for jet magnetic field parameters, it is important to recognize that these parameters can be constrained by multi-wavelength observations. In this study, we utilize the high energy $\gamma$-ray spectrum of Mrk 421 obtained from MAGIC and Fermi-LAT observations. By employing multi-wavelength fitting with a one-zone synchrotron self-Compton model, we derive the parameters characterizing the magnetic field model within the jet, and investigate their impacts on the ALP constraints., Comment: 9 pages, 7 figures

Due to the fascinating generative performance of text-to-image diffusion models, growing text-to-3D generation works explore distilling the 2D generative priors into 3D, using the score distillation sampling (SDS) loss, to bypass the data scarcity problem. The existing text-to-3D methods have achieved promising results in realism and 3D consistency, but text-to-4D generation still faces challenges, including lack of realism and insufficient dynamic motions. In this paper, we propose a novel method for text-to-4D generation, which ensures the dynamic amplitude and authenticity through direct supervision provided by a video prior. Specifically, we adopt a text-to-video diffusion model to generate a reference video and divide 4D generation into two stages: static generation and dynamic generation. The static 3D generation is achieved under the guidance of the input text and the first frame of the reference video, while in the dynamic generation stage, we introduce a customized SDS loss to ensure multi-view consistency, a video-based SDS loss to improve temporal consistency, and most importantly, direct priors from the reference video to ensure the quality of geometry and texture. Moreover, we design a prior-switching training strategy to avoid conflicts between different priors and fully leverage the benefits of each prior. In addition, to enrich the generated motion, we further introduce a dynamic modeling representation composed of a deformation network and a topology network, which ensures dynamic continuity while modeling topological changes. Our method not only supports text-to-4D generation but also enables 4D generation from monocular videos. The comparison experiments demonstrate the superiority of our method compared to existing methods.

A deep neural network (DNN) is utilized to study the mass of the pseudoscalar glueball in lattice QCD based on Monte Carlo simulations. To obtain an accurate and stable mass value, I constructed a new network. The results show that this DNN provides a more precise and stable mass estimate compared to the traditional least squares method., Comment: 5 figures

Existing text-based 3D generation methods generate attractive results but lack detailed geometry control. Sketches, known for their conciseness and expressiveness, have contributed to intuitive 3D modeling but are confined to producing texture-less mesh models within predefined categories. Integrating sketch and text simultaneously for 3D generation promises enhanced control over geometry and appearance but faces challenges from 2D-to-3D translation ambiguity and multi-modal condition integration. Moreover, further editing of 3D models in arbitrary views will give users more freedom to customize their models. However, it is difficult to achieve high generation quality, preserve unedited regions, and manage proper interactions between shape components. To solve the above issues, we propose a text-driven 3D content generation and editing method, SketchDream, which supports NeRF generation from given hand-drawn sketches and achieves free-view sketch-based local editing. To tackle the 2D-to-3D ambiguity challenge, we introduce a sketch-based multi-view image generation diffusion model, which leverages depth guidance to establish spatial correspondence. A 3D ControlNet with a 3D attention module is utilized to control multi-view images and ensure their 3D consistency. To support local editing, we further propose a coarse-to-fine editing approach: the coarse phase analyzes component interactions and provides 3D masks to label edited regions, while the fine stage generates realistic results with refined details by local enhancement. Extensive experiments validate that our method generates higher-quality results compared with a combination of 2D ControlNet and image-to-3D generation techniques and achieves detailed control compared with existing diffusion-based 3D editing approaches.

Reconstructing and editing 3D objects and scenes both play crucial roles in computer graphics and computer vision. Neural radiance fields (NeRFs) can achieve realistic reconstruction and editing results but suffer from inefficiency in rendering. Gaussian splatting significantly accelerates rendering by rasterizing Gaussian ellipsoids. However, Gaussian splatting utilizes a single Spherical Harmonic (SH) function to model both texture and lighting, limiting independent editing capabilities of these components. Recently, attempts have been made to decouple texture and lighting with the Gaussian splatting representation but may fail to produce plausible geometry and decomposition results on reflective scenes. Additionally, the forward shading technique they employ introduces noticeable blending artifacts during relighting, as the geometry attributes of Gaussians are optimized under the original illumination and may not be suitable for novel lighting conditions. To address these issues, we introduce DeferredGS, a method for decoupling and editing the Gaussian splatting representation using deferred shading. To achieve successful decoupling, we model the illumination with a learnable environment map and define additional attributes such as texture parameters and normal direction on Gaussians, where the normal is distilled from a jointly trained signed distance function. More importantly, we apply deferred shading, resulting in more realistic relighting effects compared to previous methods. Both qualitative and quantitative experiments demonstrate the superior performance of DeferredGS in novel view synthesis and editing tasks.

