Search

Recent advances in Large Language Models (LLMs) have revolutionized code generation, leading to widespread adoption of AI coding tools by developers. However, LLMs can generate license-protected code without providing the necessary license information, leading to potential intellectual property violations during software production. This paper addresses the critical, yet underexplored, issue of license compliance in LLM-generated code by establishing a benchmark to evaluate the ability of LLMs to provide accurate license information for their generated code. To establish this benchmark, we conduct an empirical study to identify a reasonable standard for "striking similarity" that excludes the possibility of independent creation, indicating a copy relationship between the LLM output and certain open-source code. Based on this standard, we propose an evaluation benchmark LiCoEval, to evaluate the license compliance capabilities of LLMs. Using LiCoEval, we evaluate 14 popular LLMs, finding that even top-performing LLMs produce a non-negligible proportion (0.88% to 2.01%) of code strikingly similar to existing open-source implementations. Notably, most LLMs fail to provide accurate license information, particularly for code under copyleft licenses. These findings underscore the urgent need to enhance LLM compliance capabilities in code generation tasks. Our study provides a foundation for future research and development to improve license compliance in AI-assisted software development, contributing to both the protection of open-source software copyrights and the mitigation of legal risks for LLM users.

To explain the well-known tension between cosmological parameter constraints obtained from the primary CMB and those drawn from galaxy cluster samples, we propose a possible explanation for the incompleteness of detected clusters are higher than estimated. We aim to search for galaxy groups and clusters with particularly extended surface brightness distributions by creating a new X-ray-selected catalog of extended galaxy clusters from the XMM-SERVS data, based on a dedicated source detection and characterization algorithm that is optimized for extended sources. Our state-of-the-art algorithm is composed of wavelet filtering, source detection, and characterization. We make a visual inspection of the optical image, and spatial distribution of galaxies within the same redshift layer to confirm the existence of clusters and estimate the cluster redshift with the spectroscopic and photometric redshifts of galaxies. The growth curve analysis is used to characterize the detections. We report a catalog of extended X-ray galaxy clusters detected from the XMM-SERVS data, named the XMM- SERVS X-ray eXtended Galaxy Cluster (XVXGC) catalog. It includes 141 cluster candidates. Specifically, there are 52 clusters previously identified as clusters with the intra-cluster medium (ICM) emission (class 3), 37 ones previously known as optical or infrared clusters but detected as X-ray clusters for the first time (class 2), and 52 identified as clusters for the first time (class 1). Compared with the class3 sample, the 'class1+2' sample is systematically fainter, and exhibits a flatter surface brightness profile. The median flux in [0.1-2.4]keV band for 'class1+2' and class3 sample is 2.336e-14 and 3.163e-14erg/s/cm2, respectively. The median slope of surface brightness profile are 0.502 and 0.577 for the 'class1+2' and class 3 samples, respectively., Comment: 16pages, 11 figures, 5 tables, submit to A&A. This entire sample is available at https://github.com/wwxu/xvxgc.github.io together with the paper publication

In the hierarchical evolution framework of cosmology, larger halos grow through matter accretion and halo mergers. To clarify the halo evolution, we need to define the halo mass and radius physically. However, the pseudo-evolution problem makes the process difficult. Thus, we aim to measure the splashback radius, a physically defined halo radius for a large number of halos with various mass and redshift, and to determine the most important parameters to affect it. We use the typical definition of splashback radius (Rsp) as the radius with the steepest radial density profile. In this work, we measure Rsp of dark matter halos within the mass of 1e13-3e15Msun and redshifts spanning 0.08-0.65. This is the measurement of the Rsp in the largest range of halo mass and redshift. Using the shear catalog of the DECaLS DR8, we investigate Rsp of halos associated with galaxies and galaxy clusters identified in the various catalogs. Our finding reveals a trend wherein massive halos demonstrate a larger Rsp, and the normalized splashback radius (Rsp/R200m) shows a U-shaped mass evolution. The upturn in these relations mainly comes from the contribution of massive halos with low redshifts. We further find Rsp increases with the peak height, while Rsp/R200m has a negative relation with the peak height. We also find the Rsp >~R200m for most halos, indicating their low accretion rates. Our result is consistent with previous literature across a wide range of mass, redshift, and peak height, as well as the simulation work from More et al. (2015)., Comment: 15 pages, 7 figures, submitted to ApJ

We propose a novel point-based representation, Gaussian surfels, to combine the advantages of the flexible optimization procedure in 3D Gaussian points and the surface alignment property of surfels. This is achieved by directly setting the z-scale of 3D Gaussian points to 0, effectively flattening the original 3D ellipsoid into a 2D ellipse. Such a design provides clear guidance to the optimizer. By treating the local z-axis as the normal direction, it greatly improves optimization stability and surface alignment. While the derivatives to the local z-axis computed from the covariance matrix are zero in this setting, we design a self-supervised normal-depth consistency loss to remedy this issue. Monocular normal priors and foreground masks are incorporated to enhance the quality of the reconstruction, mitigating issues related to highlights and background. We propose a volumetric cutting method to aggregate the information of Gaussian surfels so as to remove erroneous points in depth maps generated by alpha blending. Finally, we apply screened Poisson reconstruction method to the fused depth maps to extract the surface mesh. Experimental results show that our method demonstrates superior performance in surface reconstruction compared to state-of-the-art neural volume rendering and point-based rendering methods., Comment: Results added and improved

Low-rank matrix approximation play a ubiquitous role in various applications such as image processing, signal processing, and data analysis. Recently, random algorithms of low-rank matrix approximation have gained widespread adoption due to their speed, accuracy, and robustness, particularly in their improved implementation on modern computer architectures. Existing low-rank approximation algorithms often require prior knowledge of the rank of the matrix, which is typically unknown. To address this bottleneck, we propose a low-rank approximation algorithm termed efficient orthogonal decomposition with automatic basis extraction (EOD-ABE) tailored for the scenario where the rank of the matrix is unknown. Notably, we introduce a randomized algorithm to automatically extract the basis that reveals the rank. The efficacy of the proposed algorithms is theoretically and numerically validated, demonstrating superior speed, accuracy, and robustness compared to existing methods. Furthermore, we apply the algorithms to image reconstruction, achieving remarkable results.

A package's source code repository records the development history of the package, providing indispensable information for the use and risk monitoring of the package. However, a package release often misses its source code repository due to the separation of the package's development platform from its distribution platform. Existing tools retrieve the release's repository information from its metadata, which suffers from two limitations: the metadata may not contain or contain wrong information. Our analysis shows that existing tools can only retrieve repository information for up to 70.5% of PyPI releases. To address the limitations, this paper proposes PyRadar, a novel framework that utilizes the metadata and source distribution to retrieve and validate the repository information for PyPI releases. We start with an empirical study to compare four existing tools on 4,227,425 PyPI releases and analyze phantom files (files appearing in the release's distribution but not in the release's repository) in 14,375 correct package-repository links and 2,064 incorrect links. Based on the findings, we design PyRadar with three components, i.e., Metadata-based Retriever, Source Code Repository Validator, and Source Code-based Retriever. In particular, the Metadata-based Retriever combines best practices of existing tools and successfully retrieves repository information from the metadata for 72.1% of PyPI releases. The Source Code Repository Validator applies common machine learning algorithms on six crafted features and achieves an AUC of up to 0.995. The Source Code-based Retriever queries World of Code with the SHA-1 hashes of all Python files in the release's source distribution and retrieves repository information for 90.2% of packages in our dataset with an accuracy of 0.970. Both practitioners and researchers can employ the PyRadar to better use PyPI packages., Comment: This paper has been accepted at FSE 2024

Automatic 3D facial texture generation has gained significant interest recently. Existing approaches may not support the traditional physically based rendering pipeline or rely on 3D data captured by Light Stage. Our key contribution is a progressive latent space refinement approach that can bootstrap from 3D Morphable Models (3DMMs)-based texture maps generated from facial images to generate high-quality and diverse PBR textures, including albedo, normal, and roughness. It starts with enhancing Generative Adversarial Networks (GANs) for text-guided and diverse texture generation. To this end, we design a self-supervised paradigm to overcome the reliance on ground truth 3D textures and train the generative model with only entangled texture maps. Besides, we foster mutual enhancement between GANs and Score Distillation Sampling (SDS). SDS boosts GANs with more generative modes, while GANs promote more efficient optimization of SDS. Furthermore, we introduce an edge-aware SDS for multi-view consistent facial structure. Experiments demonstrate that our method outperforms existing 3D texture generation methods regarding photo-realistic quality, diversity, and efficiency.