As XR technology continues to advance rapidly, 3D generation and editing are increasingly crucial. Among these, stylization plays a key role in enhancing the appearance of 3D models. By utilizing stylization, users can achieve consistent artistic effects in 3D editing using a single reference style image, making it a user-friendly editing method. However, recent NeRF-based 3D stylization methods encounter efficiency issues that impact the user experience, and their implicit nature limits their ability to accurately transfer geometric pattern styles. Additionally, the ability for artists to apply flexible control over stylized scenes is considered highly desirable to foster an environment conducive to creative exploration. To address the above issues, we introduce StylizedGS, an efficient 3D neural style transfer framework with adaptable control over perceptual factors based on 3D Gaussian Splatting (3DGS) representation. We propose a filter-based refinement to eliminate floaters that affect the stylization effects in the scene reconstruction process. The nearest neighbor-based style loss is introduced to achieve stylization by fine-tuning the geometry and color parameters of 3DGS, while a depth preservation loss with other regularizations is proposed to prevent the tampering of geometry content. Moreover, facilitated by specially designed losses, StylizedGS enables users to control color, stylized scale, and regions during the stylization to possess customization capabilities. Our method achieves high-quality stylization results characterized by faithful brushstrokes and geometric consistency with flexible controls. Extensive experiments across various scenes and styles demonstrate the effectiveness and efficiency of our method concerning both stylization quality and inference speed.

The emergence of 3D Gaussian Splatting (3DGS) has greatly accelerated the rendering speed of novel view synthesis. Unlike neural implicit representations like Neural Radiance Fields (NeRF) that represent a 3D scene with position and viewpoint-conditioned neural networks, 3D Gaussian Splatting utilizes a set of Gaussian ellipsoids to model the scene so that efficient rendering can be accomplished by rasterizing Gaussian ellipsoids into images. Apart from the fast rendering speed, the explicit representation of 3D Gaussian Splatting facilitates editing tasks like dynamic reconstruction, geometry editing, and physical simulation. Considering the rapid change and growing number of works in this field, we present a literature review of recent 3D Gaussian Splatting methods, which can be roughly classified into 3D reconstruction, 3D editing, and other downstream applications by functionality. Traditional point-based rendering methods and the rendering formulation of 3D Gaussian Splatting are also illustrated for a better understanding of this technique. This survey aims to help beginners get into this field quickly and provide experienced researchers with a comprehensive overview, which can stimulate the future development of the 3D Gaussian Splatting representation.

Neural implicit representation of geometric shapes has witnessed considerable advancements in recent years. However, common distance field based implicit representations, specifically signed distance field (SDF) for watertight shapes or unsigned distance field (UDF) for arbitrary shapes, routinely suffer from degradation of reconstruction accuracy when converting to explicit surface points and meshes. In this paper, we introduce a novel neural implicit representation based on unsigned orthogonal distance fields (UODFs). In UODFs, the minimal unsigned distance from any spatial point to the shape surface is defined solely in one orthogonal direction, contrasting with the multi-directional determination made by SDF and UDF. Consequently, every point in the 3D UODFs can directly access its closest surface points along three orthogonal directions. This distinctive feature leverages the accurate reconstruction of surface points without interpolation errors. We verify the effectiveness of UODFs through a range of reconstruction examples, extending from simple watertight or non-watertight shapes to complex shapes that include hollows, internal or assembling structures., Comment: accepted by CVPR 2024

Neural implicit representations, including Neural Distance Fields and Neural Radiance Fields, have demonstrated significant capabilities for reconstructing surfaces with complicated geometry and topology, and generating novel views of a scene. Nevertheless, it is challenging for users to directly deform or manipulate these implicit representations with large deformations in the real-time fashion. Gaussian Splatting(GS) has recently become a promising method with explicit geometry for representing static scenes and facilitating high-quality and real-time synthesis of novel views. However,it cannot be easily deformed due to the use of discrete Gaussians and lack of explicit topology. To address this, we develop a novel GS-based method that enables interactive deformation. Our key idea is to design an innovative mesh-based GS representation, which is integrated into Gaussian learning and manipulation. 3D Gaussians are defined over an explicit mesh, and they are bound with each other: the rendering of 3D Gaussians guides the mesh face split for adaptive refinement, and the mesh face split directs the splitting of 3D Gaussians. Moreover, the explicit mesh constraints help regularize the Gaussian distribution, suppressing poor-quality Gaussians(e.g. misaligned Gaussians,long-narrow shaped Gaussians), thus enhancing visual quality and avoiding artifacts during deformation. Based on this representation, we further introduce a large-scale Gaussian deformation technique to enable deformable GS, which alters the parameters of 3D Gaussians according to the manipulation of the associated mesh. Our method benefits from existing mesh deformation datasets for more realistic data-driven Gaussian deformation. Extensive experiments show that our approach achieves high-quality reconstruction and effective deformation, while maintaining the promising rendering results at a high frame rate(65 FPS on average)., Comment: 11 pages, 7 figures

High-energy photons may oscillate with axion-like particles (ALPs) when they propagate through the Milky Way's magnetic field, resulting in an alteration in the observed photon energy spectrum. The ultra-high energy gamma-ray spectra, measured by the Large High Altitude Air Shower Observatory (LHAASO) up to $\mathcal{O}(1)~\mathrm{PeV}$, provide a promising opportunity to investigate the ALP-photon oscillation effect. In this study, we utilize the gamma-ray spectra of four Galactic sources measured by LHAASO, including the Crab Nebula, LHAASO J2226+6057, LHAASO J1908+0621, and LHAASO J1825-1326, to explore this effect. We employ the $\rm CL_s$ method to set constraints on the ALP parameters. Combing the observations of the four sources, our analysis reveals that the ALP-photon coupling $g_{a\gamma}$ is constrained to be smaller than $1.4\times10^{-10}$ ${\rm GeV}^{-1}$ for the ALP mass of $\sim 4\times10^{-7} ~\mathrm{eV}$ at the 95\% C.L. By combing the observations of the Crab Nebula from LHAASO and other experiments, we find that the ALP-photon coupling could be set to be about $7.2\times10^{-11}$ ${\rm GeV}^{-1}$ for the ALP mass $\sim 4 \times10^{-7}~\mathrm{eV}$ , which is in close proximity to the CAST constraint.

A modified deep convolutional generative adversarial network (M-DCGAN) frame is proposed to study the N-dimensional (ND) topological quantities in lattice QCD based on the Monte Carlo (MC) simulations. We construct a new scaling structure including fully connected layers to support the generation of high-quality high-dimensional images for the M-DCGAN. Our results show that the M-DCGAN scheme of the Machine learning should be helpful for us to calculate efficiently the 1D distribution of topological charge and the 4D topological charge density compared with the case by the MC simulation alone.

Seam carving is an image editing method that enable content-aware resizing, including operations like removing objects. However, the seam-finding strategy based on dynamic programming or graph-cut limits its applications to broader visual data formats and degrees of freedom for editing. Our observation is that describing the editing and retargeting of images more generally by a displacement field yields a generalisation of content-aware deformations. We propose to learn a deformation with a neural network that keeps the output plausible while trying to deform it only in places with low information content. This technique applies to different kinds of visual data, including images, 3D scenes given as neural radiance fields, or even polygon meshes. Experiments conducted on different visual data show that our method achieves better content-aware retargeting compared to previous methods., Comment: ECCV 2024

We propose a modified Wasserstein generative adversarial network (M-WGAN) to study the distribution of the topological charge in lattice QCD based on Monte Carlo simulations. We construct new generator and discriminator in M-WGAN to support the generation of high-quality distribution. Our results show that the M-WGAN scheme of machine learning should be helpful for us to calculate efficiently the 1D distribution of topological charge compared with the method by the MC simulation alone.