Learning 3D human motion from 2D inputs is a fundamental task in the realms of computer vision and computer graphics. Many previous methods grapple with this inherently ambiguous task by introducing motion priors into the learning process. However, these approaches face difficulties in defining the complete configurations of such priors or training a robust model. In this paper, we present the Video-to-Motion Generator (VTM), which leverages motion priors through cross-modal latent feature space alignment between 3D human motion and 2D inputs, namely videos and 2D keypoints. To reduce the complexity of modeling motion priors, we model the motion data separately for the upper and lower body parts. Additionally, we align the motion data with a scale-invariant virtual skeleton to mitigate the interference of human skeleton variations to the motion priors. Evaluated on AIST++, the VTM showcases state-of-the-art performance in reconstructing 3D human motion from monocular videos. Notably, our VTM exhibits the capabilities for generalization to unseen view angles and in-the-wild videos.

Generalized singular values (GSVs) play an essential role in the comparative analysis. In the real world data for comparative analysis, both data matrices are usually numerically low-rank. This paper proposes a randomized algorithm to first approximately extract bases and then calculate GSVs efficiently. The accuracy of both basis extration and comparative analysis quantities, angular distances, generalized fractions of the eigenexpression, and generalized normalized Shannon entropy, are rigursly analyzed. The proposed algorithm is applied to both synthetic data sets and the genome-scale expression data sets. Comparing to other GSVs algorithms, the proposed algorithm achieves the fastest runtime while preserving sufficient accuracy in comparative analysis.

Text-driven 3D scene generation techniques have made rapid progress in recent years. Their success is mainly attributed to using existing generative models to iteratively perform image warping and inpainting to generate 3D scenes. However, these methods heavily rely on the outputs of existing models, leading to error accumulation in geometry and appearance that prevent the models from being used in various scenarios (e.g., outdoor and unreal scenarios). To address this limitation, we generatively refine the newly generated local views by querying and aggregating global 3D information, and then progressively generate the 3D scene. Specifically, we employ a tri-plane features-based NeRF as a unified representation of the 3D scene to constrain global 3D consistency, and propose a generative refinement network to synthesize new contents with higher quality by exploiting the natural image prior from 2D diffusion model as well as the global 3D information of the current scene. Our extensive experiments demonstrate that, in comparison to previous methods, our approach supports wide variety of scene generation and arbitrary camera trajectories with improved visual quality and 3D consistency., Comment: 11 pages, 7 figures

Text-guided 3D face synthesis has achieved remarkable results by leveraging text-to-image (T2I) diffusion models. However, most existing works focus solely on the direct generation, ignoring the editing, restricting them from synthesizing customized 3D faces through iterative adjustments. In this paper, we propose a unified text-guided framework from face generation to editing. In the generation stage, we propose a geometry-texture decoupled generation to mitigate the loss of geometric details caused by coupling. Besides, decoupling enables us to utilize the generated geometry as a condition for texture generation, yielding highly geometry-texture aligned results. We further employ a fine-tuned texture diffusion model to enhance texture quality in both RGB and YUV space. In the editing stage, we first employ a pre-trained diffusion model to update facial geometry or texture based on the texts. To enable sequential editing, we introduce a UV domain consistency preservation regularization, preventing unintentional changes to irrelevant facial attributes. Besides, we propose a self-guided consistency weight strategy to improve editing efficacy while preserving consistency. Through comprehensive experiments, we showcase our method's superiority in face synthesis. Project page: https://faceg2e.github.io/.

Although the open source model bears many advantages in software development, open source projects are always hard to sustain. Previous research on open source sustainability mainly focuses on projects that have already reached a certain level of maturity (e.g., with communities, releases, and downstream projects). However, limited attention is paid to the development of (sustainable) open source projects in their infancy, and we believe an understanding of early sustainability determinants is crucial for project initiators, incubators, newcomers, and users. In this paper, we aim to explore the relationship between early participation factors and long-term project sustainability. We leverage a novel methodology combining the Blumberg model of performance and machine learning to predict the sustainability of 290,255 GitHub projects. Specificially, we train an XGBoost model based on early participation (first three months of activity) in 290,255 GitHub projects and we interpret the model using LIME. We quantitatively show that early participants have a positive effect on project's future sustained activity if they have prior experience in OSS project incubation and demonstrate concentrated focus and steady commitment. Participation from non-code contributors and detailed contribution documentation also promote project's sustained activity. Compared with individual projects, building a community that consists of more experienced core developers and more active peripheral developers is important for organizational projects. This study provides unique insights into the incubation and recognition of sustainable open source projects, and our interpretable prediction approach can also offer guidance to open source project initiators and newcomers., Comment: The 31st ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering (ESEC/FSE 2023)