The LHAASO collaboration recently reported the measurement of the gamma-ray spectra of GRB 221009A, which is the brightest burst ever, covering an energy range from 0.3 $\mathrm{TeV}$ to about 10 $\mathrm{TeV}$. Based on the observation, we investigate the ALP-photon oscillation effect in the host galaxy of GRB 221009A and the Milky Way. The ${\rm CL_s}$ method is applied to set constraints on the ALP parameters in this study. Given the uncertain magnetic field configuration in the host galaxy, we use three different models: a homogeneous magnetic field model, a magnetic field model identical to that of the Milky Way, and a model constructed from the HST observations of the host galaxy. We find that the constraints derived using these three host galaxy magnetic field models are comparable. Our results are complementary in the small ALP mass regions compared with other experiments., Comment: 8 pages, 13 figures

Axion-like particles (ALPs) may undergo mixing with photons in the presence of astrophysical magnetic fields, leading to alterations in the observed high energy $\gamma$-ray spectra. In this study, we investigate the ALP-photon oscillation effect using the spectra of the blazar Mrk 421 over 15 observation periods measured by Major Atmospheric Gamma Imaging Cherenkov Telescopes (MAGIC) and Fermi Large Area Telescope (Fermi-LAT). Compared with previous studies, we generate mock data under the ALP hypothesis and employ the ${\rm CL_s}$ method to set constraints on the ALP parameters. This method is widely utilized in high energy experiments and avoids the exclusion of specific parameter regions where distinguishing between the null and ALP hypotheses is challenging. We find that the ALP-photon coupling $g_{a\gamma}$ is constrained to be smaller than $\sim 2\times10^{-11}$ GeV$^{-1}$ for ALP masses ranging from $10^{-9}$ eV to $10^{-7}$ eV at the 95\% confidence level. We also present the constraints derived from the TS distribution under the null hypothesis, which is commonly utilized in previous astrophysical ALP studies. Our results reveal that the combined constraints of all the periods obtained from both methods are consistent. However, the ${\rm CL_s}$ method remains effective in cases where the latter method fails to provide constraints for specific observation periods., Comment: 10 pages, 27 figures

Federated learning protects users' data privacy through sharing users' local model parameters (instead of raw data) with a server. However, when massive users train a large machine learning model through federated learning, the dynamically varying and often heavy communication overhead can put significant pressure on the network operator. The operator may choose to dynamically change the network prices in response, which will eventually affect the payoffs of the server and users. This paper considers the under-explored yet important issue of the joint design of participation incentives (for encouraging users' contribution to federated learning) and network pricing (for managing network resources). Due to heterogeneous users' private information and multi-dimensional decisions, the optimization problems in Stage I of multi-stage games are non-convex. Nevertheless, we are able to analytically derive the corresponding optimal contract and pricing mechanism through proper transformations of constraints, variables, and functions, under both vertical and horizontal interaction structures of the participants. We show that the vertical structure is better than the horizontal one, as it avoids the interests misalignment between the server and the network operator. Numerical results based on real-world datasets show that our proposed mechanisms decrease server's cost by up to 24.87% comparing with the state-of-the-art benchmarks.

Despite the tremendous progress in neural radiance fields (NeRF), we still face a dilemma of the trade-off between quality and efficiency, e.g., MipNeRF presents fine-detailed and anti-aliased renderings but takes days for training, while Instant-ngp can accomplish the reconstruction in a few minutes but suffers from blurring or aliasing when rendering at various distances or resolutions due to ignoring the sampling area. To this end, we propose a novel Tri-Mip encoding that enables both instant reconstruction and anti-aliased high-fidelity rendering for neural radiance fields. The key is to factorize the pre-filtered 3D feature spaces in three orthogonal mipmaps. In this way, we can efficiently perform 3D area sampling by taking advantage of 2D pre-filtered feature maps, which significantly elevates the rendering quality without sacrificing efficiency. To cope with the novel Tri-Mip representation, we propose a cone-casting rendering technique to efficiently sample anti-aliased 3D features with the Tri-Mip encoding considering both pixel imaging and observing distance. Extensive experiments on both synthetic and real-world datasets demonstrate our method achieves state-of-the-art rendering quality and reconstruction speed while maintaining a compact representation that reduces 25% model size compared against Instant-ngp., Comment: Accepted to ICCV 2023 Project page: https://wbhu.github.io/projects/Tri-MipRF