The reuse and distribution of open-source software must be in compliance with its accompanying open-source license. In modern packaging ecosystems, maintaining such compliance is challenging because a package may have a complex multi-layered dependency graph with many packages, any of which may have an incompatible license. Although prior research finds that license incompatibilities are prevalent, empirical evidence is still scarce in some modern packaging ecosystems (e.g., PyPI). It also remains unclear how developers remediate the license incompatibilities in the dependency graphs of their packages (including direct and transitive dependencies), let alone any automated approaches. To bridge this gap, we conduct a large-scale empirical study of license incompatibilities and their remediation practices in the PyPI ecosystem. We find that 7.27% of the PyPI package releases have license incompatibilities and 61.3% of them are caused by transitive dependencies, causing challenges in their remediation; for remediation, developers can apply one of the five strategies: migration, removal, pinning versions, changing their own licenses, and negotiation. Inspired by our findings, we propose SILENCE, an SMT-solver-based approach to recommend license incompatibility remediations with minimal costs in package dependency graph. Our evaluation shows that the remediations proposed by SILENCE can match 19 historical real-world cases (except for migrations not covered by an existing knowledge base) and have been accepted by five popular PyPI packages whose developers were previously unaware of their license incompatibilities.

The galaxy-galaxy lensing technique allows us to measure the subhalo mass of satellite galaxies, studying their mass loss and evolution within galaxy clusters and providing direct observational validation for theories of galaxy formation. In this study, we use the weak gravitational lensing observations from DECaLS DR8, in combination with the redMaPPer galaxy cluster catalog from Sloan Digital Sky Survey data (SDSS) DR8 to accurately measure the dark matter halo mass of satellite galaxies. We confirm a significant increase in the stellar-to-halo mass ratio of satellite galaxies with their halo-centric radius, indicating clear evidence of mass loss due to tidal stripping. Additionally, we find that this mass loss is strongly dependent on the mass of the satellite galaxies, with satellite galaxies above $10^{11}~{\rm M_{\odot}/h}$ experiencing more pronounced mass loss compared to lower mass satellites, reaching 86\% at projected halo-centric radius $0.5R_{\rm 200c}$. The average mass loss rate, when not considering halo-centric radius, displays a U-shaped variation with stellar mass, with galaxies of approximately $4\times10^{10}~{\rm M_{\odot}/h}$ exhibiting the least mass loss, around 60\%. We compare our results with state-of-the-art hydrodynamical numerical simulations and find that the satellite galaxy stellar-to-halo mass ratio in the outskirts of galaxy clusters is higher compared to the predictions of the Illustris-TNG project about factor 5. Furthermore, the Illustris-TNG project's numerical simulations did not predict the observed dependence of satellite galaxy mass loss rate on satellite galaxy mass., Comment: 14 pages, 9 figures

Although part-based motion synthesis networks have been investigated to reduce the complexity of modeling heterogeneous human motions, their computational cost remains prohibitive in interactive applications. To this end, we propose a novel two-part transformer network that aims to achieve high-quality, controllable motion synthesis results in real-time. Our network separates the skeleton into the upper and lower body parts, reducing the expensive cross-part fusion operations, and models the motions of each part separately through two streams of auto-regressive modules formed by multi-head attention layers. However, such a design might not sufficiently capture the correlations between the parts. We thus intentionally let the two parts share the features of the root joint and design a consistency loss to penalize the difference in the estimated root features and motions by these two auto-regressive modules, significantly improving the quality of synthesized motions. After training on our motion dataset, our network can synthesize a wide range of heterogeneous motions, like cartwheels and twists. Experimental and user study results demonstrate that our network is superior to state-of-the-art human motion synthesis networks in the quality of generated motions., Comment: 16 pages, 26 figures

We present the measurement of total and stellar/dark matter decomposed mass density profile around a sample of galaxy groups and clusters with dynamical masses derived from integral-field stellar kinematics from the MaNGA survey in Paper I and weak lensing derived from the DECaLS imaging survey. Combining the two data sets enables accurate measurement of the radial density distribution from several kpc to Mpc scales. Intriguingly, we find that the excess surface density derived from stellar kinematics in the inner region cannot be explained by simply adding an NFW dark matter halo extrapolated from lensing measurement at a larger scale to a stellar mass component derived from the NASA-Sloan Atlas (NSA) catalogue. We find that a good fit to both data sets requires a stellar mass normalization about 3 times higher than that derived from the NSA catalogue, which would require an unrealistically too-heavy initial mass function for stellar mass estimation. If we keep the stellar mass normalization to that of the NSA catalogue but allow a varying inner dark matter density profile, we obtain an asymptotic slope of $\gamma_{\rm gnfw}$= $1.82_{-0.25}^{+0.15}$ and $\gamma_{\rm gnfw}$= $1.48_{-0.41}^{+0.20}$ for the group bin and the cluster bin respectively, significantly steeper than the NFW case. We also compare the total mass inner density slopes with those from TNG300 and find that the values from the simulation are lower than the observation by about $2\sigma$ level., Comment: 12 pages, 9 figures, accepted by MNRAS