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 the distribution of their limited training samples and thus cannot beautify freely drawn sketches with rich 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 perceptive study., Comment: Accepted by IEEE Transactions on Visualization and Computer Graphics

Van der Waals (vdW) layered materials have drawn tremendous interests due to their unique properties. Atom intercalation in the vdW gap of layered materials can tune their electronic structure and generate unexpected properties. Here we report a chemical-scissor mediated method that enables metal intercalation into transition metal dichalcogenides (TMDCs) in molten salts. By using this approach, various guest metal atoms (Mn, Fe, Co, Ni, Cu, and Ag) were intercalated into various TMDCs hosts (such as TiS2, NbS2, TaS2, TiSe2, NbSe2, TaSe2 and Ti0.5V0.5S2). The structure of the intercalated compound and intercalation mechanism was investigated. The results indicate that the vdW gap and valence state of TMDCs can be modified through metal intercalation, and the intercalation behavior is dictated by the electron work function. Such a chemical-scissor mediated intercalation provides an approach to tune the physical and chemical properties of TMDCs, which may open an avenue in functional application ranging from energy conversion to electronics.

Multi-view shape reconstruction has achieved impressive progresses thanks to the latest advances in neural implicit surface rendering. However, existing methods based on signed distance function (SDF) are limited to closed surfaces, failing to reconstruct a wide range of real-world objects that contain open-surface structures. In this work, we introduce a new neural rendering framework, coded NeUDF, that can reconstruct surfaces with arbitrary topologies solely from multi-view supervision. To gain the flexibility of representing arbitrary surfaces, NeUDF leverages the unsigned distance function (UDF) as surface representation. While a naive extension of an SDF-based neural renderer cannot scale to UDF, we propose two new formulations of weight function specially tailored for UDF-based volume rendering. Furthermore, to cope with open surface rendering, where the in/out test is no longer valid, we present a dedicated normal regularization strategy to resolve the surface orientation ambiguity. We extensively evaluate our method over a number of challenging datasets, including DTU}, MGN, and Deep Fashion 3D. Experimental results demonstrate that nEudf can significantly outperform the state-of-the-art method in the task of multi-view surface reconstruction, especially for complex shapes with open boundaries., Comment: Accepted by CVPR 2023, 24 pages, project: http://geometrylearning.com/neudf/

3D face generation has achieved high visual quality and 3D consistency thanks to the development of neural radiance fields (NeRF). Recently, to generate and edit 3D faces with NeRF representation, some methods are proposed and achieve good results in decoupling geometry and texture. The latent codes of these generative models affect the whole face, and hence modifications to these codes cause the entire face to change. However, users usually edit a local region when editing faces and do not want other regions to be affected. Since changes to the latent code affect global generation results, these methods do not allow for fine-grained control of local facial regions. To improve local controllability in NeRF-based face editing, we propose LC-NeRF, which is composed of a Local Region Generators Module and a Spatial-Aware Fusion Module, allowing for local geometry and texture control of local facial regions. Qualitative and quantitative evaluations show that our method provides better local editing than state-of-the-art face editing methods. Our method also performs well in downstream tasks, such as text-driven facial image editing.

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 methods for synthesizing 3D-aware face images have achieved rapid development thanks to neural radiance fields, allowing for high quality and fast inference speed. However, existing solutions for editing facial geometry and appearance independently usually require retraining and are not optimized for the recent work of generation, thus tending to lag behind the generation process. To address these issues, we introduce NeRFFaceEditing, which enables editing and decoupling geometry and appearance in the pretrained tri-plane-based neural radiance field while retaining its high quality and fast inference speed. Our key idea for disentanglement is to use the statistics of the tri-plane to represent the high-level appearance of its corresponding facial volume. Moreover, we leverage a generated 3D-continuous semantic mask as an intermediary for geometry editing. We devise a geometry decoder (whose output is unchanged when the appearance changes) and an appearance decoder. The geometry decoder aligns the original facial volume with the semantic mask volume. We also enhance the disentanglement by explicitly regularizing rendered images with the same appearance but different geometry to be similar in terms of color distribution for each facial component separately. Our method allows users to edit via semantic masks with decoupled control of geometry and appearance. Both qualitative and quantitative evaluations show the superior geometry and appearance control abilities of our method compared to existing and alternative solutions.