Layout is essential for graphic design and poster generation. Recently, applying deep learning models to generate layouts has attracted increasing attention. This paper focuses on using the GAN-based model conditioned on image contents to generate advertising poster graphic layouts, which requires an advertising poster layout dataset with paired product images and graphic layouts. However, the paired images and layouts in the existing dataset are collected by inpainting and annotating posters, respectively. There exists a domain gap between inpainted posters (source domain data) and clean product images (target domain data). Therefore, this paper combines unsupervised domain adaption techniques to design a GAN with a novel pixel-level discriminator (PD), called PDA-GAN, to generate graphic layouts according to image contents. The PD is connected to the shallow level feature map and computes the GAN loss for each input-image pixel. Both quantitative and qualitative evaluations demonstrate that PDA-GAN can achieve state-of-the-art performances and generate high-quality image-aware graphic layouts for advertising posters., Comment: 8 pages, 4 figures, 7 tables, accepted by CVPR2023

Content and style disentanglement is an effective way to achieve few-shot font generation. It allows to transfer the style of the font image in a source domain to the style defined with a few reference images in a target domain. However, the content feature extracted using a representative font might not be optimal. In light of this, we propose a content fusion module (CFM) to project the content feature into a linear space defined by the content features of basis fonts, which can take the variation of content features caused by different fonts into consideration. Our method also allows to optimize the style representation vector of reference images through a lightweight iterative style-vector refinement (ISR) strategy. Moreover, we treat the 1D projection of a character image as a probability distribution and leverage the distance between two distributions as the reconstruction loss (namely projected character loss, PCL). Compared to L2 or L1 reconstruction loss, the distribution distance pays more attention to the global shape of characters. We have evaluated our method on a dataset of 300 fonts with 6.5k characters each. Experimental results verify that our method outperforms existing state-of-the-art few-shot font generation methods by a large margin. The source code can be found at https://github.com/wangchi95/CF-Font., Comment: Accepted by CVPR 2023

We present MMT spectroscopic observations of two massive galaxy cluster candidates at redshift $z\sim0.07$ that show extended and diffuse X-ray emission in the ROSAT All Sky Survey (RASS) images. The targets were selected from a previous catalog of 303 newly-identified cluster candidates with the similar properties using the intra-cluster medium emission. Using the new MMT Hectospec data and SDSS archival spectra, we identify a number of member galaxies for the two targets and confirm that they are galaxy clusters at $z=0.079$ and 0.067, respectively. The size of the two clusters, calculated from the distribution of the member galaxies, is roughly 2 Mpc in radius. We estimate cluster masses using three methods based on their galaxy number overdensities, galaxy velocity dispersions, and X-ray emission. The overdensity-based masses are $(6\sim8) \rm \times10^{14}\ M_\odot$, comparable to the masses of large clusters at low redshift. The masses derived from velocity dispersions are significantly lower, likely due to their diffuse and low concentration features. Our result suggests the existence of a population of large clusters with very diffuse X-ray emission that have been missed by most previous searches using the RASS images. If most of the 303 candidates in the previous catalog are confirmed to be real clusters, this may help to reduce the discrepancy of cosmological results between the CMB and galaxy cluster measurements., Comment: 12 pages, 7 figures, 1 table

Artificial spin ices are engineered arrays of dipolarly coupled nanobar magnets. They enable direct investigations of fascinating collective phenomena from their diverse microstates. However, experimental access to ground states in the geometrically frustrated systems has proven difficult, limiting studies and applications of novel properties and functionalities from the low energy states. Here, we introduce a convenient approach to control the competing diploar interactions between the neighboring nanomagnets, allowing us to tailor the vertex degeneracy of the ground states. We achieve this by tuning the length of selected nanobar magnets in the spin ice lattice. We demonstrate the effectiveness of our method by realizing multiple low energy microstates in a Kagome artificial spin ice, particularly the hardly accessible long range ordered ground state - the spin crystal state. Our strategy can be directly applied to other artificial spin systems to achieve exotic phases and explore new emergent collective behaviors., Comment: To appear in Physical Review Letters

Quantization has proven effective in high-resolution and large-scale simulations, which benefit from bit-level memory saving. However, identifying a quantization scheme that meets the requirement of both precision and memory efficiency requires trial and error. In this paper, we propose a novel framework to allow users to obtain a quantization scheme by simply specifying either an error bound or a memory compression rate. Based on the error propagation theory, our method takes advantage of auto-diff to estimate the contributions of each quantization operation to the total error. We formulate the task as a constrained optimization problem, which can be efficiently solved with analytical formulas derived for the linearized objective function. Our workflow extends the Taichi compiler and introduces dithering to improve the precision of quantized simulations. We demonstrate the generality and efficiency of our method via several challenging examples of physics-based simulation, which achieves up to 2.5x memory compression without noticeable degradation of visual quality in the results. Our code and data are available at https://github.com/Hanke98/AutoQuantizer., Comment: 15 pages. 17 figures. Accepted to ACM Transactions on Graphics (Proceedings of SIGGRAPH 2022)

Non-rigid 3D registration, which deforms a source 3D shape in a non-rigid way to align with a target 3D shape, is a classical problem in computer vision. Such problems can be challenging because of imperfect data (noise, outliers and partial overlap) and high degrees of freedom. Existing methods typically adopt the $\ell_p$ type robust norm to measure the alignment error and regularize the smoothness of deformation, and use a proximal algorithm to solve the resulting non-smooth optimization problem. However, the slow convergence of such algorithms limits their wide applications. In this paper, we propose a formulation for robust non-rigid registration based on a globally smooth robust norm for alignment and regularization, which can effectively handle outliers and partial overlaps. The problem is solved using the majorization-minimization algorithm, which reduces each iteration to a convex quadratic problem with a closed-form solution. We further apply Anderson acceleration to speed up the convergence of the solver, enabling the solver to run efficiently on devices with limited compute capability. Extensive experiments demonstrate the effectiveness of our method for non-rigid alignment between two shapes with outliers and partial overlaps, with quantitative evaluation showing that it outperforms state-of-the-art methods in terms of registration accuracy and computational speed. The source code is available at https://github.com/yaoyx689/AMM_NRR., Comment: Accepted to IEEE Transactions on Pattern Analysis and Machine Intelligence

In this paper, we study the graphic layout generation problem of producing high-quality visual-textual presentation designs for given images. We note that image compositions, which contain not only global semantics but also spatial information, would largely affect layout results. Hence, we propose a deep generative model, dubbed as composition-aware graphic layout GAN (CGL-GAN), to synthesize layouts based on the global and spatial visual contents of input images. To obtain training images from images that already contain manually designed graphic layout data, previous work suggests masking design elements (e.g., texts and embellishments) as model inputs, which inevitably leaves hint of the ground truth. We study the misalignment between the training inputs (with hint masks) and test inputs (without masks), and design a novel domain alignment module (DAM) to narrow this gap. For training, we built a large-scale layout dataset which consists of 60,548 advertising posters with annotated layout information. To evaluate the generated layouts, we propose three novel metrics according to aesthetic intuitions. Through both quantitative and qualitative evaluations, we demonstrate that the proposed model can synthesize high-quality graphic layouts according to image compositions., Comment: Accepted by IJCAI 2022 (AI, THE ARTS AND CREATIVITY TRACK)

We propose a novel method to reconstruct the 3D shapes of transparent objects using hand-held captured images under natural light conditions. It combines the advantage of explicit mesh and multi-layer perceptron (MLP) network, a hybrid representation, to simplify the capture setting used in recent contributions. After obtaining an initial shape through the multi-view silhouettes, we introduce surface-based local MLPs to encode the vertex displacement field (VDF) for the reconstruction of surface details. The design of local MLPs allows to represent the VDF in a piece-wise manner using two layer MLP networks, which is beneficial to the optimization algorithm. Defining local MLPs on the surface instead of the volume also reduces the searching space. Such a hybrid representation enables us to relax the ray-pixel correspondences that represent the light path constraint to our designed ray-cell correspondences, which significantly simplifies the implementation of single-image based environment matting algorithm. We evaluate our representation and reconstruction algorithm on several transparent objects with ground truth models. Our experiments show that our method can produce high-quality reconstruction results superior to state-of-the-art methods using a simplified data acquisition setup.